WO2024196685A1

WO2024196685A1 - Systems and methods for adaptive care pathways for complex health conditions

Info

Publication number: WO2024196685A1
Application number: PCT/US2024/019857
Authority: WO
Inventors: Love BEEJAL
Original assignee: Symita Inc
Current assignee: Symita Inc
Priority date: 2023-03-20
Filing date: 2024-03-14
Publication date: 2024-09-26
Anticipated expiration: 2025-09-20

Abstract

In an aspect, a method for providing a care pathway for a subject undergoing treatment for a complex health condition is disclosed. The method comprises (a) receiving, via a user interface (UI), a query comprising one or more search parameters associated with a subject. The method also comprises (b) retrieving, from a computer server, health data of said subject from an electronic health record (EHR), wherein said health data of said subject is associated with said complex health condition, wherein said health data of said subject is retrieved responsive to said query. The method also comprises (c) outputting a care pathway for said subject, wherein said care pathway provides a time sequence of health procedures associated with at least said complex health condition, wherein said time sequence is based at least in part on said health data of said subject.

Description

PATENT COOPERATION TREATY (PCT) PATENT APPLICATION

INVENTION TITLE: SYSTEMSAND METHODS FOR ADAPTIVE CARE PATHWAYS FOR COMPLEX HEALTH CONDITIONS

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of United States Provisional Patent Application 63/491,216 filed on March 20, 2023 and United States Non-Provisional Patent Application 18/296,342 filed on April 5, 2023, each of which are hereby incorporated by reference in their entirety.

BACKGROUND

[0002] Complex health conditions may require multiple health procedures. For example, pregnancy may require multiple visits to an obstetrician, lab tests, ultrasound exams, injections, and other procedures. Health care providers may make errors in scheduling and may also unintentionally cause variances in health care for patients with the same health condition. Each year, $540 billion in avoidable costs are incurred due to failure of care coordination, failure in the execution of care processes, and administrative complexity of pricing and billing. And the set of procedures performed may require fulfillment through a combination of different health care providers. As different health care providers may use different electronic health record (EHR) systems, patient health care data specific to managing a health condition may be distributed across many computing systems. Accurately exchanging data among these EHR systems may be difficult and prone to errors or delays.

[0003] Intentional variances in provided health care may arise from pre-existing or evolving secondary health conditions of a patient, such as diabetes, obesity, and hypertension. This can result in additional procedures (e.g., additional obstetrician (OB) visits), or modifications to procedures. Due to the lack of a systematic approach and a high dependency on manual human intervention to manage these variations, this process can also be prone to errors and lead to unintentional variances in health care.

SUMMARY

[0004] There is a need for a system to track and manage the schedule of health procedures for treating a complex health condition. Such a system may reduce or eliminate missed appointments and added stress among other consequences, increasing the likelihood of achieving a positive outcome.

[0005] Disclosed are systems and methods for managing and navigating complex health conditions that allow for repeatability and increased effectiveness through the configuration and management of sets of health procedures.

[0006] An aspect of the present disclosure provides a method for providing care to a subject having a health condition with a plurality of potential health outcomes comprising providing to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes, where the adaptive visualization of the subject's care pathway enables the health care provider to reduce a timeframe in which the subject is treated for the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization.

[0007] In some embodiments, the health condition is a physiological or mental condition.

[0008] In some embodiments, the plurality of potential health outcomes is a plurality of potential physiological or mental outcomes.

[0009] In some embodiments, the adaptive visualization is provided as a timeline. In some embodiments, the timeline is viewable via a continuous scroll. In some embodiments, the timeline comprises a time sequence of graphical elements, where a graphical element relates to a health procedure. In some embodiments, the timeline is customizable via adding, subtracting, or modifying content associated with one or more graphical elements of the time sequence of graphical elements.

[0010] In some embodiments, customizing the timeline comprises (i) computer processing health data from the subject; and (ii) automatically updating a graphical element, responsive to the computer processing.

[0011] In some embodiments, the computer processing is performed using a trained machine learning algorithm.

[0012] Another aspect of the present disclosure provides a method for providing care to a subject having a health condition with a plurality of potential health outcomes, comprising providing to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes, where the adaptive visualization of the subject's care pathway enables the health care provider to reduce a variation effect associated with care provided to the subject for treatment of the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization. [0013] In some embodiments, the variation effect relates to a demographic characteristic of the subject, a level of care coordination, an execution of a care process, or an administrative complexity of a pricing or billing procedure, or a level of fraud or abuse.

[0014] Another aspect of the present disclosure provides a method for providing a care pathway for a subject undergoing treatment for a complex health condition, comprising (a) receiving, via a user interface (UI), a query comprising one or more search parameters associated with a subject; (b) retrieving, from a computer server, health data of the subject from an electronic health record (EHR), where the health data of the subject is associated with the complex health condition, where the health data of the subject is retrieved responsive to the query; and (c) outputting a care pathway for the subject, where the care pathway provides a time sequence of health procedures associated with at least the complex health condition, where the time sequence is based at least in part on the health data of the subject.

[0015] In some embodiments, the UI is a graphical user interface (GUI).

[0016] In some embodiments, outputting the care pathway for the subject comprises displaying the care pathway in the GUI.

[0017] In some embodiments, the time sequence of health procedures comprises a plurality of graphical elements.

[0018] In some embodiments, the time sequence of health procedures is displayed as a timeline or graphical sequence. In some embodiments, the timeline or graphical sequence is horizontal or vertical. In some embodiments, the timeline or graphical sequence is entirely viewable by continuous scroll.

[0019] In some embodiments, the method further comprises (i) generating a plurality of online calendar objects corresponding to the time sequence; and (ii) assigning the plurality of online calendar objects to the subject.

[0020] In some embodiments, an online calendar object of the plurality of online calendar objects is markable or taggable as completed during care, to be completed, completed prior to generation of the care pathway, or missed.

[0021] In some embodiments, the method further comprises, responsive to receiving a selection of a second care pathway via the GUI, augmenting the time sequence of health procedures with a second time sequence of health procedures from the second care pathway. [0022] In some embodiments, the method further comprises, responsive to receiving a reassignment to a second care pathway via the GUI, (i) determining a plurality of performed health procedures in the second care pathway; (ii) removing a set of future events from the care pathway; and (iii) displaying the second care pathway with the plurality of performed health procedures removed.

[0023] In some embodiments, the reassignment is performed by (i) requesting health data from the server; (ii) processing the requested health data with a machine learning model; and (iii) selecting a second care pathway based on the processing.

[0024] In some embodiments, prior to (c) outputting the care path for the subject, the method further comprises (i) displaying the health data on the GUI; and (ii) receiving a selection of the care pathway, via the GUI.

[0025] In some embodiments, prior to (c) outputting the care pathway for the subject, the method further comprises (i) computer processing the health data; and (ii) selecting a care pathway based at least in part on the processing.

[0026] In some embodiments, the method further comprises (iii) outputting the care pathway on the GUI; (iv) receiving a signal comprising approval of or rejection of the care pathway; (v) if the signal comprises the rejection, displaying one or more alternative care pathways; and (vi) receiving a selection of the one or more alternative care pathways.

[0027] In some embodiments, the computer processing comprises using a trained machine learning model.

[0028] In some embodiments, the computer processing comprises using an image processing algorithm.

[0029] In some embodiments, the image processing algorithm comprises optical character recognition (OCR).

[0030] In some embodiments, the care pathway is editable via the GUI.

[0031] In some embodiments, the care pathway is generated by an authorized user.

[0032] In some embodiments, the authorized user is a health care provider or administrator.

[0033] In some embodiments, the health care provider is a physician, a member of a care team, a nurse, a nurse practitioner, or a physician assistant.

[0034] In some embodiments, editing the care pathway comprises adding or removing one or more health procedures.

[0035] In some embodiments, editing the care pathway comprises modifying text associated with a health procedure of the one or more health procedures.

[0036] In some embodiments, modifying the text is performed based at least in part on at least one of (1) demographic information of the subject, (2) medical history of the subject, (3) a biological sample of the subject, (4) a location of the subject, (5) insurance information of the subject, (6) a location, (7) a provider, or (8) a date associated with a health procedure. [0037] In some embodiments, the one or more search parameters comprise an identifier of the subject.

[0038] In some embodiments, the identifier is a medical record number (MRN) of the subject, a name of the subject, or a date of birth of the subject.

[0039] In some embodiments, prior to (b) retrieving, from the computer server, health data of the subject from the EHR, the method further comprises (i) retrieving, from a server, connection information associated with the EHR; and (ii) based at least in part on the connection information, directing the query to the HER.

[0040] In some embodiments, a placement of one or more health procedures of the time sequence is based at least in part on the health data of the subject. In some embodiments, the placement is a position within the time sequence. In some embodiments, the placement is inclusion inside the time sequence.

[0041] In some embodiments, in (b) retrieving, from the computer server, health data of the subject from the EHR, the health data is selected automatically.

[0042] In some embodiments, a health procedure of the time sequence of health procedures is associated with a reference target date. In some embodiments, the reference target date corresponds to a reference date or reference date range. In some embodiments, the reference date or reference date range relates to a temporal characteristic of the subject. In some embodiments, the temporal characteristic is gestational age. In some embodiments, the time sequence of health procedures comprises at least two health procedures.

[0043] In some embodiments, the care pathway is associated with at least one secondary health condition. In some embodiments, the secondary health condition has a detrimental effect on or complicates the complex health condition. In some embodiments, the secondary health condition is obesity, diabetes, or high cholesterol. In some embodiments, the secondary health condition is determined by processing the health data of the subject.

[0044] In some embodiments, the processing is performed using a trained machine learning algorithm.

[0045] In some embodiments, the secondary health condition is a complex health condition. In some embodiments, the complex health condition is a physical or physiological health condition. In some embodiments, the complex health condition is pregnancy, end of life status, debilitation due to stroke, debilitation due to an injury, care of a premature infant, multiple trauma, ventilator dependency, or an organ transplant. In some embodiments, the complex health condition comprises one or more diseases. In some embodiments, a disease of the one or more diseases is a chronic disease. In some embodiments, the chronic disease is a progressive neuromuscular deterioration disease. In some embodiments, the progressive neuromuscular deterioration disease is Parkinson's or amyotrophic lateral sclerosis (ALS).

[0046] In some embodiments, the injury is a spinal cord injury. In some embodiments, the injury is a wound. In some embodiments, the injury is a fracture.

[0047] In some embodiments, the treatment of the complex health condition exceeds three months in duration. In some embodiments, the treatment of the complex health condition exceeds six months in duration.

[0048] In some embodiments, the complex health condition is a mental or behavioral health condition.

[0049] In some embodiments, the mental or behavioral condition is addiction, depression, anxiety, a stress disorder, bipolar disorder, schizophrenia, or obsessive-compulsive disorder (OCD). In some embodiments, the addiction is drug addiction or substance abuse. In some embodiments, the stress disorder is post-traumatic stress disorder (PTSD).

[0050] In some embodiments, a health procedure of the time sequence of health procedure is placed in the time sequence based at least in part on an availability of a provider for the health procedure. In some embodiments, the availability is retrieved from an EHR system.

[0051] In some embodiments, the method further comprises periodically retrieving additional health data of the subject from the server.

[0052] In some embodiments, the method further comprises modifying the care pathway or generating a second care pathway based at least in part on the health data.

[0053] Another aspect of the present disclosure provides a method for providing care to a subject having a health condition with a plurality of potential health outcomes, comprising providing to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes, where the adaptive visualization of the subject's care pathway enables the health care provider to increase standardization of care provided to the subject for treatment of the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization. [0054] Another aspect of the present disclosure provides a system comprising one or more computer processors and computer memory coupled thereto. The computer memory comprises machine executable code that, upon execution by the one or more computer processors, implements any of the methods above or elsewhere herein.

[0055] Another aspect of the present disclosure provides a system for providing care to a subject having a health condition with a plurality of potential health outcomes, comprising one or more computer processors that are individually or collectively programmed to provide to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes, where the adaptive visualization of the subject's care pathway enables the health care provider to reduce a timeframe in which the subject is treated for the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization.

[0056] In some embodiments, the health condition is a physiological or mental condition. [0057] In some embodiments, the plurality of potential health outcomes is a plurality of potential physiological or mental outcomes.

[0058] In some embodiments, the adaptive visualization is provided as a timeline.

[0059] In some embodiments, the timeline is viewable via a continuous scroll.

[0060] In some embodiments, the timeline comprises a time sequence of graphical elements, where a graphical element relates to a health procedure.

[0061] In some embodiments, the timeline is customizable via adding, subtracting, or modifying content associated with one or more graphical elements of the time sequence of graphical elements.

[0062] In some embodiments, customizing the timeline comprises (i) computer processing health data from the subject; and (ii) automatically updating a graphical element, responsive to the computer processing.

[0063] In some embodiments, the computer processing is performed using a trained machine learning algorithm.

[0064] Another aspect of the present disclosure provides a system for providing care to a subject having a health condition with a plurality of potential health outcomes, comprising one or more computer processors that are individually or collectively programmed to provide to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes, where the adaptive visualization of the subject's care pathway enables the health care provider to reduce a variation effect associated with care provided to the subject for treatment of the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization.

[0065] In some embodiments, the variation effect relates to a demographic characteristic of the subject.

[0066] Another aspect of the present disclosure provides a system comprising (a) a computer server; and (b) a user interface (UI), where the UI is configured to (i) receive a query comprising one or more search parameters associated with a subject, (ii) display health data of the subject from the server responsive to the query, where the health data of the subject is associated with a complex health condition, and (iii) display a care pathway for the subject, where the care pathway provides a time sequence of health procedures associated with at least the complex health condition, where the time sequence is based at least in part on the health data of the subject.

[0067] In some embodiments, the UI is a graphical user interface (GUI). In some embodiments, the UI is further configured to display analysis of the health data of the subject. [0068] In some embodiments, the health data and analysis of the health data are viewable via continuous scroll.

[0069] In some embodiments, the analysis of the health data is provided as a chart or graph. [0070] In some embodiments, the data or the analysis of the health data is downloadable via the GUI. In some embodiments, the data or the analysis of the health data is downloadable via a tabular format.

[0071] In some embodiments, the GUI is further configured to display an artificial intelligence (Al) text chat session with a subject. In some embodiments, the GUI is further configured to enable a health care provider to end the Al text chat session and initiate a provider text chat with the subject.

[0072] In some embodiments, the GUI provides a visualization indicating that the Al text chat session has ended and the provider text chat session has begun.

[0073] In some embodiments, the provider is a physician, care coordinator, or a member of medical staff

[0074] In some embodiments, the text chat session is displayed in a separate window or tab from the care pathway or the health data.

[0075] In some embodiments, the GUI is further configured to display an informational content library.

[0076] In some embodiments, the informational content comprises a clinically validated article. In some embodiments, the article is accessible via Internet.

[0077] In some embodiments, the GUI is configured to enable a provider to send the informational content to the subject.

[0078] In some embodiments, the GUI is further configured to provide a list of action items, where the list of the action items is based at least in part on the health data or the care pathway. In some embodiments, the list of action items is displayed in a separate window or tab from the care pathway or the health data. In some embodiments, the list of action items is automatically generated by processing the health data. In some embodiments, an action item of the list of action items is displayed responsive to an alert setting provided to the GUI. In some embodiments, an action item of the list of action items relates to a status of a health procedure of the care pathway. In some embodiments, the status is complete, missed, or upcoming.

[0079] In some embodiments, the care pathway is viewable via a continuous scroll. [0080] In some embodiments, the care pathway is viewable as a timeline.

[0081] In some embodiments, the server comprises an electronic health record (EHR). [0082] Another aspect of the present disclosure provides a system for providing a care pathway for a subject undergoing treatment for a complex health condition, comprising one or more computer processors that are individually or collectively programmed to (a) receive, via a user interface (UI), a query comprising one or more search parameters associated with a subject; (b) retrieve, from a computer server, health data of the subject from an electronic health record (EHR), where the health data of the subject is associated with the complex health condition, where the health data of the subject is retrieved responsive to the query, optionally in association with a data integration and/or data ingestion module; and (c) output a care pathway for the subject, where the care pathway provides a time sequence of health procedures associated with at least the complex health condition, where the time sequence is based at least in part on the health data of the subject. In association with the data retrieval aspects associated with an EHR, embodiments of the system further comprise a data integration module. Such embodiments feature a comprehensive data integration interface designed to facilitate seamless communication with multiple Electronic Health Record (EHR) systems.

This interface serves as a conduit for the transfer of health data between the system and various EHR platforms, ensuring that healthcare providers have access to a unified view of patient information, regardless of the originating EHR system. The data integration interface employs standardized protocols and formats, such as Health Level Seven (HL7) and Fast Healthcare Interoperability Resources (FHIR), to enable interoperability and real-time data exchange. The integration interface is equipped with customizable connectors that can be configured to match the data structures and communication methods used by different EHR vendors. This flexibility allows the system to adapt to the unique requirements of each EHR system, including proprietary data formats and authentication mechanisms. By providing a standardized method for EHR integration, the system ensures that patient data is accurate, complete, and up-to-date, which is essential for the generation of effective care pathways. Complementing the data integration interface is a robust data ingestion module that is responsible for interfacing with a variety of health data generation devices and services. This module is designed to capture and process data from diverse sources, including wearable health monitors, diagnostic imaging equipment, laboratory information systems, and patient self-reporting tools. The data ingestion module supports a wide range of data types, from structured electronic medical records to unstructured clinical notes and real-time biometric readings. The module includes a set of adaptable interfaces that can connect to different devices and services, ensuring that data is ingested in a consistent and reliable manner. It is capable of handling various data transmission methods, such as direct device connections, cloud-based data streams, and batch file uploads. The data ingestion module not only collects data but also normalizes it, transforming disparate data points into a standardized format suitable for analysis and integration into the care pathways. The combination of the data integration interface and the data ingestion module provides the system with a comprehensive capability to aggregate and harmonize health data from multiple sources. Examples of the data ingestion module and data integration module are described in United States Patent Application 18/296,342 filed on April 5, 2023, which is hereby incorporated by reference in its entirety with claim of priority thereto, where the integration with Electronic Health Record (EHR) systems is described as an essential feature for enabling the visualization of subject data and care pathways within a healthcare provider application, and reference is made to the server's API layer functions and cloud services. Additionally, the system's data ingestion functionality, which is critical for storing data related to generating subject care pathways, is supported by a robust server infrastructure equipped with an application programming interface layer and cloud services. This integration is vital for creating a holistic view of patient health, which supports the delivery of personalized and adaptive care pathways. By ensuring that all relevant health data is incorporated into the care pathway decision-making process, the system enhances the quality of care and supports better health outcomes for patients.

