HK40079926A - Clinical outcome tracking and analysis employing provisional/ refined nodal addresses relevant to treatment/prognosis-related outcome and risk assessment - Google Patents

Description

Clinical outcome tracking and analysis with temporary/optimized node addresses relevant to treatment/prognosis-related outcomes and risk assessment

Cross Reference to Related Applications

This application claims the benefit of U.S. provisional application No. 62/900,135 (filed on 9/13/2019), which is incorporated herein by reference in its entirety.

Technical Field

The present disclosure relates to systems and methods that facilitate early treatment support and determination of a prognosis-related prospective outcome in a patient having a disease or disorder.

Background

As the life of the population increases, the medical costs associated with an aging population also continue to increase. The costs associated with diseases such as cancer are often extremely high.

Currently, some public health care payers (e.g., Medicare) and some private health care payers (e.g., insurance companies) are transitioning at least in part from a predominantly pay-per-service reimbursement model to a value-based model that aims to match charges to objective measures of clinical quality and avoid unnecessary care and associated unnecessary charges. For example, some value-based models include a performance payment model that associates reimbursement with expected patient outcome, wherein reimbursement is reduced when worse than expected patient outcome, thereby providing economic incentives to healthcare providers to meet or exceed the expected patient outcome for the patient. As another example, some value-based models include a bundled pay/pay per treatment event model that provides a single bundled payment for the total treatment costs associated with a particular procedure or disease, thereby enabling economic incentives to be provided to health care providers to improve efficiency, coordinate care, and avoid unnecessary care and associated unnecessary costs. Some value-based models include both pay per performance and bundled/pay per treatment event aspects.

However, value-based models also face additional challenges. For example, current methods for determining a patient's expected clinical outcome fail to effectively and accurately account for many variables that may affect a particular patient's clinical outcome, resulting in inaccurate estimates of the patient's expected clinical outcome. As another example, current methods for providing a single bundled payment for treatment of a particular procedure or disease do not take into account many variables that may affect the course of treatment for a particular patient, resulting in a bundled payment that does not match the services required for treatment for a particular patient.

Some healthcare payers use models that employ risk adjustments, which are statistical processes that take into account their potential health conditions and health expenditures when viewing the healthcare outcomes or healthcare costs of insurance plan participants. However, many current risk adjustment methods do not efficiently and effectively determine how patients should be grouped in a statistical process so that similar patients are compared in terms of treatment, outcome, and cost.

Disclosure of Invention

Embodiments include methods, systems, and computer-readable media that employ temporary node addresses and optimized node addresses to provide early treatment decision guidance for target patients diagnosed with a disease (e.g., cancer) and to provide an estimated prognosis-related outcome.

According to one aspect, the described invention provides a method for facilitating early treatment decisions and determining a prognosis-related expected outcome with respect to the occurrence of defined endpoint events for a target patient diagnosed with a disease, the method comprising: accessing or receiving a first data set comprising personal health information associated with the target patient at or over a first time period, the personal health information comprising information about a phenotypic characteristic; assigning attributes to at least some variables of a set of preselected variables based on the received or accessed first data set, the set of preselected variables including a set of therapy-related variables and a set of prognosis or outcome-related variables, assigning a temporary node address to the target patient based on the assigned attributes of the set of therapy-related variables if an attribute is assigned to at least a minimum subset of the set of therapy-related variables, the temporary node address being associated with predetermined therapy plan information that is tailored to a particular combination of attributes embodied in the temporary node address to facilitate therapy decisions; providing predetermined treatment plan information to a healthcare provider of a target patient to facilitate treatment decisions for the target patient; accessing or receiving a second data set comprising updated and/or additional personal health information associated with the target patient at or for a second time period later than the first time; assigning updated attributes to at least some variables of the set of preselected variables and/or assigning new attributes to preselected variables to which attributes were not previously assigned based on the accessed or received second data set; and in case an attribute is assigned to at least a minimum subset of the treatment-related variables and at least a minimum subset of the prognosis-or outcome-related variables: assigning an optimized node address to the target patient based on the currently assigned attributes of the set of therapy-related variables and the currently assigned attributes of the set of prognosis or outcome-related variables; and determining the prognosis-related expected outcome for the patient with respect to the occurrence of the defined endpoint event based on the optimized node address assigned to the target patient.

In one embodiment of the method, the minimum subset of the treatment-related variables are the treatment-related variables in the set of pre-selected variables that are needed to provide pre-selected treatment-related information tailored to a particular combination of treatment-related attributes of a patient to guide treatment decisions. In some embodiments, the minimal subset of the treatment-related variables of the target patient is dependent at least in part on the cancer type and treatment intent of the target patient. In some embodiments, the minimum subset of the treatment-related variables includes a cancer type and a treatment intent, and which other of the treatment-related variables are included in the minimum subset of the treatment-related variables depends at least in part on the cancer type and the treatment intent of the target patient. In some embodiments, the step of accessing or receiving a first data set comprising personal health information associated with the target patient at or within a first time period comprises accessing or receiving information about the type of cancer and treatment intent of the target patient; and the method further comprises determining the minimum subset of the treatment-related variables based at least in part on the accessed or received information regarding the cancer type and the treatment intent of the target patient.

In some embodiments, the method further comprises presenting a user interface to the patient and/or a healthcare provider of the patient for inputting data in the first data set. In some embodiments, the user interface directs the user to enter at least a minimum subset of treatment-related variables. In some embodiments, the method further comprises presenting a user interface to the patient and/or a healthcare provider of the patient for inputting data in the first data set; and receiving information about the type of cancer of the target patient and the treatment intent of the target patient; and after determining the minimum subset of the therapy-related variables based on the received information regarding the cancer type of the target patient and the therapy intent of the target patient, inputting, via the user interface guide, a remaining portion of the minimum subset of the therapy-related variables. In some embodiments, the minimum subset of the prognostic or outcome-related variables is all of the prognostic or outcome-related variables in the set of preselected variables required for statistical analysis of prior outcomes. In some embodiments, the second data set comprises data obtained from a health record of the target patient. In some embodiments, the step of assigning updated attributes to at least some of the set of preselected variables based on the accessed second data set and/or assigning new attributes to preselected variables to which attributes were not previously assigned includes verifying and/or correcting problems detected in the second data set to determine updated or new attributes. In some embodiments, the first data set comprises data obtained from a health record of the target patient.

In some embodiments, the method further comprises evaluating the first data set to determine if it is correct prior to assigning the attribute to at least some variables of the set of preselected variables. In some embodiments, the prognosis-related expected outcome for the target patient is determined from a statistical analysis of previous prognosis-related outcomes for patients in a prognosis-or outcome-based patient group that are each assigned the same optimized node address as the optimized node address assigned to the target patient at a point of treatment and disease progression corresponding to the target patient. In some embodiments, the method further comprises statistically analyzing previous outcomes of patients in the prognosis or outcome based patient group to determine a current expected prognosis-related outcome for the target patient. In some embodiments, the current expected prognosis-related outcome is a time to progress from the start of second-line therapy to the start of third-line therapy, wherein the patients in the prognosis-or outcome-based patient group are patients that are each assigned the same optimized node address at the start of second-line therapy as the optimized node address assigned to the target patient at the start of second-line therapy.

In some embodiments, the method further comprises performing an updated statistical analysis of previous outcomes of patients in the prognosis or outcome based patient group to determine an updated current expected prognosis related outcome and storing information about the updated current expected prognosis related outcome. In some embodiments, the updated statistical analysis is performed periodically.

In some embodiments, the prognosis-related expected outcome for the target patient is determined from a statistical analysis of previous prognosis-related outcomes for patients in a prognosis-or outcome-based patient group, at least some of the patients being assigned the same optimized node address as the optimized node address assigned to the target patient at a point of treatment and disease progression corresponding to the target patient.

In some embodiments, the method further comprises transmitting information about the prognosis-related expected outcome to a client device associated with the patient's healthcare provider or the target patient's healthcare payer.

In some embodiments, the method further comprises accessing information about the outcome of the target patient; comparing the outcome of the target patient with the determined prognosis-related expected outcome of the target patient; and transmitting information regarding the comparison to a healthcare provider of the patient or a healthcare payer of the target patient.

In some embodiments, the method further comprises determining an expected treatment cost for the target patient for the disease during a clinically relevant period based on treatment costs for all patients in the prognosis or outcome based patient group that are each assigned the same optimized node address as the optimized node address assigned to the target patient at the treatment and disease progression point corresponding to the target patient. In some embodiments, the optimized node address assigned to the target patient has an associated expected treatment cost for the disease from diagnosis to death or cure determined by statistical analysis of prior treatment costs from diagnosis to death or cure for patients in the prognosis-or outcome-based patient group that are each assigned the same optimized node address as the optimized node address assigned to the target patient at diagnosis.

In some embodiments, the method further comprises accessing information regarding billing costs for treatment of the target patient and determining a total cost of treatment for the target patient over the clinically relevant period; and comparing the expected cost of treatment of the target patient over a clinically relevant period to the total cost of treatment of the target patient over the clinically relevant period. In some embodiments, the clinically relevant period is from diagnosis to death or cure.

In some embodiments, the method further comprises comparing the one or more outcomes of the target patient to one or more historical outcomes of patients in a prognosis-or outcome-based group of patients, each assigned the same optimized node address as the optimized node address assigned to the target patient at the time of diagnosis or at the time of progression, to determine whether the one or more outcomes of the target patient are trending away from the criteria of the prognosis-or outcome-based group.

In some embodiments, the method further comprises, upon determining that one or more outcomes of the target patient are trending away from the criteria of the prognosis-based or outcome-based group, sending an alert to a healthcare provider or healthcare payer of the target patient, the alert including information about the one or more outcomes that are trending away from the criteria.

In some embodiments, the method further comprises sending an alert to a healthcare provider or health payer of the target patient if the total cost of treatment of the patient over the clinically relevant period exceeds the expected cost of treatment of the target patient over the clinically relevant period by a threshold amount.

In some embodiments, the method further comprises, after accessing or receiving the second data set, iteratively accessing an updated or new data set comprising personal health information associated with the patient; and after accessing or receiving each updated or new data set: assigning updated attributes to at least some variables of the set of preselected variables and/or assigning attributes to preselected variables for which attributes were not previously assigned based on the accessed or new data set; and in the event that an attribute is assigned to at least a minimum subset of the therapy-related variables and at least a minimum subset of the prognosis-or outcome-related variables, assigning an optimized node address or an updated optimized node address to the target patient based on the currently assigned attributes of the set of therapy-related variables and the currently assigned attributes of the set of prognosis-or outcome-related variables.

In some embodiments, the method further comprises receiving or accessing information about a change in the set of preselected variables, the change comprising adding one or more variables to the set of treatment-related variables and/or the set of prognosis or outcome-related variables; assigning an attribute to at least one variable of the one or more variables added to the set of therapy-related variables and/or the set of prognosis or outcome-related variables based on current personal health information associated with the target patient; and assigning a different optimized node address to the target patient based on the assigned attributes of the therapy-related variable and the prognosis or outcome-related variable. In some embodiments, the second data set comprises data indicative of the progression of the disease after the first time point or after the first time period. In some embodiments, the first data set includes information about a first diagnosis and the second data set includes information about an updated diagnosis after the first diagnosis. In some embodiments, the second data set includes information about attributes that provide no information or incomplete information in the first data set. In some embodiments, the prognostic-related expected outcome with respect to defining the occurrence of an endpoint event includes one or more of overall survival, progression-free survival, or disease-free survival. In some embodiments, the predetermined treatment plan information comprises information regarding one or more predetermined patient care service packs, wherein providing the predetermined treatment plan information to the healthcare provider of the target patient comprises providing information regarding the one or more predetermined patient care service packs. In some embodiments, where the predetermined treatment plan information associated with the temporary node address assigned to the target patient changes before a treatment decision has been made or before an optimized node address has been assigned to the target patient, the method further comprises providing current predetermined treatment plan information to the healthcare provider of the target patient.

In some embodiments, the method further comprises providing an alert to a healthcare provider of the target patient that the predetermined treatment plan information associated with the temporary node address assigned to the target patient has changed.

In some embodiments, the method further comprises generating the temporary node address based on the assigned attributes of the set of therapy-related variables prior to assigning the temporary node address to the target patient.

In some embodiments, the method further comprises generating the optimized node address based on the assigned therapy-related variable and the assigned prognosis or outcome-related variable prior to assigning the optimized node address to the target patient.

In some embodiments, the method further comprises: assigning the target patient to a prognosis-or outcome-based group based on the optimized node address assigned to the target patient; measuring a change in behavior of each of a plurality of medical care providers assigned to a plurality of patients of the prognosis or outcome based group; and identifying a lack of necessary care and/or an unnecessary care being provided that causes a difference in the measured behavior of at least one of the medical care providers.

According to another aspect, the described invention provides a system for facilitating early treatment decisions and determining a prognosis-related expected outcome with respect to the occurrence of a defined endpoint event for a target patient diagnosed with a disease, the system comprising: a computing system hosting an application and in communication with a database and one or more third party systems executing the application, the computing system configured to: accessing or receiving a first data set comprising personal health information associated with the target patient at or over a first time period, the personal health information comprising information about a phenotypic characteristic; assigning attributes to at least some variables of a set of preselected variables based on the accessed or received first data set, the set of preselected variables comprising a set of therapy-related variables and a set of prognosis or outcome-related variables; in the event that an attribute is assigned to at least a minimum subset of the set of therapy-related variables and a less-than-minimum subset of the prognosis or outcome-related variables, assigning a temporary node address to the target patient based on the assigned attributes of the set of therapy-related variables, the temporary node address being associated with predetermined therapy plan information to facilitate therapy decisions, the predetermined therapy plan information being tailored to a particular combination of attributes embodied in the temporary node address; providing the predetermined treatment plan information to at least one of the patient's healthcare provider's one or more third-party systems; accessing or receiving a second data set comprising updated or additional personal health information associated with the target patient at or for a second time period later than the first time; assigning updated attributes to at least some variables of the set of preselected variables and/or assigning new attributes to preselected variables to which attributes were not previously assigned based on the accessed or received second data set; and in the case of assigning an attribute to at least a minimum subset of the treatment-related variables and at least a minimum subset of the prognosis-or outcome-related variables; assigning an optimized node address to the target patient based on the currently assigned attributes of the set of therapy-related variables and the currently assigned attributes of the set of prognosis or outcome-related variables; and determining the prognosis-related expected outcome for the target patient with respect to the occurrence of the defined endpoint event based on the optimized node address assigned to the target patient.

In one embodiment, the minimum subset of the treatment-related variables are the treatment-related variables in the set of pre-selected variables that are needed to provide pre-selected treatment-related information tailored to a particular combination of treatment-related attributes of a patient to guide treatment decisions. In some embodiments, the minimal subset of the treatment-related variables of the target patient is dependent at least in part on the type of cancer and the treatment intent of the target patient. In some embodiments, the minimum subset of the treatment-related variables includes cancer type, cancer stage, and treatment intent, wherein which other of the treatment-related variables are included in the minimum subset of the treatment-related variables depends at least in part on the cancer type and the treatment intent of the target patient. In some embodiments, accessing or receiving a first data set comprising personal health information associated with the target patient at or within a first time period comprises accessing or receiving information about the target patient's cancer type and treatment intent; wherein the computing system is further configured to determine a minimum subset of treatment-related variables based on the received information regarding the type of cancer and the treatment intent of the target patient.

In some embodiments, the computing system is further configured to present a user interface to the patient and/or a healthcare provider of the patient for inputting data in the first data set. In some embodiments, the user interface directs the user to enter at least a minimum subset of treatment-related variables.

In some embodiments, the computing system is further configured to present a user interface to the patient and/or a healthcare provider of the patient for inputting data in the first data set; and receiving information about the type of cancer of the target patient and the treatment intent of the target patient; and after determining the minimum subset of the therapy-related variables based on the received information regarding the cancer type of the target patient and the therapy intent of the target patient, inputting, via the user interface guide, a remaining portion of the minimum subset of the therapy-related variables. In some embodiments, the minimum subset of the prognostic or outcome-related variables is all of the prognostic or outcome-related variables in the set of preselected variables required for statistical analysis of prior outcomes. In some embodiments, the second data set includes data obtained from a health record of the target patient. In some embodiments, assigning updated attributes to at least some of the set of preselected variables based on the accessed second dataset and/or assigning new attributes to preselected variables to which attributes were not previously assigned includes verifying and/or correcting problems detected in the second dataset to determine updated or new attributes. In some embodiments, the first data set comprises data obtained from a health record of the target patient.

In some embodiments, the computing system is further configured to assign attributes to at least some variables of the set of preselected variables. In some embodiments, the prognosis-related expected outcome for the target patient is determined from a statistical analysis of previous prognosis-related outcomes for patients in a prognosis-or outcome-based patient group that are each assigned the same optimized node address as the optimized node address assigned to the target patient at a point of treatment and disease progression corresponding to the target patient.

In some embodiments, the computing system is further configured to perform a statistical analysis on the previous outcomes of patients in the prognosis or outcome based patient group to determine a current expected prognosis related outcome for the target patient. In some embodiments, the current expected prognosis-related outcome is a time to progress from the start of second-line therapy to the start of third-line therapy, and wherein the patients in the prognosis-or outcome-based patient group are patients that are each assigned the same optimized node address at the start of second-line therapy as the optimized node address assigned to the target patient.

In some embodiments, the computing system is further configured to perform an updated statistical analysis of previous outcomes of patients in the prognosis or outcome based patient group to determine an updated current expected prognosis related outcome, and to store information about the updated current expected prognosis related outcome.

In some embodiments, the computing system is configured to periodically perform the updated statistical analysis.

In some embodiments, the prognosis-related expected outcome for the target patient is determined from a statistical analysis of previous prognosis-related outcomes for patients in a prognosis-or outcome-based patient group, at least some of the patients being assigned the same optimized node address as the optimized node address assigned to the target patient at a point of treatment and disease progression corresponding to the target patient.

In some embodiments, the computing system is further configured to transmit information regarding the prognosis-related expected outcome to a client device associated with the patient's healthcare provider or the target patient's healthcare payer.

In some embodiments, the computing system is further configured to access information regarding the outcome of the target patient; comparing the outcome of the target patient with the determined prognosis-related expected outcome of the target patient; and transmitting information regarding the comparison to a healthcare provider of the patient or a healthcare payer of the target patient;

In some embodiments, the computing system is further configured to determine an expected treatment cost for the target patient for the disease during the clinically relevant period based on treatment costs assigned to all patients in a prognosis-or outcome-based patient group that are each assigned the same optimized node address as the optimized node address assigned to the target patient at the treatment and disease progression point corresponding to the target patient. In some embodiments, the optimized node address assigned to the target patient has an associated expected treatment cost for the disease from diagnosis to death or cure determined by statistical analysis of prior treatment costs from diagnosis to death or cure for patients in the prognosis-or outcome-based patient group that are each assigned the same optimized node address as the optimized node address assigned to the target patient at diagnosis.

In some embodiments, the computing system is further configured to access information regarding billing costs for treatment of the target patient and determine a total cost of treatment for the target patient over the clinically relevant period; and comparing the expected cost of treatment of the target patient over a clinically relevant period to the total cost of treatment of the target patient over the clinically relevant period. In some embodiments, the clinically relevant period is from diagnosis to death or cure.

In some embodiments, the computing system is further configured to compare the one or more outcomes of the target patient to one or more historical outcomes of patients in a prognosis-or outcome-based group to determine whether the one or more outcomes of the target patient are trending away from criteria of the prognosis-or outcome-based group, the patients each being assigned an optimized node address that is the same as the optimized node address assigned to the target patient at the time of diagnosis or at the time of progression.

In some embodiments, the computing system is further configured to determine whether one or more outcomes of the target patient are trending away from the criteria of the prognosis-based or outcome group, and in the event that it is determined that the one or more outcomes of the target patient are trending away from the criteria, send an alert to a health care provider or health payer of the target patient, the alert including information regarding the one or more outcomes that are trending away from the criteria.

In some embodiments, the computing system is further configured to determine whether a total cost of treatment for the patient over a clinically relevant period exceeds an expected cost of treatment for the patient over a clinically relevant period by a threshold amount, and to send an alert to a healthcare provider or health payer of the target patient if the total cost of treatment exceeds the expected cost of treatment.

In some embodiments, the computing system is further configured to, after accessing or receiving the second data set, iteratively access or receive an updated or new data set comprising personal health information associated with the patient; and after accessing or receiving each updated or new data set: assigning updated attributes to at least some variables of the set of preselected variables and/or assigning attributes to preselected variables for which attributes were not previously assigned based on the accessed or new data set; and in the event that an attribute is assigned to at least a minimum subset of the therapy-related variables and at least a minimum subset of the prognosis-or outcome-related variables, assigning an optimized node address or an updated optimized node address to the target patient based on the currently assigned attributes of the set of therapy-related variables and the currently assigned attributes of the set of prognosis-or outcome-related variables.

In some embodiments, the computing system is further configured to receive or access information regarding a change in the set of preselected variables, the change comprising adding one or more variables to the set of treatment-related variables and/or the set of prognosis or outcome-related variables; assigning an attribute to at least one variable of the one or more variables added to the set of therapy-related variables and/or the set of prognosis or outcome-related variables based on current personal health information associated with the target patient; and assigning a different optimized node address to the target patient based on the assigned attributes of the therapy-related variable and the prognosis or outcome-related variable. In some embodiments, the second data set comprises data indicative of the progression of the disease after the first time point or after the first time period. In some embodiments, the first data set includes information about a first diagnosis and the second data set includes information about an updated diagnosis after the first diagnosis. In some embodiments, the second data set includes information about attributes that provide no information or incomplete information in the first data set. In some embodiments, the prognostic-related expected outcome with respect to defining the occurrence of an endpoint event includes one or more of overall survival, progression-free survival, or disease-free survival. In some embodiments, the predetermined treatment plan information comprises information regarding one or more predetermined patient care service packs, wherein providing the predetermined treatment plan information to the healthcare provider of the target patient comprises providing information regarding the one or more predetermined patient care service packs.

In some embodiments, the computing system is further configured to provide current predetermined treatment plan information to the healthcare provider of the target patient in the event that the predetermined treatment plan information associated with the temporary node address of the target patient changes before a treatment decision has been made or before an optimized node address has been assigned to the target patient.

In some embodiments, the computing system is further configured to provide an alert to a healthcare provider of the target patient that the predetermined treatment plan information associated with the temporary node address assigned to the target patient has changed.

In some embodiments, the computing system is further configured to generate the temporary node address based on the assigned attributes of the set of therapy-related variables prior to assigning the temporary node address to the target patient.

In some embodiments, the computing system is further configured to generate the optimized node address based on the assigned treatment-related variable and the assigned prognosis or outcome-related variable prior to assigning the optimized node address to the target patient.

In some embodiments, the computing system is further configured to assign the target patient to a prognosis or outcome based group based on the optimized node address assigned to the target patient; measuring a change in behavior of each of a plurality of medical care providers assigned to the plurality of patients of the prognosis-or outcome-based group; and identifying a lack of necessary care and/or providing unnecessary care that causes a difference in the measured behavior of at least one of the medical care providers.

