[go: up one dir, main page]

WO2025015221A1 - Plateforme interactive d'aide à la prise de décision médicale - Google Patents

Plateforme interactive d'aide à la prise de décision médicale Download PDF

Info

Publication number
WO2025015221A1
WO2025015221A1 PCT/US2024/037677 US2024037677W WO2025015221A1 WO 2025015221 A1 WO2025015221 A1 WO 2025015221A1 US 2024037677 W US2024037677 W US 2024037677W WO 2025015221 A1 WO2025015221 A1 WO 2025015221A1
Authority
WO
WIPO (PCT)
Prior art keywords
patient
treatment
cure
data
probability
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/US2024/037677
Other languages
English (en)
Inventor
Radek BUKOWSKI
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Publication of WO2025015221A1 publication Critical patent/WO2025015221A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders

Definitions

  • various embodiments of this invention relate to an interactive platform for assisting with medical decision-making and, specifically, to an interactive platform that enables improved decision-making with respect to healthcare decisions such as diagnostic tests to use and treatment options.
  • At least some embodiments of the present invention are directed to a platform, system, method, and/or technique for making and/or suggesting improved healthcare-related decisions in the face of the inherent uncertainty accompanying such decisions. While this application will describe the invention with reference to certain exemplary types of decision making, e.g., which diagnostic test to use and/or rely on, which treatment course to pursue, and which clinical trial data to rely on, the invention is broader than any one category of decision making and, in general, the techniques described herein can be used and are contemplated for any appropriate type of decision-making (within and outside of the medical field).
  • the technique and/or method as disclosed in accordance with at least one embodiment of the present invention improves decision-making by integrating decision-making elements, including an interactivity with its components, and individualizing decision-making.
  • the system, method and/or technique described herein integrates different decisionmaking components in diagnostics and therapeutics (e.g., the accuracy of the test, and prevalence and/or risk of disease in diagnostics or treatment effect, harm, and their respective strengths of preference and aversion in therapeutics) into the cumulative probability of the disease or net benefit of the treatment, respectively.
  • the interactivity allows gaining an understanding of the relationship between the preferences and aversions for the treatment benefits and harms and the net benefit of the treatment or between the preferences and aversions for the potential test results before the test was taken on the cumulative probability of the disease.
  • the understanding of those relationships results in better decision-making.
  • Individualizing diagnostic and therapeutic decisions results in better decision-making because many patients do not benefit from particular tests or treatments, and individual preferences and aversions vary broadly.
  • the platform of the present invention allows combining those individual probabilities with personal preferences.
  • a good decision is not necessarily one that results in a good outcome, but rather, one that results in the highest probability of a good outcome.
  • a good decision can be the selection of a test (or tests) that have the highest probability of accurate results (e.g., true positive results and true negative results).
  • a good decision can be the treatment course that has the highest probability of cure and the lowest probability of harm.
  • FIG. 1 is a schematic network diagram of the system for assisting with medical decision-making as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 2A is a block diagram of an exemplary computing system used to implement at least one embodiment of the present invention as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 2B is another block diagram of an exemplary computing system used to implement at least one embodiment of the present invention as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 2C is yet another block diagram of an exemplary computing system used to implement at least one embodiment of the present invention as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 3A is a high-level flow chart illustrating the method as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 3B is a high-level flow chart illustrating the method for generating a synthetic dataset or digital twin as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 3C is a high-level flow chart illustrating a method of determining or estimating an outcome based upon a generated synthetic dataset, as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 4A shows an exemplary user interface to input information into the system and method for use by the diagnostic module as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 4B is an exemplary user interface showing an output of the diagnostics module as described in accordance with at least one embodiment.
  • FIG. 5A shows another exemplary user interface to input information into the system and method for use by the diagnostic module as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 5B is another exemplary user interface showing an output of the diagnostics module as described in accordance with at least one embodiment.
  • FIG. 7 is an exemplary user interface showing an output of the treatment module and a net benefit value for each of the treatment options, using the inputs from FIG. 6, as described in accordance with at least one embodiment.
  • FIG. 8 is an exemplary user interface showing the output from FIG. 7 demonstrating the uncertainty of each of the net benefits, in a different format.
  • FIG 9 shows another exemplary user interface to input information into the system and method for use by the treatment module as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 10 is an exemplary user interface showing an output of the treatment module and a net benefit value for each of the treatment options, using the inputs from FIG. 9, as described in accordance with at least one embodiment.
  • FIG. 11 is an exemplary user interface showing the output from FIG. 10 demonstrating the uncertainty of each of the net benefits, in a different format.
  • FIG. 12 shows an example user interface presented by the digital twin module as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 13 A shows an example output of the digital twin module using the information from FIG. 12.
  • FIG. 13B shows another example output of the digital twin module using the information from FIG. 12 and demonstrating the uncertainty of each of the net benefits.
  • FIG. 14A shows an example output of the digital twin module using different input information.
  • FIG. 14B shows another example output of the digital twin module using the same information as FIG. 14A and demonstrating the uncertainty of each of the net benefits.
  • FIG. 15A shows yet another example output of the digital twin module using different input information.
  • FIG. 15B shows another example output of the digital twin module using the same information as FIG. 15A and demonstrating the uncertainty of each of the net benefits.
  • FIG. 16A shows a comparison of original and synthetic data of median age data as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 16B shows a comparison of original and synthetic data of BMI data as disclosed in accordance with at least one embodiment of the present invention.
  • FIG. 17A shows outcomes in an original study and a simulated study, as described in accordance with at least one embodiment of the present invention.
  • FIG. 17B illustrates outcomes in an original study and a simulation of a future study before it was performed, as described in accordance with at least one embodiment of the present invention.
  • FIG. 17C illustrates a set of simulated synthetic individuals with the characteristics identical to the hypothetical patient being counseled about her outcomes (age 28, BMI 26, 1 prior preterm birth, etc.) - her digital twins, as described in accordance with at least one embodiment of the present invention.
  • FIG. 17D illustrates a stratification of a simulated population based on an individual for each simulated synthetic individual treatment effect into three groups of patients characteristics, as described in accordance with at least one embodiment of the present invention.
  • the present invention is directed to a platform, system 10, method 100, and/or technique for making and/or suggesting improved healthcare-related decisions in the face of the inherent uncertainty accompanying such decisions.
  • Uncertainty derived from global uncertainty of probabilities of disease, accuracy of tests or effectiveness of interventions, as well as individual differences among people in those probabilities and in preferences and aversion to the results of those tests and treatments.