[0083] Another aspect of the present disclosure provides a system for providing care to a subject having a health condition with a plurality of potential health outcomes, comprising one or more computer processors that are individually or collectively programmed to provide to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes, where the adaptive visualization of the subject's care pathway enables the health care provider to increase standardization associated with care provided to the subject for treatment of the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization. [0084] Another aspect of the present disclosure provides a non-transitory computer readable medium comprising machine executable code that, upon execution by one or more computer processors, implements any of the methods above or elsewhere herein.

[0085] Another aspect of the present disclosure provides a non-transitory computer-readable medium comprising machine-executable code that, upon execution by one or more computer processors, implements a method for providing a care pathway for a subject undergoing treatment for a complex health condition, the method comprising (a) receiving, via a user interface (UI), a query comprising one or more search parameters associated with a subject; (b) retrieving, from a computer server, health data of the subject from an electronic health record (EHR), where the health data of the subject is associated with the complex health condition, where the health data of the subject is retrieved responsive to the query; and (c) outputting a care pathway for the subject, where the care pathway provides a time sequence of health procedures associated with at least the complex health condition, where the time sequence is based at least in part on the health data of the subject.

[0086] Additional aspects and advantages of the present disclosure will become readily apparent to those skilled in this art from the following detailed description, wherein only illustrative embodiments of the present disclosure are shown and described. As will be realized, the present disclosure is capable of other and different embodiments, and its several details are capable of modifications in various obvious respects, all without departing from the disclosure. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.

INCORPORATION BY REFERENCE

[0087] All publications, patents, and patent applications mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent, or patent application was specifically and individually indicated to be incorporated by reference. To the extent publications and patents or patent applications incorporated by reference contradict the disclosure contained in the specification, the specification is intended to supersede and/or take precedence over any such contradictory material.

BRIEF DESCRIPTION OF THE DRAWINGS

[0088] The novel features of the invention are set forth with particularity in the appended claims. Abetter understanding of the features and advantages of the present invention will be obtained by reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the invention are utilized, and the accompanying drawings (also "Figure" and "FIG." herein), of which:

[0089] FIG. 1 illustrates a networked system for arranging graphical elements on a graphical user interface (GUI) of a computer system, in accordance with some embodiments;

[0090] FIG. 2 shows a computer system that is programmed or otherwise configured to implement methods provided herein;

[0091] FIGs. 3 A and 3B illustrate screenshots from a GUI of a user device displaying information associated with a patient's pregnancy, in accordance with some embodiments; [0092] FIG. 4 schematically illustrates an example normal pregnancy care pathway generated by the system, in accordance with some embodiments;

[0093] FIG. 5 illustrates an example obesity care pathway for a pregnant patient with obesity, in accordance with some embodiments;

[0094] FIG. 6 illustrates an example diabetes care pathway for a pregnant patient with diabetes, in accordance with some embodiments;

[0095] FIG. 7 illustrates another example pregnancy care pathway, in accordance with some embodiments;

[0096] FIG. 8 illustrates a GUI of a health care provider's dashboard displaying information associated with the health care provider's tasks and list of patients, in accordance with some embodiments;

[0097] FIG. 9 illustrates a GUI of a health care provider's dashboard displaying information associated with a patient, in accordance with some embodiments;

[0098] FIG. 10 illustrates a GUI of a health care provider's dashboard displaying medical information associated with one patient, in accordance with some embodiments;

[0099] FIG. 11 illustrates a patient education dashboard, which may be displayed in one or both of the patient device application and health care provider device application, in accordance with some embodiments;

[0100] FIG. 12 illustrates a process, in accordance with some embodiments;

[0101JFIG. 13 schematically illustrates management of patients on care pathways, and results of updating a patient's care pathway, in accordance with some embodiments;

[0102] FIG. 14 schematically illustrates a system architecture diagram, in accordance with some embodiments; and

[0103] FIG. 15 schematically illustrates an exemplary interaction diagram of a health care provider and patient with a software-based system assigning care pathways to the patient which are viewable and/or editable by the health care provider, in accordance with some embodiments.

DETAILED DESCRIPTION

[0104] While various embodiments of the invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Numerous variations, changes, and substitutions may occur to those skilled in the art without departing from the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed.

[0105] Whenever the term "at least," "greater than," or "greater than or equal to" precedes the first numerical value in a series of two or more numerical values, the term "at least," "greater than" or "greater than or equal to" applies to each of the numerical values in that series of numerical values. For example, greater than or equal to 1, 2, or 3 is equivalent to greater than or equal to 1, greater than or equal to 2, or greater than or equal to 3.

[0106] Whenever the term "no more than," "less than," or "less than or equal to" precedes the first numerical value in a series of two or more numerical values, the term "no more than," "less than," or "less than or equal to" applies to each of the numerical values in that series of numerical values. For example, less than or equal to 3, 2, or 1 is equivalent to less than or equal to 3, less than or equal to 2, or less than or equal to 1.

[0107] The terms "subject" and "patient" are used interchangeably herein.

Overview

[0108] Managing care of a complex health condition may require scheduling and/or prescribing many interrelated health procedures, including checkups, examinations, collections of biological samples, screenings, questionnaires, classes, treatments, surgeries, courses of medication, and/or other procedures. Patient care may be performed by individual health care providers, who may persist variations in care due to their differences in procedure from other individual health care providers. These variations may manifest at a population level as disparities and inequities in health care. For example, women who live in rural America, where there are maternal care deserts, may be about 60 percent more likely to die during pregnancy, as those in urban areas. And Black mothers may be three times more likely to die during pregnancy than mothers of other races.

[0109] Disclosed is an intelligent digital health platform that generates personalized care pathways for patients with complex health conditions that reduces or eliminates such variations in care. The disclosed system can adapt a treatment plan based on a patient's changing needs, while implementing a standardized approach on patients with similar needs. The disclosed system also may give health care providers easy access to patients' health data, may automate data exchange, integrate with electronic health record (EHRs) systems, and may facilitate effective communication of health information to patients.

[0110] The disclosed system may provide a care pathway for a patient that may include all stakeholders and staff involved with the patient's care. For example, a pregnancy care pathway may commence by showing a patient an obstetrician (OB) visit and proceed with showing all pregnancy- related health procedures assigned to the patient over the nine-month pregnancy period, including consultations (e.g., a dietitian consultation), education assignments, questionnaires, classes, mental health assessments, and immunizations, and ending with a first pediatric visit. The care pathway may be presented to the patient and/or to a health care provider in a GUI showing the health procedures as events on a timeline, which may be reviewable by continuously scrolling on a mobile device or in a browser window. Embodiments of the present invention is equipped with a dynamic care pathway updating mechanism that ensures the care pathways remain responsive to the real-time health data of the subject. This mechanism is underpinned by a robust technological framework that includes continuous health data monitoring, predictive analytics, and an agile system architecture capable of processing and responding to data changes instantaneously. Real-time health data monitoring is achieved through a network of connected devices and sensors that continuously feed health data into the system. This data is then processed by the system's backend, which employs a distributed computing architecture to manage the data streams efficiently. The architecture is designed to scale dynamically, handling varying loads of incoming data without compromising system performance. Predictive analytics play a crucial role in the dynamic updating of care pathways. The system utilizes algorithms and machine learning models to analyze the incoming health data for patterns, trends, and deviations from expected health trajectories. These analyses inform the system's predictive models, which can forecast potential health events or outcomes, enabling proactive adjustments to the care pathways. When changes in health data are detected, the system responds by initiating an update process. This process involves re-evaluating the current care pathway in light of the new data and applying decision-making algorithms to determine the necessary modifications. The updated care pathway is then automatically reflected in the user interface, providing healthcare providers and patients with the latest treatment plan. The system ensures that these updates are communicated clearly, with changes to the care pathway visualized in an intuitive and accessible manner. The dynamic care pathway generation aspects disclosed herein further comprise an updating mechanism leads to personalized and adaptive healthcare solutions. By leveraging real-time data and predictive analytics, the system ensures that each subject's care pathway is always aligned with their current and projected health needs. The preferred embodiment leverages a distributed computing architecture to manage the complex health data associated with the care pathways. This architecture is designed to distribute the computational workload across multiple servers or nodes, enabling the system to handle large volumes of health data with high efficiency and reliability. By utilizing distributed computing, the system can process vast amounts of data in parallel, significantly reducing latency and improving response times for real-time health data monitoring and care pathway updates. In conjunction with distributed computing, the system employs big data technologies to store, manage, and analyze the health data. These technologies include scalable storage solutions, such as NoSQL databases, which are optimized for the rapid retrieval and handling of large, unstructured datasets. Embodiments of the system also utilize powerful data processing frameworks like Apache Hadoop and Apache Spark, which provide the necessary infrastructure for executing complex data analytics tasks, including predictive modeling and machine learning algorithms. The benefits of integrating distributed computing with big data technologies are manifold in the context of embodiments of the invention. The system gains the ability to scale resources elastically in response to fluctuating data processing demands. It can accommodate the addition of new health data sources and the integration of new healthcare providers into the network without compromising performance. Furthermore, the use of big data technologies enables the system to perform advanced analytics, such as real-time pattern recognition and anomaly detection, which are crucial for the dynamic updating of care pathways. The combination of distributed computing and big data technologies ensures that the system can deliver personalized and adaptive healthcare solutions. It allows for the efficient management of health data from diverse sources, including electronic health records (EHRs), wearable devices, and patient-reported outcomes. Such architecture supports the system's goal of providing healthcare providers and patients with accurate, up-to-date, and actionable health information, thereby facilitating informed decision-making and improving patient outcomes. [OHl] The system may be integrated with an electronic health record (EHR) system, such as CERNER® or EPIC®. The system may facilitate bidirectional exchange of health data with the EHR system, eliminating redundancy, duplicate data entry, and/or missed information. The system may provide to health care providers a dashboard showing relevant data and analytics for the complex health condition. For example, a dashboard for a pregnant patient may immediately show a health care provider a patient's last menstrual period (LMP) or gestational age. Showing the most relevant information up front, rather than requiring a set of navigations to multiple different pages, may reduce administrative overhead. The analytics may monitor and map patient health status and vitals remotely and enable health care providers to view up- to-date information related to mental health, blood pressure (e.g., monitoring hypertension), or blood glucose monitoring (e.g., for diabetes), among other health statistics. The dashboard may also enable viewing of health documents or ultrasounds. Health data may be downloaded by a health care provider in a tabular format.

[0112] The system may adapt to patients who enter care at an advanced stage of the complex health condition. For example, if a mother comes into care at 20 weeks of gestational age, the system may assess which procedures she has already undergone and not schedule them for her. And the system may catch her up on any missed procedures.

[0113] The system may also adapt to transition care for patients who are diagnosed with secondary conditions during care. For example, midway during care, a pregnant patient may receive test results indicating diabetes. The care pathway may automatically adapt to accommodate the diabetes, modifying the remaining health procedures in the care pathway. [0114] The system may also include an artificial intelligence (Al) care coach that may be able to answer patient health questions autonomously. The care coach may be trained on clinically curated and validated content to answer the health questions. The care coach may also include built-in intelligence to escalate to a human health care provider, if necessary. Escalation may be shown in a chat window graphically and via controls. The Al care coach may be able to effectively triage a patient while not overburdening human staff

[0115] The system may provide a content library, enabling health care providers and patients to view and share educational content that has been clinically validated and curated.

[0116] Additionally, health care providers may be able to set up automatic alerts and action items using the patient health information. This may be performed manually by a health care provider. This may also be performed automatically, e.g., by scanning patient health data using an algorithm.

Description

[0117] Disclosed is a method for providing care to a subject having a health condition with a plurality of potential health outcomes. The method may comprise providing to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes. The adaptive visualization of the subject's care pathway may enable the health care provider to reduce a timeframe in which the subject may be treated for the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization.

[0118] The health condition may be a physiological or mental condition. The plurality of potential health outcomes may be a plurality of potential physiological or mental outcomes. The adaptive visualization may be provided as a timeline. The timeline may be viewable via a continuous scroll. The timeline may comprise a time sequence of graphical elements. A graphical element may relate to a health procedure. The timeline may be customizable via adding, subtracting, or modifying content associated with one or more graphical elements of the time sequence of graphical elements. Customizing the timeline may comprise (i) computer processing health data from the subject; and (ii) automatically updating a graphical element, responsive to the computer processing. The computer processing may be performed using a trained machine learning algorithm.

[0119] Disclosed is a system for providing care to a subject having a health condition with a plurality of potential health outcomes. The system may comprise one or more computer processors that are individually or collectively programmed to provide to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes. The adaptive visualization of the subject's care pathway may enable the health care provider to reduce a timeframe in which the subject may be treated for the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization. Aspects of the user interface (UI) comprise advanced adaptive visualization capabilities that enhance the user experience for both healthcare providers and patients. The UI dynamically presents care pathways with a high degree of interactivity, allowing users to visualize complex health data and treatment plans in an intuitive and accessible manner. The adaptive visualization is designed to respond to changes in real-time health data, automatically adjusting the display to reflect updates to the care pathway or shifts in patient health status. The visualization capabilities of the UI include interactive timelines, graphical representations of health procedures, and customizable views that cater to the specific needs of each user. For instance, healthcare providers can zoom in on critical aspects of a care pathway or expand the timeline to view long-term treatment plans, while patients can access simplified overviews that highlight key milestones and upcoming appointments. Complementing the adaptive visualization features is a sophisticated machine learning module that forms the core of the system's predictive analytics. This module comprises a suite of neural networks, including convolutional neural networks (CNNs) for pattern recognition within structured health data, and recurrent neural networks (RNNs) with long short-term memory (LSTM) units for analyzing temporal sequences indicative of a patient's health progression over time. The CNNs within the machine learning module are adept at processing and interpreting image data, such as diagnostic scans, to identify patterns that are critical for diagnosis and treatment planning. The RNNs with LSTM units are particularly effective in handling sequential data, such as patient vitals over time, allowing the system to predict future health events and suggest modifications to the care pathway accordingly. The machine learning module is trained on diverse datasets that encompass a wide range of health conditions and patient scenarios. Through continuous learning and validation against new health data, the module's algorithms are refined to improve their predictive performance. This ongoing training process ensures that the system remains at the forefront of medical technology, providing accurate and actionable insights that support the delivery of personalized patient care. The integration of adaptive visualization with machine learning analytics enables the system to present not only the current state of a patient's health but also to forecast potential future states. This predictive visualization aids healthcare providers in making informed decisions and allows patients to understand the potential trajectory of their health condition, fostering a proactive approach to healthcare management. [0120] The health condition may be a physiological or mental condition. The plurality of potential health outcomes may be a plurality of potential physiological or mental outcomes. The adaptive visualization may be provided as a timeline. The timeline may be viewable via a continuous scroll. The timeline may comprise a time sequence of graphical elements. A graphical element may relate to a health procedure. The timeline may be customizable via adding, subtracting, or modifying content associated with one or more graphical elements of the time sequence of graphical elements. Customizing the timeline may comprise (i) computer processing health data from the subject; and (ii) automatically updating a graphical element, responsive to the computer processing. The computer processing may be performed using a trained machine learning algorithm.

[0121] Disclosed is a method for providing care to a subject having a health condition with a plurality of potential health outcomes. The method may comprise providing to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes. The adaptive visualization of the subject's care pathway may enable the health care provider to reduce a variation effect associated with care provided to the subject for treatment of the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization. [0122] The health condition may be a physiological or mental condition. The plurality of potential health outcomes may be a plurality of potential physiological or mental outcomes. The adaptive visualization may be provided as a timeline. The timeline may be viewable via a continuous scroll. The timeline may comprise a time sequence of graphical elements. A graphical element may relate to a health procedure. The timeline may be customizable via adding, subtracting, or modifying content associated with one or more graphical elements of the time sequence of graphical elements. Customizing the timeline may comprise (i) computer processing health data from the subject; and (ii) automatically updating a graphical element, responsive to the computer processing. The computer processing may be performed using a trained machine learning algorithm. The variation effect may relate to a demographic characteristic of the subject, a level of care coordination, an execution of a care process, or an administrative complexity of a pricing or billing procedure, or a level of fraud or abuse.

[0123] Disclosed is a system for providing care to a subject having a health condition with a plurality of potential health outcomes. The system may comprise one or more computer processors that are individually or collectively programmed to provide to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes. The adaptive visualization of the subject's care pathway may enable the health care provider to reduce a variation effect associated with care provided to the subject for treatment of the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization.