According to another aspect, the described invention provides a non-transitory computer readable medium comprising program instructions for facilitating early treatment decisions and determining a prognosis-related expected outcome with respect to the occurrence of a defined endpoint event for a target patient diagnosed with a disease, wherein execution of the program instructions by one or more processors causes the one or more processors to perform the method of any one of claims 1 to 40.

Drawings

The drawings are intended to illustrate the teachings described herein, and are not intended to show relative sizes and dimensions, or to limit the scope of examples or embodiments. In the drawings, the same reference numerals are used throughout the drawings to designate the same features and components having the same functions.

Fig. 1 schematically illustrates a network diagram for providing a Clinical Outcome Tracking and Analysis (COTA) module to a user computing device, according to some embodiments of the present disclosure.

Fig. 2 schematically illustrates some of the functionality provided by a COTA module, according to some embodiments of the present disclosure.

Fig. 3A shows a block diagram of ranking data associated with colon cancer patients using a COTA module, according to one embodiment of the present disclosure.

Fig. 3B schematically illustrates aspects of a COTA module ordering data by employing a unique combination of attributes corresponding to a node address according to one embodiment of the disclosure.

Figure 3C is a block diagram illustrating a directed graph for determining strings of numbers representing phenotypic features of node addressing, according to some embodiments of the present disclosure.

Fig. 4A is a flow diagram schematically illustrating a method of assigning a temporary node address and/or an optimized node address to a target patient and providing predetermined treatment plan information based on the assigned temporary or optimized node address, according to some embodiments.

Fig. 4B is a flow diagram that schematically illustrates a method that includes accessing or receiving updated or additional data for a target patient and assigning or updating an assigned optimized node address to the target patient, determining a prognosis-related expected outcome based on the optimized node address, and providing the target patient with the determined prognosis-related outcome information, according to some embodiments.

Fig. 4C is a flow diagram illustrating a method according to some embodiments that includes measuring behavioral differences for each medical care provider for each patient and identifying a lack of necessary care and/or providing unnecessary care.

Figure 4D is a flow diagram illustrating a method according to some embodiments including determining a change in a preselected variable included in the temporary node address and assigning a modified temporary node address to the target patient based on the change in the preselected variable.

Figure 4E is a flow diagram illustrating a method according to some embodiments including determining a change in a preselected variable included in an optimized node address and assigning a modified optimized node address to a target patient based on the change in the preselected variable.

Fig. 5 shows a flow diagram of a COTA module responding to a trigger to transmit an alert according to one embodiment of the present disclosure.

Fig. 6 schematically illustrates a mobile device organizing received alerts according to one embodiment of the present disclosure.

Figure 7 depicts a graphical representation of the incidence of cancer subtypes provided by a COTA module, according to one embodiment of the present disclosure.

FIG. 8 is a graphical representation of a search optimized by variables input into a COTA module according to one embodiment of the present disclosure.

Figure 9 illustrates a graphical user interface including a list of a plurality of variables related to a particular disease, according to one embodiment of the present disclosure.

Figure 10 shows a graphical user interface including a real-time Kaplan Meier curve with confidence intervals for pancreatic cancer, according to one embodiment of the present disclosure.

Figure 11 shows a graphical user interface including a Kaplan Meier curve according to disease progression according to one embodiment of the present disclosure.

Figure 12 illustrates a graphical user interface including a graphical representation of a real-time baseline of outcomes between two parties, according to one embodiment of the present disclosure.

Figure 13 illustrates a graphical user interface including a graphical representation of an expense report showing an outcome graph as a function of treating physician based on expense, according to one embodiment of the present disclosure.

Fig. 14A and 14B illustrate a graphical user interface including a graphical representation of a treatment interface displaying outcomes based on patient decisions affecting treatment, according to one embodiment of the present disclosure.

Figure 15 illustrates a graphical user interface including a graphical representation of an ending screen according to one embodiment of the present disclosure.

Figure 16 illustrates a graphical user interface including a graphical representation of a treatment detail report screen showing a relationship between treatment cost and outcome (particularly survival rate) for lung cancer, according to one embodiment of the present disclosure.

Figure 17 illustrates a graphical user interface including a graphical representation of an analysis screen comparing toxicity and cost according to one embodiment of the present disclosure.

Figure 18 illustrates a graphical user interface including a graphical representation of an analysis screen comparing treatment and quality of life, according to one embodiment of the present disclosure.

Fig. 19 is a flow diagram of feedback support provided to a medical professional according to some embodiments of the present disclosure.

Fig. 20-22 show graphical user interfaces including treatment-related and prognosis or outcome-related variables for different diagnostic types, according to some embodiments of the present disclosure.

Figure 23 shows a graphical user interface including a graphical representation showing data generation and ranking of COTA modules for breast oncology for breast cancer histology with invasive ductal carcinoma from 2008 to 2013 and correlating Her2neu status with outcome (i.e., overall survival/survival) according to one embodiment of the present disclosure.

Figure 24 illustrates a graphical user interface including a graphical representation of data generation and ordering of COTA modules showing breast oncology for breast cancer tumor grading and staging in 2008-2013 according to one embodiment of the disclosure.

Figure 25 illustrates a graphical user interface including a graphical representation showing data generation and ordering for COTA modules in breast cancer-IIB stage 2008 to 2013, according to an embodiment of the present disclosure.

Figure 26 illustrates a graphical user interface including a graphical representation showing the overall survival outcome for a breast cancer patient according to one embodiment of the present disclosure.

Figure 27 illustrates a graphical user interface including a graphical representation showing breast cancer outcome, particularly a comparison between two parties, according to one embodiment of the present disclosure.

Figure 28 schematically shows a client device according to one embodiment of the present disclosure.

Fig. 29 is a block diagram that schematically illustrates the internal architecture of a computer, in accordance with an embodiment of the present disclosure.

Detailed Description

Embodiments will now be discussed in more detail with reference to the drawings of the present application. In the drawings, like and/or corresponding elements are referred to by like reference numerals.

Described herein are systems, methods, and non-transitory computer-readable media that assist a healthcare provider in providing treatment plan information using a temporary node address assigned to a target patient to guide treatment decisions for the target patient, and that use one or more optimized node addresses that are each usable to determine an expected outcome for the target patient. In some embodiments, the optimized node address may be used to help payers make payment decisions based on expected outcomes that are adjusted for risk. In some embodiments, the systems, methods, and non-transitory computer-readable media generate and assign temporary node addresses, and generate, assign, and update optimized node addresses for patients. In some embodiments, the methods and systems integrate the information needed for a healthcare provider to make early treatment decisions based on an initial temporary node address associated with a target patient. In some embodiments, the systems and methods integrate information needed to make a treatment decision and information related to the patient's outcome related to the expected prognosis into an optimized node address and determine the patient's outcome related to the expected prognosis. In some embodiments, the systems and methods integrate information about historical costs of a patient population and determine an expected outcome of the cost-to-risk ratio adjustment for payment decisions by an insurance provider. Further, in some embodiments, the systems and methods update (e.g., automatically or periodically) the optimized node address based on the latest information available to the system. In this regard, the system and method improves operational efficiency over conventional systems, and unlike conventional systems, reduces the need for repeated queries and information retrieval from a variety of different systems in order to determine treatment and payment decisions.

Embodiments described herein advantageously provide at least two different types of functionality in one integrated method or system. The temporary node addresses used in the methods and systems described herein facilitate early treatment decisions for the patient. For example, in some embodiments, the temporary node address assigned to the patient is associated with predetermined treatment plan information that is specific to the combination of treatment-related attributes or parameters that the temporary node address represents. The term "attribute" as used herein refers to a value of a predetermined variable, the combination of which is used to determine an optimized node address and/or a temporary node address. As described below, the treatment plan information may include information for the treatment plan and/or treatment strategy that is specific to all treatment-related variables or attributes of the patient. In some embodiments, the treatment plan information includes information about one or more predetermined patient care service packs. For example, in some embodiments, the predetermined treatment plan information may be information regarding one or more predetermined patient care service packs. The predetermined patient care service package may include recommended therapy sessions tailored to patient-specific attributes of therapy-related variables or parameters. In some embodiments, the predetermined treatment plan information associated with the temporary node address assigned to the patient is provided to the patient's healthcare provider or the patient's healthcare payer. Additionally, in some embodiments, when additional or updated information related to patient treatment is received prior to assigning the optimized node address to the patient and prior to making a treatment decision for the patient, the temporary node address is updated or changed as needed based on the additional or updated information related to treatment. If the updated or changed node address is associated with different therapy-related information, such as different predetermined patient care service packages, information regarding the different therapy-related information, such as information regarding the different predetermined patient care service packages, is provided to the patient's healthcare provider or patient healthcare payer. In some embodiments, the temporary node address is used only to guide early or initial treatment decisions (e.g., within a short time after diagnosis) when an optimized node address has not been assigned, and the optimized node address assigned to the patient later is used to guide treatment decisions after the optimized node address is assigned.

In some embodiments, the temporary node address is assigned within 2 days of diagnosis, within 3 days of diagnosis, within 4 days of diagnosis, within 5 days of diagnosis, within 6 days of diagnosis, within 7 days of diagnosis, within 8 days of diagnosis, within 9 days of diagnosis, within 10 days of diagnosis, within 11 days of diagnosis, within 12 days of diagnosis, or within 13 days of diagnosis. In some embodiments, the optimized node address is assigned within 14 days of diagnosis, within 18 days of diagnosis, within 22 days of diagnosis, within 26 days of diagnosis, within 30 days of diagnosis, within 34 days of diagnosis, within 38 days of diagnosis, or longer.

In some embodiments, initial data about a patient will be accessed, received, or provided by a system or method at the time of diagnosis or shortly after diagnosis of the patient (e.g., within 2 days of diagnosis, within 3 days of diagnosis, within 4 days of diagnosis, within 5 days of diagnosis, within 6 days of diagnosis, within 7 days of diagnosis, within 8 days of diagnosis, within 9 days of diagnosis, within 10 days of diagnosis, within 11 days of diagnosis, within 12 days of diagnosis, or within 13 days of diagnosis). In assigning a temporary node address, the patient data provided, received, or accessed may include sufficient information to determine or guide the determination of a recommended course of therapy for the patient, but insufficient to provide a prognosis-related expected outcome (e.g., overall survival, progression-free survival, or disease-free survival) with respect to the occurrence of a defined endpoint event for the patient. Rather than waiting to receive information relating to prognosis-related expected outcome, but not to early treatment recommendations, before assigning the patient a node address for determining a recommended course of treatment, assigning the patient a temporary node address containing only treatment-related information enables the system or method to assist a healthcare provider or healthcare payor in guiding treatment decisions for the patient, particularly early in the course of the disease after diagnosis. In some embodiments, the first data set including personal health information about the patient for assigning the temporary node address is obtained from the patient, a healthcare provider of the patient, or both via a user interface. The user interface may be configured to direct the patient or healthcare provider to provide at least a minimal set of information regarding the treatment-related variables used to assign the temporary node address. This may enable fast or on-demand assignment of temporary node addresses, as well as fast access to therapy information associated with the temporary node addresses. In some embodiments, at least some of the variables included in the minimum set of therapy-related variables used to assign the temporary node address may depend on the value of some of the therapy-related variables of the patient (e.g., cancer type and therapy intent). In some embodiments, the first data set includes data obtained from a health record of the patient.

The system or method provides additional functionality through the use of optimized node addresses. In some embodiments, upon accessing or receiving additional information about the patient including at least a minimal amount of information related to the prognosis-related expected outcome, the patient is assigned an optimized node address for determining the prognosis-related expected outcome of the patient. In some embodiments, the optimized node address is used to determine a risk adjusted expected outcome for the patient. In some embodiments, a patient is assigned a temporary node address at or shortly after diagnosis, and the temporary node address is used to guide treatment decisions, even if the system or method receives or accesses enough initial information to assign an optimized node address. In other embodiments, if the initial information provided is sufficient to assign the optimized node address to the patient, the optimized node address is assigned to the patient and only a portion of the optimized node address that includes the treatment-related variable is used to provide the predetermined treatment plan information (e.g., information about one or more predetermined patient care service packs) to the patient's healthcare provider or the patient's healthcare payer.

In some embodiments, the optimized node address assigned to the target patient is associated with a prognosis or outcome based patient group. In some embodiments, the prognosis-related expected outcome for the target patient is determined by statistical analysis of prior prognosis-related outcomes for patients in the outcome-based or prognosis-based group. In some embodiments, the prognosis-or outcome-based patient group includes patients that have been assigned or are assigned the same optimized node address as the optimized node address assigned to the target patient at the disease progression point (e.g., progression to cancer) of each patient corresponding to the target patient. In some embodiments, only one optimized node address is associated with a prognosis or outcome based patient group. For example, in some embodiments, each patient in a prognosis-based or outcome-based patient group used to determine a prognosis-related expected outcome for a target patient is assigned the same optimized node address as the target patient at the point of treatment and disease progression corresponding to the target patient. In other embodiments, more than one optimized node address is associated with the same prognosis or outcome based patient group to determine a prognosis-related prospective outcome for the target patient. For example, where the number of previous patients assigned optimized node addresses is relatively small, the small number of patients significantly affects the reliability of statistical analysis based solely on previous patients assigned a particular optimized node address, and patients assigned a plurality of optimized node addresses having variable differences less relevant to prognosis or outcome may be combined into a prognosis or outcome based patient group for analysis.

In some embodiments, the expected treatment cost for a patient over a treatment cycle is determined using a statistical analysis of historical costs for patients in the outcome-based or prognosis-based group associated with the optimized node address assigned to the target patient. In some embodiments, an insufficient number of previous patients may have been assigned a single optimized node address for a treatment-based statistical analysis of the patients assigned the single optimized node address. In such embodiments, since patients assigned different optimized node addresses may have common treatment-related variables and attributes and/or may have been assigned the same temporary node address, treatment-based statistical analysis of previous patients having the same attributes of variables used in the temporary node address or being assigned the same temporary node address may enable statistical analysis. In some embodiments, where variables in the plurality of optimized node addresses that differ in attributes are not or are less relevant to treatment, a treatment-based statistical analysis may be performed based on treatment groups associated with the plurality of optimized node addresses.

Assigning a temporary node address or an optimized node address to a target patient based on attributes assigned to preselected variables in personal health information associated with the target patient is described. This may also be described as assigning the patient to a temporary node address or an optimized node address. In some embodiments, this may also be described as assigning a temporary node address or an optimized node address to personal health information associated with the target patient.

Various embodiments are disclosed herein. However, it is to be understood that the disclosed embodiments and the illustrated user interfaces are merely examples of the present disclosure, which may be embodied in various forms. Furthermore, each of the examples given in connection with the various embodiments is intended to be illustrative, and not restrictive. Additionally, the figures are not necessarily to scale, some features may be exaggerated to show details of particular components (and any dimensions, materials, and similar details shown in the figures are intended to be illustrative and not limiting). Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to variously employ the disclosed embodiments.

Embodiments are described below with reference to block diagrams and operational illustrations of methods and systems. It will be understood that each block of the block diagrams or operational illustrations, and combinations of blocks in the block diagrams or operational illustrations, can be implemented by analog or digital hardware and computer program instructions. These computer program instructions may be provided to one or more processors of a general purpose computer, special purpose computer, ASIC, or other programmable data processing apparatus, or multiple programmable data processing apparatuses, such that the instructions, which execute via the one or more processors of the computer or other programmable data processing apparatus, implement the functions/acts specified in the block diagrams or operational block or blocks.

In some alternative implementations, the functions/acts noted in the blocks may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, embodiments of the methods presented and described in this disclosure as flowcharts are provided by way of example in order to provide a more complete understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is varied, and in which sub-operations described as part of larger operations are performed independently.

Although described with respect to cancer, the described clinical outcome therapy analysis may be used for any clinical disease, e.g., cardiovascular disease, metabolic disease (diabetes), immune-mediated disease (e.g., lupus, rheumatoid arthritis), organ transplantation, neurodegenerative disease, pulmonary disease, infectious disease, and liver disease. The practitioner knows the parameters for each such disease. In some embodiments, the methods and systems are specific to cancer.

Throughout the specification and claims, terms may have meanings suggested or implied above or below their meanings as specifically set forth. Likewise, the phrase "in one embodiment" as used herein does not necessarily refer to the same embodiment, and the phrase "in another embodiment" as used herein does not necessarily refer to a different embodiment. For example, the claimed subject matter is intended to include all or a partial combination of the example embodiments.

In general, terms may be understood at least in part by context. For example, terms used herein, such as "and," "or," "and/or," may include a variety of meanings that may depend at least in part on the context in which the terms are used. Typically, "or" if used in association lists, such as A, B or C, is intended to mean A, B and C in the inclusive sense, and A, B or C in the exclusive sense. Furthermore, the term "one or more" as used herein may be used to describe any feature, structure, or characteristic in the singular or may be used to describe a combination of features, structures, or characteristics in the plural, depending, at least in part, on the context. Similarly, terms such as "a," "an," or "the" may also be understood in the singular or plural, depending at least in part on the context. Moreover, the term "based on" may be understood to not necessarily convey an exclusive set of factors, but may allow for the presence of additional factors not necessarily expressly described, again depending at least in part on the context.

As used herein, a target patient refers to a patient whose personal health information is accessed or received, and that patient is assigned a temporary and/or optimized node address, or is assigned a temporary and/or optimized node address. The phrase "target" is used only to distinguish the patient from other patients that may be included in the prognosis-based or outcome patient group (e.g., to determine a prognosis-related expected outcome for the target patient).

FIG. 1 schematically illustrates a network diagram of computing systems, devices, networks, and databases that may be used in conjunction with embodiments described herein. According to one embodiment, the network diagram shown illustrates a computing system 205 (also referred to herein as a server 205) in communication with a user computing device (also referred to herein as a client device) 210 over a network 215 to provide a Clinical Outcome Tracking and Analysis (COTA) module 220 to the user computing device 210. Computing system 205 may generate and/or provide content, such as web pages, for display by a browser (not shown) of user computing device 210 over a network 215, such as the internet. In one embodiment, COTA module 220 is a web page (or portion of a web page) and is accessed by a user of user computing device 210 via a web browser. In another implementation, the COTA module 220 is a software application, such as a software or mobile "app" installed on the user computing device that may be downloaded to the user computing device 210 from the computing system 205 or a third party computing system. In further embodiments, COTA module 220, when executed on user computing device 210, provides a graphical user interface to implement the functionality described herein. For example, computing system 205 may host COTA module 220, and user computing device 210 may execute an instance of the COTA module. COTA module 220 may be a Web-based application or a non-Web-based application. In some embodiments, the user computing device is a healthcare provider, a healthcare system, a healthcare payment system, or a patient's computing device. In some embodiments, different aspects of COTA module 220 may be executed on a plurality of different user computing devices, all of which may be associated with one entity, such as with a healthcare provider, or which may be associated with different entities, such as a client device associated with a patient and another client device associated with a healthcare provider.

A computing device embodied in whole or in part as computing system 205 and/or user computing device 210 may be capable of sending or receiving signals, such as via a wired or wireless network, or may be capable of processing or storing signals in a physical memory state, such as in memory. Devices and systems capable of operating as computing system 205 include, but are not limited to, for example, dedicated rack-mounted servers, desktop computers, laptop computers, set-top boxes, integrated devices combining various features, such as two or more of the features of the aforementioned devices, and the like. Embodiments of computing system 205 may vary significantly in configuration or capability, but may generally include one or more central processing units and memory. Computing system 205 may also include one or more mass storage devices, one or more power supplies, one or more wired or wireless network interfaces, one or more input/output interfaces, or one or more operating systems, such asServer、OSAnd so on. Computing system 205 may include a number of different computing devices. Computing system 205 may include multiple computing devices networked to one another. The computing system 205 may include a network of processors, or may employ a network of remote processors for processing (e.g., cloud computing).

Computing system 205 may include a device that includes a configuration to provide content to another device via a network. The computing system 205 may also provide various services including, but not limited to, Web services, third-party services, audio services, video services, email services, Instant Messaging (IM) services, SMS services, MMS services, FTP services, Voice Over IP (VOIP) services, calendar services, photo services, and the like. Examples of content may include text, images, audio, video, etc., which may be processed in the form of physical signals (e.g., electrical signals) or may be stored in memory, e.g., in a physical state. Examples of devices that may operate as computing system 205 or be included in computing system 205 include desktop computers, multiprocessor systems, microprocessor-based or programmable consumer electronics, and the like.

In one embodiment, computing system 205 hosts or is in communication with one or more databases 240a, 240 b. Databases 240a, 240b may be stored locally or remotely from computing system 205. In one embodiment, COTA module 220 accesses or searches or orders data stored in one or more databases 240a, 240 b. COTA module 220 may also retrieve information over network 215 (e.g., from the internet). The databases 240a, 240b may store patient data or other relevant medical information individually or collectively. For example, other relevant medical information stored in a database or retrieved by the COTA module may include information related to the definition or identification of a preselected variable that is relevant to the treatment or prognosis of a disease or condition. In some embodiments, information related to the identification of preselected variables relevant to the treatment or prognosis of a disease or condition can be based on information from experts in their respective areas (e.g., oncologists with experience of more than 5 years, 10 years, 15 years, 20 years, 30 years, etc.). In some embodiments, data is entered into databases 240a, 240b and/or COTA module 220 manually, automatically, or both. The databases 240a, 240b may be individually or collectively configured to store one or more of Personal Health Information (PHI), preselected variables, attributes of preselected variables, predetermined patient care service packages, diagnostic information, temporary node addresses, optimized node addresses, and prognosis or outcome based group information associated with each patient in a group of patients. In some embodiments, the one or more databases 240a, 240b may include a plurality of different databases. The multiple different databases may store different subsets of information, different types of information, information from different health providers, information from different types of systems, or any other portion of information. In some embodiments, the databases 240a, 240b are stored in a plurality of different memories. In some embodiments, databases 240a, 240b are stored in one or more storage devices that are remote from each other. A plurality of different databases or memories may each be directly or indirectly accessed by COTA module 220 and/or directly or indirectly provide information to COTA module 220.

The network may couple the devices such that communications may be exchanged, such as between a server and a client device or other type of device, including between wireless devices coupled via a wireless network, for example. The network may also include mass storage, such as, for example, Network Attached Storage (NAS), a Storage Area Network (SAN), or other forms of computer or machine readable media. The network may include the internet, one or more Local Area Networks (LANs), one or more Wide Area Networks (WANs), wired type connections, wireless type connections, or any combination thereof. Likewise, subnetworks that may employ different architectures or may comply or be compatible with different protocols may interoperate within a larger network. For example, various types of devices may be used to provide interoperability for different architectures or protocols. As one illustrative example, a router may provide links between separate and independent LANs.