  • the system 10 and/or method of the various embodiments features an interactive platform with multiple modules, e.g., a diagnostic module 40 and a treatment module 50, that, enabled with computational and processing power, facilitates improved decision-making.
  • the term “platform” generally refers to any system that enables a user to input certain information and receive an output.
  • the platform can feature an application executed on any computing device or terminal 20, 30, including but in no way limited to a mobile device, mobile phone, smartphone, tablet, wearable device, laptop computer, desktop computer, etc.
  • the platform can present one or more graphical user interfaces (GUIs) that enable interaction with a user. More information about the operating apparatus and operating environment of the platform is described below.
  • GUIs graphical user interfaces
  • FIG. 1 shows an exemplary schematic diagram of the system 10 as disclosed in at least one embodiment of the present invention, which may include one or more remote management systems 20, disposed in a communicative relation with one or more user devices 30 via network 15.
  • the network 15, as used herein, may include virtually any computer, communication or data network such as the World Wide Web, Internet, Intranet, local area network (LAN), Wide AreaNetwork(s), metro area network (MAN), Telecommunication Network(s) (e.g., 3G, 4G, 5G, LTE), cellular or wired networks, similar networks and any combination(s) thereof, etc.
  • the communication modes or protocols may include, for example, such as GSM voice calls, SMS, EMS, or MMS messaging, CDMA, TDMA, PDC, WCDMA, CDMA2000, or GPRS, among others.
  • the management system 20 as disclosed in connection with certain embodiments of the present invention is structured and/or configured to manage, store and process account or patient information (e.g., usernames, passwords, account information, contacts, etc.), facilitate the storage and analysis of patient data, patient test results, clinical or other information, etc.
  • account or patient information e.g., usernames, passwords, account information, contacts, etc.
  • the management system 20 of at least one embodiment of the present invention may include at least one web or cloud-based computer or server, desktop computer, laptop computer, tablet, mobile or handheld computer, etc. capable of facilitating implementation of the present invention disclosed herein.
  • the management system 20 may include one or more databases or other like storage components, implemented in hardware and/or software to store data and facilitate implementation of at least one embodiment of the present invention in the intended manner.
  • the various embodiments of the remote management system 20 and the user devices 30 of at least one embodiment each includes at least one or all of the following components, among other components and devices structured to facilitate implementation of the present invention in the intended manner: a computer processor or processing circuitry, memory, one or more data storage devices, and one or more communication or network device(s) or interface(s).
  • the corresponding processor or processing circuitry may be coupled to the corresponding memory, storage device and network interface to facilitate implementation of the present invention in the intended manner.
  • the computing devices including the user device 30 and/or remote management system 20 includes a processor 32a, memory 32b, an input/output device such as a display 32c, and a communication interface 32d, among other components, such as a transceiver 32e.
  • the device 30 may also be provided with a storage device 32f, such as a micro-drive or other device, to provide additional storage.
  • a storage device 32f such as a micro-drive or other device, to provide additional storage.
  • Each of the components 32a-f are interconnected using various buses, and several of the components may be mounted on a common motherboard or in other manners as appropriate.
  • the processor 32a or processing circuitry may be realized as one or more hardware logic components or circuits, such as, without limitation, one or more types of components that may include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-a-chip systems (SOCs), general purpose microprocessors, microcontrollers, digital signal processors (DSPs), or other like hardware components that can execute or implement computer instructions, software, etc., including, for example, the various features and components as described in accordance with at least one embodiment of the present invention and configured to implement or facilitate the implementation of the method 100 herein.
  • the processor 32a can execute instructions within the computing device 20, 30, including instructions stored in the memory 32b.
  • the processor 32a may be implemented as a chipset of chips that include separate and multiple analog and digital processors.
  • the processor may provide, for example, for coordination of the other components of the device 20, 30, such as control of user interfaces, applications run by device 20, 30, and wireless communication by device 20, 30.
  • the processor 32a may communicate with a user through control interface 34a and display interface 34b coupled to a display 32c.
  • the display 32c may be, for example, a TFT LCD (Thin-Film-Transistor Liquid Crystal Display) or an OLED (Organic Light Emitting Diode) display, or other appropriate display technology.
  • the display interface 34b may comprise appropriate circuitry for driving the display 32c to present graphical and other information to a user.
  • the control interface 34a may receive commands from a user and convert them for submission to the processor 32a.
  • an external interface 34c may be provided in communication with processor 32a, so as to enable near area communication of device 20, 30 with other devices.
  • External interface 34c may provide, for example, for wired communication in some implementations, or for wireless communication in other implementations, and multiple interfaces may also be used.
  • the memory 32b stores information within the computing device 20, 30.
  • the memory 32b can be implemented as one or more of a computer-readable medium or media, a volatile memory unit or units, or a non-volatile memory unit or units.
  • a computer-readable medium or media such as random access memory (RAM), read-only memory (ROM, flash memory, etc., or other like device(s) configured to implement the present invention in the intended manner, for example, by storing and assisting with the execution of one or more applications, modules, or components capable of implementing the system 10 and method 100 described herein.
  • RAM random access memory
  • ROM read-only memory
  • flash memory etc.
  • non- transitory computer readable media includes all computer-readable media except for a transitory, propagating signal.
  • Expansion memory 34d may also be provided and connected to device 20, 30 through expansion interface 34e, which may include, for example, a SIMM (Single In Line Memory Module) card interface.
  • SIMM Single In Line Memory Module
  • expansion memory 34d may provide extra storage space for device 20, 30, or may also store applications or other information for device 20, 30.
  • expansion memory 34d may include instructions to carry out or supplement the processes described above, and may include secure information also.
  • expansion memory 34d may be provided as a security module for device 20, 30, and may be programmed with instructions that permit secure use of device 20, 30.
  • secure applications may be provided via the SIMM cards, along with additional information, such as placing identifying information on the SIMM card in a non-hackable manner.
  • the memory may include, for example, flash memory and/or NVRAM memory, as discussed below.
  • a computer program product is tangibly embodied in an information carrier.
  • the computer program product contains instructions that, when executed, perform one or more methods, such as those described herein.
  • the information carrier is a computer- or machine-readable medium, such as the memory 32b, expansion memory 34d, memory on processor 32a, or a propagated signal that may be received, for example, over transceiver 32e or external interface 34e.
  • Device 20, 30 may communicate wirelessly through communication interface 32d, which may include digital signal processing circuitry where necessary.
  • Communication interface 32d may in some cases be a cellular modem. Such communication may occur, for example, through radio-frequency transceiver 32e.
  • short-range communication may occur, such as using a Bluetooth, WiFi, or other such transceiver (not shown).
  • GPS Global Positioning System
  • GPS receiver module 34f may provide additional navigation- and location-related wireless data to device 20, 30, which may be used as appropriate by applications running on device 20, 30.