[0124] The health condition may be a physiological or mental condition. The plurality of potential health outcomes may be a plurality of potential physiological or mental outcomes. The adaptive visualization may be provided as a timeline. The timeline may be viewable via a continuous scroll. The timeline may comprise a time sequence of graphical elements. A graphical element may relate to a health procedure. The timeline may be customizable via adding, subtracting, or modifying content associated with one or more graphical elements of the time sequence of graphical elements. Customizing the timeline may comprise (i) computer processing health data from the subject; and (ii) automatically updating a graphical element, responsive to the computer processing. The computer processing may be performed using a trained machine learning algorithm. The variation effect may relate to a demographic characteristic of the subject, a level of care coordination, an execution of a care process, or an administrative complexity of a pricing or billing procedure, or a level of fraud or abuse.

[0125] Disclosed is a method for providing a care pathway for a subject undergoing treatment for a complex health condition. The method may comprise (a) receiving, via a user interface (UI), a query comprising one or more search parameters associated with a subject, (b) retrieving, from a computer server, health data of the subject from an electronic health record (EHR) system. The health data of the subject may be associated with the complex health condition. The health data of the subject may be retrieved responsive to the query. The method may also comprise (c) outputting a care pathway for the subject. The care pathway may provide a time sequence of health procedures associated with at least the complex health condition. The time sequence may be based at least in part on the health data of the subject. [0126] The health data may comprise biographical or demographic information. The health data may comprise medical history or family medical history. The health data may comprise insurance information. The health data may comprise information collected from biological samples or from medical observation of the patient.

[0127] The time sequence of health procedures may extend a plurality of weeks, months, or years. The time sequence of health procedures may comprise a journey through a plurality of touch points or landmarks of the complex health condition. For example, a pregnancy care pathway may begin at a first obstetrician visit and end with a first pediatric visit.

[0128] The UI may be a graphical user interface (GUI). Outputting the care pathway for the subject may comprise displaying the care pathway in the GUI. The care pathway may comprise audio, video, text, or a combination thereof. For example, the care pathway may be displayed as an electronic report or a visualization.

[0129] The time sequence of health procedures may comprise a plurality of graphical elements. The graphical elements may be arranged in a temporal order, (e.g., earliest to latest in time or latest to earliest in time).

[0130] The time sequence of health procedures may be displayed as a timeline or graphical sequence. The timeline or graphical sequence may be displayed horizontally or vertically on a screen of a computing device. The timeline or graphical sequence may be entirely viewable by continuously scrolling on a single electronic page. In some cases, the timeline may be displayed on multiple pages.

[0131] The method may further comprise (i) generating a plurality of online calendar objects corresponding to the time sequence; and (ii) assigning the plurality of online calendar objects to the subject. The online calendar objects may comprise, for example, a date, a duration, a time, and/or description of a health procedure (e.g., an office visit, a scan, a treatment, or collection of a biological sample). Assignment of the plurality of online calendar objects to the subject may be performed automatically. For example, after the care pathway is generated, the online calendar objects may be automatically exported to a subject's (e.g., a patient's) online calendar, such as APPLE® iCal, GOOGLE® Calendar, or MICROSOFT® OUTLOOK calendar. An online calendar object of the plurality of online calendar objects may be markable or taggable as completed during care, to be completed, completed prior to generation of the care pathway, scheduled, unscheduled, or missed.

[0132] The method may further comprise, responsive to receiving a selection of a second care pathway via the GUI, augmenting the time sequence of health procedures with a second time sequence of health procedures from the second care pathway. Augmenting the time sequence of health procedures may comprise adding one or more health procedures of the second care pathway to the time sequence of health procedures.

[0133] The method may further comprise, additionally or alternatively, reassigning the subject to a second care pathway. Reassignment may comprise replacing all future health procedures of the currently assigned care pathway with one or more health procedures of the second care pathway. For example, health procedures of the second care pathway that overlap with those already completed from the original care pathway may not be included. The reassignment may be performed by (i) determining a plurality of performed health procedures in said second care pathway; (ii) removing a set of future events from said care pathway; and (iii) displaying said second care pathway with said plurality of performed health procedures removed.

[0134] The method may also comprise, prior to (c); (i) displaying the subject's health data on the GUI; and (ii) receiving a selection of the care pathway, via the GUI. The selection may be performed by a health care provider. The selection may be performed automatically, based at least in part on one or more predefined rules implemented by, e.g., a health care provider, health care staff, or health care administration.

[0135] The method may also comprise, prior to (c), (i) computer processing the subject's health data; and (ii) selecting a care pathway based at least in part on the processing.

[0136] The method may also comprise (iii) outputting the care pathway on the GUI; (iv) receiving a signal comprising approval of or rejection of the care pathway; (v) if the signal comprises the rejection, displaying one or more alternative care pathways; and (vi) receiving a selection of the one or more alternative care pathways. This may be performed if a health care provider (e.g., a physician) wishes to override an algorithmic or rules-based selection of a care pathway. The health care provider may be presented with a graphical window including a selection of alternate care pathways to choose from. For example, if a health care provider believes the system incorrectly applied a diabetes care pathway, the health care provider may instead select a normal care pathway. [0137] The computer processing may comprise using a trained machine learning model. The machine learning model may comprise one or more classifiers which may generate a prediction of a care pathway that corresponds to input health data. Example classifier algorithms may include, for example, support vector machines (SVMs), decision tree algorithms (e.g., AdaBoost, random forests), k-nearest neighbors, nai:ve Bayes, or neural networks (e.g., convolutional neural networks (CNNs) or recurrent neural networks (RNNs)).

[0138] The computer processing may comprise using an image processing algorithm. The image processing algorithm may comprise optical character recognition (OCR).

[0139] The care pathway may be generated by one or more authorized users. For example, one class of authorized users may be given edit permissions only, one class of authorized users may be given generation and edit permissions, and one class of authorized users may be given readonly permissions. An authorized user may be a health care provider or administrator. The health care provider may be a physician, a member of a care team (e.g., a care coordinator), a nurse, a nurse practitioner, or a physician assistant.

[0140] Editing the care pathway may comprise adding or removing one or more health procedures from the time sequence of health procedures or modifying a time order of the health procedures in sequence.

[0141] Editing the care pathway may comprise modifying information associated with a health procedure of the one or more health procedures. Modifying the information may be performed based at least in part on at least one of (1) demographic information of the subject, (2) medical history of the subject, (3) a biological sample of the subject, (4) a location of the subject, (5) insurance information of said subject, (6) a location, (7) a health care provider, or (8) a date associated with a health procedure.

[0142] The one or more search parameters may comprise an identifier of the subject. The identifier may be a medical record number (MRN) of the subject. The identifier may also be a name (e.g., given name and/or last name), social security number, date of birth, or insurance identifier.

[0143] The method may also comprise, prior to (b), (i) retrieving, from a server, connection information associated with the EHR; and (ii) based at least in part on the connection information, directing the query to the EHR. The connection information may include one or more of an IP address, the name of a server, and usemame/password.

[0144] A placement of one or more health procedures of the time sequence may be based at least in part on the health data of the subject. The placement may be a position within the time sequence. The placement may be inclusion inside the time sequence. For example, analyzed health data may indicate that a subject has a particular health condition (e.g., diabetes), that may necessitate a particular health procedure to be placed into the time sequence, that would otherwise not be placed in the care pathway of a healthy subject. Or some health conditions may require alternate sequences of the same health procedures to be undertaken.

[0145] In (b), the health data may be selected automatically. For example, particular health data items that may be relevant for generating a care pathway for a particular complex health condition. The system may implement rules for the selection of relevant health data. In some cases, the relevant health data may be selected algorithmically, (e.g., by a trained machine learning algorithm). In some cases, the health data may be selected by the health care provider. In some cases, a health care provider may override an automatic (e.g., algorithmic) selection of the health data.

[0146] A health procedure of the time sequence of health procedures may be associated with a reference target date. The reference target date may be a date along the care pathway relative to the commencement of the care pathway. For example, the reference target date may be a first week, second week, or third week along the care pathway. The reference target date may correspond to a reference date or a reference date range. The reference date or reference date range may correspond to a particular stage of the complex health condition. For example, the reference date, for pregnancy, may comprise the first, second, or third trimester. The reference date may relate to a temporal characteristic of the subject or of a health condition of the subject. The temporal characteristic may be gestational age.

[0147] The time sequence of health procedures may comprise at least two health procedures. For example, the time sequence of health procedures may comprise at least two of an examination, a biological sample collection, a surgery, a screening, or the like.

[0148] The care pathway may be associated with at least one secondary health condition. The secondary health condition has a detrimental effect on or complicates the complex health condition (e.g., pregnancy). The secondary health condition may itself be a complex health condition. The secondary health condition may be obesity, diabetes, or high cholesterol. The secondary health condition may be determined by processing the health data of the subject. For example, a determination of obesity may be made by processing information related to characteristics of the subject, including height, weight, diet, or body mass index (BMI).

[0149] The processing may be performed using a trained machine learning algorithm. For example, the processing may be performed by a classifier.

[0150] The complex health condition may be a physical or physiological health condition. The complex health condition may be pregnancy, end of life status, debilitation due to stroke, debilitation due to an injury, care of a premature infant, multiple trauma, ventilator dependency, or an organ transplant. The complex health condition may comprise one or more diseases. A disease of the one or more diseases may be a chronic disease. The chronic disease may be a progressive neuromuscular deterioration disease. The progressive neuromuscular deterioration disease may be Parkinson's or amyotrophic lateral sclerosis (ALS). The injury may be a spinal cord injury. The injury may be a wound. The injury may be a fracture. Treatment of the complex health condition may exceed three months in duration. Treatment of the complex health condition may exceed six months in duration.

[0151] The complex health condition may be a mental or behavioral health condition. The mental or behavioral condition may be addiction, depression, anxiety, a stress disorder, bipolar disorder, schizophrenia, or obsessive-compulsive disorder (OCD). The addiction may be drug addiction or substance abuse. The stress disorder may be post-traumatic stress disorder (PTSD).

[0152] A health procedure of the time sequence of health procedure may be placed in the time sequence based at least in part on an availability of a health care provider for the health procedure. The availability may be retrieved from an EHR or an online scheduling application. [0153] The method may further comprise periodically retrieving additional health data of the subject from the server.

[0154] The method may further comprise codifying the care pathway or generating a second care pathway based at least in part on the health data.

[0155] Disclosed is a system. The system may comprise (a) a computer server, and (b) a user interface (UI). The UI may be configured to (i) receive a query comprising one or more search parameters associated with a subject, and (ii) display health data of the subject from the server responsive to the query. The health data of the subject may be associated with a complex health condition. The UI may be further configured to (iii) display a care pathway for the subject. The care pathway may provide a time sequence of health procedures associated with at least the complex health condition. The time sequence may be based at least in part on the health data of the subject

[0156] The UI may be a graphical user interface (GUI). The GUI may be further configured to display analysis of the health data of the subject. The health data and analysis of the health data are viewable via continuous scroll. In some cases, the health data and analysis of health data may be viewable on multiple electronic pages. The analysis of the health data may be provided as a chart or graph. The data or the analysis of the health data may be downloadable via the GUI. The data or the analysis of the health data may be downloadable via a tabular format. An embodiment features an interactive user interface (UI) that is central to the user experience, providing a seamless and intuitive means for healthcare providers and patients to engage with the care pathways. The UI is designed with a focus on usability, ensuring that users can easily navigate and interact with the system to manage care pathways effectively. A key feature of the UI in embodiments is the interactive timeline, which serves as a visual representation of the subject's care pathway over time. Each health procedure within the care pathway is represented by a distinct graphical element on the timeline, such as an icon, shape, or color-coded marker. These graphical elements are not only visually distinct but also interactive, allowing users to click or tap on them to reveal more detailed information about the associated health procedure, such as its purpose, scheduled time, or any special instructions. In association with intended methods of use, users can make adjustments to the care pathway directly through the interactive timeline. For instance, healthcare providers can drag and drop graphical elements to reschedule procedures, or they can add new elements to the timeline to incorporate additional steps into the care pathway. Patients can also interact with the timeline, for example, by confirming the completion of a procedure or by accessing educational materials related to a particular health event. The timeline is designed to be dynamic, automatically updating in real time as changes are made to the care pathway or as new health data is received. This ensures that the care pathway displayed on the UI is always current, providing users with up-to-date information. The system's backend supports this dynamic updating by processing health data and user inputs in real time, employing algorithms that translate these inputs into visual changes on the timeline. The interactive timeline is a critical component of the UI in association with the preferred embodiment, enhancing the decision-making process for care pathway management by providing a clear, concise, and current view of the subject's treatment plan. It empowers users to take an active role in the management of healthcare, fostering a collaborative and informed approach to treatment.

[0157] The GUI may be further configured to display an artificial intelligence (Al) text chat session with a subject. The Al text chat session may comprise a chatbot that processes text input by the subject and responds with relevant information. For example, the chatbot may answer questions from the subject regarding the subject's complex health condition. The chatbot may interpret text using one or more natural language processing (NLP) and/or natural language understanding (NLU) models. The chatbot may use an autoregressive model to produce output text. The chatbot may produce output text using a transformer-based model. A transformer model may comprise an encoder and/or a decoder stage. A transformer-based model may be a generative pre-trained transformer (GPT) model. For example, when the subject inputs an inquiry, the chatbot may determine the intent of the subject by identifying one or more keywords in the inquiry and one or more contexts of the inquiry and previous inquiries, at least in part by processing the inquiry of the subject. The chatbot may provide answers to the inquiry or ask targeted questions for specific information. In some embodiment, the chatbot may be built or integrated with GOOGLE® Dialogflow, AMAZON® Lex, IBM® Watson Assistant, ChatGPT or the like.

[0158] The GUI may be further configured to enable a health care provider to end the Al text chat session and initiate a health care provider text chat with the subject. The GUI may provide a visualization indicating that the Al text chat session has ended, and the health care provider text chat session has begun. The visualization may comprise text, image, and/or video content. The health care provider may be a physician, care coordinator, or a member of medical staff [0159] The text chat session may be displayed in a separate window or tab from the care pathway or the health data. In some embodiments, the text chat session may be displayed in the same window or tab as the care pathway.

[0160] The GUI may be further configured to display an informational content library. The informational content may comprise a clinically validated article. The article may be accessible via Internet (e.g., on the World Wide Web). The GUI may be configured to enable a health care provider to send the informational content to the subject.

[0161] The GUI may be further configured to provide a list of action items. The list of action items may be based at least in part on the health data or the care pathway. The list of action items may be displayed in a separate window or tab from the care pathway or the health data. The list of action items may be automatically generated by processing the health data. In some cases, the list of action items may be generated by a health care provider. An action item of the list of action items may be displayed responsive to an alert setting provided to the GUI. An action item of the list of action items may relate to a status of a health procedure of the care pathway. The status may be complete, missed, or upcoming, scheduled, or unscheduled.

[0162] Disclosed is a system for providing a care pathway for a subject undergoing treatment for a complex health condition. The system may comprise one or more computer processors that may be individually or collectively programmed to:(a) receive, via a user interface (UI), a query comprising one or more search parameters associated with a subject, (b) retrieve, from a computer server, health data of the subject from an electronic health record (EHR) system. The health data of the subject may be associated with the complex health condition. The health data of the subject may be retrieved responsive to the query. The computer processors may additionally be individually or collectively programmed to (c) output a care pathway for the subject. The care pathway may provide a time sequence of health procedures associated with at least the complex health condition. The time sequence may be based at least in part on the health data of the subject.

[0163] Disclosed is a non-transitory computer-readable medium comprising machineexecutable code that, upon execution by one or more computer processors, implements a method for providing a care pathway for a subject undergoing treatment for a complex health condition. The method may comprise (a) receiving, via a user interface (UI), a query comprising one or more search parameters associated with a subject. The method may also comprise (b) retrieving, from a computer server, health data of the subject from an electronic health record (EHR) system. The health data of the subject may be associated with the complex health condition. The health data of the subject may be retrieved responsive to the query. The method may also comprise (c) outputting a care pathway for the subject. The care pathway may provide a time sequence of health procedures associated with at least the complex health condition. The time sequence may be based at least in part on the health data of the subject. [0164] Disclosed is a method for providing care to a subject having a health condition with a plurality of potential health outcomes. The method may comprise providing to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes. The adaptive visualization of the subject's care pathway may enable the health care provider to increase standardization of care provided to the subject for treatment of the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization.

[0165] Disclosed is a system for providing care to a subject having a health condition with a plurality of potential health outcomes. The system may comprise one or more computer processors that are individually or collectively programmed to provide to a health care provider of the subject an adaptive visualization of the subject's care pathway for the health condition having the plurality of potential health outcomes. The adaptive visualization of the subject's care pathway may enable the health care provider to increase standardization of care provided to the subject for treatment of the health condition along the care pathway as compared to treatment of the subject in absence of the adaptive visualization.

System

[0166] FIG. 1 illustrates a networked system 100 for arranging graphical elements on a graphical user interface (GUI) of a computer system, in accordance with some embodiments. The system 100 may include one or more patient devices 120, one or more health care provider devices 140, and one or more servers 160. The patient devices 120, health care provider devices 140 and servers 160 may be connected to a network 110.

[0167] The patient devices 120 may be devices used by patients and may provide interfaces for the patients to communicate with one or more health care providers. The patient devices 120 may be a computing device. A computing device may be a mobile computing device. A mobile computing device may be a smartphone, wearable device, personal digital assistant (PDA), tablet computer, or the like. A computing device may also be a desktop computer, laptop computer, supercomputer, or mainframe computer. The desktop or laptop computer may comprise a patient device application 130 implemented using MICROSOFT® WINDOWS or APPLE® MACINTOSH operating systems. The patient device application 130 allows a patient to receive medical information associated with the patient, appointment schedule reminders, educational classes targeted to the patient.