The communication links or channels may include, for example, analog telephone lines, all-or partial-digital lines including T1, T2, T3, or T4 type lines, Integrated Services Digital Networks (ISDN), Digital Subscriber Lines (DSL), wireless links including satellite links, or other communication links or channels as may be known to those of skill in the art. Further, the computing device or other related electronic devices may be remotely coupled to the network, such as via a telephone line or link, for example.

A wireless network may couple the client device with the network 215. The wireless network 215 may employ a standalone ad hoc network, a mesh network, a wireless lan (wlan), a cellular network, or the like. The wireless network 215 may also include a system of terminals, gateways, routers, and the like coupled by radio links, and the like, that can move freely, randomly, or organize themselves arbitrarily such that the network topology may change from time to time or even rapidly. The wireless network 215 may also employ a variety of network access technologies including Long Term Evolution (LTE), WLAN, Wireless Router (WR) networking, or 2 nd, 3 rd, or 4 th generation (2G, 3G, or 4G) cellular technologies, and the like. Network access technologies may enable wide area coverage, such as client devices with varying degrees of mobility, for example.

For example, the network 215 may enable RF or wireless type communications via one or more network access technologies such as Global System for Mobile communications (GSM), Universal Mobile Telecommunications System (UMTS), General Packet Radio Service (GPRS), Enhanced Data GSM Environment (EDGE), 3GPP Long Term Evolution (LTE), LTE-advanced, Wideband Code Division Multiple Access (WCDMA), Bluetooth, 802.11b/g/n, and so forth. A wireless network may include virtually any type of wireless communication mechanism by which signals may communicate between devices, such as client devices or computing devices, between or within networks, and the like.

In one embodiment, the user computing device 210 is a computer. In one embodiment, the user computing device 210 is a terminal of a computer system. In one embodiment, the user computing device 210 is a tablet computer. In one embodiment, the user computing device 210 is a smartphone. The user computing device 210 may be any other suitable computing device or computing system.

In one embodiment, some or all of COTA module 220 may be implemented in a "cloud computing" environment or as a "software as a service" (SaaS). For example, at least some of the operations may be performed by a set of computers (as an example of machines including processors), where the operations may be accessed via a network (e.g., the internet) and via one or more appropriate interfaces (e.g., APIs). The example embodiments may be implemented in digital electronic circuitry, or in computer hardware, firmware, software, or in combinations of them. Example embodiments may be implemented using at least one computer program product, e.g., a computer program tangibly embodied in an information carrier, e.g., in a machine-readable medium, for execution by, or to control the operation of, data processing apparatus, e.g., a programmable processor, a computer, or multiple computers.

In some embodiments, COTA module 220 enables effective management of patient care for better clinical outcome at a controlled cost. In one embodiment, COTA module 220 is a connector or interface between a third party and a medical professional (e.g., oncologist) including a medical provider. In one embodiment, COTA module 220 is an analysis tool configured to rank cancers and cancer patients to the highest level of clinical and molecular fidelity associated with treatment decisions and with prognostic-related predicted outcomes. In some embodiments, COTA module 220 tracks outcomes, such as Overall Survival (OS) (meaning the length of time from the date of diagnosis or treatment of a disease, such as cancer, that a patient diagnosed with the disease still survives, with the end event being death from any cause), Progression Free Survival (PFS) (meaning the length of time during and after treatment of a disease, such as cancer, that the patient lives with the disease but the disease does not worsen, and uses the progression of the disease as an end point, e.g., tumor growth or spread), disease free survival (in cancer, meaning the length of time that the patient survives without any signs or symptoms of the cancer after the end of primary treatment of the cancer, with the end event being a recurrence), and real-time costs. In some embodiments, the methods and systems generate and assign temporary node addresses and generate, assign, and update optimized node addresses to assist healthcare providers in making treatment decisions, including making early treatment decisions immediately after diagnosis, and to assist healthcare providers and/or healthcare payers by providing information about expected prognosis-related outcomes specific to patients. In some embodiments, the prospective prognosis-related outcome may be used to adjust risk analysis of outcomes when making decisions regarding treatment payment.

As described above, in various embodiments, the user computing device 210 or one of the multiple computing devices 210 may be operated by any one of a patient, a healthcare provider system, a payer (e.g., an insurance company), and a medical professional. A patient, healthcare provider system, medical professional, or insurance company may execute an instance of COTA module 220 on user computing device 210 to interface with computing system 205. COTA module 220 may present GUI 250 on display 245. It will be appreciated that in some embodiments, GUI 250 may be different for each type of user. For example, in some embodiments, the patient, the healthcare provider system, the medical professional, or the insurance company may each be presented with a different GUI 250. In some embodiments, some aspects of the system or method may be executed on a user computing device 210 associated with a healthcare provider, and other aspects of the system or method may be executed on a user computing device 210 associated with a patient or a healthcare payer.

In one embodiment, COTA module 220 may alert a user of computing device 210 (e.g., a medical professional, a healthcare provider, a healthcare system, a healthcare payer) to provide relevant information at a critical moment in time. In some embodiments, COTA module 220 may also enable communication and collaboration between healthcare professionals, healthcare systems, healthcare payer systems, and content distribution (e.g., by healthcare professionals or healthcare systems). In one embodiment, COTA module 220 may enable a health professional to execute a risk contract (e.g., a bundled payment) with a payer.

Although COTA modules 220, systems, and methods are described herein for cancer, COTA modules 220, systems, and methods may be advantageously utilized to manage any of the diseases or conditions described above.

Fig. 2 is a block diagram illustrating some of the functionality 300 provided by the COTA module 220, according to one embodiment. In one embodiment, COTA module 220 performs ordering/grouping 310 that orders, groups, and/or identifies patients that meet one or more parameters. The parameter may be a parameter related to determining a course of treatment for the patient, a parameter related to an expected or actual outcome of the patient, a parameter related to a therapy provided to the patient, a parameter related to a healthcare provider or healthcare payer of the patient, or other potentially related parameters. Parameters can include, for example, demographic parameters such as gender, age, race, comorbidity, tobacco usage, medical record number, insurance source, primary healthcare professional, referral medical professional, hospital, approved service provider (e.g., pharmacy), disease-specific clinical and molecular phenotype, intent-to-treat, stage of treatment with respect to disease progression, and biomarkers. The parameter may be a simple indicator (e.g., positive, negative, inaccessible), a numerical-based parameter (e.g., tumor size), a criteria-based parameter (e.g., tumor grade), etc. In some embodiments, the parameters may be received by COTA module 220 as input of a user selection. In some embodiments, the user may be a healthcare provider of one or more patients, a medical professional treating one or more patients, a healthcare provider system of one or more patients, a healthcare service payer of one or more patients, or a patient. In some embodiments, parameters for grouping or ordering may be received or accessed by COTA module 220 in a manner other than user-selected input (e.g., automatically or periodically based on a query from another system, or based on information stored in a database). In some embodiments, the user-selected input may identify the patients and rank, group, or identify a group of patients (e.g., a treatment-based group of patients) having the same treatment-related parameters as the identified patients. In some embodiments, COTA module 220 may provide personal and/or collective information about patients in a patient group having the same therapy-related parameters as the identified patient without providing any personally identifiable information about the patients in the group. In some embodiments, the user-selected input may identify a patient (e.g., a target patient) and rank, group, or identify a group of patients (e.g., a prognosis or outcome based group of patients) having the same prognosis or outcome-related parameter as the identified patient. In some embodiments, COTA module 220 may provide personal and/or collective information about patients in a group of patients having the same prognosis or outcome parameters as the identified patient, without providing any personally identifiable information about the patients in the group. In some embodiments, the ordering or grouping is based at least in part on the temporary node address assigned to the identified patient or target patient, as described in further detail below. In some embodiments, the ordering or grouping is based at least in part on an optimized node address assigned or assigned to the identified patient or target patient at some point in the disease progression, as described in further detail below. In some embodiments, the ordering or grouping may be based at least in part on a temporary node address or an optimized node address assigned or assigned to the identified patient or target patient at some point in the progression of the disease.

In some embodiments, because each patient has a different mortality, morbidity, treatment, and cost associated with the expected outcome, the methods and systems may use the ranking or grouping function 310 of the COTA module 220 to rank the patients to the highest level of clinical and/or molecular fidelity. The term "highest level of clinical and/or molecular fidelity" refers to the highest level of patient information available according to the latest scientific and/or medical guidelines accepted in its related art. For example, where, for example, 10 tests can be conducted for lung cancer, the results of the 10 tests represent the highest level of clinical and/or molecular fidelity of the lung cancer. COTA module 220 may rank patients with lung cancer with any combination of the 10 outcomes. COTA module 220 may include additional scientific and/or medical guidelines accepted in the relevant art. In one embodiment, COTA module 220 collects all information that affects patient survival and/or prognosis and/or treatment based on the latest scientific and/or medical guidelines. In some embodiments, the ordering is performed using temporary node addresses or optimized node addresses as described below. In some embodiments, some information relevant to prognosis or outcome may be unknown at the time of diagnosis, but for parameters or variables relevant to early treatment decisions, the patient may still be ranked to the highest level of clinical and/or molecular fidelity using the temporal node address using the ranking or grouping function 310 of the COTA module 220. In some embodiments, some information related to treatment on a longer time scale and related to prognosis or outcome may not be available at or shortly after diagnosis. Although this information may be relevant to some treatment decisions, it should not wait until such information is available to guide early treatment decisions. In some embodiments, the temporary node address enables patients to be ranked or matched to guidelines on recommended treatments, using a ranking or grouping function 310, based on information about a minimum subset of treatment-related variables. In some embodiments, the optimized node address enables ranking of patients using a ranking or grouping function 310 and analysis of patients using the expected outcome function 160 of the COTA module with respect to information comprising a minimal subset of prognosis and outcome related variables. In some embodiments, the variable may be both a treatment-related variable and a prognosis and outcome-related variable.

In some embodiments, a temporary node address is assigned to the patient at or shortly after diagnosis, and an optimized node address is assigned to the patient after diagnosis, and at least at each subsequently identified disease progression. Thus, over time (e.g., as the disease progresses, as treatment intent changes, etc.), different optimized node addresses may be assigned to the patient. During the analysis, the relevant node address of the target patient depends on the specific analysis target. For example, if the expected time for the target patient to progress from the beginning of second-line therapy to the beginning of third-line therapy is of interest, the relevant optimized node address will be the optimized node address for the target patient at the beginning of second-line therapy. Similarly, for a outcome or prognosis based patient group whose historical data is to be analyzed to address the problem, in some embodiments, each patient in the outcome or prognosis based patient group has the same optimized node address as the target patient at the beginning of the second line treatment of that patient.

In some embodiments, the COTA module provides patient care plan information 314 specific to all treatment-related attributes or variables of the patient. In some embodiments, the patient care plan information is predetermined treatment plan information specific to a combination of treatment-related attributes or parameters represented by the temporary node address. As described below, the predetermined treatment plan information may include information about a treatment plan and/or treatment strategy that is specific to all treatment-related variables or attributes of the patient, or at least a minimum subset of the treatment-related attributes. In some embodiments, the treatment plan information includes information about one or more predetermined patient care service packs. The predetermined patient care service package may include recommended therapy sessions tailored to patient-specific attributes of therapy-related variables or parameters. In some embodiments, the predetermined treatment plan information associated with the temporary node address assigned to the target patient is provided to the patient's healthcare provider or the patient's healthcare payer. As used herein, the term "treatment-related variable" refers to a variable that is relevant to guide early treatment decisions. The minimum subset of therapy-related variables is the subset of therapy-related variables needed to provide a recommended course of therapy that is tailored to the patient information and therapy intent available at a point in time. If a variable is likely to be relevant to treatment and to prognosis or treatment, but is not needed to provide an accurate recommended course of treatment and may or may not be available shortly after diagnosis, then the variable may be considered to be a treatment-related variable that is not in the minimum subset required for treatment and is a prognostic or outcome-based variable, or may also be considered to be only a prognostic or outcome-based variable. The COTA module assigns a temporary node address and an optimized node address to the patient based on the received or accessed data including personal health information associated with the patient, as further described below.

In some embodiments, each temporary node address is associated with predetermined treatment plan information (e.g., one or more predetermined patient care service packs). In some embodiments, only one temporary node address is associated with a particular predetermined treatment plan information. In some embodiments, the one or more temporary node addresses are associated with the same predetermined treatment plan information (e.g., information about a particular patient care service bundle or bundles). In some embodiments, each optimized node address is associated with predetermined treatment plan information (e.g., information about one or more predetermined patient care service packs). In some embodiments, the at least one optimized node address is associated with the same predetermined treatment plan information (e.g., the same information about one or more predetermined patient care service packs). The predetermined treatment plan information associated with the temporary node address or the optimized node address will be updated over time as needed to reflect current criteria and guidelines for treatment of patients having a particular combination of treatment-related attributes corresponding to the temporary node address or the optimized node address.

In some embodiments, upon accessing or receiving the identification of the patient, the COTA module 220 determines or identifies a temporary node address assigned to the patient and provides predetermined treatment plan information (e.g., information about one or more predetermined patient care service packs) associated with the temporary node address (patient care plan function 314). In some embodiments, if the system provides or accesses enough initial information to assign an optimized node address at a particular start date for a particular analysis, the COTA module 220 provides the scheduled treatment plan information (e.g., information about one or more scheduled patient care service packs) then associated with the optimized node address. As described above, the treatment plan information may include information for the treatment plan and/or treatment strategy that is specific to all treatment-related variables or attributes of the patient. In some embodiments, the treatment plan information includes information about one or more predetermined patient care service packs.

In some embodiments, COTA module 220 provides prognostic-related expected outcome information specific to a particular patient's prognosis and outcome-related variables and attributes via expected outcome function 316 of COTA module 220. Based on the optimized node address assigned to the target patient, prognosis-related expected outcome information may be determined for the target patient. For a prognosis-related expected outcome, the outcome is relative to the occurrence of a defined endpoint event. For example, when the prognosis-related outcome is overall survival, the endpoint event is defined as death from any cause. As another example, when the prognosis-related outcome is progression-free survival, the endpoint is progression of the disease, such as tumor growth or spread. As another example, when the prognosis-related outcome is disease-free survival, the endpoint is relapse.

Additionally, in some embodiments, COTA module 220 performs outcome tracking and analysis 320. In some embodiments, providing prognosis-related expected outcome information 316 is part of outcome tracking and analysis 320. In other embodiments, providing prognostic-related expected outcome information 316 may be separate from outcome tracking and analysis 320. In some embodiments, the COTA module 220 tracks outcomes in real time. In some embodiments, COTA module 220 periodically tracks outcomes. In some embodiments, COTA module 220 tracks outcomes on demand or on demand. In one embodiment, the outcome tracking includes any or all of the following parameters: progression-free survival, overall survival, physical status/quality of life indicators, toxicity incidence/severity (e.g., degree of drug or drug damage to an individual), mortality, and drug utilization (e.g., delivered dose intensity, dose interval, and treatment duration). Other types of outcomes are also contemplated.

The overall survival may be the end point of the assay, which is typically expressed as a period of time (survival), e.g., several months. A median is typically used so that the endpoint of the assay can be calculated once 50% of the subjects have reached the endpoint. One example is disease-free survival, which is commonly used to analyze the outcome of treatment for localized disease, rendering the patient disease-free by, for example, surgery or surgery plus adjuvant therapy. In disease-free survival, the event is a relapse rather than death. Relapsed patients remain viable, but are no longer considered disease-free.

Progression-free survival refers to the length of time during and after a drug or treatment during which the treated disease (e.g., cancer) does not deteriorate. Progression-free survival is sometimes used as an indicator of the health status of patients with disease in an attempt to determine the effectiveness of a new therapy.

The element ECOG physical state/quality of life index refers to a method that can track the long-term quality of life of a patient. This index is part of the demographic parameter disease-specific clinical molecular phenotype (i.e., the stage of a patient's health at the start of treatment) and can be used for ranking. For example, ECOG physical status refers to the scale and criteria used by physicians and researchers to assess the progression of a patient's disease, to assess the effect of the disease on the patient's ability to live daily, and to determine appropriate treatment and prognosis. See, Oken, MM et al, "sensitivity and sensitivity criterion of the soft and easy collaborative environmental group," am.J.Clin.Oncol. (1982)5: 649-55. ECOG has a value from 0 to 5, wherein 0 indicates that the patient is functioning normally and not as foreign to the disease precursor; 1 indicates that the body is severely restricted in activity, but is ambulatory and capable of doing tasks of a mild or sedentary nature, such as mild housework, office work; 2 means ambulatory and capable of self-care at all, but not capable of any working activity, more than 50% of the waking hours being spent in bed activity; 3 means that there is limited self-care capacity, more than 50% of the waking hours are in bed or in wheelchair; 4 indicates that the patient is completely disabled, cannot take care of himself, and only lies in bed or sits on a wheelchair; and 5 means death. Comparison of the ECOG at the beginning of treatment with that after treatment reflects some aspects of the therapeutic effect.

In one embodiment, exemplary parameters regarding the outcome toxicity of a treatment include incidence and severity.

In one embodiment, the system and method enable increased accuracy of risk financial contracts between payers and providers so that parties can reduce treatment variability, waste, and inefficiency while still achieving the intended outcome.

In some embodiments, COTA module 220 may also transmit communications, such as alerts 330, to a medical professional (e.g., a doctor) (or, in another embodiment, to the patient's insurance company or any other payor entity) at critical points in real time, such as at the time of diagnosis, at the time of progression, at the time of dose change/drug change/toxicity, and/or when there is a tendency to deviate from a desired or expected outcome. In one embodiment, COTA module 220 provides an alert to the healthcare professional identifying the particular patient that the healthcare professional is searching for. For example, COTA module 220 may provide alerts in real time to a pharmaceutical company seeking a particular patient to administer a particular (e.g., new) drug or alternative. The alert may identify a particular patient as a good candidate for a particular drug. As another example, an alert may be provided to inform the care provider that the patient's outcome is deviating from the expected outcome for patients with similar treatment and prognosis related parameters, so that a review of the patient's treatment and possible modification of the patient's treatment may be performed.

As used herein, the term "real-time" or "real-time" means without appreciable delay or information being transmitted immediately after collection or processing. These terms also include time delays introduced by automated processes (e.g., near real-time).

Fig. 3A is a block diagram illustrating ranking of data associated with a colon cancer patient according to one embodiment. Although described with respect to colon cancer, the description and drawings may apply to any type of cancer, or in another embodiment, any type of disease for which data associated with a patient exists.

Data 410 associated with a cancer patient is collected for all cancers (or, in another embodiment, for more than one type of cancer, or in other embodiments, for all cardiovascular diseases, or pulmonary diseases, or gastrointestinal diseases, or neurological diseases, etc.), and the data 410 is narrowed to a subgroup 420 associated with, for example, a colon cancer patient. In one embodiment, the colon cancer-related data subset 420 is then analyzed and classified by COTA module 220 to produce a classified colon cancer data set 430. The ordered colon cancer data set 430 can include one or more groupings, where each grouping includes data associated with patients having the same type of specific colon cancer. Thus, COTA module 220 enables ranking of patients with similar cancer and data from patients with similar cancer to the highest fidelity levels associated with diagnosis, treatment, and prognosis.

COTA module 220 classifies, orders, and facilitates grouping of patient types based on the value of a preselected variable embodied in the node address or a combination of attributes assigned to the preselected variable. The preselected variables may include treatment-related variables and prognosis or outcome-related variables. COTA module 220 may generate and assign unique temporary node addresses and optimized node addresses, which embody a unique combination of values of preselected variables. The temporary node address or the optimized node address assigned to the patient or to which the patient is assigned embodies the particular combination of values of the preselected variables. For temporary node addresses, the temporary node address may include values for only a subset of pre-selected classification variables, e.g., only a minimal subset of treatment-related variables, which aid the medical professional in making early treatment decisions at the time of care.

The personal health information of each patient is used to determine the values of preselected variables, referred to herein as attributes, which are used to assign temporary node addresses and optimized node addresses to the patient. In some embodiments, at least some personal health information, such as initial treatment-related information for assigning temporary node addresses, may be entered or provided by the healthcare provider in a structured form. In some embodiments, at least some personal health information may be accessed from data from a patient health record. In some embodiments, at least some personal health information used to determine attributes of the optimized node address is accessed or obtained from the patient's health record.

Typically, the patient information is stored in an Electronic Medical Record (EMR). However, EMRs often contain too much information, and thus it is difficult for a medical professional to locate information of particular interest from the vast amount of information stored in an EMR. In addition, most of the information in the EMR is not relevant to the information that the healthcare professional is searching for. The objective of the EMR is to capture all or most of the data associated with patients entering and leaving the doctor's office, unlike EMRs, COTA module 220 is targeted because module 220 enables a user to locate specific data relevant to diagnosis and prognosis associated with a particular patient.

In some embodiments, the user selection may receive (e.g., via a Web browser, software executing on the client device, or via an application) information accessed or received for the therapy-related variables used to determine the temporary node address. In some embodiments, at least some of the data received by COTA module 220 is via a web page and is discrete data (e.g., typically provided by a user selecting one or more options in a menu, via one or more check boxes or buttons, etc.). In some embodiments, at least some of the patient data is received as data in a structured field. In some embodiments, the information accessed or received relating to the variables used to determine the optimized node address may be provided in part as data from a patient medical record. In some embodiments, COTA module 220 accesses unstructured personal health information and identifies and selectively extracts data relevant to diagnosis and prognosis. See, for example, U.S. patent application publication No. US 2018/0121618a1 entitled "SYSTEMAND METHOD FOR EXTRACTING ONCOLOGICAL INFORMATION OF PROGNOSTIC SIGNIFICANT FROM NATURAL LANGUAGE" published on 5/3/2018, which is incorporated herein by reference in its entirety. In some embodiments, the method for obtaining initial data after diagnosis may be at least partially different from the method for obtaining later data associated with prognosis or outcome.

In one embodiment, data may be ingested into the system via a human user or a technical process (e.g., API). In some embodiments, one layer of COTA module 220 may parse and evaluate data at the time of data ingestion. For example, COTA module 220 may check whether the data is correct, corrupt, integrity of the data, format, spelling of the data, and other factors to verify the integrity of the data. In some embodiments, COTA module 220 may correct detected data problems. In some embodiments, COTA module 220 evaluates data, e.g., whether the data is correct, whether it is corrupt, what information is contained, what information is missing/corrupted in the information, how it is formatted, spelled, etc., and corrects any information problems detected thus far. In some embodiments, the checking, verifying, and/or correcting of the detected problem in the data occurs at least in part during data ingestion. In some embodiments, the checking, verifying, and/or correcting of the detected problem in the data occurs at least in part after data ingestion. COTA module 220 may store the ingested data in databases 240a, 240 b. Some methods for checking and verifying input data are described in US 2018/0121618 a1, which is incorporated herein by reference in its entirety. In some embodiments, problems detected in the data can be checked, verified, and/or corrected for accessed or received data related to variables used to determine an optimized node address before and/or after the data is taken from the medical record.