  • Device 20, 30 may also communicate audibly using audio codec 34g, which may receive spoken information from a user and convert it to usable digital information. Audio codec 34g may likewise generate audible sound for a user, such as through a speaker, e.g., in a handset of device 20, 30. Such sound may include sound from voice telephone calls, may include recorded sound (e.g., voice messages, music files, etc.) and may also include sound generated by applications operating on device 20, 30.
  • Audio codec 34g may receive spoken information from a user and convert it to usable digital information. Audio codec 34g may likewise generate audible sound for a user, such as through a speaker, e.g., in a handset of device 20, 30. Such sound may include sound from voice telephone calls, may include recorded sound (e.g., voice messages, music files, etc.) and may also include sound generated by applications operating on device 20, 30.
  • system 10 and method 100 of the various embodiments described herein can be implemented in various architectures and arrangements of components, FIG. 1 being one example of such architecture and arrangement.
  • a remote management system or device 20 some or all of the modules described herein, such as a diagnostic module 40, treatment module 50, and /or digital twin module 70 may reside on or be executed by the remote management system 20, with outputs and results therefrom communicated to the user devices 30, as schematically represented in FIG. 2B.
  • FIG. 2B In other embodiments, for example, as represented in FIG.
  • the user device(s) 30 may operate and/or implement certain embodiments of the present invention independent of a remote management system such that at least one or all of the components, including the diagnostic module 40, treatment module 50, and/or digital twin module 70, may reside on or be executed by the user device 30.
  • the interactive platform, system 10 and/or method 100 described herein can include a diagnostic module, generally referenced as 40 in FIGs. 2A and 2B, that assists users, e.g., patients, healthcare professionals, industry, and policy makers to make diagnostic decisions.
  • the diagnostics module 40 can facilitate realtime decision making, as the module 40 can be used with information available at the time of decision-making.
  • the platform, system 10 or method 100 can use as an input the prior probability of a disease (or complications from the disease). Such prior probability can be estimated from the prevalence (e.g., frequency) of the disease in a given population of patients and/or from the results of previous observations and/or tests (e.g., signs (patient experiences, e.g., pain, cough, bleeding, etc.), symptoms (patient examination findings, e.g., tenderness, warmness, distention, etc.), lab tests and/or imaging (e.g., blood counts, iron levels, CT scan results, etc.))
  • the platform, system 10 or method 100 can also use as an input a Bayesian factor, which can be different depending on if the test result was positive or negative.
  • the Bayesian factor is the ratio of the test's sensitivity over the test’s false positive rate (1-specificity). If the test is negative, the Bayesian factor is the ratio of the test’s false negative rate (1 -sensitivity) over the test’s specificity.
  • the platform, system 10 or method 100 can use as an input the posterior probability of the disease after prior tests.
  • the posterior probability in Bayesian statistics, is the revised or updated probability of an event occurring after taking into consideration new material or new information, for example, symptoms or not of prior test results.
  • the posterior probability value can be characterized by two measures: (1) maximum a posteriori (MAP) (which is a central tendency) and the high-density interval between 2.5 and 97.5 percentile (95% HDI), or a measure of uncertainty and (2) relative risk (ratio of MAP to prior) or how many times the patient is more (relative risk greater than 1) or less (relative risk less than 1) likely to have the disease than an average person (defined by the prior).
  • MAP maximum a posteriori
  • HDI high-density interval between 2.5 and 97.5 percentile
  • relative risk ratio of MAP to prior
  • test accuracy measures, sensitivity and specificity, as well as prevalence (probability in the group of patients) of the disease can be derived from: (1) clinical studies and/or reports of average test’s sensitivity, specificity, and prevalence of the disease, including information obtained using Artificial Intelligence (Al); (2) average sensitivity, specificity of a test and prevalence of the disease derived from a study which participants are similar to, digital twins of, (for definition and methodology please see below) particular patient or group of patients; (3) individual for a particular patient sensitivity and specificity, and probability of the disease derived from clinical studies data using:
  • the user can input any of or any combination of the following: (1) the test’s sensitivity and specificity into the platform and (2) whether or not the results of the test were positive, negative or not performed.
  • the sensitivity and specificity of a test may be already known by the system 10 or method 100, such that the user may not need to input that information each time.
  • the platform can generate an output representing any one or more of or any combination of the following: (1) the prior probability of the disease before any test was performed, (2) the probability of the disease (e.g., the posterior probability of the disease accounting for prior probability, and any previous test results), (3) the relative risk of the disease (e.g., a ratio of the probability of disease to the prior probability of disease) - this measure can demonstrate how many times the risk of disease increased or decreased as a result of the test results, (4) the probability of the disease which, according to clinical guidelines, should trigger some sort of treatment or intervention.
  • the probability of the disease e.g., the posterior probability of the disease accounting for prior probability, and any previous test results
  • the relative risk of the disease e.g., a ratio of the probability of disease to the prior probability of disease
  • the platform can also allow objective evaluation of medical care and the decision- making process at the time care was given and with the information available at the time the decision was made. Such an approach may be useful, for example, in medical malpractice legal proceedings.
  • FIGs. 4A and 4B show example user interfaces 42, 46, respectively, presented by the diagnostics module 40.
  • FIG. 4A is a user interface 42, e.g., accessible on user device 30, in which a user can input information about one or more diagnostic tests (Test 1, Test 2, Test 3, Test 4), as represented at 44a-44d, being considered.
  • the input may be provided by a user on user device through several sliders (as shown in FIG. 4A) to select or input the various reference points or data.
  • Other input modules or device, including dropdown lists, text inputs, etc. can also be implemented instead of or in addition to the sliders shown.
  • FIG. 4B is an example user interface 46, e.g., accessible on user device 30, illustrating an output chart showing the cumulative probability of the disease based on the results of each of the diagnostic tests (Test 1, Test 2, Test 3, Test 4) represented in FIG. 4A.
  • FIGs. 5A and 5B show another example according to another embodiment with different tests, represented as 44e-44i, being evaluated.
  • FIGs 4A and 4B are examples of the counterintuitive high rate of true positive and low rate of false positive test results of a positive test in patients at high risk of the disease as a consequence of prior tests results or prevalence of the disease.
  • FIGs. 5A and 5B demonstrate counterintuitive relatively low rate of true negatives and high rate of false negatives of a negative test in patients at high risk of the disease due to prior tests results or prevalence of the disease.
  • the interactive platform e.g., the system 10 and method 100, described herein can include a treatment module 50 that assists users, e.g., patients, healthcare professionals, industry, policy makers, and others to make treatment decisions (e.g., which course of treatment to pursue). In some instances, this can be achieved by synthesizing the probabilities of treatment outcomes and patient preferences into a single number and by allowing a better understanding of the interplay between the probabilities and preferences interactively.
  • a treatment module 50 that assists users, e.g., patients, healthcare professionals, industry, policy makers, and others to make treatment decisions (e.g., which course of treatment to pursue). In some instances, this can be achieved by synthesizing the probabilities of treatment outcomes and patient preferences into a single number and by allowing a better understanding of the interplay between the probabilities and preferences interactively.
  • the platform incorporates the concept that a decision about a treatment choice depends on the probability of a cure and the probability of treatment-related harm.