[0168] A mobile device may comprise one or more mobile device applications. Therefore, the patient device application 130 may include a mobile device application. The mobile device applications described herein may also be implemented on desktop patient devices as desktop applications. The mobile device applications may be implemented using ANDROID® or iOS® operating systems. Desktop versions of these applications may be implemented using MICROSOFT® WINDOWS or APPLE® MACINTOSH operating systems. An example patient device application 130 may enable a user to receive medical information associated with the user, appointment schedule reminders, educational classes targeted to the user.

[0169] Health care provider devices 140 may be devices in clinician offices, clinics, and hospitals used by health care providers. The health care provider devices 140 may also be mobile devices. The health care provider devices 140 may comprise one or more applications 150, which may be desktop applications or mobile device applications. Application 150 may provide a dashboard for a health care provider to review health information associated with one or more users and to establish care pathways designated to the particular health condition of each user. For example, using the dashboard application 150, an obstetrician may determine a pregnancy care pathway based on the particular health condition of the user. The obstetrician may also use the dashboard application 150 to monitor the perinatal depression of the user during and after pregnancy.

[0170] The server 160 may provide data storage functions. The server 160 may store information associated with patients, including electronic medical record (e.g., diagnoses, medicines, tests, allergies, immunizations, and treatment plans), social history (e.g., alcohol and tobacco use), demographic information, mental health conditions, insurance information and other data. The server 160 may also provide functions of generating care pathways designated to a user based on his or her health conditions.

[0171] For example, the server 160 may provide capabilities to use models (e.g., computer vision and/or machine learning models) to classify or predict the care pathways designated to a user based on his or her health condition. The model may be trained to predict a user with gestational diabetes needs more frequent blood glucose tests based on her recent test results, and to generate a sequence of schedules for blood glucose tests during different trimesters of the pregnancy. The model may automatically adjust the sequence of schedules based on updated test results and recommend the types of glucose challenge test based on the pregnancy trimester, previous test results and medical history of the user.

[0172] The server 160 may implement storage of data using one or more databases. A database may comprise storage containing a variety of data consistent with disclosed embodiments. For example, a database may store health information associated with patients, data about a predictive model (e.g., parameters, hyper-parameters, model architecture, threshold, rules, etc.), data generated by a predictive model (e.g., intermediary results, output of a model, latent features, or input and output of a component of the model system, etc.).

[0173] A database may be implemented as a computer system with a storage device. In one aspect, the databases such as the local database and cloud databases may be used by components of the system to perform one or more operations consistent with the disclosed embodiments. One or more cloud databases and local databases may utilize any suitable database techniques. For instance, structured query language (SQL) or "NoSQL" database may be utilized for storing the data transmitted from the edge computing system or the local network 110 such as real-time data (e.g., location data, motion data, audio/video data, messages, etc.), processed data such as report, alert, historical data, predictive model or algorithms. Some of the databases may be implemented using various standard data structures, such as an array, hash, (linked) list, struct, structured text file (e.g., XML), table, JavaScript Object Notation (JSON), NOSQL and/or the like. Such datastructures may be stored in memory and/or in (structured) files. In another alternative, an object-oriented database may be used. Object-oriented databases can include several object collections that are grouped and/or linked together by common attributes; they may be related to other object collections by some common attributes. Object-oriented databases perform similarly to relational databases with the exception that objects are not just pieces of data but may have other types of functionalities encapsulated within a given object. In some embodiments, the database may include a graph database that uses graph structures for semantic queries with nodes, edges and properties to represent and store data. Also, the database may be implemented as a mix of data structures, objects, and relational structures. Databases may be consolidated and/or distributed in variations through standard data processing techniques. Portions of databases, e.g., tables, may be exported and/or imported and thus decentralized and/or integrated.

[0174] The network 110 may be a wired or wireless network 110 that is, in turn, connected to a remote server 160 and the Internet, and may enable the stakeholders of the system (e.g., patients and health care providers). The network 110 may be a combination of wired and wireless network 110. The network 110 may be a local area network (LAN), a wide area network (WAN), the Internet, or another type of network.

[0175] The electronic health record (EHR) system 170 may comprise a systematized collection of electronically stored patient and population health information in a digital format. The EHR system may include a range of data, including demographics, medical history, medication and allergies, immunization status, laboratory test results, radiology images, vital signs, personal statistics like age and weight, and billing information. The EHR system may be integrated with the other system components (e.g., via communication over network 110) and may exchange data with them, enabling, for example, visualization of subject data and/or care pathways in a health care provider application.

[0176] FIGs. 3 A and 3B illustrate screenshots from a GUI of a user device (e.g., a device of a patient or subject) displaying information associated with a patient's pregnancy, in accordance with some embodiments. The GUI may be displayed in the patient device application 130 on the patient device 120. As illustrated, panel 310 of the GUI displays a pregnancy timeline of the patient, including a due date, a number of weeks in the pregnancy, and a number of weeks remaining in the pregnancy. Panel 320 displays upcoming appointments and highlights a most recently canceled appointment as a reminder for rescheduling. Navigation panel 330 allows the patient to navigate between different sections including the patient's designated care pathway, chat area with health care providers, and a content library that stores educational materials for the patient to review. Panel 340 displays week-by-week highlights providing health care information and suggestions corresponding to the patient's pregnancy timeline. Panel 350 displays an interface for the patient to input her mental health status (e.g., feelings or mood). The system 100 may monitor the mental health status over the course of the pregnancy. If the mental status is degrading, the system 100 may generate a schedule for consultation with a psychiatrist and/or courses related to mental health, or display related information (e.g., educational materials) at other panels of the GUI. Panel 360 displays suggested and/or scheduled courses for the patient to attend. The patient may select and schedule courses for their interest. The system 100 may also suggest or schedule courses based on the timeline of the pregnancy and the health condition of the patient.

[0177] FIG. 4 schematically illustrates an example normal pregnancy care pathway 400 generated by the system 100, in accordance with some embodiments. The pathway 400 may comprise a plurality of panels 410, 420, 430 and 440, each comprising one or more graphical elements. The plurality of panels may be displayed representing a sequence of clinical events in chronological order. In other words, the GUI for the normal pregnancy care pathway 400 may display a timeline of clinical events generated by the system 100, based on the health condition of the patient. The panels and graphical elements may be arranged in a vertical or horizontal manner, which allows the patient or health care provider to easily view or edit the events along the timeline without manually scheduling each of them. In some cases, panel 410 comprises graphical elements 412 and 414 indicating a number of weeks in the pregnancy and the content of the clinical event (e.g., an OB visit), which may include recommended and/or required actions including e.g., preparations prior to the visit. The graphical elements may be displayed in proximity to a scheduled date (e.g., 416) corresponding to the clinical event. Panels 420, 430 and 440 may represent other clinical events in the timeline automatically generated by the system 100, including lab tests, injection (e.g., flu shots) and questionnaires, respectively.

[0178] The plurality of panels and graphical elements may be displayed within a single web page via a desktop application. Alternatively, they may be displayed on a mobile device via a mobile device application. The graphical elements 414, 424, 434, and 444 may allow the patient or health care provider to quickly understand the nature of the clinical events without reading through the corresponding text. It may be particularly helpful when the patient or health care provider is reviewing the pathway on a mobile device with a relatively small display screen.

[0179] The patient or health care provider may customize the pathway based on the change in the health condition of the patient and the change in the schedules of the patient or health care provider. For example, the patient or health care provider may remove at least one graphical element from the sequence representing removal of the originally scheduled clinical event or add a graphical element corresponding to a new event. The patient or health care provider may modify the information within the graphical elements, where the modification may be performed based on at least one of demographic information, medical history, recent medical examination results, a location or health insurance information of the patient. Alternatively, the system 100 may automatically customize the pathway based on the health condition, past examination results, and lab test results of the patient. For example, the predictive model stored in the server 160 may process the health information associated with the patient and recommend changes in the care pathway.

[0180] The care pathway may be selected based on one or more health conditions of the patient. For example, when a new patient is enrolled, the health care provider or the patient may select a care pathway based on the health condition of the patient. When the patient has a normal pregnancy without pre-existing conditions, she may have been assigned to a normal pregnancy pathway 400. For a patient who has a pre-existing condition (e.g., obesity, diabetes, hypertension), she may be assigned to other pregnancy pathways corresponding to her health condition. When the patient who was assigned to a normal pregnancy care pathway later developed a new health condition, the health care provider may adjust her care pathway to accommodate the current health condition. Alternatively, the system 100 may automatically generate a care pathway including a sequence of clinical events based on the health condition and other health information associated with the patient. The generated care pathway may seamlessly reflect the clinical needs of the patient during her pregnancy and avoid timeconsuming and labor-intensive scheduling of each of the clinical events from the patient or the health care provider.

[0181] FIG. 5 illustrates an example obesity care pathway 500 for a pregnant patient with obesity, in accordance with some embodiments. The system 100 may generate an obesity care pathway based on the health condition of the patient who has a pre-existing or newly developed obesity. Unlike the normal pregnancy care pathway 400, the pathway 500 comprises a different sequence of clinical events represented by panels and graphical elements, reflecting changes to care because of obesity, when compared to a normal care pathway. For example, along with regular clinical events (e.g., OB visit displayed in panel 510 and routine lab tests displayed in panel 530), the obesity care pathway 500 comprises a sleep consultation displayed in panel 520 and a variety of lab tests including electrocardiogram (ECG), screenings for comorbid conditions and a sleep apnea test displayed in panels 540, 550, and 560. As obesity can accompany a variety of medical issues, for example, sleep apnea and maternal cardiovascular complications, obesity care pathway 500 may substantially reduce health risks from obesity and other accompanying issues. Like the care pathway illustrated in FIG. 4, the panels and graphical elements in FIG. 5 may be arranged in a vertical or horizontal manner, which allows the patient or health care provider to easily view or edit the events along the timeline without manually scheduling each of them. [0182] FIG. 6 illustrates an example diabetes care pathway 600 for a pregnant patient with diabetes, in accordance with some embodiments. The system 100 may generate a diabetes care pathway based on the health condition of the patient. The diabetes care pathway 600 may comprise a different sequence of clinical events represented by panels and graphical elements when compared to a care pathway corresponding to a normal pregnancy, reflecting targeted care for treating a pregnancy complicated by diabetes. For example, in addition to regular clinical events (e.g., obstetrician (OB) visit displayed in panel 610 and routine lab tests displayed in panel 640), the diabetes care pathway 600 may comprise a maternal-fetal medicine (MFM) consultation, dietician consultation and a retinal assessment displayed in panels 620, 630, and 650, respectively. The panels and graphical elements in FIG. 6 may be arranged in a vertical or horizontal manner, which allows the patient or health care provider to easily view or edit the events along the timeline without manually scheduling each of them. [0183] FIG. 7 illustrates another example pregnancy care pathway 700, in accordance with some embodiments. The system 100 may provide alternative GUis for displaying the care pathway. The pregnancy care pathway 700 may parse the scheduled clinical events into panels 710, 720, and 730 by each pregnancy week and within each panel, list the content and time for each clinical event. The pregnancy care pathway 700 may be displayed in a mobile application. As illustrated in FIGS. 4-6, a sequence of clinical events in the care pathway may be displayed in multiple panels in a chronological order by date. Each clinical event may be performed during a different week during pregnancy. For example, an OB visit can be performed during weeks six through nine and imaging for retinal assessment can be performed during weeks six through 11. Information associated with each clinical event may be also displayed in the pathway, including the content of the event, and recommendations and/or requirements for the patient. In the alternative GUis as illustrated in FIG. 7 here, the pregnancy care pathway may be parsed by pregnancy week. For example, panels 710, 720, and 730 display all clinical events scheduled during pregnancy week 4, 5, and 6, respectively. For each week, the GUI may list the name and schedule of each clinical event in a chronological order. This configuration may enable the pregnancy care schedule for multiple weeks to be displayed on the same page. The patient may find scheduled clinical events holistically and obtain more information by clicking a particular event for more details.

[0184] FIG. 8 illustrates a GUI of a health care provider's dashboard 800 displaying information associated with the health care provider's tasks and list of patients, in accordance with some embodiments. The health care provider's dashboard 800 may be displayed in a health care provider's application 150. The dashboard 800 provides a panel 810 listing a plurality of tasks assigned to the health care provider and panel 820 listing the patients to be seen. Patients may be assigned to care pathways corresponding to their health conditions. A health care provider may also assign a care pathway to new patients or change care pathways for existing patients based on their health conditions. Alternatively, the system 100 may automatically generate a care pathway that corresponds to a health condition of the patient. When a health care provider selects a particular patient, the dashboard 800 may provide health information associated with this patient.

[0185] FIG. 9 illustrates a GUI of a health care provider's dashboard 900 displaying information associated with a patient, in accordance with some embodiments. The dashboard 900 displays health and social history information closely related to a patient's pregnancy, including active allergies in panel 910, recently recorded vital signs in panel 920 likely associated with obesity, recent lab results likely associated with diabetes in panel 930, and social history including alcohol and tobacco use in panel 940. Panel 950 lists the care pathway corresponding to this patient.

[0186] FIG. 10 illustrates a GUI of a health care provider's dashboard 1000 displaying medical information associated with one patient, in accordance with some embodiments. Panel 1010 provides an Edinburgh postnatal depression scale (EPDS) that monitors the patient's level of depression during each trimester of pregnancy and post childbirth. The scales may be established based on the daily input from the patient (see, e.g., "how are you feeling today?" displayed in panel 350 on the GUI of the patient device). Alternatively, the scale may be established based on the input from the patient and the health care providers during OB visits and consultations scheduled on the care pathway. Panel 1020 displays the active medication of the patient. Panels 1030 and 1040 display blood glucose and blood pressure monitoring during the pregnancy. Based on collective information of the pregnancy showing trends and/or changes corresponding to the patient's health condition, her care pathway may also be changed accordingly.

[0187] FIG. 11 illustrates a patient education dashboard 1100, which may be displayed in one or both of the patient device application and health care provider device application, in accordance with some embodiments. The system 100 may identify and display educational materials on the dashboard 1100, based on week-by-week stages of pregnancy, existing health conditions, newly developed health issues, social history and living style of the patient. [0188] FIG. 12 illustrates a process 1200, in accordance with some embodiments.

[0189] In a first operation 1210, via a GUI, the system 100 may obtain search parameters (e.g., medical record number (MRN), date of birth, name, insurance identifier, or social security number (SSN)) from a health care provider (e.g., a physician, member of care team, nurse, nurse practitioner, or physician assistant) to query for a patient in the health care provider's existing electronic health record (EHR) system. In this system configuration, the health care provider's EHR connection information may have been previously captured and stored in the system. It may be retrieved from system storage to direct and formulate the patient search query to the appropriate EHR system.

[0190] In some cases, upon performing the search query to the EHR system, multiple matching patient records may be returned from the EHR system. The system may provide a mechanism via a GUI to allow the health care provider to select a specific patient for which to import the patient profile history. Once a target patient has been specified, the system may also allow the health care provider to configure or override the specific information to be imported from the EHR system by the system. This may support variations in system configuration where import configuration details may not be provided in advance, or where the system may allow the health care provider to customize the import options from the default configuration.

[0191] In a second operation 1220, once a matching patient is found, the system may automatically import a patient's medical profile and history as appropriate for the health condition being managed. Data imported may include, for example, pregnancy history, recent vitals, and/or allergies. The medical profile information pulled may be configured in the system based on a particular health condition or may be configured based on health care provider's preferences as previously captured.

[0192] In a third operation 1230, the system may also provide a mechanism via a GUI to receive as input from a health care provider a specific care pathway to be assigned to a target patient. The patient profile information may then be displayed on a GUI to a health care provider. Based on a health care provider-supplied care pathway assignment request, the system may assign a patient to that care pathway, and assign all health procedures associated with that care pathway to the patient. The system may be augmented to automatically schedule the health procedures assigned to the patient as appropriate.

[0193] Upon importing the patient profile information, the system may automatically assign a preconfigured care pathway to the patient based on one or more detected health conditions. In this variation, the system may be designed with artificial intelligence capable of detecting health conditions based on patient profile information.

[0194] After a care pathway has been assigned, the system may provide a mechanism for a health care provider to update the care pathway selection for a patient. This is important both to support and facilitate changes in care based on changes in a patient's health condition, but also to enable a health care provider to override the system's Al-enabled decision-making ability. [0195] Table I schematically illustrates a format in which care pathways are configured in a disclosed system (e.g., the system 100), highlighting critical information for defining a care pathway. The below table may represent a simplification of a data model governing how a care pathway is maintained in a database.

Table 1: Care Pathways

[0196] Each care pathway may be mapped specifically to a particular health condition (e.g. - normal pregnancy, pregnancy with gestational diabetes, etc.), represented above as health condition ID (1, 2, 3).

[0197] Each care pathway may contain multiple health procedures (e.g., an obstetrician visit, a lab injection, etc.), represented above as health procedure ID (A, B, C, D, E, F). Health procedures may be reused across different care pathways, as well as within a care pathway. Each health procedure may be also associated with a reference target date. This target date would be relative to a particular reference date (e.g., gestational age), and could also represent a range (e.g., week six) rather than an exact date.

[0198] FIG. 13 schematically illustrates management 1300 of patients on care pathways, and results of updating a patient's care pathway, in accordance with some embodiments. Reusing the same two care pathways described in Table 1, FIG. 13 illustrates what happens when a patient is initially assigned to the care pathway based on health condition 1. A patient may be assigned the health procedures A, Band C for weeks 1, 2 and 3 respectively. At week 2, the health care provider may update the patient's health condition to health condition 2. The system may then assign the patient the health procedures D and C for weeks 5 and 7 respectively. At week 3, the health care provider adds a health condition 3 to the patient, resulting in the patient being assigned the health procedures E and F for weeks 6 and 8 respectively. When all health procedures for assigned care pathways have completed, the patient may be re-assigned to a default care pathway (e.g., a normal care pathway) with the default health procedures G (e.g., an annual checkup).