The level of checking, verifying and/or correcting a problem detected in the data may be different for the provided or accessed data used to initially determine the temporary node address and the provided or accessed data used to determine the optimized node address. In some embodiments, this may be due in part to the different formats, methods, or mechanisms in which the two different types of node addresses are entered or retrieved. In some embodiments, as described above, the information for the treatment-related variable may be initially obtained in a more structured format. This may facilitate efficient assignment of temporary node addresses and fast or immediate on-demand access to predetermined treatment plan information (e.g., one or more predetermined patient service packages) that may be associated with the temporary node addresses to guide treatment decisions early (e.g., at diagnosis, shortly after diagnosis, during first appointment after diagnosis). In some embodiments, the structured format may also be used for the user to enter information on some prognostic or outcome-related variable. In other embodiments, at least some of the data for the prognosis or outcome related variable may be provided as medical record data, which may include data in an unstructured format. This type of data may require multiple checks, verifications, and/or corrections for problems detected in the data. In addition, the time requirements for initial allocation of optimized node addresses may be less stringent because they are not used to guide early treatment decisions. In some embodiments, if the initial information received or accessed includes information sufficient to assign attributes to at least a minimum subset of the therapy-related variables and a minimum subset of the prognosis-or outcome-related variables, the patient may be assigned an optimized node address without assigning a temporary node address to the patient.

The COTA module 220 assigns the temporary node address and/or the optimized node address to a set of personal health information about the patient based on a value (referred to as an attribute) of a preselected variable included in the temporary node address or the optimized node address. In some embodiments, the temporary node address is no longer used after the optimized node address is assigned, e.g., the temporary node address is only used to guide a healthcare professional to make a treatment decision at the point-of-care for a short time after diagnosis. In some embodiments, after assigning the optimized node address, the optimized node address may be used to access predetermined treatment plan information associated with the optimized node address assigned to the patient.

As described above, the preselected variables may include treatment-related variables and prognosis or outcome-related variables. In some embodiments, at least some of the treatment-related variables are also prognosis or outcome-related variables. The temporary node address includes attributes corresponding to at least a minimum subset of the therapy-related preselected variables. For a temporary node address to be assigned to a patient or a data record associated with a patient, the personal health information associated with the patient provided to or accessed by the system or method must include sufficient information to assign an attribute to at least a minimum subset of the therapy-related variables. In some embodiments, which variables to include in the minimal subset of treatment-related variables depends on the type of cancer and/or more stages of cancer and the intent of treatment, as described in further detail below. In some embodiments, the minimum subset of treatment-related variables is less than all of the treatment-related variables, and when at least the minimum subset of treatment-related variables is assigned, a temporary node address is assigned even if all of the treatment-related variables are not assigned. In some embodiments, the minimum subset of treatment-related variables is all of the treatment-related variables, and for the temporary node address to be assigned, an attribute must be assigned to all of the treatment-related variables. As described above, in some embodiments, variables that are relevant to treatment (e.g., relevant to later stages of treatment), but whose values may not be available at or shortly after diagnosis (e.g., within days after diagnosis) and which are not needed to determine an accurate early treatment recommendation may be considered treatment-relevant variables that are not included in the minimal subset. If the variable is also associated with prognosis and outcome, in some embodiments, where the minimal subset of treatment-related variables includes all treatment-related variables, the variable may be considered to be only the prognosis and outcome-related variable, and not the treatment-related variable, even if it has some correlation with treatment. Thus, the decision whether a variable is considered to be a treatment-related variable within the set of pre-selected variables and/or part of the minimum subset of treatment-related variables depends on how relevant the variable is to providing an accurate recommendation of a course of treatment, and the likelihood that information about the variable is available in time for most patients to guide early treatment decisions, and may also depend on the value of one or more other variables, such as for some cancers, cancer type and intent-to-treat. An early treatment decision may be a treatment decision made within 3 days of diagnosis, within 5 days of diagnosis, within 7 days of diagnosis, within 10 days of diagnosis, within one week of diagnosis, within 2 weeks of diagnosis, within 3 weeks of diagnosis, or within one month of diagnosis.

In some embodiments, the treatment-related variable, the prognosis, or the outcome-related variable, or both, are selected by a national panel of experts (e.g., a national sub-specialist panel) that meet on a regular (e.g., monthly) basis. These experts understand all key documents and all key biomarkers for the disease and maintain a list of preselected variables determined based on published documents and their own expertise. In some embodiments, the expert classifies the preselected variable as being associated with treatment, or prognosis or outcome, or both. A variable is considered to be a treatment-related variable for the purpose of determining whether to assign at least a minimum subset of the treatment-related variables, and for the purpose of assigning a temporary node address, if the variable is treatment-related and is prognosis or outcome.

At a later time or later period after the initial node address is assigned, updated and/or additional personal health information associated with the patient is provided to the system, received by the system, or accessed by the system. In some embodiments, the initial node address may be a temporary node address where at least a minimum subset of the treatment-related variables are assigned, but less than the minimum subset of the prognosis-or outcome-related variables, or an optimized node address where at least the minimum subset of the treatment-related variables and the minimum subset of prognosis-or outcome-related variables are assigned. If the assigned initial node address is a temporary node address and the updated and/or additional personal information includes sufficient information to assign attributes to at least a minimum subset of the therapy-related variables and at least a minimum subset of the prognosis-or outcome-related variables, then an optimized node address is assigned to the patient or the personal health information associated with the patient.

In some embodiments, the patient is assigned an updated temporary node address if at least some of the therapy-related variables are assigned new or updated attributes based on the new or updated personal health information, but the updated and/or additional personal health information in combination with the initial personal health information fails to enable assignment of attributes to at least a minimum subset of the prognosis or outcome related attributes. In other embodiments, if new or updated attributes are assigned to at least some variables based on new or updated personal health information, but the updated and/or additional personal health information does not enable the assignment of attributes to at least a minimum subset of prognosis or outcome related variables, the system or method does not assign updated temporary node addresses, but rather awaits additional information that, in conjunction with previously received or accessed information, would be sufficient to assign optimized node addresses. If the assigned initial node address is an optimized node address and the new or updated personal health information includes new or updated values for one or more therapy-related or prognosis-or outcome-related variables, an updated optimized node address may be assigned to the patient based on the new or updated values.

Over time, the optimized node address may be assigned to the patient (e.g., without previously assigning the patient an optimized node address) or the optimized node address assigned to the patient may be updated as additional subsequent personal health information is received.

For example, in one embodiment, personal health information about the target patient is provided to or accessed by the method or system at or shortly after the time the patient is diagnosed, and the provided personal health information includes information about at least a minimum subset of attributes of the treatment-related preselected variables, but also includes less than the minimum subset of information about prognosis-or outcome-related variables. A temporary node address is assigned to the target patient based on the attributes of the therapy-related variable. Later, additional personal health information (e.g., additional test results) about the target patient is provided to or accessed by the method or system, and the additional personal health information includes sufficient information about at least a minimum subset of attributes of the prognosis or outcome related variable for the target patient to assign an optimized node address to the target patient based on the attributes of the therapy related variable and the prognosis or outcome related variable, and to assign the optimized node address to the target patient based on the additional personal health information alone or in combination with the initial personal health information.

In one embodiment, the temporary node address and the optimized node address are used to classify similar data or similar patients. For example, because patients assigned the same temporary node address all have the same attributes of the treatment-related variables, analyzing previous or current treatments for all patients assigned the same temporary node address enables similar patients to be compared in terms of treatment. In some embodiments, the treatment-related group may be analyzed, wherein each patient in the treatment-related group is included in the treatment-related group based on the temporary node address assigned or once assigned to the patient. In some embodiments, assignment of patients to treatment-related groups may be replaced by treatment-related variables based on optimized node addresses assigned to patients at or shortly after diagnosis, or at some other point in disease progression relevant to the analysis. As described in further detail below, patients in a treatment-related group or prognosis or outcome-related group are assigned based on node addresses (e.g., optimized node addresses) assigned to the patients at particular points or stages of their disease progression, which are determined based on the analysis goals of the treatment-related group or prognosis or outcome-related group.

As another example, because patients assigned the same optimized node address all have the same attributes of both treatment-related variables and prognosis or outcome-related variables, analyzing the previous or current outcomes of all patients assigned or assigned the same optimized node address at a particular point in the progression of the disease reduces or eliminates the impact of biological variability on outcomes, thereby making the performance of healthcare providers a major source of outcome variability. In addition, the determination of the outcome associated with the prognosis of the target patient may be based on previous outcomes of a group of patients based on the prognosis or outcome, wherein each patient in the group based on the prognosis or outcome is assigned the same optimized node address as the target patient at the point of disease progression corresponding to the target patient. In some embodiments, more than one optimized node address may be included in the group to analyze previous or current outcomes. For example, if the therapy-related parameter is not related to outcome, different optimized node addresses with different values of the therapy-related parameter may be grouped in the same group for analysis. In some embodiments, a prognosis or outcome based patient group may include patients assigned an optimized node address that is different at a corresponding point in disease progression from the optimized node address assigned to the target patient, where the different optimized node addresses have different values for one or more variables that are not or less relevant to the prognosis or outcome or a particular type of prognosis or outcome.

For example, due to the nature of the diagnostic tests being ordered and the waiting for results, some test results that may be relevant to treatment but more relevant to prognosis or outcome may not be available at or shortly after diagnosis (e.g., within a few days or a week after diagnosis). However, given that information is provided or accessible regarding at least a minimum subset of the attributes of the therapy-related variables, a temporary node address may be assigned to the patient based on the limited subset of therapy attributes available at the time. In some embodiments, test results that are not typically available at or shortly after diagnosis may be characterized as prognostic or outcome-related variables. Later, when additional test results are available, the optimized node address may be assigned to the target patient based on information from the additional test results. Additional patient information may become available over time that is relevant to treatment, prognosis (which may account for the extent of disease progression and correlate it to survival), and historical care costs. Thus, each temporary node address and optimized node address is an identifier of the patient at a particular point in time or within a particular time period, like a snapshot of the patient at a particular point in time or within a particular time period. After assigning the temporary node address, the patient is assigned an optimized node address based on additional information that is updated over time based on the patient's new or changed personal health information. In some embodiments, the temporary node address and the optimized node address enable a user to easily and efficiently compare similar patients with respect to treatment and/or prognosis or outcome related variables during analysis. The specificity of this comparison enables the biological variability of outcome to be minimized during the analysis, and thus may provide greater accuracy with respect to the effect of a therapeutic, treatment or intervention on outcome.

The optimized node address and the temporary node address may be stored in one or more databases 240a, 240 b. Information regarding temporary node addresses assigned to a particular patient and/or optimized node addresses assigned to a particular patient and corresponding to points or time periods in patient disease progression may be stored in one or more databases 240a, 240 b. Information about other patients, which may include historical cost information, may also be stored in one or more databases 240a, 240 b. COTA module 220 associates each temporary node address with a particular combination of attributes for each therapy-related variable in the at least a minimum subset of therapy-related variables and each optimized node address with a particular combination of attributes for each therapy-related variable in the at least a minimum subset of therapy-related variables and each prognosis-or outcome-related variable in the at least a minimum subset of prognosis-or outcome-related variables.

By definition, the temporary node address is based only on the properties of the treatment-related variables. As described above, in some embodiments, treatment-related variables are selected based on expert knowledge of the panel and publications that influence treatment decisions. Typically, the minimum set of treatment-related variables required to assign a temporary node address includes variables that are relevant to treatment decision whose values are known at or shortly after diagnosis. As described above, which variables to include in the minimal subset of treatment-related variables may depend on the value of one or more treatment-related variables, e.g., for cancer, the minimal subset of treatment-related variables may depend on the type of cancer, the stage of the cancer, and/or the intent-to-treat. At the time of diagnosis, the values of at least some prognostic or outcome-related variables may be unknown. As noted above, some variables may be both treatment-related variables and prognosis or outcome-related variables.

In some embodiments, the temporary node address assigned to the patient is updated based on new or changed values of the therapy-related variables based on the acquisition, receipt, or access of additional patient-related personal health information that affects therapy decisions over time. In some embodiments, an optimized node address or updated refinement is assigned to a patient based on the acquisition, receipt, or access of additional personal health information, based on the value/attribute of the therapy-related variable and the attribute/value of the prognosis or outcome-related variable. The expected outcome may be determined using previous outcome data for a patient who has been assigned or is assigned the same optimized node address as that assigned to the target patient at the corresponding point in disease progression based on the optimized node address assigned to the patient. Additionally, an expected treatment cost for the target patient may be determined based on historical cost data for other patients assigned the same optimized node address as the optimized node address assigned to the target patient at the same disease progression point as the target patient. In some embodiments, the comparison is performed for patients assigned the same optimized node address as the target patient at the same disease progression and treatment point as the target patient. In some embodiments, the expected total cost of care is determined, where "total cost" is the cost of care from diagnosis to death or cure. Determining a total expected care cost by using historical cost information for patients assigned the same optimized node address as the optimized node address assigned to the target patient at the disease progression point corresponding to the target patient, the determined total expected care cost taking into account risks associated with a particular combination of treatment and prognosis and outcome-related attributes of the target patient.

As described above, in some embodiments, the COTA module 220 associates each node address (e.g., temporary node address and/or optimized node address) with a combination of specified attributes of at least some of the preselected variables. As described above, the temporary node address includes only the attributes of the treatment-related variable, but the optimized node address includes the attributes of the treatment-related variable and the prognosis or outcome-related variable. The preselected variable may be a factor related to the patient and a disease associated with the patient, such as cancer. The preselected variables may include variables that are relevant to the diagnosis, treatment, and prognosis of a particular disease or condition, a group of similar diseases or conditions, or a class of diseases or conditions. For example, in some embodiments, the preselected variables may include diagnosis, demographics, outcomes, phenotypes, and the like.

In some embodiments, the preselected variables are defined or identified by a group of experts in the relevant field (e.g., oncologists with experience of more than 5 years, 10 years, 15 years, 20 years, 30 years, etc.). In some embodiments, the preselected variables are defined or identified based at least in part on information about current medical knowledge and treatment and/or information from experts in the relevant field. In some embodiments, the definition or identification of the preselected variables to be included in the temporary node address and the optimized node address is updated based on new information about current medical knowledge and treatment and/or updated information from experts in the field. In some embodiments, the definition or identification of the preselected variable is updated periodically. In some embodiments, the definition or identification is updated as needed based on the newly obtained information.

COTA module 220 may store the definitions or identifications of the preselected variables in one or more databases 240a, 240 b. It will be appreciated that the definition of the preselected variable may vary over time for any given disease. The preselected variables include treatment-related variables and prognosis or outcome-related variables, as described above and in further detail below.

The definition or identification of the preselected variable may be specific to the disease or condition. In some embodiments, the treatment-related variable and the prognosis-or outcome-related variable can be specific to a certain type of cancer (e.g., breast cancer, colon cancer, prostate cancer, rectal cancer, lung cancer, etc.). For example, for breast cancer, treatment-related variables may include Estrogen Receptor (ER) status, human epidermal growth factor 2(HER2) status, staging, and ECOG. Prognostic or outcome-related variables may include information about the outcome of a genetic test, such as an aerophile DX score, or information about comorbidities. In some embodiments, genetic test results that are not available within a short time after diagnosis, such as OncotypeDX scores, may be considered prognosis or outcome related variables, rather than treatment related variables.

As described above, which variables to include in the minimal subset of treatment-related variables may depend on some treatment-related variables, such as cancer, cancer type, stage, and/or treatment intent. Even for a single specific disease or disorder, such as breast cancer, the identification of the smallest set of treatment-related variables may be specific to the stage and/or treatment intent.

For example, for breast cancer, the minimum set of treatment-related variables may depend on whether the treatment is intended to be an adjuvant treatment (meaning that additional cancer treatment is administered after the primary treatment to reduce the risk of cancer recurrence; the adjuvant treatment may include chemotherapy, radiation therapy, hormonal therapy, targeted therapy or biological therapy), neoadjuvant treatment (meaning that treatment is administered as the first step in shrinking the tumor before the primary treatment (usually surgery; examples of neoadjuvant therapy include chemotherapy, radiation therapy and hormonal therapy) or the treatment of metastatic cancer. For example, the minimum set of treatment variables for breast cancer where treatment is intended as an adjunct therapy may include: treatment type, sex, Tumor Node Metastasis (TNM) staging, ECOG status, treatment-related comorbidity type (meaning disease other than the primary diagnosis affecting the outcome of treatment), histological grade, histology, human epidermal growth factor receptor 2(Her2) status, (estrogen receptor (ER) status, Progesterone Receptor (PR) status, presence or absence of extensive lymphatic vessel invasion and menopausal status. J.clin.oncol. (2005)23(30) 7399-. Additional prognostic or outcome-related variables may include: patient preference for treatment, genomic test results such as BRCA 1 mutation status, BRCA2 mutation status, and Partner and Localizer of BRCA2(PALB 2) mutation status, genetic test results such as Oncotype DX recurrence score (for invasive breast cancer), Oncotype dxdis (for Ductal Carcinoma In Situ (DCIS) only), and breast cancer index test, whether the patient is african americans, and age. In some embodiments, some of the foregoing variables, such as one or more of BRCA 1, BRCA2, and PALB 2 mutation status, and genetic test results, such as Oncotype DX recurrence score (for invasive breast cancer), Oncotype DX DCIS (for ductal carcinoma in situ (DCIS only)), and breast cancer index test, can be considered to be therapy-related variables that are not included in the required minimal subset of therapy-related variables, in addition to being prognostic or outcome-related variables, such that even if these variables are not assigned attributes, temporary node addresses can be assigned. In other embodiments, one or more of the BRCA 1, BRCA2, and PALB 2 mutation states, as well as genetic test results, such as Oncotype DX recurrence score (for invasive breast cancer), Oncotype DXDCIS (for Ductal Carcinoma In Situ (DCIS) only), and breast cancer index test may only be considered as a prognosis and outcome related variable, but not as a treatment related variable.

As another example, the minimum set of treatment-related variables for breast cancer where the treatment intent is neoadjuvant therapy may include: treatment type, sex, TNM staging (meaning system T which describes the amount and spread of cancer in a patient, which describes the size of the tumor and any spread of cancer to nearby tissues; N which describes the spread of cancer to nearby lymph nodes; and M which describes the metastasis or spread of cancer to other parts of the body), ECOG status, treatment-related comorbidity type, Her 2 status, ER status, PR status, and menopausal status. Additional prognostic or outcome-related variables may include: patient preference for treatment, genomic test results such as BRCA 1 mutation status, BRCA2 mutation status, PALB 2 mutation status, genetic test results such as breast cancer index test, whether the patient is african american, age, histological grade, histology, and whether there is extensive lymphatic vascular invasion.

As another example, the minimum set of treatment-related variables for breast cancer where treatment is intended to be the treatment of metastatic cancer may include: gender, ECOG status, treatment-related comorbidity type, Her 2 status, ER status, PR status, and menopausal status. Prognostic or outcome-related variables may include: patient preference for treatment, genomic test results such as BRCA 1 mutation status, BRCA2 mutation status, PALB 2 mutation status, whether the patient is african american, age, and metastatic site.

As another example, for adjuvant treatment of stage I-IIIC prostate cancer, the minimum set of treatment-related variables may include: ECOG status, TNM phase, Gleason score, ranging from 1-5 and describes how much cancer from biopsy looks like healthy tissue (lower score) or abnormal tissue (higher score), and Prostate Specific Antigen (PSA) test results. For the treatment of metastatic prostate cancer, a minimum set of treatment-related variables may include: ECOG status, TNM staging and progression trajectory.

As another example, for adjuvant treatment of non-stage II colon cancer, the minimum set of treatment-related variables may include: ECOG status, TNM staging and comorbidity type. For adjuvant treatment of stage II colon cancer, the minimum set of treatment-related variables may include: ECOG status, TNM stage, comorbid type, microsatellite instability (MSI) status (meaning a hypervariable phenotype caused by loss of DNA mismatch repair activity; see Boland, CR and Goel, a., gastroenterology (2010)138(6): 2073-87; doi:10.1053/j. gastro.2009.12.064)), whether sampling was less than 12 lymph nodes, obstruction, perforation and T stage. T0 (carcinoma in situ or intra-mucosal carcinoma (Tis)) means that the cancer has not grown beyond the inner layer (mucosa) of the colon or rectum. T1 indicates that the cancer has grown to submucosa through the muscularis mucosae (T1). T2 indicates that the cancer has grown to the intrinsic muscle layer. N0 indicates that the cancer has not spread to nearby lymph nodes. M0 indicates that the cancer has not spread to distant sites. T3 indicates that the cancer has grown to but not through the outermost layer of the colon or rectum, has not reached nearby organs, has not spread to nearby lymph nodes (N0), and has not spread to distant sites (M0). T4a indicates that the cancer has grown through the wall of the colon or rectum but has not grown to other nearby tissues or organs (T4a) and has not spread to nearby lymph nodes (N0) or distant sites (M0). T4(b) indicates that the cancer has grown through the wall of the colon or rectum and is attached to or has grown into other nearby tissues or organs (T4b) and has not spread to nearby lymph nodes (N0) or distant sites (M0). (htt ps:// www.cancer.org/cancer/colon-total-cancer/detection-diagnosis-station/station. For treatment of metastatic colon cancer, a minimum set of treatment-related variables may include: ECOG status, TNM staging, progression trajectory, MSI status, KRAS mutation status, NRAS mutation status, BRAF mutation status, and tumor laterality.

As another example, for neoadjuvant and adjuvant therapy of rectal cancer, the minimum set of treatment-related variables may include: ECOG status, TNM stage and location. For the treatment of metastatic rectal cancer, the minimum set of treatment-related variables may include: ECOG status, TNM staging, progression trajectory, MSI status, KRAS mutation, NRAS mutation, and BRAF mutation.

As another example, for adjuvant or neoadjuvant treatment of non-small cell lung cancer (NSCLC), the minimum set of treatment-related variables may include: TNM staging, histology, ECOG status and co-morbidities. For treatment of metastatic NSCLC that is symptomatic and requires immediate treatment, the minimum set of treatment-related variables may include: histology, comorbidities and ECOG status. For treatment of NSCLC that is non-symptomatic and/or does not require immediate treatment, the minimum set of treatment-related variables may include: histology, comorbidities, ECOG status, programmed death ligand 1(PD-L1) expression, EGFR mutation status, and Anaplastic Lymphoma Kinase (ALK) mutation status. For the treatment of Small Cell Lung Cancer (SCLC), the minimum set of treatment-related variables may include: ECOG status, comorbidities and TNM staging.

Fig. 3B is a flow diagram of assigning a temporary node address or an optimized node address according to some embodiments. In one embodiment, COTA module 220 may ingest data, confirm the integrity of the data, verify and/or correct the data, and store the data in databases 240a, 240b, as described above, prior to assigning an optimized node address. In some embodiments, the COTA module may receive or access data input by user selection and perform more limited validation and verification of the data prior to assigning the temporary node address.