  • Such values can be obtained from outside or third- party materials, literature or sources, generally referenced as 60 in FIG. 1 for example, and the platform, system 10, and method 100 of at least one embodiment of the present invention can be pre-programmed with such information and/or can have access (e.g., through a web searching or SaaS platform) to such data.
  • the platform can largely categorize outcomes of various treatment options into four quadrants / outcomes: Cure, No Cure, Cure and Harm, and No Cure and Harm.
  • Each treatment typically differs in probabilities of cure and harm, thus in probabilities of the potential outcomes.
  • the platform incorporates the concept that a personally optimal decision depends on the importance or weight an individual person assigns to the probability of cure (e.g., preference for cure) and probability of harm (aversion for cure with harm and aversion for no cure and harm).
  • the platform 10, 100 can synthesize or integrate the probabilities and preferences into a net benefit. While many examples are available, in some embodiments, the platform can add together the following values: (1) probability of cure x preference for the cure, (2) probability of cure with harm x aversion to this outcome, (3) probability of no cure with harm x aversion to this outcome, to calculate a normalized net benefit of the approach.
  • the platform is programmed and configured to synthesize the probabilities of cure and harm and personal preferences for each possible outcome, treatment or intervention into a single value of the net benefit.
  • the platform can also express the level of uncertainty in the net benefit prediction using known statistical techniques, e.g., a Monte Carlo simulation.
  • the method of at least one embodiment includes interacting with the treatment module 60 through a user interface by providing various probabilities and preferences.
  • the user can input any one or more of or any combination of the following: (1) for each treatment Tl, T2, T3, the probability that the treatment Tl, T2, T3 will result in a cure (e.g., based on available data sources) 62al, 62a2, 62a3, (2) for each treatment Tl, T2, T2, the probability that the treatment Tl, T2, T3 will cause the patient harm (e.g., based on available data sources) 62b 1, 62b2, 62b3, (3) patient’s preference for a cure (e.g., on some normalized scale, e.g., 0-100) 62c, (4) patient’s aversion for cure with
  • any normalized scale can be used to indicate preferences for a cure 62c, aversion to a cure with harm 62d and aversion to a cure with no harm 62e. This can be manually input by the user using techniques such as a slide bar (as shown in FIG. 6), an input field, etc.
  • the system 10 and/or method 100 of the present invention can synthesize or generate an output, which in some embodiments is a single number, character or reference representing a net benefit 65, for example, as shown in FIGs. 7 and 8.
  • the platform, system 10, and/or method 100 can output any one or more of or any combination of the following: (1) a net benefit 65 of a particular course of treatment (e.g., on some normalized scale), and in some instances a probability distribution (e.g., using statistical techniques, such as a Monte Carlo simulation) and (2) size of overlap between distributions of net benefits of multiple compared treatment options.
  • the probabilities of cure and harm can be derived from (1) clinical studies and/or reports of average treatment effect and harm, including information obtained using Al; (2) average treatment effect and harm derived from a study which participants are similar to, are digital twins of, (for definition and methodology, please see below) of particular patient or group of patients; (3) Individual treatment effect or harm derived from clinical studies data using:
  • the data modification is done using various over- and under-sampling techniques and the creation of synthetic data;
  • (3C) estimating individual treatment effect or harm for each person, estimating the probability of an outcome, e.g., disease if a given person would or would not have received the treatment (factual and counterfactual, depending what actually happened in the study) — then applying to a particular patient treatment effect and harm of a patient in the study with identical characteristics.
  • the latter is aided in small studies by creating synthetic data, as described in 3 A.
  • (3D) synthetic data generated using computer simulation, for example, agent based modeling, Bayesian networks, etc. Such data can be generated in unlimited size and with random variation based on the aggregate characteristics of people or patients in the target population, research study, etc.
  • Each synthetic individual in such a simulated data has an individual set of characteristics and a number of combination matches the target population.
  • the subset of those simulated individuals with identical or near identical characteristics to the counseled patient constitute that counseled patient’s digital twins and their outcomes in the simulated data of the probability of the outcome - probability of cure and harm combinations, in the particular counseled patient.
  • the 3B and 3C are achieved with different causal discovery and inference techniques and machine learning methods.
  • a patient can be faced with a choice of three different treatments Tl, T2, T3, which have a chance of cure of 50%, 60%, and 70%, respectively, and a probability of treatment-related harm of 0%, 10%, and 20%, respectively.
  • the optimal treatment with the best net benefit might be any one of the first, second, or third treatments Tl, T2, T3, depending on the personal importance attached to the chance of getting cured and the aversion to treatment-related harm.
  • the platform 10, 100 of at least one embodiment can determine that the treatment course with the best net benefit for this individual is treatment T3.
  • the platform 10, 100 can determine that the treatment course with the best net benefit is treatment Tl .
  • other combinations of preferences and aversions may result in treatment T2 having the best net benefit and being the personally optimal treatment.
  • optimal treatment with the best net benefit is monitoring.
  • optimal treatment with the best net benefit is radiation therapy.
  • the personally optimal treatment can be surgery.
  • the interactive platform 10, 100 of at least one embodiment can enable a person to better interact with the probabilities and preferences, gaining a good sense of their interrelationship, aiding in personally optimal decisions, and facilitating recommended shared- decision making with the care provider.
  • FIG. 6 is an example user interface 62 that can be presented by the treatment module 60 in which a user can input information related to a treatment option being considered.
  • FIG. 7 is an example user interface output, showing a net benefit 65 for each of the treatment options Tl, T2, T3, that can be generated by the treatment module 60 comparing different treatment options Tl, T2, T3.
  • FIG. 8 displays the data from FIG. 7, including the net benefits 65, in a different format and showing uncertainty surrounding net benefits 65 of considered treatments and the overlaps of uncertainty of treatment choices.
  • FIGS. 9, 10, and 11 show user interfaces 62 of the treatment module 60 using a different example of treatment option considerations.
  • the platform, system 10, and/or method 100 can be used for policy or implementation strategy decisions.
  • the uncertainty measures, such as confidence or credible intervals, of the individual treatment effect in therapeutics or cumulative probability of the disease in diagnostics can be used to stratify the population into groups benefiting, uncertain, or harmed by an intervention. Such stratification can inform a better policy or strategy regarding diagnostic tests or therapeutic interventions.
  • the interactive platform 10, 100 described herein can include a digital twin module 70 that assists patients and healthcare professionals to determine which clinical trial data should be relied upon.
  • the decision of which clinical trial data to rely upon can be used as a parameter of data relied upon by the diagnostic module 40 and/or the treatment module 50.
  • the digital twin module 70 of at least one embodiment of the present invention is programmed to identify a study which included patients most similar to the current patient, thus increasing the likelihood that the findings reported in this study would be applicable to the given patient.
  • the platform 10, 100 can generate a synthetic dataset by extracting certain parameters (e.g., but not limited to, race, ethnicity, age, sex, and BMI corresponding to a given study), which, for example, can be done using a study means and covariance matrix using multivariate normal distribution and a random sample generator.
  • the clinical studies can also be simulated using techniques such as agent based modeling or Bayesian networks.
  • the covariance matrix is derived from the publicly available national data, such as CDC (Centers for Disease Control and Prevention), HCUPS (Healthcare Cost and Utilization Project), National Vital Statistics, Census data, etc. In other cases, private datasets can be used.