[0199] Any patient's care pathway may be unique based on a patient's particular combination of health conditions experienced over time, and how those health conditions may evolve. This may result in a dynamically assigned set of health procedures based on the assignment of various care pathways at different times and the consequent assignment of a unique set of health procedures based on those care pathways. The re-assignment of a user from one care pathway to another may be performed manually by a health care provider, but may also be performed by the system by using artificial intelligence to detect changes in a patient's health condition (e.g. - monitoring changes in blood glucose levels to detect diabetes) [0200] The system could also be configured to support the assignment of multiple conditions to a patient coincidentally. This process may result in a care pathway that aggregates the health procedures from the care pathways associated with each health condition.

[0201] FIG. 14 schematically illustrates a system architecture diagram 1400, in accordance with some embodiments. The system architecture diagram 1400 may include external connected systems 1410, application programming interface layer 1420, and user applications 1460.

[0202] External connected systems 1410 may comprise an EHR system 1412, a rule server 1414, and a licensed content engine 1416. The EHR system 1412 may comprise structured patient data from one or more health care providers. The rule server 1414 may provide one or more services to facilitate access to and exchange of the patient health care data. The licensed content engine 1416 may provide informational content (e.g., online articles or publications). [0203] A server (e.g., the server 160) may provide application programming interface layer 1420 functions, which may include a plurality of cloud services 1434A and 1434B. The cloud services 1434A-B may, for example, comprise a virtual private cloud 1422. The virtual private cloud 1422 may comprise one or more cloud databases 1432 (e.g., a primary database, a read replica database, and/or a standby database for backup and recovery purposes) for storing data related to generating subject care pathways. The virtual private cloud 1422 may comprise a cloud application 1428 that may perform tasks such as load balancing and auto scaling to make access to resources efficient, backup, data persistence, and secure access to external connected systems 1410. Embodiments of the invention employ advanced load balancing strategies to ensure the efficient distribution of data requests across the system's infrastructure. This load balancing in such examples is crucial for maintaining high system performance and availability, particularly when handling a large number of simultaneous requests from healthcare providers and patients accessing the care pathways. The system in an embodiment utilizes a combination of hardware and software load balancers that dynamically allocate network traffic and computational tasks among multiple servers. This approach prevents any single server from becoming a bottleneck, thereby enhancing the overall responsiveness of the system. In addition to load balancing, the system features a real-time monitoring component that plays a pivotal role in the continuous updating of care pathways. This component is responsible for the ongoing surveillance of health data as it is received from various sources, including wearable devices, diagnostic equipment, and electronic health records (EHRs). The real-time monitoring component uses a set of predefined rules and algorithms to detect significant changes in health data that may necessitate an update to the care pathway.

Continuous synchronization with EHR systems is a key aspect of the real-time monitoring component. The system is designed to interface seamlessly with EHRs, ensuring that the care pathways reflect the most current and comprehensive health data available. This synchronization occurs in real time, with any updates to the EHRs being immediately captured and processed by the system. The integration with EHR systems is facilitated by the use of standardized health data exchange protocols, which allow for the secure and efficient transfer of information. The combination of load balancing and real-time monitoring ensures that the care pathways are both accurate and up-to-date, reflecting the latest health data and clinical insights. This real-time data processing capability enables healthcare providers to make informed decisions quickly, adapting the care pathways to the evolving needs of the patients. The system's ability to synchronize with EHRs and other health data sources in real time further enhances the continuity and quality of care, providing a seamless experience for both providers and patients. Additionally, cloud service 1434A may also include storage 1422, a virtual private network 1424, backup 1426, and developer tools, security, monitoring, and notification services 1436. Cloud service 1434B may provide SMS service 1438 (for communicating with the health care provider device application 1462 (e.g., health provider device application 150 illustrated in FIG. 1)), authentication service 1454, in-application messages 1446 provided to the patient application 1464 (e.g., patient device application 130 illustrated in FIG. 1), data store 1442 for analytics and chat data, analytics dashboard 1448 and an Al chatbot service 1452. Other aspects of the system associated with the above comprise a robust security compliance module designed to uphold the highest standards of data privacy and security across various healthcare settings. This module is integral to the system's architecture and operates to ensure that all health data is managed in strict adherence to regulatory requirements, including the Health Insurance Portability and Accountability Act (HIPAA) and other relevant data protection laws. The security compliance module employs multiple layers of security measures to safeguard sensitive health information. These measures include end-to-end encryption of data both in transit and at rest, ensuring that all health data is encoded and can only be accessed by authorized individuals with the appropriate decryption keys. The system also implements secure authentication protocols, such as two-factor authentication and biometric verification, to control access to the health data. In addition to access controls, the security compliance module features comprehensive auditing and logging capabilities. Every interaction with the health data is recorded, creating an immutable audit trail that can be reviewed for compliance purposes. This level of transparency helps to prevent unauthorized access and provides a mechanism for tracking and reporting any potential security incidents. The system's security compliance module is configured to perform regular vulnerability assessments and penetration testing to identify and address potential security weaknesses. It also includes automated tools for real-time monitoring of security threats, enabling the system to respond promptly to any detected anomalies. To maintain compliance with HIPAA and other regulations, the security compliance module is updated regularly to align with the latest legal requirements and best practices in healthcare data security. The system's commitment to security and privacy extends to its partnerships with healthcare providers, ensuring that all parties involved in the care pathway management process are compliant with the necessary security standards. By integrating these comprehensive security measures, the preferred embodiment provides a secure and trustworthy platform for managing care pathways, giving healthcare providers and patients confidence that their health information is protected and handled with the utmost care.

[0204] The user applications 1460 may comprise the health care provider application 1462 (e.g., health care provider device application 150 illustrated in FIG. 1) and the patient (or subject) application 1464 (e.g., patient device application 130 illustrated in FIG. 1). The health care provider application 1464 may display care pathways and data visualizations to the health care provider and enable the health care provider to view informational content. The patient application 1464 may enable a patient to view a care pathway, engage in an Al or health care provider chat, or view informational content.

[0205] FIG. 15 schematically illustrates an exemplary interaction diagram 1500 of a health care provider and patient with a software-based system (e.g., the system 100) assigning care pathways to the patient which are viewable and/or editable by the health care provider, in accordance with some embodiments. The system may include multiple components to facilitate authentication, authorization, secure exchange of health data, storage of health data, and provision of other software-based services (e.g., visualization in a GUI) to both a health care provider and a subject (e.g., a patient). In other cases, the software-based system may include additional or fewer components, and interactions between the components may differ.

[0206] For example, a health care provider may sign up to use the system, providing login credentials to a database 1520 via a network. The database 1520 may store these details and send a verification email to the health care provider, to enable the provider to log in. Subsequently logging in may comprise requesting a token, and retrieving a generated token, from a server 1510 that may handle authentication and/or authorization, as well as provide other service tasks used by the system. For example, the server 1510 may provide Al chatbot functionality to the patient. The database 1520 may store health data from a plurality of patients. Many functions of the system may comprise querying with or otherwise interacting with the database, including, for the health care provider, adding patients, viewing patient profile information, viewing notifications, viewing informational content, viewing a patient's care pathway and/or date visualizations, viewing patient health information (e.g., in a GUI), or viewing messages (e.g., from health care providers, patients, or health care staff), or for patients, viewing chat messages, viewing upcoming appointments, updating health information, viewing a care pathway, viewing a content library, viewing care team information, and/or viewing notifications. Notifications may be pushed to a patient via the server 1510. An embodiment of the invention incorporates a predictive analytics engine that links to the notification aspects that is central to the system's ability to offer dynamic and responsive care pathways. This engine utilizes advanced algorithms and machine learning techniques to analyze health data trends and patterns, extracting actionable insights that can inform the adjustment of care pathways. By processing large datasets, the predictive analytics engine can identify correlations and causal relationships that may not be immediately apparent to healthcare providers, thereby enabling the system to anticipate potential health events or outcomes. The predictive analytics engine is trained on historical health data, including outcomes of previous care pathways, to refine its predictive models. This training allows the engine to improve its accuracy over time, adapting to new data and evolving medical knowledge. The engine's predictive capabilities are crucial for suggesting updates to care pathways, as it can forecast the likelihood of future health events, such as the risk of a patient developing a complication or the potential for a treatment to be particularly effective. In tandem with the notification aspects of the system and its predictive analytics engine, the system features an alert system that provides immediate notifications to healthcare providers and patients. This alert system is configured with predefined triggers or thresholds, which, when reached or breached, prompt the system to issue an alert. These triggers are based on clinical guidelines and can be customized to each patient's specific health condition and risk profile. For example, a trigger may be set for a diabetic patient's blood glucose levels; if readings fall outside the desired range, the system will generate an alert for both the patient and their healthcare provider. The alert system is designed to be both sensitive and specific, minimizing the occurrence of false positives while ensuring that significant health changes are not overlooked. Alerts can take various forms, including visual indicators on the user interface, email notifications, or messages sent to mobile devices. The immediacy of these alerts is critical for enabling timely interventions, which can be vital for patient health and safety. By integrating predictive analytics with an alert system, an embodiment of the present invention provides a proactive approach to healthcare management. The system not only reacts to changes in health data but also anticipates them, ensuring that care pathways are always aligned with the best possible outcomes for patients. Database content may be viewable based on permissions associated with user profiles of the health care provider and/or patient. For example, informational content may be curated based on the health care provider or patient's needs. The patient may log into the system in a similar manner to the health care provider. It is an aspect of the system to provide an environment where patients and healthcare providers can engage in joint decision-making and care coordination. This shared platform is designed to bridge the communication gap between all parties involved in the patient's care, providing a centralized hub for the exchange of information, discussion of treatment options, and monitoring of health progress. The collaboration platform allows healthcare providers to access and contribute to a patient's care pathway in real time. It supports multi-disciplinary teams in coordinating care efforts, ensuring that each provider is aware of the others' actions and plans. This coordination is critical for complex health conditions that require input from various specialists. The platform's interface presents care pathways in an intuitive format, allowing providers to view, update, and annotate them as needed, facilitating a cohesive treatment strategy. For patients, the platform serves as an empowering tool that provides transparency into their care process. It enables them to view their care pathways, understand the rationale behind each prescribed health procedure, and track their progress over time. Patients can also contribute to their care by providing feedback on their health status, reporting symptoms, and expressing preferences regarding treatment options. This input is valuable for healthcare providers to tailor care pathways that align with the patient's needs and circumstances. The system's collaboration platform is equipped with features that support secure messaging, document sharing, and virtual consultations. These features ensure that patients and providers can communicate effectively, regardless of their physical location. The platform's design prioritizes user-friendliness and accessibility, making it easy for individuals with varying levels of technical proficiency to participate in the care management process. By facilitating a collaborative approach to care pathway management, the system enhances the quality of care delivered to patients. It promotes a patient-centered model where informed consent and shared decision-making are the norms. The platform's ability to synchronize care activities among multiple providers and involve patients in their care journey represents a significant advancement.

[0207] The server 1510 may provide a chatbot function. The chatbot may use an Al chat model 1530 comprising, for example, a natural language understanding (NLU) or natural language processing (NLP) platform to generate messages based on prompts by the patient. The chat messages may be stored in the database. The Al chat model 1530 may have access to health data stored in the database that is provided as input which is processed to generate chat responses. [0208] Queries for patient information may be governed by rule system 1560 to facilitate efficient and secure health care data exchange. Rule system 1560 may be, for example, Fast Health care Interoperability Resources (FHIR). For example, a health care provider may search for a patient (e.g., by using an identifier) via a user interface, by querying the database in a manner facilitated by rule system 1560. Rule system 1560 may also facilitate data exchange between the system and an EHR (e.g., CERNER® or EPIC®). Searching for a patient may be performed by providing a patient's medical record number (MRN), name, or date of birth, for example.

[0209] If a new patient is added, in a pregnancy context, the patient's last menstrual period (LMP) and estimated delivery date (EDD) may be added to the system. The patient's information may be displayed if the LMP and EDD are available (patients who this information is not available for may not be displayed). The relevant information for patient care may then be displayed to the health care provider (e.g., care pathway, care team, health vitals, health records, appointments, questionnaire, and patient education).

Machine Learning

[0210] The preferred embodiment utilizes a machine learning model that undergoes a rigorous training and validation process to ensure its efficacy in classifying and predicting individualized care pathways for subjects with complex health conditions. The training phase involves feeding the model a diverse dataset comprising various types of health data, including but not limited to, demographic information, clinical notes, diagnostic images, laboratory test results, and patient-generated data from wearable devices. This dataset is carefully curated to represent a wide spectrum of scenarios encountered in the treatment of the specified health conditions. The machine learning model employs a combination of algorithms tailored to the nuances of healthcare data. These may include convolutional neural networks (CNNs) for image-based data, recurrent neural networks (RNNs) with long short-term memory (LSTM) units for time-series data, and other appropriate classifiers for structured data. The model is trained to recognize patterns, correlations, and anomalies within this data, enabling it to make informed predictions about the most effective care pathways. Validation of the machine learning model is conducted using a separate validation dataset that has not been exposed to the model during the training phase. This dataset is used to evaluate the model's accuracy and its ability to generalize from the training data to new, unseen data. The validation process helps in fine-tuning the model's parameters and in assessing its performance metrics, such as precision, recall, and the area under the receiver operating characteristic (ROC) curve. The training and validation of the machine learning model are iterative processes, with continuous refinement to improve the model's predictive capabilities. The end goal is to achieve a model that can reliably support healthcare providers in developing care pathways that are personalized, timely, and responsive to the evolving health status of the subjects. a. Training Phase

[0211] A machine learning software module may be provided by a server and may implement one or more machine learning algorithms. A machine learning software module as described herein is configured to undergo at least one training phase wherein the machine learning software module is trained to carry out one or more tasks including data extraction, data analysis, and generation of output. In some embodiments of the software application described herein, the software application comprises a training module that trains the machine learning software module. The training module is configured to provide training data to the machine learning software module, the training data comprising, for example, subject health data and ground truth data comprising a portion of an expert-generated patient care pathway. In some embodiments of a machine learning software module described herein, a machine learning software module utilizes automatic statistical analysis of data to determine which features to extract and/or analyze from the subject health data. In some of these embodiments, the machine learning software module determines which features to extract and/or analyze from subject health data based on the training that the machine learning software module receives. [0212] In some embodiments, a machine learning software module is trained using a data set and a target in a manner that might be described as supervised learning. In these embodiments, the data set is conventionally divided into a training set, a test set, and, in some cases, a validation set. In some embodiments, the data set is divided into a training set and a validation set. A target is specified that contains the correct classification of each input value in the data set. For example, a set of subject health data is repeatedly presented to the machine learning software module, and for each sample presented during training, the output generated by the machine learning software module is compared with the desired target. The difference between the desired target and the generated output is calculated, and the machine learning software module is modified to cause the output to more closely approximate the desired target value. In some embodiments, a back-propagation algorithm is utilized to cause the output to more closely approximate the desired target value. After many training iterations, the machine learning software module output will closely match the desired target for each sample in the input training set. Subsequently, when new input data, not used during training, is presented to the machine learning software module, it may generate an output classification value indicating which of the categories the new sample is most likely to fall into. The machine learning software module is said to be able to "generalize" from its training to new, previously unseen input samples. This feature of a machine learning software module allows it to be used to classify almost any input data which has a mathematically formulatable relationship to the category to which it should be assigned.

[0213] In some embodiments of the machine learning software module described herein, the machine learning software module utilizes a simulated training model. A simulated training model is based on the machine learning software module having trained at least in part on simulated subject health data.

[0214] In some embodiments, the use of training models changes as the availability of subject health data changes. For instance, a simulated training model may be used if there are insufficient quantities of subject health data available for training the machine learning software module to a desired accuracy. As additional data becomes available, the training model can change to a global or individual model. In some embodiments, a mixture of training models may be used to train the machine learning software module. For example, a simulated and global training model may be used, utilizing a mixture of real subject health data and simulated data to meet training data requirements.

[0215] Unsupervised learning is used, in some embodiments, to train a machine learning software module to use input data such as, for example, subject health data and output, for example, a portion of a care pathway for the subject. Unsupervised learning, in some embodiments, includes feature extraction which is performed by the machine learning software module on the input data. Extracted features may be used for visualization, for classification, for subsequent supervised training, and more generally for representing the input for subsequent storage or analysis. In some cases, each training case may consist of a plurality of subject health data.

[0216] Machine learning software modules that are commonly used for unsupervised training include k-means clustering, mixtures of multinomial distributions, affinity propagation, discrete factor analysis, hidden Markov models, Boltzmann machines, restricted Boltzmann machines, autoencoders, convolutional autoencoders, recurrent neural network autoencoders, and long short- term memory autoencoders. While there are many unsupervised learning models, they all have in common that, for training, they require a training set consisting of biological sequences, without associated labels.

[0217] A machine learning software module may include a training phase and a prediction phase. The training phase is typically provided with data to train the machine learning algorithm. Non- limiting examples of types of data inputted into a machine learning software module for the purposes of training include encoded data, encoded features, or metrics derived from subject health data. Data that is inputted into the machine learning software module is used, in some embodiments, to construct a hypothesis function to determine a predicted portion of a subject care pathway. In some embodiments, a machine learning software module is configured to determine if the outcome of the hypothesis function was achieved and based on that analysis determine with respect to the data upon which the hypothesis function was constructed. That is, the outcome tends to either reinforce the hypothesis function with respect to the data upon which the hypothesis functions was constructed or contradict the hypothesis function with respect to the data upon which the hypothesis function was constructed. In these embodiments, depending on how close the outcome tends to be to an outcome determined by the hypothesis function, the machine learning algorithm will either adopt, adjust, or abandon the hypothesis function with respect to the data upon which the hypothesis function was constructed. As such, the machine learning algorithm described herein dynamically learns through the training phase what characteristics of an input (e.g., data) are most predictive in determining whether the features of subject health data are associated with a portion of a care pathway for the subject.