The data ingested or accessed by the COTA module includes Personal Health Information (PHI) associated with the patient. As used herein, a PHI refers to any information in a medical record or a given case set that can be used to identify an individual patient and be created, used, or published in the process of providing healthcare services, such as diagnosis or treatment. Examples of personal identifiers in a PHI include, but are not limited to: name, all geographic subdivisions less than state, including street address, city, county, region, zip code; all date elements (except years) of the date directly related to the individual including date of birth, date of admission, date of discharge, date of death and age, and all date elements (including years) indicating such age; a telephone number; a fax number; an email address; social security number, medical record number; health plan beneficiary number; an account number; certificate/license number; vehicle identifiers and serial numbers, including license plate numbers; a device identifier and a serial number; a network Uniform Resource Locator (URL); an Internet Protocol (IP) address number; a biometric identifier including a fingerprint and a voiceprint; full-face photographic images and any comparable images; and any other unique identification number, characteristic, or code (but not a unique code assigned by the researcher to encode data). The PHI may include a phenotypic characteristic of the patient. A phenotype is a combination of observable characteristics or traits of an individual, such as its morphological, developmental, biochemical or physiological properties, phenology, behavior, and behavioral products. Phenotypes are caused by the gene expression of individuals as well as the influence of environmental factors and interactions between the two.

In some embodiments, a user, such as a healthcare provider, patient, or payer/insurance company, may enter the patient's PHI into the GUI 250 presented by the COTA module 220. For example, the PHI can be uploaded using a specified file format. In some embodiments, at least some of the PHIs can be received or accessed based on user selection of values of at least some of the variables, for example, via selection from an option in a graphical user interface of a web browser, application program, or mobile application. The computing system 205 may receive the PHI via the COTA module 220 and store the PHI in a database. In other embodiments, the COTA module may access a memory that includes a copy of the PHI for one or more patients, and may obtain the PHI for one or more patients in this manner. COTA module 220 may receive or access an initial set of PHIs for a patient and subsequently receive an updated set of PHIs.

For example, the patient's PHI can be at least partially entered into the browser. In other embodiments, at least some of the PHIs are retrieved from a database that includes stored patient data. In some embodiments, the PHI is sent to a classification layer that determines attributes of at least some of the predetermined variables based on the PHI. In some embodiments, the classification layer also examines, validates, and corrects at least some of the data before or during the determination of the attributes. A temporary node address or an optimized node address is determined for the patient data based on attributes of at least some of the predetermined variables, and the temporary node address or the optimized node address is assigned to the patient. In some embodiments, once the temporary node address or the optimized node address is assigned, each time the user visits the COTA module, the COTA module provides access to personal health information about the patient and information about the association of the node address assigned to the patient based on the PHI (e.g., through a graphical user interface) or information about the node address itself. In some embodiments, the COTA module enables efficient comparison of the PHI for a particular patient with information about other patients that have or had similar attributes for some or all of the predetermined variables encoded in the node address at the point of progression corresponding to that particular patient. In some embodiments, the comparison is made with other patients assigned the same optimized node address as the optimized node address assigned to the particular patient at the corresponding point of disease progression and treatment.

In one embodiment, COTA module 220 may access or receive an initial set of PHI for a patient. The COTA module 220 may assign attributes to at least some variables of a set of preselected variables based on values in the PHI of the preselected variables. In some embodiments, the attribute may be a designated input assigned to a preselected variable. For example, the attribute may be one or more options from a specified list or menu. Alternatively, the attribute may be alphanumeric input. As described above, in some embodiments, the attributes are determined based at least in part on PHIs included in one or more unstructured documents of the natural language.

Fig. 3B is a flow diagram of the above classification and ordering by the COTA module according to one embodiment by creating node addresses embodying different unique combinations of attributes. As shown in fig. 3B, as an example, referring to fig. 3B, the set of preselected variables may include gender 440 (variable a), ethnicity 445 (variable B), variables C, D, E and F (not identified), and KRAS 450 (variable G). K-Ras is a protein in humans encoded by the KRAS gene. The protein product of the normal KRAS gene plays an important role in normal tissue signaling, and mutation of the KRAS gene is an important step in the development of many cancers.

In some embodiments, the COTA module analyzes the sorted and ordered data 430 for attribute combinations of the set of preselected variables (e.g., variables 440, 445, 450) to identify each unique attribute combination in the sorted and ordered data. Each unique combination of attributes 455 is now in or represented by a unique node address. In some embodiments, the format of the node address represents the value of each attribute in a unique combination of preselected variables. Data corresponding to a particular patient at a particular point in time or for a particular period of time is assigned one of the unique node addresses, i.e., a temporary node address or an optimized node address. Multiple different patients may be assigned the same temporary node address or the same optimized node address. As described above, the node addresses may be used to filter and sort the data. Variables may include, for example, diagnosis, demographics, outcomes, phenotypes, and the like. A phenotype is a combination of observable characteristics or traits of an individual, such as its morphological, developmental, biochemical or physiological properties, phenolics, behavior, and behavioral products. Phenotypes are caused by the gene expression of a person as well as the influence of environmental factors and interactions between the two. In some embodiments, the node addresses enable efficient partitioning of data into clinically relevant groupings.

As described above, the unique combination of attributes of preselected variables 455 are represented as node addresses within COTA module 220. In one embodiment, the node address is represented as a list of attributes of a predetermined variable (as a function of the letter representing the variable and the number representing the attribute selection of the variable). For example, as shown in FIG. 3B, the unique combination of attributes 455 represented as node addresses includes A1-2(A represents a gender variable and 1-2 represents female and male patients), with the female and male variables of the gender variable A being boxed. The unique combination of attributes 455 also includes B1-4, where B represents an ethnicity variable and 1-4 represent different options for the ethnicity variable. Unique attribute combination 455 also includes G representing the KRAS variable and numbers 1-3 representing different options for the KRAS variable. Thus, in some embodiments, unique variable combination 455 may have node addresses A1-2, B1-4, … … G1-G3 (e.g., A1, B2, … … G1).

In another embodiment, the optimized node address or the temporary node address is represented as a plurality of strings of numbers separated by periods, where each string of numbers indicates one or more preselected variables and attributes assigned to the variables (e.g., disease, phenotype, treatment type, progression/trajectory, gender, etc.). For example, a first string of numbers may represent a particular disease, a second string of numbers may represent a type of disease, a third string of numbers may indicate a subtype of disease, and a fourth string of numbers may represent a phenotype. Thus, in this example, the first string of numbers may be 01, indicating cancer, the second string of numbers may be 02, indicating a breast tumor, the third string of numbers may be 01, indicating breast cancer, and the fourth string of numbers may be 1201, representing a particular feature of the phenotype, such that the node address is 01.02.01.1201. It should be understood that the optimized node address or temporary node address may include any number of strings of numbers and is not limited to four strings. In addition, the optimized node address and the temporary node address are not limited to being represented by a string of numbers. The temporary node address and the optimized node address may be represented in any format, so long as the format conveys information characterizing and identifying the combination of attributes of the preselected variables represented by the node address.

In one embodiment, a string of numbers representing a phenotype may be provided by representing a feature of the phenotype as a directed graph. Figure 3C schematically illustrates a directed graph 460 showing characteristics of a phenotype to provide a string of numbers representing the phenotype, according to one embodiment. The directed graph 460 includes nodes that are depicted as ellipses representing phenotypes and edges representing relationships between the nodes. The graph is tracked from the root "start" node to the nodes of the selected phenotype. Each edge is associated with a number. A string of numbers representing a phenotype of the node address is provided in the form of a combination of numbers. For example, a numeric string of selected phenotypic characteristics for males and whites will be represented as 11. Other types of combinations may also be employed. Advantageously, representing the characteristics of a phenotype as a directed graph allows for the addition of other nodes corresponding to other phenotypes without altering the overall structure. FIG. 3C includes a manner of graphically depicting a directed graph. One of ordinary skill in the art will appreciate that the directed graph may be depicted in different graphical manners.

The node address representing the unique combination of attributes 455 provides the COTA module 220 with the ability to match resources and alerts specific to each relevant phenotype. Resources may include information, content, real-time support links, and the like. In some embodiments, each patient is classified into one or more optimized node addresses and/or temporary node addresses, assuming that sufficient PHI is provided to classify the patient. In one embodiment, a resource is "tagged" with the appropriate associated node address. In some embodiments, node addresses are replaceable over time to maintain synchronization with scientific/medical progress.

As described above, when Personal Health Information (PHI) is initially provided to or by a target patient, the PHI may not include enough information to determine the attributes of all the predetermined variables in the optimized node address; however, the PHI may include sufficient information to determine the properties of at least a minimum subset of the treatment-related variables. The temporary node address may be assigned to the target patient based on an attribute of at least a minimum subset of the therapy-related variables. Even if the values of all the predetermined variables associated with the optimized node address are unknown values, the temporary node address can be used to provide relevant treatment information to the target patient and compare the treatment of the target patient to the treatment of similar patients. The temporary node address may include an incomplete or non-existent attribute of one or more therapy-related variables that are not in the minimal subset of therapy-related variables. The minimum subset of treatment-related variables may be a designated subset of treatment-related variables having an assigned attribute. As described above, which treatment-related variables to include in the minimal subset of treatment-related variables may depend on at least some treatment-related variables, such as cancer type, cancer stage, and/or treatment intent.

As described above, the optimized node address may contain at least a minimum subset of therapy-related variables having assigned attributes and at least a minimum subset of prognosis-or outcome-related variables having assigned attributes. The minimal subset of therapy-related variables may be a specified subset of therapy-related variables having an assigned attribute, and the minimal subset of prognosis or outcome-related variables having an assigned attribute may be a specified subset of prognosis or outcome-related variables.

As described above, COTA module 220 may assign attributes to some or all of the preselected variables based on the initial PHI received for the patient. In some embodiments, COTA module 220 may determine that an attribute has been assigned to at least a minimum subset of therapy-related variables, but that an attribute has been assigned to less than the minimum subset of prognosis-or outcome-related variables. In response to determining that an attribute has been assigned to at least a minimum subset of the therapy-related variables, but an attribute is assigned to less than the minimum subset of the prognosis-or outcome-related variables, COTA module 220 may assign a temporary node address to the patient based on the attribute assigned to the minimum subset of the therapy-related variables from database 240. In some embodiments, the temporary node address may include one or more treatment-related preselected variables having unassigned attributes. In some embodiments, the temporary node address assigned to the patient is previously generated based on personal health information from another patient. In some embodiments, the temporary node address is regenerated based on the attributes assigned to the patient, and the newly generated temporary node address is then assigned to the patient.

Each temporary node address and/or optimized node address may be associated with predetermined treatment plan information (e.g., one or more predetermined patient care service packs). As described above, in some embodiments, only one temporary node address and/or only one optimized node address is associated with a particular predetermined treatment plan information. In other embodiments, more than one optimized node address is associated with a particular predetermined treatment plan information. Where the predetermined treatment plan information includes one or more predetermined patient care service packages, each package may also be associated with one or more temporary node addresses or one or more optimized node addresses. The predetermined treatment plan information (e.g., services in each predetermined patient care service package) may be determined by one or more medical professionals, hospitals, groups, payers (e.g., insurance companies, etc.) to optimize patient care and/or cost. In one example, the package may indicate the number of imaging scans, drug or drug selection, schedule of administration, surgery or procedure, number and frequency of follow-up visits, and the like. The bundling of patient care services may be particularly useful for risk contracts. For example, each package corresponding to a temporary or optimized node address (associated with a particular disease) may have a predetermined fee, allowing a user (e.g., physician, patient, etc.) to select an appropriate package. The fee may be determined or negotiated based on historical data or optimized or temporary node addresses associated with a particular disease.

As described above, challenges in value-based medical services payment models include determining that a patient's accurate expected outcome is difficult, this determination taking into account non-care related variables that may affect a particular patient's clinical outcome, and determining that a patient's expected treatment costs are difficult to estimate accurately. By combining or containing information for all variables relevant to treatment and prognosis, the optimized node address can be used to reliably estimate a patient's prognosis-related outcome. The COTA module generates reliable prognosis-related outcome information and estimated cost information for optimized node addresses using previously obtained information about prognosis-based or outcome-based groups (a group of people considered as a group) grouped based on one or more optimized node addresses assigned to patients in the group at a particular point in the progression of the disease. Analysis of the previous data from the group provides an estimated outcome associated with the optimized node address and an estimated cost of the different treatment points associated with the optimized node address. In some embodiments, a dynamic statistical analysis is performed on the previous outcome of the group when needed. In some embodiments, the statistical analysis may be performed when new relevant information is obtained about patients in the group, or when new patients are added to the group. In some embodiments, the previous outcome of the group is periodically statistically analyzed and stored, or is performed on an as-needed basis. The time or frequency at which the statistical analysis is performed may be different for different outcomes.

Advantageously, in some embodiments, the predetermined treatment plan information (e.g., service bundles) provides insurance companies and/or hospitals with disease-specific cost certainty. This may also reduce the cost of handling and maintaining records. In addition, the medical professional will know the scheduled course of treatment in advance, which motivates the physician to get better outcomes at a lower cost.

In one embodiment, COTA module 220 may retrieve predetermined treatment plan information associated with the corresponding temporary node address or optimized node address from database 240. The COTA module 220 may communicate the scheduled treatment plan (e.g., information about the scheduled care service package) to the health care provider of the target patient. For example, a healthcare provider may execute an instance of COTA module 220 on user computing device 210. The COTA module 220 may present a GUI 250 for the healthcare provider on the user computing device 210. The computing system 205 may transmit the scheduled treatment plan information (e.g., information about the scheduled care service bundle) to the health care provider using the COTA module 220. The predetermined treatment plan information may be presented to the healthcare provider on the GUI 250 on the user computing device 210. Alternatively or additionally, the predetermined treatment plan information may be provided in one or more transmitted documents, one or more documents for download, one or more documents provided as an attachment to an electronic communication, or in any other suitable format or by any other suitable method.

In some embodiments, COTA module 220 may receive updated and/or new PHI for the patient over time. COTA module 220 may update the attributes assigned to the preselected variables based on the patient's updated and/or new PHI. Based on the updated attributes assigned to the preselected variables, the COTA module 220 may assign a new or different temporary node address or a new or different optimized node address to the patient. In some embodiments, a new or different temporary node address or a new or different optimized node address is generated in advance. In some embodiments, a new or different temporary node address or a new or different optimized node address is newly generated based on the update attributes assigned to the preselected variables. In one embodiment, the predetermined treatment plan information (e.g., one or more predetermined patient care service packs) associated with the temporary node address or the optimized node address may be updated or changed. In some embodiments, each time the predetermined treatment plan information associated with the optimized node address or temporary node address (e.g., information about one or more predetermined patient care service packages) is updated or changed, COTA module 220 may automatically transmit information about the updated or changed predetermined treatment plan information to the health care provider of the patient currently assigned the optimized or temporary node address associated with the updated or changed one or more predetermined patient care service packages.

In some embodiments, the predetermined variable to be included in the temporary node address or the optimized node address is changed, for example, due to a change in understanding of disease-related variables. For example, a group of experts may determine that new or different variables should be included in a treatment-related variable or a prognosis or outcome-related variable based on their own experience and/or development reported in a paper or publication. In this case, the patient may be reassigned a new currently modified optimized node address or a new currently modified temporary node address based on a new set of predetermined variables. In some embodiments, the modified optimized node address or the modified temporary node address is used only on an ongoing modified basis, and the modified node address is not assigned to the patient's past point in time. In some embodiments, the system or method maintains a mapping of the manner in which previous node addresses correlate with modified node addresses to enable analysis based on historical patient data including previous node addresses. In other embodiments, the system may reevaluate historical patient data and assign one or more patients a modified node address corresponding to past or outdated medical information.

Fig. 4A is a flowchart illustrating an exemplary process performed by COTA module 220, according to an exemplary embodiment. In operation 500, the COTA module 220 accesses or receives an initial data set, which may be described as a first data set, including the PHI of the target patient. The initial data set includes a PHI associated with the target patient at or within a first time period. The PHI may include information associated with a phenotypic characteristic of the patient. In some embodiments, COTA module 220 accesses or receives an initial data set stored in databases 240a, 240 b. In some embodiments, at least some of the initial data sets are transmitted by a user computing device 210 operated by the patient, healthcare/medical care provider, or insurance company. In operation 502, the COTA module 220 assigns attributes to at least some variables in a set of preselected variables using the PHI in the initial dataset for the target patient. In some embodiments, COTA module 220 may retrieve preselected variables for a particular disease or group of diseases from database 240 or a different database. In some embodiments, COTA module 220 employs a graphical user interface that directs the entry of at least some of the data in the initial data set. In some embodiments, the set of preselected variables may include a set of treatment-related variables and a set of prognosis or outcome-related variables. In operation 504, the COTA module 220 may determine whether an attribute has been assigned to at least a minimum subset of the set of therapy-related variables. In some embodiments, COTA module 220 employs a graphical user interface that directs the input of at least some data for a minimum subset of therapy-related variables. In some embodiments, the data entered into one or more minimal sets of treatment-related variables (e.g., cancer type, cancer stage, and/or treatment intent) can determine which variables to include in other minimal sets of treatment-related variables, as described above and below. In some embodiments, the method includes an operation 505 in which COTA module 220 determines whether an attribute has been assigned to at least a minimum subset of the set of prognosis or outcome related variables. In some embodiments, operation 504 and operation 505 may be combined into one operation.

The identification or definition of the minimal subset of treatment-related variables and the minimal subset of prognosis or outcome-related variables may be predefined and may be stored in a database. In some embodiments, which variables to include in the minimal subset of treatment-related variables may depend on the value of one or more treatment-related variables. For example, in cancer, which variables to include in the minimal subset of treatment-related variables may depend at least in part on the type of cancer, stage of cancer, and/or intent-to-treat. In some embodiments, the system or method may depend on the stored identity of different variables included in a minimal subset of treatment-related variables for different cancer types, cancer stages, treatment intents, or combinations thereof. In some embodiments, the identification or definition of the smallest group of treatment-related variables may be determined based, at least in part, on current medical knowledge. In some embodiments, the identification or definition of the minimum set of treatment-related variables may be determined, at least in part, by one or more medical professionals.

In some embodiments, if it is determined in operation 504 that the attribute is not assigned to the minimum subset of therapy-related variables needed to make the therapy decision, the method performs operation 506 and the COTA module 220 waits to receive, access, or obtain further data including the PHI of the target patient to assign a further attribute to the minimum subset of therapy-related variables. In some embodiments, at operation 506, COTA module 220 may check to see if there is any new or updated information associated with the patient's PHI. In some embodiments, COTA module 220 receives new or updated information associated with the patient's PHI. In some embodiments, new or updated information is pushed to the COTA module. In some embodiments, the new or updated information associated with the patient's PHI is pulled by the COTA module. In some embodiments, if in operation 504, the attributes have been assigned to less than the minimum subset of the therapy-related variables, the system or method may provide a notification or information to a user of the system (e.g., a healthcare provider or payer) that the provided information is insufficient to assign the temporary node address.

In some embodiments, where it is determined in operation 504 that the attributes have been assigned to at least a minimum subset of the at least treatment-related variables, the method proceeds directly to operation 508, where a temporary node address is assigned to the target patient. In other embodiments, where it is determined in operation 504 that an attribute has been assigned to at least a minimum subset of the treatment-related variables, the method further determines in operation 505 whether an attribute has been assigned to less than the minimum subset of the prognosis or outcome related variables. In the event that the attributes have been assigned to at least a minimum subset of the therapy-related variables in operation 504, and the attributes have been assigned to less than the minimum subset of the prognosis-or outcome-related variables in operation 504, the method proceeds to operation 508, where a temporary node address based on the therapy-related variables is assigned to the target patient.

In some embodiments, the temporary node address was previously generated based on specific attributes of a preselected variable assigned to another patient. The previously generated temporary node address may be stored in the database 240. COTA module 220 may query database 240 using the attributes assigned to the smallest subset of therapy-related variables to retrieve the temporary node address. In some embodiments, the temporary node address is generated based on a particular attribute assigned to the preselected variable. In some embodiments, the temporary node address includes an indication that one or more therapy-related preselected variables have not been assigned and/or absent. Where initial information about the patient is provided to the COTA module at or shortly after diagnosis, the provided initial information will typically include information sufficient to assign attributes to at least a minimum subset of the therapy-related variables, but not to at least a minimum subset of the prognosis or outcome-related variables, resulting in assigning temporary node addresses to the patient based on the initial information in operation 508.

The temporary node address may be associated with predetermined treatment plan information (e.g., information about one or more predetermined patient care service packages). COTA module 220 may retrieve information regarding predetermined treatment plan information (e.g., information regarding one or more predetermined patient care service packs) from database 240 based on the assigned temporary node address. In operation 510, the COTA module 220 may transmit and/or provide predetermined treatment plan information associated with one or more patient care service packs to a healthcare provider of the target patient. For example, COTA module 220 may communicate the scheduled treatment plan information (e.g., information about one or more scheduled patient care service packs) to a health care provider of the target patient who operates the user computing device 210 executing an instance of COTA module 220.

In accordance with some embodiments, where the initial data set includes information sufficient to assign attributes to a minimum subset of treatment-related variables and to assign attributes to at least a minimum subset of prognosis or outcome-related variables, in operation 509, an optimized node address is assigned to the target patient. Specifically, in some embodiments, where the attributes have been assigned to at least a minimal subset of the treatment-related variables in operation 504, and the attributes have been assigned to at least a minimal subset of the prognosis or outcome-based variables in 505, an optimized node address may be assigned to the target patient 509, but no temporary node address is assigned. As with the temporary node address, the optimized node address may be associated with predetermined treatment plan information (e.g., information about one or more predetermined patient care service packs). After assigning the optimized node address 509, the COTA module 220 may provide and/or transmit predefined treatment plan information (e.g., information about one or more scheduled patient care service packages) associated with the optimized node address assigned to the target patient in operation 510. In such embodiments, the predetermined treatment plan information 510 may be provided based on the optimized node address assigned to the target patient.

After providing the predetermined treatment plan information in operation 510, the method continues 512 to the flowchart shown in FIG. 4B. In operation 514, if the optimized node address has been assigned to the target patient, the method proceeds to determine a prognosis-related expected outcome for the target patient based on the optimized node address assigned to the target patient in operation 516. In some embodiments, based on operation 526, the determined prognosis-related expected outcome information may be provided to the target patient's healthcare provider, the target patient's healthcare payer, and/or the target patient.

In operation 518, the COTA module 220 accesses or receives new or updated information associated with the PHI of the target patient. For example, the system may access or receive a second data set including updated and/or additional personal health information associated with the target patient at a second time or within a second time period that is later than the first time or first time period corresponding to the initial data. In some embodiments, COTA module 220 receives new or updated information associated with the patient's PHI. In some embodiments, new or updated information is pushed to the COTA module. In some embodiments, the COTA module pulls new or updated information associated with the patient's PHI. In response to or after accessing and/or receiving new or updated information associated with the PHI of the target patient in operation 518, the process may proceed to operation 520, where COTA module 220 assigns attributes to preselected variables based on the new or updated PHI. It will be appreciated that the COTA module 220 may change the attributes already assigned to the preselected variables and/or assign the attributes to preselected variables that were not previously assigned in operation 502 of fig. 4A. If at least a minimal subset of the treatment-related variables and a minimal subset of the prognosis-or outcome-related variables have not been assigned attributes in operation 522, the method again accesses or receives updated or additional data for the target patient in operation 518.