  • the synthetic data is validated by comparing the distribution of race, ethnicity, age, sex, and BMI in the synthetic and original study.
  • an aggregated / normalized value or vector can be generated, e.g., reflecting the selected parameters (e.g., race, ethnicity, age, sex, and BMI) or such a set of frequencies used to generate synthetic simulated data with individuals with the same distribution of characteristics as the target population from which the aggregated data was derived. .
  • a set of values can be generated for such patient based on their patient parameters (e.g., but not limited to, race, ethnicity, age, sex, and BMI or body mass index), as generally shown at 122 in FIG. 3B.
  • patient parameters e.g., but not limited to, race, ethnicity, age, sex, and BMI or body mass index
  • a distance measure is generated between the vectors describing patients in the studies and the patient to be counseled.
  • the platform, system 10 and/or method 100 can then identify 126 a certain number of patients (e.g., 1, 2, 3, 5, 10, 15, 20, 50, 100, etc.) that are most similar to the patient being counseled. Such similar patients are referred to herein as digital neighbors.
  • the mode of the digital neighbors is considered to be the patient’s digital twin.
  • the study in which most of the digital neighbors participated (referred to herein as the digital twin study), thus with the patients most similar to the patient being counseled, is determined to be the most applicable to the patient being counseled 128.
  • the proportion of different studies among the ten most similar patients can be an indicator of the accuracy of the digital twin study.
  • the synthetic data can be generated 130 using computer simulation, for example, agent-based modeling, Bayesian networks, etc. Such data can be generated in unlimited size and with random variation based on the aggregate characteristics of people or patients in the target population, research study, etc. Each synthetic individual in such a simulated data has an individual set of characteristics and number of combinations matches the target population. The subset of those simulated individuals with identical characteristics to the counseled patient constitute that patient’s digital twins and their outcomes in the simulated data the probability of the outcome for the counseled patient.
  • the synthetic dataset can be generated by a causal model using e.g., Bayesian network and the digital neighbors and twin identified using causal inference and explored using counterfactuals.
  • a large number of simulated patients may be generated from aggregate data of an original, published or publicly available dataset or study 130a.
  • the method of generating the synthetic dataset 120 of at least one embodiment may include identifying, among the generated synthetic dataset(s) and/or among the original studies, patients with characteristics (e.g., sex, age, BMI, etc.) that are identical to those characteristics of the patient being counseled 130b, and identify those patients as “digital twins.” Then, using the digital twins identified in the synthetic dataset, determining an outcome of the treatment or test to determine a probability of the test results, effectiveness of treatment or probability of treatment- related harm for the patient being counseled. 130c
  • the study results can be the inputs used in the diagnostic module 40 and/or treatment module 50, e.g., the probability of cure or harm that can be used in the treatment module 50 and/or the sensitivity and specificity of diagnostic or prognostic tests that can be used in the diagnostic module 40.
  • the digital twin module 70 is simply used in the background to improve outcomes from the diagnostic and/or treatment module(s) 40, 50 and not actively used by the patient. In other instances, the patient or clinician can independently interact with the digital twin module 70.
  • the user can input any one or more of or any combination of the following:
  • parameters of interest of each clinical study to be relied upon e.g., but not limited to, proportion of females and males, proportion of patients identifying as Black, White, Asian, Hispanic, or Other, mean BMI of patients, mean age of patients, number of events (outcomes of interest) among treated, exposed, or having a disease patients, depending on the study design (randomized, clinical trial, observational study), number of treated, exposed, or having a disease patients, depending on the study design (randomized, clinical trial, observational study), number of events (outcomes of interest) among control, unexposed, or not having a disease patients, depending on the study design (randomized, clinical trial, observational study), and/or number of control, unexposed, or not having a disease patients, depending on the study design (randomized, clinical trial, observational study), (2) parameters of the patient being counseled (e.g., but not limited to, sex, race and ethnicity, age, BMI, etc.)
  • the platform can output:
  • digital twin accuracy e.g., proportion of studies among the ten digital neighbors. For example, if all digital neighbors were from the same study, then the accuracy of the digital twin study is very accurate (e.g., 100%); if 2 of 10 digital neighbors participated in each of Studies 1, 2, 3, 4, and 5, then the accuracy of the digital twin study is comparatively lower (e.g., 20%), although the digital twin can still be identified as the ones with the highest similarity to the patient being counseled,
  • type of treatment e.g., dosage, route of administration, etc.
  • type of test being used in the study
  • the digital twin participated and thus most applicable to the patient being counseled, and/or (6 probability of cure or harm of a treatment, or sensitivity, specificity, positive and negative predictive values of a test, their median, and distribution based on statistical methods (e.g., Monte Carlo simulation among treated and controls).
  • the percent of overlap of distributions e.g., for treated and controls, can demonstrate the uncertainty of the difference between the two groups.
  • the platform can evaluate the probability of the disease if the test is positive (posttest probability or positive predictive value) and the probability of no disease if the test is negative (posttest probability or negative predictive value).
  • the module was used to compare 6 studies of two progesterone administrations intramuscular injection of 17OH Progesterone and vaginal progesterone for preventing preterm birth.
  • the digital twin will be predominantly (40% of digital neighbors) in study 1.
  • Study 1 from 2003 showed great benefit, was terminated prematurely as it was considered unethical for patients in the study to receive placebo.
  • the digital twin is in study 4, which used vaginal progesterone preparation.
  • the study shows the probability of desired term birth among controls and treated of 82 and 84 %, only a 2% difference with substantial overlap and uncertainty, of the estimates of cure of 38%.
  • the digital twin is in study 6, which uses vaginal progesterone in a different dosage than study 4. The accuracy is 30% for study 6 and study 2, but the patients from study 6 were more similar.
  • Study 6 shows the probability of term birth among controls and treated of 81 and 84 %, only a 3% difference with a moderate overlap, uncertainty, of the estimates of cure of 18%.
  • the differences in age and BMI also influence the identity of the digital twin, as is in other examples the patient's sex and other characteristics.
  • the computing device or user device 30 includes or utilizes a machine learning model or other predictive tool for determining the optimal diagnostic, treatment, or digital twin.
  • a machine learning model can be trained using a set of training data.
  • the training data can be or include, for example, historical data from previous patient outcomes or clinical studies.
  • the machine learning model can be trained to recognize how to optimize, maximize, or minimize one or more of the target features based on a given set of input parameters. Once trained, the machine learning model can receive the input parameters as input, generate an optimized outcome, and provide the optimized outcome and an output.
  • FIG. 12 shows an example user interface 72 presented by the digital twin module 70 for collecting input information for use by the module 70.
  • the inputs 74 can include, but are not limited to sex, race and ethnicity, age, BMI, etc.
  • the inputs are entered through a sliding bar, however, other manners to input data are contemplated.
  • FIGS. 13A-13B show an example output 75a of the digital twin module 70 identifying digital twin information 75b and charts indicating the probability of a cure when using the course of treatment identified in a study within which the digital twin participated.
  • FIGS. 14A-14B and 15A-15B show similar outputs 75a, 75b for different examples.
  • FIGS. 16A and 16B shows outputs 76, 77 of a comparison of original and synthetic data of median age and BMI data.