[0218] For example, a machine learning software module is provided with data on which to train so that it, for example, can determine the most salient features of received subject health data to operate on. The machine learning software modules described herein train as to how to analyze the subject health data, rather than analyzing the subject health data using pre-defined instructions. As such, the machine learning software modules described herein dynamically learn through training what characteristics of an input signal are most predictive in determining whether the features of subject health data predict a particular generated portion of a care pathway.

[0219] In some embodiments, training begins when the machine learning software module is given subject health data and asked to predict a portion of a care pathway. The predicted portion of the care pathway is then compared to a validated (e.g., expert-determined) portion of the care pathway that corresponds to the subject health data. An optimization technique such as gradient descent and backpropagation is used to update the weights in each layer of the machine learning software module to produce closer agreement between the portion of the care pathway predicted by the machine learning software module, and the expert-generated portion of the care pathway. This process is repeated with new subject health data and portions of care pathways until the accuracy of the predicted care pathway has reached the desired level. [0220] In some embodiments, a strategy for the collection of training data is provided to ensure that the subject health data represents a wide range of conditions to provide a broad training data set for the machine learning software module. For example, a prescribed number of measurements during a set period may be required as a section of a training data set. Additionally, these measurements can be prescribed as having a set amount of time between measurements.

[0221] In general, a machine learning algorithm is trained using subject health data and/or any features or metrics computed from the above said data with the corresponding ground-truth values. The training phase constructs a hypothesis function for predicting a portion of a care pathway from subject health data and/or any features or metrics derived from metadata. The machine learning algorithm dynamically learns through training what characteristics of input data are most predictive in determining a portion of a care pathway. A prediction phase uses the constructed and optimized hypothesis function from the training phase to predict the portion of the care pathway by using the subject health data and/or any features or metrics computed from or derived from metadata. b. Prediction Phase

[0222] Following training, the machine learning algorithm is used to determine, for example, the portion of the care pathway on which the system was trained using the prediction phase. With appropriate training data, the system can identify a portion of a care pathway.

[0223] The prediction phase uses the constructed and optimized hypothesis function from the training phase to predict a portion of a care pathway from the subject health data.

[0224] In some embodiments, a probability threshold can be used in conjunction with a final probability to determine whether a portion of the care pathway matches the trained portion of the care pathway. In some embodiments, the probability threshold is used to tune the sensitivity of the trained machine learning algorithm. For example, the probability threshold can be 1%, 2%, 5%, 10%, 15%, 20%, 25%, 30%, 35%, 40%, 45%, 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 95%, 98% or 99%. In some embodiments, the probability threshold is adjusted if the accuracy, sensitivity or specificity falls below a predefined adjustment threshold. In some embodiments, the adjustment threshold is used to determine the parameters of the training period. For example, if the accuracy of the probability threshold falls below the adjustment threshold, the system can extend the training period and/or require additional subject health data and/or portions of care pathways. In some embodiments, additional measurements and/or portions of care pathways can be included into the training data. In some embodiments, additional measurements and/or portions of care pathways can be used to refine the training data set.

Computer systems

[0225] The present disclosure provides computer systems that are programmed to implement methods of the disclosure. FIG. 2 shows a computer system 201 that is programmed or otherwise configured to generate care pathways designated to a user based on his or her health condition and to arrange graphical elements that represent the care pathway on a GUI of a computer system. The computer system 201 can regulate various aspects of generating care pathways and arrange corresponding graphical elements of the present disclosure, such as, for example, implementing machine learning algorithms relevant to the machine learning module. The machine learning module in the preferred embodiment provides an engine that enables the management and adaptation of care pathways for subjects with complex health conditions. In an embodiment, the machine learning module is hosted on a computer server, optionally a cloud-based server, and is designed to process vast amounts of health data, which it retrieves from a comprehensive network of electronic health records (EHR). The module's core functionality is underpinned by its training on a curated dataset, in an embodiment constituting an evolving data set based on a large number of data sources, which includes a diverse array of health data points ranging from physiological metrics to patient-reported outcomes. The training process is validated against a separate validation dataset to ensure the highest levels of accuracy and reliability in its predictive capabilities. The machine learning module in an embodiment employs a convolutional neural network (CNN) architecture, optimized for the nuanced analysis of image data, such as radiological scans and dermatological images. This allows for the extraction of critical features and patterns that may not be readily apparent to the human eye. Complementing the CNN, a recurrent neural network (RNN) with long short-term memory (LSTM) units is deployed to adeptly handle time-series data, such as continuous glucose monitoring readings or ECG tracings in exemplary uses, providing insights into the temporal progression of a subject's health condition. The module is not static; it is dynamically configured to learn and evolve from ongoing health data. As new data is ingested, the module refines its predictive models, ensuring that the care pathways it suggests are tailored to the individual's response to treatment over time. This dynamic learning process is facilitated by a feedback loop that captures outcomes and patient feedback, which is then used to fine-tune the algorithms for even greater personalization and efficacy. The machine learning module in an embodiment operates in concert with a real-time monitoring component, which includes an array of data sources, such as sensors in an exemplary embodiment, that continuously feed health data into the system. This integration enables the module to provide immediate, data- driven recommendations for care pathway adjustments, ensuring that the subject's treatment is responsive to their current needs. The predictive analytics engine, also hosted on the server in an embodiment, leverages the module's output to generate comprehensive recommendations, which are then presented to healthcare providers through the user interface. This interface displays the care pathway as an interactive timeline, with graphical elements representing health procedures, which are dynamically updated in real-time based on the module's ongoing analysis. The machine learning module's design and functionality in the preferred embodiment enable the system's ability to provide an adaptive approach to healthcare management, setting it apart from conventional methods and providing a clear technical advancement in the field of personalized medicine. The computer system 201 can be an electronic device of a user or a computer system that is remotely located with respect to the electronic device. The electronic device can be a mobile electronic device or a desktop computing device.

[0226] The computer system 201 includes a central processing unit (CPU, also "processor" and "computer processor" herein) 205, which can be a single core or multi core processor, or a plurality of processors for parallel processing. The computer system 201 also includes memory or memory location 210 (e.g., random-access memory, read-only memory, flash memory), electronic storage unit 215 (e.g., hard disk), communication interface 220 (e.g., network adapter) for communicating with one or more other systems, and peripheral devices 225, such as cache, other memory, data storage and/or electronic display adapters. The memory 210, storage unit 215, interface 220 and peripheral devices 225 are in communication with the CPU 205 through a communication bus (solid lines), such as a motherboard. The storage unit 215 can be a data storage unit (or data repository) for storing data. The computer system 201 can be operatively coupled to a computer network ("network") 230 with the aid of the communication interface 220. The network 230 can be the Internet, an intranet and/or extranet, or an intranet and/or extranet that is in communication with the Internet. The network 230 in some cases is a telecommunication and/or data network. The network 230 can include one or more computer servers, which can enable distributed computing, such as cloud computing. The network 230, in some cases with the aid of the computer system 201, can implement a peer-to-peer network, which may enable devices coupled to the computer system 201 to behave as a client or a server.

[0227] The CPU 205 can execute a sequence of machine-readable instructions, which can be embodied in a program or software. The instructions may be stored in a memory location, such as the memory 210. The instructions can be directed to the CPU 205, which can subsequently program or otherwise configure the CPU 205 to implement methods of the present disclosure. Examples of operations performed by the CPU 205 can include fetch, decode, execute, and writeback.

[0228] The CPU 205 can be part of a circuit, such as an integrated circuit. One or more other components of the system 201 can be included in the circuit. In some cases, the circuit is an application specific integrated circuit (ASIC).

[0229] The storage unit 215 can store files, such as drivers, libraries and saved programs. The storage unit 215 can store user data, e.g., user preferences and user programs. The computer system 201 in some cases can include one or more additional data storage units that are external to the computer system 201, such as located on a remote server that is in communication with the computer system 201 through an intranet or the Internet.

[0230] The computer system 201 can communicate with one or more remote computer systems through the network 230. For instance, the computer system 201 can communicate with a remote computer system of a user (e.g., a mobile device). Examples of remote computer systems include personal computers (e.g., portable PC), slate or tablet PC's (e.g., Apple® iPad, Samsung® Galaxy Tab), telephones, Smart phones (e.g., Apple® iPhone, Android-enabled device, Blackberry®), or personal digital assistants. The user can access the computer system 201 via the network 230.

[0231] Methods as described herein can be implemented by way of machine (e.g., computer processor) executable code stored on an electronic storage location of the computer system 201, such as, for example, on the memory 210 or electronic storage unit 215. The machine executable or machine-readable code can be provided in the form of software. During use, the code can be executed by the processor 205. In some cases, the code can be retrieved from the storage unit 215 and stored on the memory 210 for ready access by the processor 205. In some situations, the electronic storage unit 215 can be precluded, and machine-executable instructions are stored on memory 210.

[0232] The code can be pre-compiled and configured for use with a machine having a processor adapted to execute the code, or can be compiled during runtime. The code can be supplied in a programming language that can be selected to enable the code to execute in a precompiled or as- compiled fashion.

[0233] Aspects of the systems and methods provided herein, such as the computer system 201, can be embodied in programming. Various aspects of the technology may be thought of as "products" or "articles of manufacture" typically in the form of machine (or processor) executable code and/or associated data that is carried on or embodied in a type of machine readable medium. Machine- executable code can be stored on an electronic storage unit, such as memory (e.g., read-only memory, random-access memory, flash memory) or a hard disk. "Storage" type media can include any or all of the tangible memory of the computers, processors or the like, or associated modules thereof, such as various semiconductor memories, tape drives, disk drives and the like, which may provide non-transitory storage at any time for the software programming. All or portions of the software may at times be communicated through the Internet or various other telecommunication networks. Such communications, for example, may enable loading of the software from one computer or processor into another, for example, from a management server or host computer into the computer platform of an application server. Thus, another type of media that may bear the software elements includes optical, electrical and electromagnetic waves, such as used across physical interfaces between local devices, through wired and optical landline networks and over various air-links. The physical elements that carry such waves, such as wired or wireless links, optical links or the like, also may be considered as media bearing the software. As used herein, unless restricted to non-transitory, tangible "storage" media, terms such as computer or machine "readable medium" refer to any medium that participates in providing instructions to a processor for execution.

[0234] Hence, a machine readable medium, such as computer-executable code, may take many forms, including but not limited to, a tangible storage medium, a carrier wave medium or physical transmission medium. Non-volatile storage media include, for example, optical or magnetic disks, such as any of the storage devices in any computer(s) or the like, such as may be used to implement the databases, etc. shown in the drawings. Volatile storage media include dynamic memory, such as main memory of such a computer platform. Tangible transmission media include coaxial cables; copper wire and fiber optics, including the wires that comprise a bus within a computer system. Carrier-wave transmission media may take the form of electric or electromagnetic signals, or acoustic or light waves such as those generated during radio frequency (RF) and infrared (IR) data communications. Common forms of computer-readable media therefore include for example: a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, DVD or DVD-ROM, any other optical medium, punch cards paper tape, any other physical storage medium with patterns of holes, a RAM, a ROM, a PROM and EPROM, a FLASH-EPROM, any other memory chip or cartridge, a carrier wave transporting data or instructions, cables or links transporting such a carrier wave, or any other medium from which a computer may read programming code and/or data. Many of these forms of computer readable media may be involved in carrying one or more sequences of one or more instructions to a processor for execution.

[0235] The computer system 201 can include or be in communication with an electronic display 235 that comprises a user interface (UI) 240 for providing, for example, a dashboard. Examples of UI include, without limitation, a graphical user interface (GUI) and web-based user interface.

[0236] Methods and systems of the present disclosure can be implemented by way of one or more algorithms. An algorithm can be implemented by way of software upon execution by the central processing unit 205. The algorithm can, for example, estimate a pose of a user during a physical activity.

[0237] While preferred embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. It is not intended that the invention be limited by the specific examples provided within the specification. While the invention has been described with reference to the aforementioned specification, the descriptions and illustrations of the embodiments herein are not meant to be construed in a limiting sense. Numerous variations, changes, and substitutions will now occur to those skilled in the art without departing from the invention. Furthermore, it shall be understood that all aspects of the invention are not limited to the specific depictions, configurations or relative proportions set forth herein which depend upon a variety of conditions and variables. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention. It is therefore contemplated that the invention shall also cover any such alternatives, modifications, variations or equivalents. It is intended that the following claims define the scope of the invention and that methods and structures within the scope of these claims and their equivalents be covered thereby.

Claims

CLAIMS We Claim:

1. A computer-implemented method for providing a care pathway for a subject undergoing treatment for a complex health condition, the method comprising: a. receiving, via a user interface (UI) of a computer application, a query comprising one or more search parameters associated with a subject; b. retrieving, from a computer server, health data of said subject from an electronic health record (EHR), wherein said health data of said subject is associated with said complex health condition, wherein said health data of said subject is retrieved responsive to said query, and wherein said health data is formatted in accordance with a rule system for health care data exchange; c. processing, via the computer server, said health data of said subject using a machine learning model trained on a dataset comprising health data and validated against a validation dataset to classify or predict the care pathway to be designated to at least the subject based on the said complex health condition; d. generating a care pathway for said subject using the machine learning model to analyze said one or more aspects, wherein the care pathway is dynamically updated based on real-time health data monitoring and predictive analytics; e. assigning the care pathway to the subject by either i. a healthcare provider selecting the care pathway from the UI, or ii. the computer server dynamically assigning the care pathway via the execution of the machine learning model; f. displaying on the UI said time sequence of health procedures, wherein each procedure is represented by a graphical element, and wherein the UI includes an interactive timeline that allows for user input to adjust the care pathway; g. monitoring automatically for changes in the health data of the subject patient over time by repeating the retrieving and processing steps, wherein the monitoring includes employing a distributed computing architecture to handle the health data efficiently; and h. dynamically updating said care pathway comprising said time sequence of health procedures on said UI, based at least in part on detection of a change in said health data of said subject during the monitoring step, wherein the updating includes utilizing big data technologies for data analysis and predictive modeling.

2. The method of claim 1, wherein said UI is a graphical user interface (GUI) configured to provide adaptive visualization of the care pathway, including real-time updates to the care pathway based on the health data of the subject and predictive analytics.

3. The method of claim 2, wherein displaying said care pathway in said GUI includes visualizing the care pathway as an interactive timeline with graphical elements representing health procedures, and wherein the timeline is updated in real-time based on the processing of the health data.

4. The method of claim 3, wherein said time sequence of health procedures comprises a plurality of graphical elements, wherein said time sequence of health procedures is displayed as a timeline or graphical sequence within the UI, and wherein the time sequence of health procedures is updated with any changes to the selected care pathway, wherein the time sequence of health procedures is displayed within the UI as an adaptive visualization.

5. The method of claim 4, further comprising generating a plurality of online calendar objects corresponding to said time sequence of health procedures, assigning said plurality of online calendar objects to said subject, wherein each calendar object corresponds to a health procedure associated with the selected care pathway, and wherein each calendar object is displayed within the UI as an adaptive visualization comprising a unique graphical representation.

6. The method of claim 5, further comprising, responsive to receiving a selection of a second care pathway via said GUI, augmenting said time sequence of health procedures with a second time sequence of health procedures from said second care pathway, wherein the augmentation is performed by the computer server dynamically based on the health data of the subject.

7. The method of claim 6, further comprising, responsive to receiving a reassignment to a second care pathway via said GUI, removing a set of future events from said care pathway, and displaying said second care pathway comprising health procedures each represented by a unique graphical element with said plurality of performed health procedures removed, wherein the reassignment is performed by the computer server dynamically based on the health data of the subject.

8. The method of claim 7, wherein said reassignment is performed by requesting health data from said server, processing to dynamically assign the care pathway based on a computer vision model, a machine learning model, or a predictive model executable on a computer server, wherein the model is determinant of the portion of the care pathway that is most applicable to the health data of said subject patient, and automatically adjusting a portion of the care pathway and its associated sequence of health procedures corresponding to each updated portion of the care pathway most applicable to the health data of said subject patient following computer processing of the health data of the subject patient, and selecting a second care pathway based on said processing.

9. The method of claim 8, further comprising, prior to (c), (i) computer processing said health data using a trained machine learning model that dynamically learns via computer processing of a training data set comprising formatted health data what of the characteristics of the health data of said subject patient are most determinant to predict a particular generated portion of a care pathway, and (ii) selecting a care pathway based at least in part on said processing.

10. The method of claim 9, further comprising (iii) outputting said care pathway on said GUI; (iv) receiving a signal comprising approval of said care pathway; (v) if said signal comprises rejection of said care pathway, displaying one or more alternative care pathways; and (vi) receiving a selection of said one or more alternative care pathways, wherein the alternative care pathways are generated based on the processing of the health data using the trained machine learning model.

11. The method of claim 10, wherein said computer processing comprises using a trained machine learning model that is further validated via computer processing of a validation data set comprising formatted health data to confirm the accuracy of the predicted care pathway.

12. The method of claim 11, wherein said care pathway is editable via said GUI, and wherein editing said care pathway comprises adding or removing one or more health procedures, or modifying text associated with a health procedure, based on the processing of the health data using the trained machine learning model.