If the attributes have been assigned to at least a minimum subset of the therapy-related variables and a minimum subset of the prognosis-or outcome-related variables in operation 522, the method proceeds to assign an optimized node address to the target patient in operation 524 and determine a prognosis-related expected outcome for the target patient based on the optimized node address in operation 526. In some embodiments, information regarding the prognosis-related expected outcome is provided or displayed to the healthcare provider of the target patient or the healthcare payer of the target patient in operation 526.

In some embodiments, the method continues with COTA module 220 accessing or receiving new or updated personal health information for the target patient at operation 518. It will be appreciated that each time the COTA module 220 accesses, retrieves, or receives updated or new data associated with the patient's PHI, the COTA module 220 may assign updated or new attributes to the preselected variables, and based on the updated or new attributes assigned to the preselected variables, the target patient may be assigned a new or updated optimized node address in operation 524. In some embodiments, an updated prognosis-related expected outcome will be determined based on the new or updated optimized node address in operation 516. In some embodiments, the determined updated prognosis-related output information may be provided to a healthcare provider of the target patient. In some embodiments, the attributes and optimized node addresses are continuously updated throughout the patient's treatment or throughout the patient's lifetime. In some embodiments, COTA module 220 may end the process in response to failing to access, receive, or retrieve any new or updated PHI data for the patient. In some embodiments, the COTA module periodically or on a schedule checks, accesses, or is provided with any additional data that is available. In some embodiments, the COTA module performs additional iterations of updating the optimized node address based on updated or additional data, periodically, according to a schedule, or whenever additional data for the target patient is accessed or received.

In one embodiment, the initial information associated with the patient's PHI received, accessed, or retrieved by COTA module 220 may be the patient's PHI at a first point in time, and the new or updated information associated with the patient's PHI subsequently received, accessed, or retrieved may be the patient's PHI at a second point in time after the first point in time. The new or updated information associated with the patient's PHI that is subsequently received, accessed or retrieved may be the progression of a disease (such as cancer) that the target patient is diagnosed with.

In one embodiment, the initial information associated with the patient's PHI received, accessed, or retrieved by COTA module 220 may be associated with an initial diagnosis of the patient, and the new or updated information associated with the patient's PHI subsequently received, accessed, or retrieved may be associated with subsequent diagnostic information.

It will be appreciated that each time the COTA module 220 accesses, retrieves, or receives updated or new information associated with the patient's PHI, the COTA module 220 may assign an updated or new attribute to the preselected variable and may assign an updated temporary node address to the target patient (if a point of care treatment decision has not been made and if an optimized node address has not been assigned to the patient), or may assign an optimized node address or an updated optimized node address based on the updated or new attribute assigned to the preselected variable to the target patient. In addition, new predetermined treatment plan information or new prognosis-related prospective outcomes may be provided to the target patient's healthcare provider or the target patient's healthcare payer based on the updated temporary node address or the new or updated optimized node address assigned to the target patient. It will be appreciated that each new or updated optimization or temporary address assigned to a patient may be previously generated for a particular attribute assigned to a treatment-related variable and/or a prognostic or outcome variable.

As described above, in operation 516, the optimized node address may be used to determine a prognosis-related expected outcome for the occurrence of a defined endpoint event for a patient diagnosed with a disease. In operation 516 of fig. 4B, the determined prognosis related expected outcome for the target patient may be obtained from a statistical analysis of previous prognosis related outcomes for patients in the prognosis or outcome based patient group that are assigned the same optimized node address as the optimized node address assigned to the target patient at the disease progression point corresponding to the target patient or the treatment and disease progression point corresponding to the target patient for the correlation analysis. For example, the system or method may access historical patient data for a patient's prognosis or outcome based patient group. In some embodiments, each patient in the prognosis or outcome based patient group is assigned or has been assigned the same optimized node address as the optimized node address assigned to the target patient at the disease progression point corresponding to the target patient for correlation analysis. In other embodiments, at least some but not all patients in the prognosis or outcome based patient group are assigned or have been assigned the same optimized node address as the optimized node address assigned to the target patient at the corresponding point of disease progression for correlation analysis.

The point of relevance of the optimized node address to which a patient in disease progression or disease progression and treatment is assigned or has been assigned for outcome-based analysis depends on the particular goal or type of analysis. For example, as described above, if the expected time for the target patient to progress from the beginning of second-line therapy to the beginning of third-line therapy is of interest, the relevant optimized node address will be the optimized node address for the target patient at the beginning of second-line therapy. Similarly, for an outcome or prognosis-based patient group whose historical data is to be analyzed to address the problem, in some embodiments, each patient in the outcome or prognosis-based patient group has the same optimized node address as the target patient at the beginning of the second-line therapy for that respective patient.

In some embodiments, when determining the risk adjustment, the method or system will use a group of patients that are or have been assigned the same optimized node address as the optimized node address assigned to the target patient at the same disease progression as the target patient or at corresponding points of both treatment and disease progression. In some embodiments, the patient group may include more than one optimized node address, wherein differences in the optimized node addresses do not significantly affect the risk adjustment analysis. In some embodiments, statistical analysis of historical prognosis-related outcomes for a group of patients having a prognosis or outcome assigned the same optimized node address as the target patient at a particular point in disease progression may be used to provide an expected prognosis-related outcome to the target patient having an optimized node address assigned at a particular point in disease progression. Similarly, statistical analysis of historical cost data at a particular point in the treatment for a prognosis-or outcome-based patient group assigned an optimized node address at a particular point in the treatment and disease progression may provide information about the expected cost at the corresponding particular point in the treatment for a target patient assigned the same optimized node address at the corresponding particular point in the treatment and disease progression. In some embodiments, a dynamic statistical analysis is performed on previous outcomes when needed. In some embodiments, a statistical analysis of previous outcomes associated with patients assigned a particular optimized node address may be stored. In some embodiments, the statistical analysis may be performed periodically, at different intervals, or as needed.

As described above, in one embodiment, the initial information associated with the patient's PHI received, accessed, or retrieved by COTA module 220 may be the patient's PHI at a first point in time or a first time period, and the new or updated information associated with the patient's PHI subsequently received, accessed, or retrieved may be the patient's PHI at a second point in time or a second time period after the first point in time or the first time period. The new or updated information associated with the patient's PHI that is subsequently received, accessed or retrieved may include information regarding the progression of a disease (such as cancer) that the patient is diagnosed with.

In one embodiment, the initial information associated with the patient's PHI received, accessed, or retrieved by COTA module 220 may be associated with an initial diagnosis of the patient, and the new or updated information associated with the patient's PHI subsequently received, accessed, or retrieved may include subsequent diagnostic information.

In some embodiments, the method further comprises comparing one or more outcomes of the target patient to one or more historical outcomes of patients in the prognosis-or outcome-based group to determine whether the one or more outcomes of the target patient are trending away from criteria of the prognosis-or outcome-based group, the patients being assigned the same optimized node address as the optimized node address assigned to the target patient at the time of diagnosis or progression. In some embodiments, where it is determined that one or more outcomes of the target patient are trending away from the criteria of the prognosis or outcome based group, the method further comprises: sending an alert to a healthcare provider or healthcare payer of the target patient, the alert including information about one or more outcomes that are trending away from the criteria.

In some embodiments, COTA module 220 may measure the difference in behavior of each healthcare provider for each patient of a prognosis or outcome based group by comparing the difference in cost of each patient in the patient population for treatment, testing, follow-up, adherence to prescribed medications, and/or assignment of optimized node addresses between one healthcare provider and another healthcare provider, according to some embodiments. Biological differences between patients are removed because any two patients assigned the same optimized node address at the same point of disease progression have the same relevant biological attributes by definition. Thus, at a given point in time, any difference in the outcome of these patients can be attributed to their mode of treatment. If the system or method is used to compare doctor Y who is treating a patient who has been assigned or is assigned an optimized node address a with doctor Z who is also treating a patient who has been assigned or is assigned an optimized node address a, the patient treated by doctor Y and the patient treated by doctor Z may have statistically different clinical outcomes, although the expected prognosis for the two groups is the same due to the common optimized node address. The outcome difference (in terms of treatment, testing, follow-up, adherence to prescribed medications) between one medical care provider and another is used to identify the lack of necessary care and the presence of unnecessary care that causes a difference between the health care providers. Alerts may be provided to medical providers that are deviating from standards to enable the medical providers to self-correct to meet the standards by providing the necessary care that was previously lacking and/or reducing unnecessary care. In some embodiments, COTA module 220 may identify a lack of necessary care and/or an unnecessary care being provided that causes a difference in measured behavior of at least one of the medical care providers. According to some embodiments, because patients at the same optimized node address are grouped together, similar patients may be compared in terms of treatment, outcome, and cost. For example, by comparing both the cost and outcome of patients each assigned the same optimized node address, the system can be used to identify specific patients whose treatment costs are much higher than the group but whose outcome is not better than the reorganization. The system can send alerts to healthcare payers for particular patients who have high treatment costs, and the same outcome can be achieved at a lower cost.

Fig. 4C is a flow diagram of a method for identifying a lack of necessary care and/or a medical care provider providing unnecessary care, according to some embodiments. As described above, in operation 536, the target patient is assigned to a node address. The target patient is then assigned to a prognosis or outcome based group based on the optimized node address assigned to the target patient in operation 538, as described above. In operation 542, behavioral changes are measured for each of a plurality of medical care providers assigned to a plurality of patients of the prognosis or outcome based group. Based on the behavioral differences, a lack of necessary care and/or unnecessary care provided that caused the measured behavioral change of at least one of the medical care providers is identified in operation 544.

Fig. 4D is a flowchart illustrating a process performed by COTA module 220 according to an example embodiment. As described above, the temporary node address may contain values or attributes of pre-selected variables that are therapy-related. As noted above, in some embodiments, the preselected variables are defined or identified by a panel of experts in the relevant field (e.g., oncologists with experience of more than 5 years, 10 years, 15 years, 20 years, 30 years, etc.). In some embodiments, the preselected variables are defined or identified based at least in part on information about current medical knowledge and treatment and/or information from experts in the relevant field. In some embodiments, the definition or identification of the preselected variables included in the temporary node address and the optimized node address are continuously updated based on new information about current medical knowledge and treatment and/or updated information from experts in the field. In some embodiments, the definition or identification of the preselected variable is updated periodically. In some embodiments, the definition or identification is updated as needed based on newly obtained information. In some embodiments, the preselected variables may include treatment and prognosis or outcome related variables for which attributes are needed to provide assistance in making treatment and payment decisions.

In operation 550, the COTA module 220 may access an initial data set that includes the PHI of the patient. In operation 552, the COTA module 220 may assign attributes to at least some of the set of preselected variables using the PHI of the patient. COTA module 220 may retrieve preselected variables for a particular disease from database 240. The set of preselected variables may include a set of treatment-related variables and a set of prognosis or outcome-related variables.

In operation 554, in response to COTA module 220 being able to assign attributes to a minimum subset of the set of therapy-related variables and less than the minimum subset of the prognosis or outcome-related variables, COTA module 220 may assign a temporary node address to the patient based on the assigned attributes of the set of therapy-related variables. In operation 556, the COTA module 220 determines that a preselected variable for the patient-specific disease (i.e., cancer) has changed, or accesses or receives information that the preselected variable has changed, before the point-of-care makes a treatment decision, or in some embodiments, before the optimized node address is assigned. The change may be an increase or a change in the treatment-related variable set or the treatment-related variable minimal set of the temporary node address. For example, the preselected variables may be continuously updated based on new data, new scientific findings, or new developments in treatment. In some embodiments, updates to preselected variables may be entered by an instance of COTA module 220 executing on user computing device 210. In some embodiments, another method may be used to update the preselected variables to a database that includes the preselected variables and provide information about the updates to the COTA module. Alternatively or additionally, in some embodiments, COTA module 220 may receive input from various sources to update preselected variables.

In operation 558, COTA module 220 may assign attributes to one or more therapy-related variables added to the preselected variables based on the most up-to-date information associated with the patient's PHI available to COTA module 220. In response to assigning attributes to one or more therapy-related variables added to the preselected variable, the process proceeds to operation 559, at which point, if a therapy decision has not been made, or in some embodiments, if an optimized node address has not been assigned, COTA module 220 may assign a modified temporary node address to the patient based on the attributes assigned to the newly added therapy-related variable. It will be appreciated that the COTA module 220 may assign the modified temporary node address to the patient if a treatment decision has not been made, or in some embodiments, each time the preselected treatment-related variable of the temporary node address is changed before assigning the optimized node address. It is to be appreciated that the COTA module 220 may generate the modified temporary node address prior to assigning the modified temporary node address to the patient, if desired. For example, in some embodiments, a modified temporary node address may have been generated for some other patients having the same value of the treatment-related variable, and the previously generated modified temporary node address is assigned to the target patient.

Fig. 4E is a flowchart illustrating a process performed by COTA module 220 according to an example embodiment. As described above, the optimized node address may contain at least a minimum subset of therapy-related variables and at least a minimum subset of prognosis-or outcome-related variables of the preselected variables. The preselected variables may be defined or selected as described above. The preselected variables may include treatment and prognosis or outcome related variables for which attributes are needed to provide assistance in making treatment and payment decision-making.

In operation 570, the COTA module 220 assigns an optimized node address to the target patient based on the attributes assigned to at least the minimal subset of therapy-related variables and the minimal subset of prognosis or outcome-related variables, as described above. In operation 572, the COTA module 220 may determine whether a preselected variable for a particular disease (i.e., cancer) of the patient has changed or may receive or access information regarding the change in the preselected variable included in the optimized node address. The change may be an addition to the set of treatment-related variables and/or the set of prognosis or outcome-related variables. As described above, the predetermined variable may be continuously updated. In operation 574, the COTA module 220 may assign an attribute to one or more therapy-related variables or prognosis or outcome-related variables added to the preselected variable based on the most recent information associated with the patient's PHI available to the COTA module 220. In response to assigning attributes to one or more therapy and/or prognosis or outcome related variables added to the preselected variable, the process may return to operation 570, at which time the COTA module 220 may continually assign a modified optimized node address to the target patient based on the attributes of the newly added therapy and/or prognosis or outcome related variable assigned to the preselected variable. It will be appreciated that in some embodiments, the COTA module 220 may continually assign the patient a modified optimized node address at the time of diagnosis and at each subsequent progression, depending on the start date of the particular analysis and the specific change in the attributes of the predetermined variables.

Some personal health information of the patient does not change. Other personal health information of the patient changes over time. In some embodiments, the COTA module groups the personal health information at a relevant point in time or a relevant time period and assigns a temporary node address or an optimized node address to the grouped information about the relevant point in time or the relevant time period. In some embodiments, the temporary node address is used only before the optimized node address is assigned. After assigning the optimized node addresses, the temporary node addresses are no longer used and all subsequent points in time or subsequent periods in time with respect to disease progression will be assigned the appropriate optimized node addresses.

In some embodiments, the grouped personal health information associated with different points in time or time periods may be assigned the same optimized node address or different optimized node addresses depending on the start date of the particular analysis and the specific change in the attributes of the predetermined variables. Thus, in some embodiments, the assigned temporary or optimized node address may be described as a node address associated with or assigned to the patient at a certain point in time or time period, or a node address associated with or assigned to the personal health information of the patient at a certain point in time or time period. In some embodiments, the optimized node address is assigned to the patient at least at or shortly after diagnosis and at each subsequently identified disease progression. Even if different optimized node addresses have been assigned to patients or later assigned to patients based on their time-varying variable values, the above-described grouping of personal health information at relevant points in time or time periods and the above-described node address assignment based on relevant health information at the above-described points in time facilitates the comparison of similar patients who have or have had the same relevant variable values at relevant corresponding points in the disease progression of each patient.

In some embodiments, the optimized node addresses enable identification of clinically relevant patient groups for analysis. Analyzing the data record may include tracking (e.g., in real-time) the clinical outcome of a patient with the disease. Outcomes may include, for example, dose intensity, therapeutic agent received, dose interval and dose duration, incidence and severity of toxicity, cost, Progression Free Survival (PFS), Overall Survival (OS), response rate, and the like. The COTA module 220 may compare tracking outcomes between patients. COTA module 220 may also determine, based on the tracking, whether a particular doctor associated with the tracked patient is treating the patient according to the treatment techniques of other doctors treating other (similar) patients. In one embodiment, COTA module 220 determines this based on the outcome of a number of patients whose similarities are determined based on the temporary node address or optimized node address assigned to the patient.

In another example, as described above, the analysis based on the optimized node address may provide an expected prognosis-related outcome associated with the optimized node address. In some embodiments, the prognostic-related outcome of the optimized node address may be compared to a standard prognostic-related outcome, which is a mean, median, or other statistically determined value or range of a population having various different relevant biological factors, to determine whether the patient assigned the optimized node address is likely to have a prognostic-related outcome that is better or worse (e.g., poor, good, average, or better than average) than the standard prognostic-related outcome.

In an outcome-based payment mode, the payer desires to incentivize good outcomes. However, if the expected outcome is not based on all relevant biological factors, but is based only on an average of a population with various different relevant biological factors, the provider may be penalized because the patient did not reach the average expected outcome when the reason for the expected outcome was not due to the biological factors, rather than the patient's treatment and care. Similarly, when the outcome of the patient is better than the expected outcome because of a biological factor rather than the patient's treatment and care, the provider may be awarded a prize over the expected outcome. When employing an analysis based on optimized node addresses and including information about all available relevant treatment-related variables and all available prognosis-or outcome-related variables, patients are grouped and analyzed to determine a reasonable and accurate expected outcome for a patient-specific combination of biologically-related variables, such that payers can increase or decrease payments based on achieving or not achieving a reasonable and accurate expected outcome tailored to the patient. In some embodiments, a standard outcome based on patients having different values of the biologically relevant variable may be employed, and the optimized node address is used to determine a probability that the expected outcome of the patient assigned the optimized node address substantially meets, does not meet, or exceeds the standard outcome.

As described above, the analysis based on the optimized node address may also provide the expected treatment costs at various points in the treatment associated with the optimized node address. This enables the system/method to provide a cost estimate for a particular combination of patient-specific bio-related variables that a payer can use to implement a reasonable bundled payment/pay per treatment event model.

As noted above, some value-based healthcare reimbursement models require the determination of a patient's prognosis-related outcome and/or the patient's expected cost of treatment during a clinically relevant period. Unfortunately, some conventional systems would expect outcomes to be based solely on billing codes, which may be useful for providing an average predicted outcome for patients with a particular disease, but do not account for non-care and treatment-related prognostic differences based on biological differences between patients. Such systems fail to provide an accurate prognosis for individual patients with a particular disease, such as breast cancer. For example, a population, such as a breast cancer patient population, may be composed of multiple sub-populations with different survival expectations. These survival expectations may be associated with a poor, good, average, or better than average prognosis. If payments are made based on a comparison of the individual patient's outcome with the average outcome for all breast cancer patients, this will result in under-compensation for all patients with worse outcome than average outcome, even those patients with poorer prognosis at the outset, and over-compensation for all patients with better outcome than average outcome, even those with good prognosis. Similarly, such systems do not provide an accurate estimate of the cost of treatment needed to obtain the prognosis described above.

The optimized node address contains and aggregates all biological variables relevant to the treatment and prognosis of the patient assigned the optimized node address. The optimized node addresses enable grouping of patients by treatment and diagnosis related variables and corresponding grouping of all patients with the same risk/prognosis. By analyzing historical data for appropriate patient groupings, an expected outcome specific to the relevant attributes of the patient's treatment and prognosis can be obtained. In some embodiments, patients assigned multiple different optimized node addresses in disease processes with similar prognoses may be combined into a single prognosis-or outcome-based group, such as a large risk group, a mean risk group, or a small risk group. Additionally, where historical data regarding a patient group includes historical cost information, a cost of care estimate for a clinically relevant period may be determined.

By grouping patients based on treatment and prognosis related attributes, the optimized node address enables accurate and reasonable prognosis and cost expectations to be determined, such that payers can increase or decrease payments based on achieved outcomes related to patient care rather than to the potential biological factors of the patients themselves.

In another embodiment, analyzing the data records may include updating at least some of the data records based on the outcome of the tracking (e.g., in real-time). For example, COTA module 220 may determine that patient ABC has colon cancer, has been prescribed and has taken drug XYZ for two years, and is in remission for the last 3 years. If the COTA module 220 determines the above information from the tracking of patient ABC, the module 220 may update the data record associated with patient ABC with this information. Additionally, COTA module 220 may receive information regarding costs associated with treatment of patient ABC and update records regarding costs of treatment of patient ABC over time.

In other embodiments, analyzing the data record comprises performing an analysis to determine patient survival, for example, by creating a kaplan profile. The Kaplan Meier curve is a curve showing five-year survival, which may be formed, for example, for one doctor (or medical professional) or for a group of doctors (or medical professionals). Kaplan meier curves may be created for overall survival and/or progression-free survival. Other types of analysis are also contemplated. In some embodiments, the data records to be compared may be selected based on the data records assigned to each patient or the optimized node address assigned to each patient at a given point in time during the disease process, such that only patients having similar attributes related to the treatment or prognosis of a particular disease or condition at the same point in the disease progression or treatment are compared.

To facilitate analysis, COTA module 220 may also include analysis tools that may be executed by or accessed via user computing device 210. The analysis tool may be a user interface accessible via a web page, a tag on an existing web page, a software application, an application, or the like. The user interfaces shown in the figures herein are exemplary. The analysis tool may enable a user to compare, analyze, or further rank the data records.

In some embodiments, COTA module 220 provides communication based on the analysis. The communication may be in the form of an alert to the user. In one embodiment, COTA module 220 may transmit the sorted and ordered data records and/or the updated data records to user computing device 210. For example, COTA module 220 communicates tables, charts, lists, links, etc. that enable a user to access sorted or updated data records. In another embodiment, COTA module 220 may transmit an advertisement with (e.g., related to) a data record to user computing device 210. In other embodiments, COTA module 220 may identify a particular patient as a candidate for a particular therapy or drug. This information may have value to, for example, pharmaceutical companies, health plans, managed care alliances, insurance companies, and the like. COTA module 220 may transmit the communication to user computing device 210 or any other entity (e.g., via network 215).

Fig. 5 shows a flowchart 600 of an alert provided by the COTA module 220, according to one embodiment. In one embodiment, the alert is issued based on the preferences of the doctor or other medical professional. These preferences may be set by a medical professional/physician and may include, for example, a trigger 610 for an alarm and/or a technique for providing an alarm. For example, a doctor or other medical professional may set preferences using the COTA module 220 executing on their respective user computing device 210. Triggers for alarms may include, for example, updates to the diagnosis at the new patient diagnosis 615, scheduling events in real time, changes in team members (e.g., identifying new genes that may change the grouping, and/or someone leaving the group), toxicity and/or dose intensity changes 620, disease progression 625, administration of particular drugs, alarms that tend to deviate from the expected outcome 630 and/or are associated with an expected time or period 635 (e.g., side effect alarms and/or diagnostic test reminders). The alert may include a text message 640 or an email 645 sent to the user computing device 210. Other types of alerts are also contemplated, such as phone calls to the user computing device 210, updates on a web page, social media updates, use of, for example OrOr messages sent by other social media sites, adding content to a software library or web page, and/or sendingTo the user or any other message or communication accessed by the computing device 210. Although described above as providing an alert, the trigger may be any action that causes COTA module 220 to perform any other action.