  • the computing device or user device uses, as inputs, simulated synthetic data of studies or populations based on their publicly-available aggregate characteristics (which can include, but are not limited to sex, race and ethnicity, age, BMI, etc.) Since simulated data can be of unlimited size and can include simulated individual with any possible combinations of characteristics, a large number of digital twins (simulated individuals with the identical or near identical characteristics to the counseled patient(s)) can be identified and provided as inputs to the diagnostic or treatment modules.
  • aggregate characteristics which can include, but are not limited to sex, race and ethnicity, age, BMI, etc.
  • FIG. 17A illustrates outcomes (e.g., duration of pregnancy) in an original study and a simulated study.
  • the original study includes the control group - GAD-ori-TO 82a and treatment group - GAD-ori-Tl 82b.
  • the simulated study is based on the publicly-available aggregate data of patient characteristics (e.g., age, race, BMI, rate of preterm birth, etc.) (control group - GAD-sim-TO 84a and treatment group GAD-sim-Tl 84b) showing nearly identical results.
  • FIG. 17B illustrates outcomes (e.g., duration of pregnancy) in an original study and a simulation of a future study before it was performed - if a simulated study was performed in a similar population with the knowledge of the actual study population.
  • the original study (control group GAD-ori-TO 83a and treatment group GAD-ori-Tl 83b) and in simulated synthetic data based on the publicly-available aggregate characteristics of a population (e.g., age, race, BMI, rate of preterm birth, etc.) (control group GAD-sim-TO 85a and treatment group GAD-sim-Tl 85b) showing nearly identical results.
  • FIG. 17C illustrates a set 90 of simulated synthetic individuals with the characteristics identical to the hypothetic patient being counseled about her outcomes (age 28, BMI 26, 1 prior preterm birth, etc.) - her digital twins.
  • the individual treatment effect (ITE) is the effect of treatment in the simulated data of the digital twins.
  • Complementary are the probabilities of the digital twin’s outcome “with treatment predict,” “without treatment predict,” median ITE, and its confidence interval limits upper and lower “ite ib” and “ite ub.”
  • FIG. 17D illustrates a stratification 95 of a simulated population based on an individual for each simulated synthetic individual treatment effect into three groups of patients’ characteristics which are associated with a benefit (improvement of outcome of treatment), uncertain benefit, and harm (worsening of outcome with treatment.)
  • Implementations of the subject matter and the operations described in this specification can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them.
  • Implementations of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions, encoded on computer storage medium for execution by, or to control the operation of, data processing apparatus.
  • the program instructions can be encoded on an artificially generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode information for transmission to suitable receiver apparatus for execution by a data processing apparatus.
  • a computer storage medium can be, or be included in, a computer- readable storage device, a computer-readable storage substrate, a random or serial access memory array or device, or a combination of one or more of them. Moreover, while a computer storage medium is not a propagated signal, a computer storage medium can be a source or destination of computer program instructions encoded in an artificially generated propagated signal. The computer storage medium can also be, or be included in, one or more separate physical components or media (e.g., multiple CDs, disks, or other storage devices).
  • the operations described in this specification can be implemented as operations performed by a data processing apparatus on data stored on one or more computer-readable storage devices or received from other sources.
  • the term “data processing apparatus” encompasses all kinds of apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, a system on a chip, or multiple ones, or combinations, of the foregoing.
  • the apparatus can include special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).
  • the apparatus can also include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, a cross-platform runtime environment, a virtual machine, or a combination of one or more of them.
  • the apparatus and execution environment can realize various different computing model infrastructures, such as web services, distributed computing and grid computing infrastructures.
  • a computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment.
  • a computer program may, but need not, correspond to a file in a file system.
  • a program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language resource), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code).
  • a computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.
  • the processes and logic flows described in this specification can be performed by one or more programmable processors executing one or more computer programs to perform actions by operating on input data and generating output.
  • the processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).
  • processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer.
  • a processor will receive instructions and data from a read only memory or a random access memory or both.
  • the essential elements of a computer are a processor for performing actions in accordance with instructions and one or more memory devices for storing instructions and data.
  • a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks.
  • mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks.
  • a computer need not have such devices.
  • a computer can be embedded in another device, e.g., a mobile telephone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device (e.g., a universal serial bus (USB) flash drive), to name just a few.
  • Devices suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto optical disks; and CD ROM and DVD-ROM disks.
  • the processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.
  • implementations of the subject matter described in this specification can be implemented on a computer having a display device, e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, for displaying information to the user and a keyboard and a pointing device, e.g., a mouse or a trackball, by which the user can provide input to the computer.
  • a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • keyboard and a pointing device e.g., a mouse or a trackball
  • Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback, e.g., visual feedback, auditory feedback, or tactile feedback; and input from the user can be received in any form, including acoustic, speech, or tactile input.
  • a computer can interact with a user by sending resources to and receiving resources from a device that is used
  • Implementations of the subject matter described in this specification can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a client computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the subject matter described in this specification, or any combination of one or more such back end, middleware, or front end components.
  • the components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (“LAN”) and a wide area network (“WAN”), an internetwork (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks).
  • LAN local area network
  • WAN wide area network
  • Internet internetwork
  • peer-to-peer networks e.g.,
  • the computing system can include clients and servers.
  • a client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
  • a server transmits data (e.g., an HTML page) to a client device (e.g., for purposes of displaying data to and receiving user input from a user interacting with the client device). Data generated at the client device (e.g., a result of the user interaction) can be received from the client device at the server.
  • a system of one or more computers can be configured to perform particular operations or actions by virtue of having software, firmware, hardware, or a combination of them installed on the system that in operation causes or cause the system to perform the actions.
  • One or more computer programs can be configured to perform particular operations or actions by virtue of including instructions that, when executed by data processing apparatus, cause the apparatus to perform the actions.
  • each numerical value presented herein for example, in a table, a chart, or a graph, is contemplated to represent a minimum value or a maximum value in a range for a corresponding parameter. Accordingly, when added to the claims, the numerical value provides express support for claiming the range, which may lie above or below the numerical value, in accordance with the teachings herein. Absent inclusion in the claims, each numerical value presented herein is not to be considered limiting in any regard.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Urology & Nephrology (AREA)
  • Surgery (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