13. The method of claim 12, wherein editing said care pathway comprises adding or removing one or more health procedures, modifying text associated with a health procedure of said one or more health procedures, or changing the date associated with said one or more health procedures, wherein the modifications are informed by the processing of the health data using the trained machine learning model.

14. The method of claim 13, wherein modifying said text is performed based at least in part on at least one of demographic information of said subject, medical history of said subject, a biological sample of said subject, a location of said subject, insurance information of said subject, a location, a provider, or a date associated with a health procedure, and wherein the modifications are informed by the processing of the health data using the trained machine learning model.

15. The method of claim 14, further comprising, prior to (b), (i) retrieving, from a server, connection information associated with said EHR; and (ii) based at least in part on said connection information, directing said query to said EHR, wherein the connection information includes data formats and transmission methods used by various health data providers, and wherein the directing of the query is informed by the processing of the health data using the trained machine learning model.

16. The method of claim 15, wherein a placement of one or more health procedures of said time sequence is based at least in part on said health data of said subject, and wherein the placement is informed by the processing of the health data using the trained machine learning model.

17. The method of claim 16, wherein said care pathway is associated with at least one secondary health condition, wherein said secondary health condition has a detrimental effect on or complicates said complex health condition, and wherein the association is informed by the processing of the health data using the trained machine learning model.

18. The method of claim 17, wherein processing health data of the subject is in association with the computer vision model, machine learning model, or predictive model on a database communicatively connected to the system configured to process the health data associated with the subject patient and correspondingly recommend changes in the care pathway, wherein the processing and recommendation of changes are informed by the processing of the health data using the trained machine learning model.

19. The method of claim 18, wherein said complex health condition is a physical health condition, physiological health condition, mental health condition, or behavioral health condition, and wherein an adaptive visualization of the subject patient's care pathway corresponding to the complex health condition is depicted upon the UI, wherein the adaptive visualization is informed by the processing of the health data using the trained machine learning model.

20. The method of claim 19, wherein the processing further comprises: a. employing a distributed computing architecture to handle the health data of the subject without significant impact on performance; b. utilizing big data technologies to manage and analyze the health data; c. dynamically allocating computing resources based on current data processing demands; d. provisioning additional cloud resources to accommodate new patient data; and e. employing data caching mechanisms to store frequently accessed data in fast-access storage layers, wherein the distributed computing, big data technologies, dynamic resource allocation, cloud resources, and data caching mechanisms are configured to support the processing of the health data using the trained machine learning model.

21. The method of claim 1, further comprising: a. implementing load balancing strategies to distribute data requests evenly across the system infrastructure; b. providing immediate alerts to both patients and healthcare providers when a predefined trigger or threshold for a health condition is reached or breached; and c. employing predictive analytics to proactively suggest updates to the care pathway based on trends and patterns in the health data of the subject.

22. The method of claim 1, wherein the generating of the care pathway further comprises: a. integrating with multiple EHR systems using customized data integration protocols tailored to specific data structures and standards used by different EHR vendors; b. interfacing with various health data generation devices and services through adaptable data ingestion modules; and c. ensuring data privacy and security compliance across different healthcare settings through robust security measures.

23. The method of claim 1, wherein the monitoring automatically for changes in the health data of the subject patient over time further comprises: a. continuous synchronization with EHR systems to provide real-time updates to the care pathway; b. analyzing new health data against existing care plans considering the latest medical guidelines and evidence-based practices; and c. facilitating collaboration between patients and healthcare providers through a shared platform for care pathway management.

24. A system for managing care pathways for subjects with complex health conditions, the system comprising: a. a user interface (UI) configured to receive queries and display care pathways; b. a computer server communicatively coupled to the UI, the server having access to electronic health records (EHR) and configured to retrieve and process health data of subjects; c. a machine learning module hosted on the server, trained on a dataset comprising health data and validated against a validation dataset, the module configured to classify or predict care pathways based on the processed health data; d. a real-time monitoring component configured to automatically monitor changes in the health data and update the care pathways displayed on the UI; e. a load balancing component configured to distribute data requests across the system infrastructure; f. an alert system configured to provide immediate notifications when predefined triggers or thresholds for health conditions are reached or breached; g. a predictive analytics engine configured to analyze trends and patterns in the health data and proactively suggest updates to the care pathways; h. a data integration interface configured to interface with multiple EHR systems using customized data integration protocols; i. a data ingestion module configured to interface with various health data generation devices and services; and j . a security compliance module configured to ensure data privacy and security across different healthcare settings.

25. The system of claim 24, wherein the UI includes an interactive timeline with graphical elements representing health procedures, and the timeline is dynamically updated in real-time based on the processed health data.

26. The system of claim 24, wherein the machine learning module comprises a convolutional neural network (CNN) for pattern recognition within structured health data and a recurrent neural network (RNN) with long short-term memory (LSTM) units for analyzing temporal sequences in the health data.

27. The system of claim 24, wherein the real-time monitoring component includes a continuous synchronization mechanism with EHR systems to provide real-time updates to the care pathways.

28. The system of claim 24, wherein the load balancing component employs distributed computing architecture to handle large datasets efficiently.

29. The system of claim 24, wherein the alert system is further configured to adjust the sensitivity and specificity of notifications based on individual patient risk profiles.

30. The system of claim 24, wherein the predictive analytics engine utilizes big data technologies to manage and analyze the health data.

31. The system of claim 24, wherein the data integration interface is further configured to adapt to data formats and transmission methods used by various health data providers.

32. The system of claim 24, wherein the data ingestion module is further configured to provide a shared platform for collaboration between patients and healthcare providers for care pathway management.

33. The system of claim 24, wherein the security compliance module includes robust authentication and authorization checks for accessing sensitive patient information.

34. A method for managing care pathways for subjects with complex health conditions, the method comprising: receiving, via a user interface, a query comprising one or more search parameters associated with a subject; retrieving, from a computer server, health data of the subject from an electronic health record (EHR), wherein the health data is responsive to the query; and generating a care pathway for the subject based on the retrieved health data, wherein the care pathway provides a sequence of health procedures tailored to the subject's complex health condition.

35. The method of claim 34, wherein the care pathway is further configured to include a health data analysis module that employs artificial intelligence to identify and integrate relevant health data from disparate sources, including but not limited to genomic data, biometric data, and environmental data, to create a comprehensive and personalized care pathway for the subject.

36. The method of claim 35, wherein the health data analysis module utilizes a combination of machine learning techniques, including deep learning and natural language processing, to extract and interpret complex health data patterns, thereby enabling the dynamic adaptation of the care pathway in response to the subject's changing health condition.

37. The method of claim 34, wherein the care pathway includes a patient engagement module that facilitates interactive communication between the subject and healthcare providers, and wherein the module utilizes machine learning algorithms to tailor communication strategies based on the subject's preferences and response patterns.

38. The method of claim 37, wherein the patient engagement module is further configured to provide personalized educational content and health management tools to the subject, and wherein the content and tools are dynamically adjusted based on the subject's interaction data and health progress.

39. The method of claim 34, wherein the care pathway is configured to support a multidisciplinary approach to healthcare delivery, and wherein the pathway integrates specialized care plans from various healthcare disciplines, including but not limited to nutrition, physical therapy, and mental health, to address the holistic needs of the subject.

40. The method of claim 39, wherein the multidisciplinary approach is supported by a collaborative platform within the UI that enables seamless communication and data sharing among the healthcare team, and wherein the platform employs encryption and access control mechanisms to ensure the security and privacy of health data.

41. The method of claim 34, wherein the care pathway includes a real-time monitoring and alert system that utilizes sensor data from wearable and implantable devices to monitor the subject's health parameters, and wherein the system employs predictive analytics to provide early warnings of potential health risks.

42. The method of claim 41, wherein the real-time monitoring and alert system is further configured to automatically adjust medication dosages and treatment interventions based on the sensor data, and wherein the adjustments are validated by the healthcare provider through the UI.

43. The method of claim 34, wherein the care pathway includes a remote patient monitoring module that enables healthcare providers to track the subject's health status and adherence to the care pathway through telehealth technologies, and wherein the module is integrated with the EHR system to maintain an up-to-date health record for the subject.

44. The method of claim 43, wherein the remote patient monitoring module is further configured to utilize video conferencing and remote diagnostic tools to conduct virtual health assessments, and wherein the assessments are incorporated into the care pathway to refine treatment plans.

45. The method of claim 34, wherein the care pathway is configured to include a decision support system that provides healthcare providers with evidence-based recommendations for treatment options, and wherein the system employs a knowledge base that is continuously updated with the latest clinical research and guidelines.

46. The method of claim 45, wherein the decision support system is further configured to present a comparative analysis of treatment outcomes based on similar patient profiles, and wherein the analysis assists healthcare providers in making informed decisions tailored to the subject's specific health condition.

47. The method of claim 34, wherein the care pathway is provided with a health outcomes tracking module that collects and analyzes data on treatment efficacy and patient satisfaction, and wherein the module utilizes this data to continuously improve the quality and effectiveness of the care pathway.

48. The method of claim 47, wherein the health outcomes tracking module is further configured to generate reports that highlight key performance indicators and trends in the subject's health journey, and wherein the reports are used to inform strategic healthcare planning and resource allocation.

49. The method of claim 34, wherein the care pathway includes a compliance and adherence module that monitors the subject's engagement with the prescribed treatment plan, and wherein the module employs behavioral science principles to design interventions that promote adherence and positive health behaviors.

50. The method of claim 49, wherein the compliance and adherence module is further configured to provide personalized incentives and support mechanisms to the subject, and wherein the incentives and support are adapted based on the subject's feedback and progress within the care pathway.

51. The method of claim 34, wherein the care pathway is configured to support a valuebased care model, and wherein the pathway aligns treatment interventions with the subject's health outcomes to ensure cost-effective and high-quality care delivery.

52. The method of claim 51, wherein the value-based care model is further supported by a cost analysis tool within the UI that evaluates the economic impact of different treatment options, and wherein the tool assists healthcare providers and subjects in making cost-conscious healthcare decisions.

53. The method of claim 34, wherein the care pathway includes a risk management module that assesses the subject's risk factors for adverse health events, and wherein the module employs stratification algorithms to prioritize interventions for high-risk subjects.

54. The method of claim 53 wherein the risk management module is further configured to develop personalized risk mitigation plans for the subject, and wherein the plans are integrated into the care pathway to proactively address potential health challenges.

55. The method of claim 34, wherein the care pathway is provided with a continuity of care module that ensures seamless transitions between different levels of care, such as from acute care to rehabilitation or home care, and wherein the module coordinates the exchange of health information among care settings to maintain a consistent and comprehensive care experience for the subject.

56. The method of claim 55, wherein the continuity of care module is further configured to involve the subject and their caregivers in the care transition process, and wherein the involvement includes providing education and resources to support self-management and recovery.

57. The method of claim 34, wherein the care pathway includes a quality of life assessment module that evaluates the subject's physical, emotional, and social wellbeing, and wherein the module employs patient-reported outcome measures to capture the subject's perspective on their health status and quality of life.

58. The method of claim 57, wherein the quality of life assessment module is further configured to integrate the assessment results into the care pathway, and wherein the integration informs the personalization of care to enhance the subject's overall wellbeing and satisfaction with their healthcare experience.

59. The method of claim 34, wherein the care pathway is configured to include a population health module that analyzes aggregated health data from a community or population group, and wherein the module identifies patterns and trends that inform public health interventions and policies.

60. The method of claim 59, wherein the population health module is further configured to support community health initiatives, and wherein the initiatives leverage the insights gained from the aggregated health data to address social determinants of health and reduce health disparities within the population.

61. The method of claim 34, wherein the care pathway includes a clinical research integration module that facilitates the subject's participation in clinical trials and research studies, and wherein the module matches the subject with appropriate research opportunities based on their health data and care pathway.

62. The method of claim 61, wherein the clinical research integration module is further configured to streamline the consent process for research participation, and wherein the module ensures that the subject's rights and preferences are respected throughout the research engagement.

63. The method of claim 34, wherein the care pathway is provided with a health innovation module that incorporates emerging healthcare technologies and treatments into the care pathway, and wherein the module evaluates the safety, efficacy, and applicability of these innovations for the subject's care.

64. The method of claim 63, wherein the health innovation module is further configured to foster collaboration between healthcare providers, researchers, and technology developers, and wherein the collaboration aims to accelerate the translation of innovative solutions into clinical practice.

65. The method of claim 34, wherein the care pathway includes a health literacy enhancement module that provides the subject with accessible and understandable health information, and wherein the module empowers the subject to make informed decisions about their healthcare.

66. The method of claim 65, wherein the health literacy enhancement module is further configured to offer interactive learning tools and resources, and wherein the tools and resources are tailored to the subject's learning preferences and health literacy level.

67. The method of claim 34, wherein the care pathway is configured to support a personalized medicine approach, and wherein the pathway incorporates genetic and molecular information to customize treatments to the subject's unique biological characteristics.

68. The method of claim 67, wherein the personalized medicine approach is further supported by a precision diagnostics module within the UI that provides healthcare providers with advanced tools for identifying biomarkers and genetic variants that influence the subject's response to treatment.

69. The method of claim 34, wherein the care pathway includes a health ecosystem integration module that connects the subject with a network of healthcare services and resources, and wherein the module facilitates access to a wide range of care options that complement the subject's care pathway.

70. The method of claim 69, wherein the health ecosystem integration module is further configured to provide a centralized platform for managing appointments, referrals, and follow-up care, and wherein the platform streamlines the coordination of services across the healthcare ecosystem.

71. The method of claim 34, wherein the care pathway is provided with a digital health engagement module that leverages digital platforms and social networks to enhance the subject's engagement with their health management, and wherein the module utilizes data analytics to optimize engagement strategies.

72. The method of claim 71, wherein the digital health engagement module is further configured to offer virtual health communities and support groups, and wherein the communities and groups provide peer support and shared learning experiences for subjects with similar health conditions.

73. The method of claim 34, wherein the care pathway includes a health data consent management module that enables the subject to control the sharing and use of their health data, and wherein the module provides transparent and user-friendly mechanisms for managing data consent preferences.

74. The method of claim 73, wherein the health data consent management module is further configured to comply with data protection regulations, and wherein the module ensures that the subject's health data is handled in a secure and ethical manner.

75. The method of claim 34, wherein the care pathway is configured to include a health data linkage module that connects the subject's health data from various sources, including wearable devices, home monitoring systems, and patient portals, to create an integrated health profile.

76. The method of claim 75, wherein the health data linkage module is further configured to utilize interoperability standards to facilitate the seamless exchange of health data, and wherein the module enhances the continuity and coordination of care for the subject.

77. The method of claim 34, wherein the care pathway includes a health data analytics module that applies machine learning and artificial intelligence to analyze the subject's health data, and wherein the module generates insights that inform the optimization of the care pathway.

78. The method of claim 77, wherein the health data analytics module is further configured to identify patterns and correlations within the health data, and wherein the module provides predictive modeling to anticipate the subject's future health needs.

79. The method of claim 34, wherein the care pathway is provided with a health data visualization module that presents the subject's health data in a visually engaging and informative manner, and wherein the module aids in the comprehension and interpretation of complex health information.

80. The method of claim 79, wherein the health data visualization module is further configured to offer customizable dashboards and interactive charts, and wherein the dashboards and charts enable healthcare providers and subjects to visualize health trends and treatment progress.

81. The method of claim 34, wherein the care pathway includes a health data security module that implements robust cybersecurity measures to protect the subject's health data from unauthorized access and breaches, and wherein the module ensures the integrity and confidentiality of the data.

82. The method of claim 81, wherein the health data security module is further configured to monitor and respond to security threats in real-time, and wherein the module employs advanced encryption and authentication technologies to safeguard the health data.

83. The method of claim 34, wherein the care pathway is configured to include a health data governance module that establishes policies and standards for the management of the subject's health data, and wherein the module ensures that data practices align with ethical and legal requirements.

84. The method of claim 83, wherein the health data governance module is further configured to oversee data quality and accuracy, and wherein the module implements data stewardship principles to maintain the trustworthiness of the health data.

85. The method of claim 34, wherein the care pathway includes a health data interoperability module that enables the subject's health data to be exchanged and utilized across different healthcare systems and platforms, and wherein the module promotes the seamless flow of information to support integrated care.

86. The method of claim 85, wherein the health data interoperability module is further configured to adhere to industry standards for data exchange, such as HL7 FHIR, and wherein the module facilitates the aggregation and analysis of health data for improved clinical decision-making.

87. The method of claim 34, wherein the care pathway is provided with a health data consent module that empowers the subject to make informed decisions about the sharing and use of their health data, and wherein the module provides clear and accessible options for managing consent.

88. The method of claim 87, wherein the health data consent module is further configured to support dynamic consent models, and wherein the module allows the subject to adjust their consent preferences in response to changes in their health condition or treatment plan.

89. The method of claim 34, wherein the care pathway includes a health data quality module that ensures the reliability and validity of the subject's health data, and wherein the module employs data verification and validation processes to enhance data integrity.

90. The method of claim 89, wherein the health data quality module is further configured to implement data cleaning and standardization techniques, and wherein the module improves the consistency and comparability of health data for accurate care pathway generation.

91. The method of claim 34, wherein the care pathway is configured to include a health data exchange module that facilitates the transfer of health data between the subject, healthcare providers, and authorized third parties, and wherein the module ensures secure and efficient data sharing.

92. The method of claim 91, wherein the health data exchange module is further configured to support data sharing agreements and collaborations, and wherein the module enables the participation of the subject in health information exchanges and research networks.

93. The method of claim 34, wherein the care pathway includes a health data consent management module that provides the subject with control over their health data, and wherein the module incorporates mechanisms for obtaining, recording, and managing consent for data use.