In one embodiment, the alert may also include and/or be triggered by information about a new optimized node address assigned to the patient, for example, as it progresses. Additionally or alternatively, the alert may include and/or be triggered by information regarding new predetermined treatment plan information for the patient based on a change in a new or updated provisional or optimized node address or predetermined treatment plan information associated with a provisional or optimized node address (e.g., information regarding one or more patient care service packs). in some embodiments, the alert may be triggered by a change in a preselected variable of a particular disease.

Fig. 6 is a graphical representation illustrating a mobile device 705 (e.g., user computing device 210) organizing alerts received by the device 705, according to one embodiment. As shown in fig. 7, the received COTA alerts are listed by headings or subjects such as new colon cancer 710, new renal cell carcinoma 715, dose adjustment 720, drug decommissioning 725, new progression 730, new breast cancer 735, third cycle CHOP alert 740, neutropenia risk alert 745, and available clinical trial 750. CHOP is an abbreviated name for drug combinations used in chemotherapy, including cyclophosphamide (Cytoxan/Neosar), doxorubicin (or adriamycin), vincristine (Oncovin), and prednisolone, and is used, for example, to treat non-hodgkin's lymphoma.

COTA module 220 may provide specific disease data sets (e.g., on-demand and real-time), including, for example, disease incidence (e.g., ordered by COTA), progression-free survival by progression status, and/or overall survival. In one embodiment, COTA module 220 may provide a drug utilization data set, such as data associated with all or part of a therapy, toxicity, and/or change in therapy.

Fig. 7 shows a graphical representation 800 of the incidence of cancer subtypes that may be provided by COTA module 220, according to one embodiment. Herein, COTA diagram 800 shows lymphoma from 2010 to 2013. The user may narrow the drawn information using the graphical search input segment 810. The graphical search input field 810 may include, for example, what is selected for reporting (e.g., minimal diagnosis, complete diagnosis, and/or patient under examination, type of diagnosis, location/subtype of cancer, ICD9 (international classification of disease, ninth edition) code, comorbidities, disease progression, gender, age, date range, race, diabetes, tobacco use history, history of prior chemotherapy or radiation, etc.).

Fig. 8 illustrates a graphical representation 900 that may be provided by the COTA module 220 based on the ordering of variables input to the COTA module 220, according to one embodiment. Graphical representation 900 shows a COTA plot of Hodgkin's Lymphoma divided by male versus female in 2010-2013. The graphical representation 900 shows the statistics 910 of different patients with the disease plotted in the graphical representation 900. Fig. 9 shows an exemplary list of a plurality of clinical and molecular variables 1005 associated with a particular disease (here, the variables shown are for lymphoma), according to one embodiment.

Fig. 10 shows a graphical representation 1100 including a real-time Kaplan Meier curve with confidence intervals for pancreatic cancer that may be provided by the COTA module 220, according to one embodiment. As described above, the Kaplan Meier curve is a curve showing five-year survival rate, which may be formed, for example, for one doctor (or medical professional) or for a group of doctors (or medical professionals). Kaplan Meier curves may be created for overall lifetime and/or progression-free lifetime. The user indicates the variables of his graphical search in graphical search input segment 1110.

Fig. 11 is a graphical representation 1200 of a kaplan eier curve illustrating disease progression that may be provided by the COTA module 220, according to one embodiment. Line 1205 represents all pancreatic cancers, and thick line 1210 represents pancreatic cancer that has progressed for the first time.

Fig. 12 is a graphical representation 1300 of a real-time benchmark of outcome between two parties that may be provided by COTA module 220, according to one embodiment. The diagram 1300 includes a curve 1305 of John Doe physician's outcome for treating pancreatic cancer, a curve 1310 of the outcome of the remaining physicians for treating pancreatic cancer, and a meter 1320 that measures whether the John Doe physician's outcome is positive tracking or negative tracking.

Fig. 13 to 18 relate to the measurement of the outcome. Fig. 13 is a graphical representation of an expense report 1400 associated with (e.g., provided by) COTA module 220, according to one embodiment. Expense report 1400 may be associated with expense label 1220 of fig. 12. The expense report 1400 may be used, for example, to estimate treatment expenses, acquire knowledge, and/or translate knowledge into a particular implementation. In one embodiment, COTA module 220 tracks the costs of various treatments, doctors, hospitals, etc. in real time. As shown in fig. 14, the expense report 1400 shows an outcome graph that includes a comparison between the average cost of the physician and each revenue center (e.g., hospital). The expense report 1400 may also include other comparisons, such as hospital margin in dollars and percentages, average hospital revenue and expenses (e.g., average revenue per patient, average expense per patient), average physician expenses per case (e.g., average expense per case per physician, weighted average), average physician expenses per revenue (e.g., average expense per physician for imaging, laboratory work, assessment and management, medications, medical supplies and other expenses), and so forth. In an outcome-based payment mode, the payer wishes to incentivize a favorable outcome. By ordering patients using optimized node addresses that include all available treatment elements and all available progression elements, a patient group with reasonable expectations of progression is created. In some embodiments, this enables payments by payers to be increased or decreased based on actually achieved results related to treatment and care, rather than increased or decreased based on biological attributes of patients that affect prognosis and outcome.

Fig. 14A and 14B are graphical representations of a therapy interface 1500 associated with (e.g., provided by) COTA module 220 for facilitating a link between outcome and therapy, according to one embodiment. Fig. 14A and 14B illustrate the outcome of a patient decision based on an impact on treatment. As shown in fig. 14A, the treatment interface 1500 may include a list of different types of treatments to be administered (or rejected) to a breast cancer patient, such as surgery, antineoplastic drugs, cell therapy, radiation therapy, and the like. Treatment can be scheduled according to disease progression. For example, drugs in oncology are typically administered on a periodic basis, and any number of drugs may be administered in any one period. In one embodiment, the user may select progression (e.g., represented as progression 0 through progression 4), where progression 0 is after the first diagnosis, the cycle, and may select a drug in or from multiple categories.

In fig. 14B, in another embodiment, a therapy interface 1510 can include therapy protocols for one or more therapies, represented graphically on the therapy interface 1510 as a label 1515. The treatment interface 1510 may include fields indicating start and end data for a regimen, dose intensity, treatment description, specific brands of drugs, and the like. The treatment plan may be summarized graphically or represented as a list of treatments in table 1520. The table 1520 may include an action icon 1505 for each treatment. Action icon 1505 may facilitate actions such as editing, closing, viewing parts, and the like. In one embodiment, the action icon 1505 may be a shortcut to perform a complex task with a single selection (e.g., requiring multiple clicks or selections). For example, an icon on the diagnosis line may turn the user to the diagnosis screen.

FIG. 15 is a graphical representation of an ending screen 1600 that facilitates ending tracking according to one embodiment. The outcome screen 1600 may facilitate outcome tracking from, for example, diagnosis (i.e., zero progression), first progression, second progression, to fourth progression, where each progression is considered a different disease. The results screen tab may include (e.g., in one or more drop-down menus or other fields) a diagnosis date, treatment start and end dates, response to treatment (e.g., complete, partial, stable) and response dates, input fields for comments on the response (e.g., partial fields, CR-RA-Pet negative fields, CR fields, etc.), and tracking end data, which may include fields for last contact and death. The outcome screen 1600 may also include other fields, such as toxicity of the medication, input area that enables input of occurrences (e.g., interruption, continuation, no change, medication dose change, and how many times), number of delays, number of medication changes, and/or number of reductions. In one embodiment, a user of the COTA module 220 may mark the patient.

Fig. 16 is a graphical representation of a treatment details report screen 1700 showing a comparison between costs and outcomes, according to one embodiment. Specifically, the chart in the report shows the cost and outcome of treatment for lung cancer. Curves 1705, 1710, 1715 in the figure are Kaplan Meier survival curves for lung cancer with different spending ranges. The treatment details report screen 1700 correlates care costs with clinical outcomes to optimize care value. Hospitals, doctors, etc. may collect and analyze cost and financial data over a given period of time (e.g., 5 years). The cost and financial data may be represented by one or more cost ranges. In one embodiment, the fee range includes a range 1705 for fees greater than $25,000, a range 1710 for fees from $10,000 to $25,000, and a range 1715 for fees less than $10,000. As shown by the curves 1702, 1710, 1715 for the different fee ranges in the figure, higher fees are associated with improved survival over time. When combined with clinical data, COTA module 220 may provide cost data for different treatments over a given time period based on different clinical categories.

Fig. 17 is a graphical representation of an analysis screen 1800 provided by COTA module 220 showing a comparison between toxicity and cost, according to one embodiment. The analysis screen 1800 correlates the incidence and severity of toxicity with care costs and care outcomes. The analysis screen 1800 includes a bar graph showing the toxicity level and treatment cost of the adjuvant therapy for breast cancer patients. Toxicity can be expressed in terms of numbers (e.g., ranges), standards (e.g., ratings), and the like. For example, as shown in fig. 17, toxicity is expressed as toxicity classes 1-4 classified based on Common Terminology Criteria for Adverse Events (CTCAE). Toxicity ratings are compared to costs by means of a graph. As shown, higher treatment costs may be associated with increased toxicity and corresponding decreased quality over time. The analysis screen 1800 may be used to optimize the value and efficacy of care, where the value is efficacy/cost. In one embodiment, COTA module 220 attempts to achieve high efficiency and low cost.

Fig. 18 is a graphical representation of an analysis screen 1900 provided by COTA module 220, the analysis screen 1900 including a chart comparing the quality of life of various adjunctive treatments for breast cancer. Treatment may be represented by the treatment medication in analysis screen 1900. However, other forms of treatment are also contemplated, such as surgery, and the like. In one embodiment, treatment includes the incidence, severity and toxicity of the treatment. Quality of life can be measured based on the average ECOG (eastern cooperative group of tumors) scale, ranging from level 0 (i.e. fully active) to level 5 (i.e. dead). Any suitable metric may also be used to measure quality of life. The analysis screen 1900 may be helpful in assessing a patient's disease progression, the impact of the disease on the patient's ability to live daily, and appropriate treatment and prognosis. As shown, ECOG is highest for Herceptin (Herceptin), followed by runing (Arimidex), Taxol (Taxol), taxotere (taxotere) and TAC.

Fig. 19 is a flow diagram 2000 illustrating an alert system of a COTA module providing an alert to a medical professional, a system of a medical provider, or a system of a payer or payer, according to some embodiments. In one embodiment, the information in the alert assists the user in making decisions about future actions. In one embodiment, the information in the alert is about some past action, past result, or change in status. In one embodiment, the information provided both proactively affects the user's decisions and reactively provides a summary report of the performance of the medical staff over the past week, month, quarter, etc. In one embodiment, there are different alerts for different users, each of which may affect the decision the user makes. For example, in the event that the administered treatment deviates from the desired outcome, the alarm may be used for real-time procedural correction to achieve an optimal value. In block 2005, the definition is triggered based on the clinical data. Any standard trigger definition may be used, for example, new disease diagnosis, disease progression, patient response, changes in patient characteristics, dose changes/drug toxicity changes, trends away from desired results, and the like. The criteria may be adjusted based on the disease and its parameters. Based on the triggered definition, alerts 2010-A, 2010-B, 2010-C (collectively alerts 2010) are transmitted. It should be understood that the alerts 2010 may include any number of alerts. The alert 2010 may include content or a link to content. The alert 2010 may be transmitted to a responsible doctor, other medical professional, a hospital, a pharmaceutical company, a payer of medical services, or any other individual or entity.

Content 2015-a, 2015-B, 2015-C (collectively referred to as content 2015) is displayed, e.g., using user computing device 210 to provide alerts. Content 2015 may include patient data, comparisons, or any other relevant content associated with alert 2010. In one embodiment, the comparison may be, for example, a comparison between physicians, a comparison between a patient of one physician and the entire patient population, a comparison between one physician and all physicians at a particular location, and the like. The comparison may be based on trend analysis to show trends in the treatment and whether the treatment deviates from orbit (i.e., results are not normalized). The comparison may be illustrated as one or more curves on a graph. In one embodiment, COTA module 220 is used with cloud computing. COTA module 220 may also implement or use a connection to hospital records.

In one embodiment, the content 2015 may include feedback support for a medical professional. In some embodiments, the feedback may be a graphical symbol or indicator. For example, the feedback may include a traffic light feedback indicator (not shown) on the display. For example, blue may mean very good performance (i.e., better than standard), green may mean standard performance, yellow may mean sufficient performance but may require attention, and red may mean that the user may need attention regarding the method that the medical professional took for the disease. Other feedback indicator implementations may also be employed.

Fig. 20-22 show graphical representations of different diagnostic types in accordance with one or more embodiments. Fig. 20 shows a diagnostic screen 2100 for gastrointestinal oncology (e.g., colon cancer). For colon cancer with intent to assist in treatment, ECOG status, stage and comorbidity will be the smallest subset of treatment-related variables that must have the attribute of assigning temporary node addresses. Information about comorbidities and cancer sites is the only information available. Thus, less than the minimum subgroup of treatment-related variables has attributes and more information must be provided to the temporary node address assigned to the patient. Fig. 21 shows a diagnostic screen 2200 of breast oncology (e.g., breast cancer). For the intent of adjuvant treatment of breast cancer, a minimal subset of treatment-related variables include treatment type, gender, TNM, ECOG status, treatment-related co-morbidities, histological grade, histology, Her2 status, ER status, PR status, lymphatic vessel invasion; and menopausal status. As shown, information about comorbidities and cancer sites is the only information available. Thus, a less than minimum subset of the treatment-related variables has the value of the patient, and more information must be provided to assign the patient a temporary node address. Fig. 22 shows a diagnostic screen 2300 of breast oncology (e.g., lung cancer). For non-small cell lung cancer (NSCLC) with the intent of adjuvant/neoadjuvant therapy, staging, histology, ECOG, and comorbidities would constitute the smallest subset of treatment-related variables. Information about comorbidities and cancer sites is the only information available. Thus, a less than minimum subset of the treatment-related variables has the value of the patient, and more information must be provided to assign the patient a temporary node address. The diagnostic screens 2100, 2200, 2300 include many different parameters such as tests or aspects of disease. The parameters may be represented as simple indicators, numeric based parameters, standard based parameters, and the like.

In some embodiments, the diagnostic screen may include a guide, region, or menu for selecting or entering values of a first predetermined variable that determines which other values are included in the minimal subset of treatment-related variables, and the guide, region, window, or menu for selecting or entering values of the other variables in the minimal subset of predetermined variables may be presented based on the values selected for the first predetermined variable. For example, in some embodiments, the initial screen or a portion of the screen may include a guide, window, menu, or region of activity to input values for the cancer site/subtype and treatment intent, and in response to or based on the values input for the cancer site/subtype and treatment intent, a guide, window, menu, or region for inputting a minimum subset of other values for the predetermined treatment-related variables may be displayed or activated. In some embodiments, the navigation, window, menu, or area for entering the values of the minimum subset of treatment-related variables may be separate or visually distinguishable from the navigation, window, menu, or area for entering the values of the predetermined variables that do not belong to the minimum subset of treatment-related variables. In this manner, in some embodiments, the user interface may guide the entry of information for a minimum subset of treatment-related variables.

Fig. 23 is a graphical representation of a reporting screen 2400 showing the data generation and ordering of COTA module 220 for breast oncology. According to one embodiment, the report screen 2400 shows histologically between 2008 and 2013 breast cancer, i.e., with invasive ductal cancer. Histology is one example of a treatment-related variable for breast cancer adjuvant therapy intent, and is an outcome element for new adjuvant therapy intent. The chart demonstrates Her2neu status in patients with invasive ductal cancer, and the chart correlates Her2neu status with outcome (i.e., overall survival/survival): the survival rate for Her2 neu-negative patients was 72%, while the survival rate for all Her2 neu-positive patients was 16.8%. Thus, both histological type (invasive ductal carcinoma) and Her2neu status of the tumor are prognostic indicators. The reporting screen 2400 allows breast cancer patients to be selected in real time based on stage, age, progress, or any other parameter using the optimized node address for each patient. Advantageously, the reporting screen 2400 allows for sorting in a clinically relevant manner.

Fig. 24 is a graphical representation of a report screen 2500 showing data generation and ordering for the COTA module of breast oncology. According to one embodiment, the report screen 2500 shows all grade 2 breast cancers from 2008 to 2013 in stages. Breast cancer stage is an example of a breast cancer treatment-related variable, and also a prognosis or outcome-related variable (see column heading-survival). Breast cancer stage is also a prognostic variable or attribute.

Fig. 25 is a graphical representation of a report screen 2600 that illustrates data generation and ordering by the COTA module 220 for breast cancer. According to one embodiment, the report screen 2600 shows IIB breast cancer for all stages from 2008 to 2013. The chart 2605 on the report screen 2600 shows all stages of IIB breast cancer by progesterone receptor status. Progesterone receptor status is an example of a variable relevant for breast cancer treatment, as well as a prognostic or outcome-related variable (see column headings — survival).

Fig. 26 illustrates a graphical representation of an analysis screen 2700 showing overall survival outcome for a breast cancer patient, according to one embodiment. This is an example of a standard expected outcome for breast cancer and is not specific to the optimized node address or the prognosis-based or outcome group associated with the optimized node address.

Fig. 27 illustrates a graphical representation 2800 showing survival outcome of breast cancer as a comparison between John Doe physician (bold line) and the collective (not bold line) side, according to an embodiment. This screen shows analyzing the effect of non-biological factors (such as treatment differences between providers) on patient outcomes, which can be used to identify providers whose outcomes tend to deviate from the norm.

In one embodiment, the above-described "node" data elements or node addresses may represent each permutation of variables shown in one or more graphical representations (e.g., in one or more of fig. 20-26). In some embodiments, the node data element or node address may represent each permutation of variables present in the patient data accessed by or made available to the COTA module.

As shown in the example of fig. 28, client device 2905 may include one or more processing units (also referred to herein as CPUs) 2922 that interface with at least one computer bus 2925. Client device 2905 may be part of user computing device 210 or computing system 205, for example. The memory 2930 may be a persistent memory and interface with the computer bus 2925. The memory 2930 includes RAM 2932 and ROM 2934. ROM 2934 includes BIOS 2940. The memory 2930 interfaces with the computer bus 2925 to provide information stored in the memory 2930 to the CPU 2922 during execution of software programs, such as an operating system 2941, application programs 2942, device drivers, and software modules 2943, 2945 including program code, and/or computer-executable process steps, which incorporate the functions described herein, such as one or more of the process flows described herein. First, the CPU 2922 loads computer-executable process steps from memory, such as the memory 2932, one or more data storage media 2944, a removable media drive, and/or other storage devices. The CPU 2922 may then execute the stored process steps in order to execute the loaded computer-executable process steps. Stored data, such as data stored by a memory device, may be accessed by the CPU 2922 during execution of the computer-executable process steps.

One or more persistent storage media 2944 are computer-readable storage media that may be used to store software and data, such as an operating system and one or more application programs. One or more persistent storage media 2944 may also be used to store device drivers, such as one or more digital camera drivers, monitor drivers, printer drivers, scanner drivers, or other device drivers, web pages, content files, playlists, and other files. The one or more persistent storage media 2206 may also include program modules and data files for implementing one or more embodiments of the disclosure.

For the purposes of this disclosure, a computer-readable medium stores computer data in a machine-readable form, which data can include computer program code executable by a computer. By way of example, and not limitation, computer-readable media may comprise computer-readable storage media for tangible or fixed storage of data or communication media for transient interpretation of signals containing the code. Computer-readable storage media, as used herein, refers to physical or tangible memory (as opposed to signals) and includes, but is not limited to, volatile and non-volatile, removable and non-removable media implemented in any method or technology for tangible storage of information such as computer-readable instructions, data structures, program modules or other data.

Computer-readable storage media includes, but is not limited to, RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other physical or material medium which can be used to tangibly store the desired information or data or instructions and which can be accessed by a computer or processor.

The client device 2905 may also include one or more of the following: power supply 2926, network interface 2950, audio interface 2952, display 2954 (e.g., display 245 as shown in fig. 2), keypad 2956, illuminator 2958, I/O interface 2960, haptic interface 2962, GPS 2964, microphone 2966, a video camera, a TV/radio tuner, audio/video capture card, sound card, analog audio input with a/D converters, modem, digital media input (HDMI, optical link), digital I/O port (RS232, USB, FireWire, Thunderbolt), expansion slot (PCMCIA, ExpressCard, PCI, PCIe).

For purposes of this disclosure, a module is a software, hardware, or firmware (or combination thereof) system, process, or functionality, or component thereof, that performs or facilitates the processes, features, and/or functions described herein (with or without human interaction or enhancement). The module may include sub-modules. The software components of the module may be stored on a computer readable medium. The modules may be integral to, loaded and executed by, one or more servers. One or more modules may be grouped into engines or applications.

Fig. 28 is a block diagram illustrating an internal architecture of an example of a computer, such as computing system 205 and/or user computing device 210, according to one or more embodiments of the present disclosure. A computer as referred to herein refers to any device having one or more processors capable of executing logic or coded instructions, and may be a server, personal computer, set-top box, tablet, smartphone, tablet or media device, or the like. As shown in the example of fig. 29, the internal architecture 3000 includes one or more processing units (also referred to herein as CPUs) 3012 that interface with at least one computer bus 3002. Also interfacing with computer bus 3002 are one or more persistent storage media 3006, network interface 3014, memory 3004, e.g., Random Access Memory (RAM), run-time transient memory, read-only memory (ROM), etc., media disk drive interface 2308 as an interface for a drive that can read and/or write to media including removable media such as floppy disks, CD-ROMs, DVDs, and the like, display interface 3010 as an interface for a monitor or other display device, keyboard interface 3016 as an interface for a keyboard, pointing device interface 3018 as an interface for a mouse or other pointing device, and various other interfaces not separately shown, such as parallel and serial port interfaces, Universal Serial Bus (USB) interfaces, and the like.

The memory 3004 interfaces with the computer bus 3002 to provide information stored in the memory 3004 to the CPU 3012 during execution of software programs, such as an operating system, application programs, device drivers, and software modules including program code and/or computer-executable process steps, which incorporate the functionality described herein, e.g., one or more of the process flows described herein. First, the CPU 3012 loads computer-executable process steps from a memory, such as the memory 3004, one or more storage media 3006, a removable media drive, and/or other storage devices. CPU 3012 may then execute the stored process steps to perform the loaded computer-executable process steps. Stored data, such as data stored by a storage device, may be accessed by the CPU 3012 during execution of computer-executable process steps.