L'invention concerne une plateforme interactive, un système et un procédé d'aide à la prise de décision médicale. Le système et le procédé comprennent la réception de données de diagnostic, qui sont définies pour comprendre, pour chacun d'une pluralité de tests de diagnostic pour une maladie, une sensibilité de test, une spécificité de test et un résultat de test. À l'aide d'un module de diagnostic, une probabilité postérieure de la maladie est déterminée en fonction au moins d'une probabilité antérieure de la maladie et des données de diagnostic. Le système et le procédé comprennent en outre la réception de données de traitement, qui comprennent une préférence du patient pour un traitement, une aversion du patient pour un traitement sans dommage et une aversion du patient pour un traitement avec dommage. À l'aide des données de traitement, une sortie de bénéfice net est générée pour chacune d'une pluralité d'options de traitement, le bénéfice net étant utilisé pour fournir une assistance avec la prise de décision médicale. Pour des données plus précises et applicables, un ensemble de données synthétiques peut être généré.
PCT/US2024/037677 2023-07-12 2024-07-11 Plateforme interactive d'aide à la prise de décision médicale Pending WO2025015221A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US202363526289P 2023-07-12 2023-07-12
US63/526,289 2023-07-12
US202363542875P 2023-10-06 2023-10-06
US63/542,875 2023-10-06