94. The method of claim 93, wherein the health data consent management module is further configured to comply with regulatory frameworks such as GDPR and HIPAA, and wherein the module ensures that consent practices meet legal and ethical standards.

95. The method of claim 34, wherein the care pathway is provided with a health data linkage module that connects the subject's health data from multiple sources to create a unified health profile, and wherein the module leverages data linkage to enhance the continuity of care.

96. The method of claim 95, wherein the health data linkage module is further configured to utilize data mapping and matching techniques, and wherein the module aligns disparate data sets to provide a comprehensive view of the subject's health.

97. The method of claim 34, wherein the care pathway includes a health data analytics module that applies advanced data analysis techniques to the subject's health data, and wherein the module generates actionable insights to inform care pathway adjustments.

98. The method of claim 97, wherein the health data analytics module is further configured to perform predictive modeling and risk assessment, and wherein the module identifies potential health risks and suggests preventive measures within the care pathway.

99. The method of claim 34, wherein the care pathway is provided with a health data visualization module that presents the subject's health data in an engaging and informative format, and wherein the module aids in the visualization of health trends and care pathway progress.

100. The method of claim 99, wherein the health data visualization module is further configured to offer interactive data displays and infographics, and wherein the module enhances the subject's and healthcare provider's understanding of the health data.

101. The method of claim 34, wherein the care pathway includes a health data security module that implements measures to protect the subject's health data from unauthorized access and breaches, and wherein the module ensures the confidentiality and integrity of the data.

102. The method of claim 101, wherein the health data security module is further configured to monitor for security threats and vulnerabilities, and wherein the module employs encryption and access controls to safeguard the health data.

103. The method of claim 34, wherein the care pathway is configured to include a health data governance module that establishes policies for the management of the subject's health data, and wherein the module ensures that data practices are ethical and compliant with regulations.

104. The method of claim 103, wherein the health data governance module is further configured to oversee data quality and consistency, and wherein the module implements data stewardship to maintain the trustworthiness of the health data.

105. The method of claim 34, wherein the care pathway includes a health data interoperability module that enables the subject's health data to be utilized across different healthcare systems and platforms, and wherein the module promotes the seamless flow of information for integrated care.

106. The method of claim 105, wherein the health data interoperability module is further configured to adhere to data exchange standards, and wherein the module facilitates the aggregation and analysis of health data for improved clinical decision-making.

107. The method of claim 34, wherein the care pathway is provided with a health data consent module that empowers the subject to make informed decisions about the sharing and use of their health data, and wherein the module provides transparent options for managing consent preferences.

108. The method of claim 107, wherein the health data consent module is further configured to support dynamic consent models, and wherein the module allows the subject to adjust their consent preferences in response to changes in their health condition or care pathway.

109. A system for managing care pathways for subjects with complex health conditions, comprising: a user interface (UI) configured to receive queries comprising one or more search parameters associated with a subject; a computer server communicatively coupled to the UI, the server having access to electronic health records (EHR) and configured to retrieve and process health data of subjects; a machine learning module hosted on the server, trained on a dataset comprising health data and validated against a validation dataset, the module configured to classify or predict care pathways based on the processed health data; a real-time monitoring component configured to automatically monitor changes in the health data and update the care pathways displayed on the UI; a predictive analytics engine hosted on the server, configured to analyze the health data and provide recommendations for care pathway adjustments; a data integration interface on the server, configured to interface with multiple EHR systems and aggregate health data for the subject; a data ingestion module configured to interface with health data generation devices and services; a security compliance module configured to ensure data privacy and security compliance across different healthcare settings.

110. The system of claim 109, wherein the UI is further configured to display the care pathway as a timeline comprising a sequence of graphical elements representing health procedures, and wherein the timeline is dynamically updated in real-time based on the subject's health data.

111. The system of claim 109, wherein the machine learning module includes a convolutional neural network (CNN) for image data analysis and a recurrent neural network (RNN) with long short-term memory (LSTM) units for processing time-series health data.

112. The system of claim 109, wherein the machine learning module is further configured to dynamically learn from the subject's ongoing health data and adapt the care pathway predictions based on the subject's response to treatment.

113. The system of claim 109, wherein the real-time monitoring component includes sensors for collecting health data from wearable and implantable devices, and the system is configured to trigger alerts based on predefined health condition thresholds.

114. The system of claim 109, wherein the predictive analytics engine is further configured to utilize big data technologies to manage and analyze large volumes of health data from the subject and similar patient profiles.

115. The system of claim 109, wherein the data integration interface is customized to adapt to specific data structures and standards used by different EHR vendors, facilitating seamless data exchange and integration.

116. The system of claim 109, wherein the data ingestion module is adaptable to various health data generation devices and services through configurable data ingestion protocols.

117. The system of claim 109, wherein the security compliance module includes robust authentication and authorization checks for accessing sensitive patient information and is configured to comply with regulatory standards such as HIPAA and GDPR.

118. The system of claim 109, wherein the UI is further configured to provide a shared platform for collaboration between patients and healthcare providers for care pathway management, including communication tools and access to educational content.

119. The system of claim 109, wherein the UI includes an interactive module for patient engagement, configured to facilitate communication between the subject and healthcare providers using tailored strategies based on machine learning analysis of the subject's preferences.

120. The system of claim 109, wherein the UI is further configured to provide a decision support system that offers healthcare providers evidence-based treatment options and recommendations, which are continuously updated based on the latest clinical research.

121. The system of claim 109, wherein the UI includes a health outcomes tracking module that collects and analyzes data on treatment efficacy and patient satisfaction, utilizing this data to inform continuous improvement of the care pathway.

122. The system of claim 109, wherein the UI includes a compliance and adherence module that monitors the subject's engagement with the treatment plan and employs behavioral science principles to design interventions that promote adherence.

123. The system of claim 109, wherein the UI supports a value-based care model by aligning treatment interventions with the subject's health outcomes and includes a cost analysis tool for evaluating the economic impact of treatment options.

124. The system of claim 109, wherein the UI includes a risk management module that assesses the subject's risk factors for adverse health events and employs stratification algorithms to prioritize interventions for high-risk subjects.

125. The system of claim 109, wherein the UI includes a continuity of care module that ensures seamless transitions between different levels of care and coordinates the exchange of health information among care settings.

126. The system of claim 109, wherein the UI includes a quality of life assessment module that evaluates the subject's well-being using patient-reported outcome measures and integrates the assessment results into the care pathway.

127. The system of claim 109, wherein the UI includes a population health module that analyzes aggregated health data to identify patterns and trends that inform public health interventions and policies.

128. The system of claim 109, wherein the UI includes a clinical research integration module that facilitates the subject's participation in clinical trials and research studies based on their health data and care pathway.

129. The system of claim 109, wherein the UI includes a health innovation module that incorporates emerging healthcare technologies and treatments into the care pathway and evaluates their safety, efficacy, and applicability.

130. The system of claim 109, wherein the UI includes a health literacy enhancement module that provides the subject with accessible and understandable health information and offers interactive learning tools and resources.

131. The system of claim 109, wherein the UI supports a personalized medicine approach by incorporating genetic and molecular information into the care pathway and includes a precision diagnostics module for healthcare providers.

132. The system of claim 109, wherein the UI includes a health ecosystem integration module that connects the subject with a network of healthcare services and resources and provides a centralized platform for managing appointments and care coordination.

133. The system of claim 109, wherein the UI includes a digital health engagement module that leverages digital platforms and social networks to enhance the subject's engagement with their health management and utilizes data analytics to optimize engagement strategies.

134. The system of claim 109, wherein the UI includes a health data consent management module that enables the subject to control the sharing and use of their health data and provides mechanisms for managing data consent preferences.

135. The system of claim 109, wherein the UI includes a health data linkage module that connects the subject's health data from various sources to create an integrated health profile and leverages data linkage to enhance the continuity of care.

136. The system of claim 109, wherein the UI includes a health data analytics module that applies machine learning and artificial intelligence to analyze the subject's health data and generates insights that inform the optimization of the care pathway.

137. The system of claim 109, wherein the UI includes a health data visualization module that presents the subject's health data in an engaging and informative format and aids in the visualization of health trends and care pathway progress.

138. The system of claim 109, wherein the UI includes a health data security module that implements robust cybersecurity measures to protect the subject's health data from unauthorized access and breaches.

139. The system of claim 109, wherein the UI includes a health data governance module that establishes policies for the management of the subject's health data and ensures that data practices are ethical and compliant with regulations.

140. The system of claim 109, wherein the UI includes a health data interoperability module that enables the subject's health data to be utilized across different healthcare systems and platforms and promotes the seamless flow of information for integrated care.

141. The system of claim 109, wherein the UI includes a health data consent module that empowers the subject to make informed decisions about the sharing and use of their health data and provides transparent options for managing consent preferences.

142. The system of claim 109, wherein the UI includes a health data quality module that ensures the reliability and validity of the subject's health data and employs data verification and validation processes to enhance data integrity.

143. The system of claim 109, wherein the UI includes a health data exchange module that facilitates the transfer of health data between the subject, healthcare providers, and authorized third parties and ensures secure and efficient data sharing.

144. The system of claim 109, wherein the UI includes a health data consent management module that provides the subject with control over their health data and incorporates mechanisms for obtaining, recording, and managing consent for data use.

145. The system of claim 109, wherein the UI includes a health data linkage module that connects the subject's health data from multiple sources to create a unified health profile and leverages data linkage to enhance the continuity of care.

146. The system of claim 109, wherein the UI includes a health data analytics module that applies advanced data analysis techniques to the subject's health data and generates actionable insights to inform care pathway adjustments.

147. The system of claim 109, wherein the UI includes a health data visualization module that presents the subject's health data in an engaging and informative format and aids in the visualization of health trends and care pathway progress.

148. The system of claim 109, wherein the UI includes a health data security module that implements measures to protect the subject's health data from unauthorized access and breaches.

149. The system of claim 109, wherein the UI includes a health data governance module that establishes policies for the management of the subject's health data and ensures that data practices are ethical and compliant with regulations.

150. The system of claim 109, wherein the UI includes a health data interoperability module that enables the subject's health data to be utilized across different healthcare systems and platforms and promotes the seamless flow of information for integrated care.

151. The system of claim 109, wherein the UI includes a health data consent module that empowers the subject to make informed decisions about the sharing and use of their health data and provides transparent options for managing consent preferences.

152. The system of claim 109, wherein the UI includes a health data quality module that ensures the reliability and validity of the subject's health data and employs data verification and validation processes to enhance data integrity.

153. The system of claim 109, wherein the UI includes a health data exchange module that facilitates the transfer of health data between the subject, healthcare providers, and authorized third parties and ensures secure and efficient data sharing.

154. The system of claim 109, wherein the UI includes a health data consent management module that provides the subject with control over their health data and incorporates mechanisms for obtaining, recording, and managing consent for data use.

155. The system of claim 109, wherein the UI includes a health data linkage module that connects the subject's health data from multiple sources to create a unified health profile and leverages data linkage to enhance the continuity of care.

156. The system of claim 109, wherein the UI includes a health data analytics module that applies advanced data analysis techniques to the subject's health data and generates actionable insights to inform care pathway adjustments.

157. The system of claim 109, wherein the UI includes a health data visualization module that presents the subject's health data in an engaging and informative format and aids in the visualization of health trends and care pathway progress.

158. The system of claim 109, wherein the UI includes a health data security module that implements measures to protect the subject's health data from unauthorized access and breaches.

159. The system of claim 109, wherein the UI includes a health data governance module that establishes policies for the management of the subject's health data and ensures that data practices are ethical and compliant with regulations.

160. The system of claim 109, wherein the UI includes a health data interoperability module that enables the subject's health data to be utilized across different healthcare systems and platforms and promotes the seamless flow of information for integrated care.

161. The system of claim 109, wherein the UI includes a health data consent module that empowers the subject to make informed decisions about the sharing and use of their health data and provides transparent options for managing consent preferences.

162. The system of claim 109, wherein the UI includes a health data quality module that ensures the reliability and validity of the subject's health data and employs data verification and validation processes to enhance data integrity.

163. The system of claim 109, wherein the UI includes a health data exchange module that facilitates the transfer of health data between the subject, healthcare providers, and authorized third parties and ensures secure and efficient data sharing.

164. The system of claim 109, wherein the UI includes a health data consent management module that provides the subject with control over their health data and incorporates mechanisms for obtaining, recording, and managing consent for data use.

165. The system of claim 109, wherein the UI includes a health data linkage module that connects the subject's health data from multiple sources to create a unified health profile and leverages data linkage to enhance the continuity of care.

166. The system of claim 109, wherein the UI includes a health data analytics module that applies advanced data analysis techniques to the subject's health data and generates actionable insights to inform care pathway adjustments.

167. The system of claim 109, wherein the UI includes a health data visualization module that presents the subject's health data in an engaging and informative format and aids in the visualization of health trends and care pathway progress.

168. The system of claim 109, wherein the UI includes a health data security module that implements measures to protect the subject's health data from unauthorized access and breaches.

169. The system of claim 109, wherein the UI includes a health data governance module that establishes policies for the management of the subject's health data and ensures that data practices are ethical and compliant with regulations.

170. The system of claim 109, wherein the UI includes a health data interoperability module that enables the subject's health data to be utilized across different healthcare systems and platforms and promotes the seamless flow of information for integrated care.

171. The system of claim 109, wherein the UI includes a health data consent module that empowers the subject to make informed decisions about the sharing and use of their health data and provides transparent options for managing consent preferences.

172. The system of claim 109, wherein the UI includes a health data quality module that ensures the reliability and validity of the subject's health data and employs data verification and validation processes to enhance data integrity.

173. The system of claim 109, wherein the UI includes a health data exchange module that facilitates the transfer of health data between the subject, healthcare providers, and authorized third parties and ensures secure and efficient data sharing.

174. The system of claim 109, wherein the UI includes a health data consent management module that provides the subject with control over their health data and incorporates mechanisms for obtaining, recording, and managing consent for data use.

175. The system of claim 109, wherein the UI includes a health data linkage module that connects the subject's health data from multiple sources to create a unified health profile and leverages data linkage to enhance the continuity of care.

176. The system of claim 109, wherein the UI includes a health data analytics module that applies advanced data analysis techniques to the subject's health data and generates actionable insights to inform care pathway adjustments.

177. The system of claim 109, wherein the UI includes a health data visualization module that presents the subject's health data in an engaging and informative format and aids in the visualization of health trends and care pathway progress.

178. The system of claim 109, wherein the UI includes a health data security module that implements measures to protect the subject's health data from unauthorized access and breaches.

179. The system of claim 109, wherein the UI includes a health data governance module that establishes policies for the management of the subject's health data and ensures that data practices are ethical and compliant with regulations.

180. The system of claim 109, wherein the UI includes a health data interoperability module that enables the subject's health data to be utilized across different healthcare systems and platforms and promotes the seamless flow of information for integrated care.

181. The system of claim 109, wherein the UI includes a health data consent module that empowers the subject to make informed decisions about the sharing and use of their health data and provides transparent options for managing consent preferences.

182. The system of claim 109, wherein the UI includes a health data quality module that ensures the reliability and validity of the subject's health data and employs data verification and validation processes to enhance data integrity.

183. The system of claim 109, wherein the UI includes a health data exchange module that facilitates the transfer of health data between the subject, healthcare providers, and authorized third parties and ensures secure and efficient data sharing.

184. The system of claim 109, wherein the UI includes a health data consent management module that provides the subject with control over their health data and incorporates mechanisms for obtaining, recording, and managing consent for data use.

185. The system of claim 109, wherein the UI includes a health data linkage module that connects the subject's health data from multiple sources to create a unified health profile and leverages data linkage to enhance the continuity of care.

186. The system of claim 109, wherein the UI includes a health data analytics module that applies advanced data analysis techniques to the subject's health data and generates actionable insights to inform care pathway adjustments.

187. The system of claim 109, wherein the UI includes a health data visualization module that presents the subject's health data in an engaging and informative format and aids in the visualization of health trends and care pathway progress.

188. The system of claim 109, wherein the UI includes a health data security module that implements measures to protect the subject's health data from unauthorized access and breaches.

189. The system of claim 188, wherein the UI includes a health data governance module that establishes policies for the management of the subject's health data and ensures that data practices are ethical and compliant with regulations.

190. The system of claim 109, wherein the UI includes a health data interoperability module that enables the subject's health data to be utilized across different healthcare systems and platforms and promotes the seamless flow of information for integrated care.

191. The system of claim 109, wherein the UI includes a health data consent module that empowers the subject to make informed decisions about the sharing and use of their health data and provides transparent options for managing consent preferences.

192. The system of claim 109, wherein the UI includes a health data quality module that ensures the reliability and validity of the subject's health data and employs data verification and validation processes to enhance data integrity.

193. The system of claim 109, wherein the UI includes a health data exchange module that facilitates the transfer of health data between the subject, healthcare providers, and authorized third parties and ensures secure and efficient data sharing.

194. The system of claim 109, wherein the UI includes a health data consent management module that provides the subject with control over their health data and incorporates mechanisms for obtaining, recording, and managing consent for data use.

195. The system of claim 109, wherein the UI includes a health data linkage module that connects the subject's health data from multiple sources to create a unified health profile and leverages data linkage to enhance the continuity of care.

196. The system of claim 109, wherein the UI includes a health data analytics module that applies advanced data analysis techniques to the subject's health data and generates actionable insights to inform care pathway adjustments.

197. The system of claim 109, wherein the UI includes a health data visualization module that presents the subject's health data in an engaging and informative format and aids in the visualization of health trends and care pathway progress.

198. The system of claim 109, wherein the UI includes a health data security module that implements measures to protect the subject's health data from unauthorized access and breaches.