As described above, persistent storage media 3006 is a computer-readable storage medium that can be used to store software and data, such as an operating system and one or more application programs. One or more persistent storage media 3006 can also be used to store device drivers such as one or more digital camera drivers, monitor drivers, printer drivers, scanner drivers, or other device drivers, web pages, content files, playlists, and other files. One or more of the persistent storage media 3006 can also include program modules and data files for implementing one or more embodiments of the disclosure.

The internal architecture 3000 of the computer may include (as described above): microphones, cameras, TV/radio tuners, audio/video capture cards, sound cards, analog audio inputs with a/D converters, modems, digital media inputs (HDMI, optical link), digital I/O ports (RS232, USB, FireWire, Thunderbolt) and/or expansion slots (PCMCIA, ExpressCard, PCI, PCIe).

Those skilled in the art will recognize that the methods and systems of the present disclosure may be implemented in a variety of ways and, thus, are not limited by the foregoing exemplary embodiments and examples. In other words, the functional elements and individual functions performed by a single or multiple components in various combinations of hardware and software or firmware can be distributed among software applications at either the user computing device or the server or both. In this regard, any number of the features of the different embodiments described herein may be combined into a single or multiple embodiments, and alternate embodiments having fewer than or more than all of the features described herein are possible. The functionality may also be distributed, in whole or in part, among multiple components, in manners now known or later known. Thus, myriad software/hardware/firmware combinations can implement the functions, features, interfaces and preferences described herein. Further, it will be understood by those skilled in the art, both now and in the future, that the scope of the present disclosure covers conventionally known manners for carrying out the described features and functions and interfaces, as well as variations and modifications that may be made to the hardware or software or firmware components described herein. While the system and method has been described in terms of one or more embodiments, it is to be understood that the disclosure is not necessarily limited to the disclosed embodiments. To cover various modifications and similar arrangements included within the spirit and scope of the claims, the scope of the claims should be accorded the broadest interpretation so as to encompass all such modifications and similar structures. The present disclosure includes any and all embodiments of the following claims.

Claims (31)

1. A method for facilitating early treatment decisions and determining a prognosis-related prospective outcome with respect to the occurrence of defined endpoint events for a target patient diagnosed with a disease, the method comprising:

accessing or receiving a first data set comprising personal health information associated with the target patient at or over a first time period, the personal health information comprising information about a phenotypic characteristic;

assigning attributes to at least some of a set of preselected variables based on the received or accessed first data set, the set of preselected variables including a set of therapy-related variables and a set of prognosis or outcome-related variables,

assigning a temporary node address to the target patient based on the assigned attributes of the set of therapy-related variables, the temporary node address being associated with predetermined therapy plan information tailored to a particular combination of attributes embodied in the temporary node address to facilitate therapy decisions, if an attribute is assigned to at least a minimal subset of the set of therapy-related variables;

providing the predetermined treatment plan information to a healthcare provider of the target patient to facilitate a treatment decision for the target patient;

Accessing or receiving a second data set comprising updated and/or additional personal health information associated with the target patient at or for a second time period later than the first time;

assigning updated attributes to at least some variables of the set of preselected variables and/or assigning new attributes to preselected variables for which attributes were not previously assigned based on the accessed or received second data set; and

in the case where an attribute is assigned to at least the minimum subset of the treatment-related variables and at least the minimum subset of the prognosis-or outcome-related variables:

assigning an optimized node address to the target patient based on the currently assigned attributes of the set of therapy-related variables and the currently assigned attributes of the set of prognosis or outcome-related variables; and

determining the prognosis-related expected outcome for the patient with respect to the occurrence of the defined endpoint event based on the optimized node address assigned to the target patient.

2. The method of claim 1, wherein said at least one of said first and second methods,

(a) wherein the minimum subset of the treatment-related variables are treatment-related variables in the set of pre-selected variables that are needed to provide pre-selected treatment-related information tailored to a particular combination of treatment-related attributes of a patient to guide treatment decisions; or

(b) Wherein the minimal subset of the treatment-related variables of the target patient depends at least in part on the target patient's cancer type and treatment intent; or alternatively

(c) Wherein the minimum subset of the treatment-related variables comprises a cancer type and a treatment intent, and wherein which other of the treatment-related variables are included in the minimum subset of the treatment-related variables depends at least in part on the cancer type and the treatment intent of the target patient; or alternatively

(d) Wherein accessing or receiving a first data set comprising personal health information associated with the target patient at or within a first time period comprises accessing or receiving information about the type of cancer and treatment intent of the target patient; and wherein the method further comprises determining the minimum subset of the therapy-related variables based at least in part on the accessed or received information regarding the cancer type and the therapy intent of the target patient; or

(e) Wherein the minimum subset of the prognostic or outcome-related variables is all of the prognostic or outcome-related variables in the set of preselected variables required for statistical analysis of prior outcomes; or

(f) Wherein the second data set comprises data obtained from a health record of the target patient; or alternatively

(g) Wherein the first data set comprises data obtained from a health record of the target patient; or alternatively

(h) Wherein the method further comprises evaluating the first data set to determine if it is correct prior to assigning the attribute to at least some variables in the set of preselected variables; or alternatively

(i) Wherein the predetermined treatment plan information comprises information regarding one or more predetermined patient care service packs, and wherein providing the predetermined treatment plan information to the healthcare provider of the target patient comprises providing information regarding the one or more predetermined patient care service packs.

3. The method of claim 1, wherein said at least one of said first and second methods,

(a) further comprising presenting a user interface to the patient and/or a healthcare provider of the patient for entering data in the first data set; or alternatively

(b) Further comprising, after accessing or receiving the second data set, iteratively accessing an updated or new data set comprising personal health information associated with the patient; and after accessing or receiving each updated or new data set:

Assigning updated attributes to at least some variables of the set of preselected variables and/or assigning attributes to preselected variables to which attributes have not previously been assigned based on the accessed or new data set; and

assigning an optimized node address or an updated optimized node address to the target patient based on currently assigned attributes of the set of therapy-related variables and currently assigned attributes of the set of prognosis or outcome-related variables, with the attributes assigned to at least the minimum subset of the therapy-related variables and at least the minimum subset of the prognosis or outcome-related variables; or

(c) Further comprising:

receiving or accessing information about a change in the set of preselected variables, the change comprising adding one or more variables to the set of therapy-related variables and/or the set of prognosis or outcome-related variables;

assigning an attribute to at least one of the one or more variables added to the set of therapy-related variables and/or the set of prognosis or outcome-related variables based on current personal health information associated with the target patient; and

assigning a different optimized node address to the target patient based on the assigned attributes of the therapy-related variable and the prognosis or outcome-related variable; or

(d) In the event that the predetermined treatment plan information associated with the temporary node address assigned to the patient changes before a treatment decision has been made or an optimized node address has been assigned to the target patient, the method further comprises providing current predetermined treatment plan information to the healthcare provider of the target patient; or alternatively

(e) Further comprising providing an alert to a healthcare provider of the target patient that the predetermined treatment plan information associated with the temporary node address assigned to the target patient has changed; or

(f) Further comprising generating the temporary node address based on the assigned attributes of the set of therapy-related variables prior to assigning the temporary node address to the target patient; or

(g) Further comprising generating the optimized node address based on the assigned therapy-related variable and the assigned prognosis or outcome-related variable prior to assigning the optimized node address to the target patient; or

(h) Further comprising:

assigning the target patient to a prognosis or outcome based group based on the optimized node address assigned to the target patient;

Measuring behavioral differences for each of a plurality of medical care providers assigned to a plurality of patients of the prognosis or outcome based group; and

identifying a lack of necessary care and/or providing unnecessary care that causes a difference in measured behavior of at least one of the medical care providers.

4. The method of claim 3, wherein the user interface directs the user to input at least the minimum subset of therapy-related variables.

5. The method of claim 2, further comprising:

presenting a user interface for inputting data in the first data set to the patient and/or a healthcare provider of the patient; and

receiving information about the type of cancer of the target patient and the treatment intent of the target patient; and

after determining the minimum subset of the therapy-related variables based on the received information regarding the cancer type of the target patient and the therapy intent of the target patient, directing input of a remainder of the minimum subset of the therapy-related variables via the user interface.

6. The method of claim 1, wherein the prognosis-related expected outcome for the target patient is determined from a statistical analysis of prior prognosis-related outcomes of patients in a prognosis-or outcome-based patient group that are each assigned the same optimized node address as the optimized node address assigned to the target patient at a point of treatment and disease progression corresponding to the target patient.

7. The method of claim 6, wherein said at least one of said first and second sets of parameters is selected from the group consisting of,

(a) further comprising statistically analyzing the previous outcomes of patients in the prognosis or outcome based patient group to determine a current expected prognosis-related outcome for the target patient; or

(b) Further comprising performing an updated statistical analysis of the previous outcomes of patients in the prognosis or outcome based patient group to determine an updated current expected prognosis related outcome and storing information about the updated current expected prognosis related outcome; or

(c) Further comprising transmitting information regarding the prognosis-related expected outcome to a client device associated with the patient's healthcare provider or the target patient's healthcare payer; or

(d) Further comprising accessing information regarding billing costs for treatment of the target patient and determining a total cost of treatment for the target patient over a clinically relevant period; and comparing an expected cost of treatment of the target patient over a clinically relevant period to the total cost of treatment of the target patient over the clinically relevant period; or

(e) Further comprising comparing one or more outcomes of the target patient to one or more historical outcomes of the patients in the prognosis-or outcome-based patient group to determine whether the one or more outcomes of the target patient are trending away from criteria of the prognosis-or outcome-based group, the patients each being assigned the same optimized node address as that assigned to the target patient at the time of diagnosis or progression.

8. The method of claim 7, wherein the current expected prognosis-related outcome is a time to progress from the beginning of second-line therapy to the beginning of third-line therapy, and wherein the patients in the prognosis-or outcome-based patient group are patients that are each assigned the same optimized node address at the beginning of second-line therapy as the optimized node address assigned to the target patient at the beginning of second-line therapy.

9. The method of claim 7, wherein the updated statistical analysis is performed periodically.

10. The method of claim 6, wherein said at least one of said first and second sets of parameters is selected from the group consisting of,

further comprising:

(a) accessing information about the outcome of the target patient;

comparing the outcome of the target patient with the determined prognosis-related expected outcome of the target patient; and

transmitting information regarding the comparison to a healthcare provider of the patient or a healthcare payer of the target patient; or

(b) Determining an expected treatment cost for the target patient with respect to the disease over a clinically relevant period based on treatment costs for all patients in the prognosis or outcome based patient group, the patients each being assigned an optimized node address at a point of treatment and disease progression corresponding to the target patient that is the same as the optimized node address assigned to the target patient.

11. The method of claim 10, wherein the optimized node address assigned to the target patient has an associated expected treatment cost for the disease from diagnosis to death or cure determined by statistical analysis of previous treatment costs for the patients in the prognosis or outcome based patient group from diagnosis to death or cure, each assigned the same optimized node address as assigned to the target patient at diagnosis.

12. The method of claim 7, wherein the clinically relevant period is from diagnosis to death or cure.

13. The method of claim 7, further comprising:

in an instance in which it is determined that one or more outcomes of the target patient are trending away from the criteria of the prognosis-or outcome-based group, sending an alert to a healthcare provider or healthcare payer of the target patient, the alert including information about the one or more outcomes that are trending away from the criteria.

14. The method of claim 7, further comprising: sending an alert to a healthcare provider or health payer of the target patient if the total cost of treatment of the target patient over the clinically relevant period exceeds the expected cost of treatment of the target patient over the clinically relevant period by a threshold amount.

15. The method of claim 1, wherein said at least one of said first and second methods,

(a) wherein the second data set comprises data indicative of the progression of the disease after the first time point or after the first time period; or alternatively

(b) Wherein the first data set includes information about a first diagnosis and the second data set includes information about an updated diagnosis after the first diagnosis; or alternatively

(c) Wherein the second data set comprises information about attributes in which no information or incomplete information is provided in the first data set; or alternatively

(d) Wherein the prognostic-related outcome associated with the occurrence of a defined endpoint event comprises one or more of overall survival, progression-free survival or disease-free survival.

16. A system for facilitating early treatment decisions and determining a prognosis-related prospective outcome with respect to the occurrence of defined endpoint events for a target patient diagnosed with a disease, the system comprising:

a computing system hosting an application and in communication with a database and one or more third party systems executing the application, the computing system configured to:

accessing or receiving a first data set comprising personal health information associated with the target patient at or over a first time period, the personal health information comprising information about a phenotypic characteristic;

Assigning attributes to at least some of a set of preselected variables based on the accessed or received first data set, the set of preselected variables comprising a set of treatment-related variables and a set of prognosis or outcome-related variables,

assigning a temporary node address to the target patient based on the assigned attributes of the set of therapy-related variables, the temporary node address being associated with predetermined treatment plan information to facilitate treatment decisions, the predetermined treatment plan information being tailored to a particular combination of attributes embodied in the temporary node address, if an attribute is assigned to at least a minimum subset of the set of therapy-related variables and a less-than-minimum subset of the prognosis-or outcome-related variables;

providing the predetermined treatment plan information to at least one of the one or more third-party systems of the healthcare provider of the target patient;

accessing or receiving a second data set comprising updated or additional personal health information associated with the target patient at or for a second time period later than the first time;

assigning updated attributes to at least some variables of the set of preselected variables and/or assigning new attributes to preselected variables for which attributes were not previously assigned based on the accessed or received second data set;

In the case that an attribute is assigned to at least the minimal subset of the treatment-related variables and at least the minimal subset of the prognosis-or outcome-related variables:

assigning an optimized node address to the target patient based on the currently assigned attributes of the set of therapy-related variables and the currently assigned attributes of the set of prognosis or outcome-related variables; and

determining the prognosis-related expected outcome for the target patient with respect to the occurrence of the defined endpoint event based on the optimized node address assigned to the target patient.

17. The system of claim 16, wherein the system further comprises,

(a) wherein the minimum subset of the treatment-related variables are treatment-related variables in the set of pre-selected variables that are needed to provide pre-selected treatment-related information tailored to a particular combination of treatment-related attributes of a patient to guide treatment decisions; or

(b) Wherein the minimum subset of the treatment-related variables for the target patient is dependent at least in part on the target patient's cancer type and treatment intent; or

(c) Wherein the minimum subset of the treatment-related variables comprises a cancer type and a treatment intent, and wherein which other of the treatment-related variables are included in the minimum subset of the treatment-related variables depends at least in part on the cancer type and the treatment intent of the target patient; or

(d) Wherein accessing or receiving a first data set comprising personal health information associated with the target patient at or within a first time period comprises accessing or receiving information about the type of cancer and intent-to-treat of the target patient; and wherein the method further comprises determining the minimum subset of the therapy-related variables based at least in part on the accessed or received information regarding the cancer type and the therapy intent of the target patient; or alternatively

(e) Wherein the minimum subset of the prognostic or outcome-related variables is all of the prognostic or outcome-related variables in the set of preselected variables required for statistical analysis of prior outcomes; or alternatively

(f) Wherein the second data set comprises data obtained from a health record of the target patient; or

(g) Wherein the first data set comprises data obtained from a health record of the target patient; or

(h) Wherein the method further comprises evaluating the first data set to determine if it is correct prior to assigning the attribute to at least some variables of the set of preselected variables; or

(i) Wherein the predetermined treatment plan information comprises information regarding one or more predetermined patient care service packs, and wherein providing the predetermined treatment plan information to the healthcare provider of the target patient comprises providing information regarding the one or more predetermined patient care service packs.

18. The method as set forth in claim 16, wherein,

(a) wherein the computing system is further configured to present a user interface to the patient and/or a healthcare provider of the patient for entering data in the first data set; or alternatively

(b) Wherein the computing system is further configured to, after accessing or receiving the second data set, iteratively access or receive an updated or new data set comprising personal health information associated with the patient; and

after accessing or receiving each updated or new data set:

assigning updated attributes to at least some variables of the set of preselected variables and/or assigning attributes to preselected variables for which attributes were not previously assigned based on the accessed or new data set; and

assigning an optimized node address or an updated optimized node address to the target patient based on currently assigned attributes of the set of therapy-related variables and currently assigned attributes of the set of prognosis or outcome-related variables, with the attributes assigned to at least the minimal subset of the therapy-related variables and at least the minimal subset of the prognosis or outcome-related variables; or alternatively

(c) Wherein the computing system is further configured to:

receiving or accessing information about a change in the set of preselected variables, the change comprising adding one or more variables to the set of treatment-related variables and/or the set of prognosis or outcome-related variables;

assigning an attribute to at least one of the one or more variables added to the set of therapy-related variables and/or the set of prognosis or outcome-related variables based on current personal health information associated with the target patient; and

assigning different optimized node addresses to the target patient based on the assigned attributes of the treatment-related variable and the prognosis or outcome-related variable; or alternatively

(d) Wherein in the event that the predetermined treatment plan information associated with the temporary node address of the target patient changes before a treatment decision has been made or before an optimized node address has been assigned to the target patient, the computing system is further configured to provide current predetermined treatment plan information to the healthcare provider of the target patient; or alternatively

(e) Wherein the computing system is further configured to provide an alert to a healthcare provider of the target patient that the predetermined treatment plan information associated with the temporary node address assigned to the target patient has changed; or alternatively

(f) Wherein the computing system is further configured to generate the temporary node address based on the assigned attributes of the set of therapy-related variables prior to assigning the temporary node address to the target patient; or

(g) Wherein the computing system is further configured to generate the optimized node address based on the assigned therapy-related variable and the assigned prognosis or outcome-related variable prior to assigning the optimized node address to the target patient; or

(h) Wherein the computing system is further configured to:

assigning the target patient to a prognosis or outcome based group based on the optimized node address assigned to the target patient;

measuring behavioral differences for each of a plurality of medical care providers assigned to a plurality of patients of the prognosis or outcome based group; and

identifying a lack of necessary care and/or providing unnecessary care that causes a difference in measured behavior of at least one of the medical care providers.

19. The system of claim 18, wherein the user interface directs the user to input at least the minimum subset of therapy-related variables.

20. The system of claim 17, wherein the computing system is further configured to:

presenting a user interface for inputting data in the first data set to the patient and/or a healthcare provider of the patient;

receiving information about the type of cancer of the target patient and the treatment intent of the target patient; and

after determining the minimum subset of the therapy-related variables based on the received information regarding the cancer type of the target patient and the therapy intent of the target patient, inputting a remaining portion of the minimum subset of the therapy-related variables via the user interface guide.

21. The system of claim 16, wherein the prognosis related expected outcome for the target patient is determined from a statistical analysis of prior prognosis related outcomes for patients in a prognosis or outcome based patient group that are each assigned to the same optimized node address as the optimized node address assigned to the target patient at a point of treatment and disease progression corresponding to the target patient.

22. The system of claim 21, wherein the first and second sensors are arranged in a single unit,

(a) wherein the computing system is further configured to perform a statistical analysis on the previous outcomes of patients in the prognosis or outcome based patient group to determine a current expected prognosis-related outcome for the target patient; or

(b) Wherein the computing system is further configured to perform an updated statistical analysis of the previous outcomes of patients in the prognosis or outcome based patient group to determine an updated current expected prognosis related outcome and to store information about the updated current expected prognosis related outcome; or

(c) Wherein the computing system is further configured to:

transmitting information regarding the prognosis-related expected outcome to a client device associated with the patient's healthcare provider or the target patient's healthcare payer; or

(d) Wherein the computing system is further configured to access information regarding billing costs for treatment of the target patient and determine a total cost of treatment for the target patient over a clinically relevant period; and

comparing an expected cost of treatment of the target patient over a clinically relevant period to the total cost of treatment of the target patient over the clinically relevant period; or

(e) Wherein the computing system is further configured to:

comparing one or more outcomes of the target patient to one or more historical outcomes of patients in the prognosis-or outcome-based group to determine whether the one or more outcomes of the target patient are trending away from criteria of the prognosis-or outcome-based group, the patients each being assigned an optimized node address that is the same as the optimized node address assigned to the target patient at the time of diagnosis or progression.

23. The system of claim 22, wherein the current expected prognosis-related outcome is a time to progress from the beginning of second-line therapy to the beginning of third-line therapy, and wherein the patients in the prognosis-or outcome-based patient group are patients that are each assigned the same optimized node address at the beginning of second-line therapy as the optimized node address assigned to the target patient at the beginning of second-line therapy.

24. The system of claim 22, wherein the computing system is configured to periodically perform the updated statistical analysis.

25. The system of claim 21, wherein the first and second sensors are arranged in a single unit,

wherein the computing system is further configured to:

(a) accessing information about the outcome of the target patient;

comparing the outcome of the target patient with the determined prognosis-related expected outcome of the target patient; and

transmitting information regarding the comparison to a healthcare provider of the patient or a healthcare payer of the target patient; or

(b) Determining an expected treatment cost for the target patient with respect to the disease during a clinically relevant period based on treatment costs assigned to all patients in a prognosis-or outcome-based patient group, the patients each being assigned to the same optimized node address as the optimized node address assigned to the target patient at a point of treatment and disease progression corresponding to the target patient.

26. The system of claim 25, wherein the optimized node address assigned to the target patient has an associated expected treatment cost for the disease from diagnosis to death or cure determined by statistical analysis of previous treatment costs for the patients in the prognosis or outcome based patient group from diagnosis to death or cure, each assigned the same optimized node address as assigned to the target patient at diagnosis.

27. The system of claim 22, wherein the clinically relevant period is from diagnosis to death or cure.

28. The system of claim 22, wherein the computing system is further configured to:

determining whether one or more outcomes of the target patient are trending away from the criteria of the prognosis-based or outcome group, and in the event that it is determined that the one or more outcomes of the target patient are trending away from the criteria, sending an alert to a healthcare provider or healthcare payer of the target patient, the alert including information about the one or more outcomes that are trending away from the criteria.

29. The system of claim 22, wherein the computing system is further configured to determine whether the total cost of treatment for the target patient over the clinically relevant period exceeds the expected cost of treatment for the target patient over the clinically relevant period by a threshold amount, and to send an alert to a healthcare provider or healthcare payer of the target patient if the total cost of treatment exceeds the expected cost of treatment.

30. The system of claim 16, wherein the first and second sensors are arranged in a single unit,

(a) wherein the second data set comprises data indicative of the progression of the disease after the first time point or after the first time period; or alternatively

(b) Wherein the first data set includes information about a first diagnosis and the second data set includes information about an updated diagnosis subsequent to the first diagnosis; or alternatively

(c) Wherein the second data set comprises information about attributes that provide no information or incomplete information in the first data set; or

(d) Wherein the prognostic-related expected outcome with respect to the occurrence of a defined endpoint event includes one or more of overall survival, progression-free survival or disease-free survival.

31. A non-transitory computer readable medium comprising program instructions for facilitating early treatment decisions and determining prognosis-related expected outcomes for target patients diagnosed with disease with respect to the occurrence of defined endpoint events, wherein execution of the program instructions by one or more processors causes the one or more processors to perform the method of claim 1.