Publications (1)

Publication Number Publication Date
WO2025015221A1 true WO2025015221A1 (fr) 2025-01-16

Family

ID=94216455

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2024/037677 Pending WO2025015221A1 (fr) 2023-07-12 2024-07-11 Plateforme interactive d'aide à la prise de décision médicale

Country Status (1)

Country Link
WO (1) WO2025015221A1 (fr)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2531333A (en) * 2013-10-18 2016-04-20 Soar Biodynamics Ltd Dynamic analysis and dynamic screening
JP7095001B2 (ja) * 2014-08-14 2022-07-04 メメド ダイアグノスティクス リミテッド 多様体および超平面を用いる生物学的データのコンピュータ分析

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2531333A (en) * 2013-10-18 2016-04-20 Soar Biodynamics Ltd Dynamic analysis and dynamic screening
JP7095001B2 (ja) * 2014-08-14 2022-07-04 メメド ダイアグノスティクス リミテッド 多様体および超平面を用いる生物学的データのコンピュータ分析

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
STAMULI EUGENA, CORRY SORCHA, FOSS PETTER: "Patient preferences do matter: a discrete choice experiment conducted with breast cancer patients in six European countries, with latent class analysis", INTERNATIONAL JOURNAL OF TECHNOLOGY ASSESSMENT IN HEALTH CARE, CAMBRIDGE UNIVERSITY PRESS, CAMBRIDGE, GB, vol. 39, no. 1, 1 January 2023 (2023-01-01), GB , XP093266878, ISSN: 0266-4623, DOI: 10.1017/S0266462323000168 *

Similar Documents

Publication Publication Date Title
Zammit et al. Individuals, schools, and neighborhood: a multilevel longitudinal study of variation in incidence of psychotic disorders
Vogenberg Predictive and prognostic models: implications for healthcare decision-making in a modern recession
US20250226093A1 (en) Predictive machine learning models for preeclampsia using artificial neural networks
US20200234826A1 (en) Providing personalized health care information and treatment recommendations
US10770180B1 (en) Processing clinical notes using recurrent neural networks
US20210192365A1 (en) Computer device, system, readable storage medium and medical data analysis method
Roffman et al. Development and validation of a multiparameterized artificial neural network for prostate cancer risk prediction and stratification
CN116205306A (zh) 一种数据处理方法及数据处理装置
WO2014151626A1 (fr) Classification électronique de variantes
WO2019183122A1 (fr) Plateforme d'intelligence artificielle et d'apprentissage automatique pour identifier des tests génétiques et génomiques
Mackintosh et al. Benefits of a virtual interstitial lung disease multidisciplinary meeting in the face of COVID‐19
Lee et al. Real-world data analysis on effectiveness of integrative therapies: a practical guide to study design and data analysis using healthcare databases
Gashu et al. Assessing survival time of outpatients with cervical cancer: at the university of Gondar referral hospital using the Bayesian approach
CN113220895A (zh) 基于强化学习的信息处理方法、装置、终端设备
Zimba et al. Provider preferences for delivery of HIV care coordination services: results from a discrete choice experiment
US11621081B1 (en) System for predicting patient health conditions
CN115620879A (zh) 医疗检查项目的智能推荐方法、装置、设备及存储介质
Kattan When and how to use informatics tools in caring for urologic patients
Sharma et al. An explainable artificial intelligence based prospective framework for COVID-19 risk prediction
WO2025015221A1 (fr) Plateforme interactive d'aide à la prise de décision médicale
US20250046409A1 (en) Systems and methods for phenotyping using large language model prompting
Devashish et al. Bayesian model inference: Exploring parsimonious models with MCMC and optimization approximations
EP3905255A1 (fr) Mappage d'un patient avec des essais cliniques pour l'aide à la décision clinique spécifique à un patient
US20230420073A1 (en) Machine learning models for determining pathogenic genetic variants
US20200075163A1 (en) Diagnostic decision support for patient management

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24840595

Country of ref document: EP

Kind code of ref document: A1