Computer-implemented dashboard providing dynamic digital health care data

Abstract

A computer-implemented dashboard for providing digital healthcare data is generated by a computer system as a user interface for display on a display device operatively coupled to the computer system. A computer system generates a first map that includes genetic and / or epigenetic and / or other marker test results of a patient determined by performing a genetic and / or epigenetic and / or other marker test on genetic and / or epigenetic and / or other markers obtained from the patient to assess whether the patient has a disease. Genetic and / or epigenetic and / or other marker test results of the patient population to which the patient belongs are overlaid on the plot. Genetic and / or epigenetic and / or other marker test results of a population of patients are obtained from a queue test of genetic and / or epigenetic and / or other marker tests performed on the patients. A user interface is displayed on a display device. The first drawing is displayed within a user interface.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to computer-implemented methods, computer-readable media, and computer systems for generating computing resources for health, wellness, and other data for an individual, such as a patient, and displaying the generated computing resources in a display device for review by the patient or others. BACKGROUND

[0002] Information for review by a patient, a healthcare provider (e.g., clinician, physician), an employer, a health plan, a life insurance company, and a drug developer (e.g., pharmaceutical company) can vary based on their particular needs and backgrounds. Generally, one or more individuals viewing digital data, for example, on a display device of a computer system, are interested in obtaining comparative information and / or more detail associated with the data, allowing the individuals to make informed decisions regarding potential healthcare issues, priorities, costs, risks and risk mitigation actions, management, interventions (e.g., treatments), and monitoring addressed by the data. SUMMARY

[0003] This specification describes technologies relating to computer-implemented methods, computer-readable media, and computer systems for generating and displaying dashboards to provide digital data.

[0004] In one aspect, a method is provided that includes generating, by a computer system, a user interface for display on a display device operatively coupled to the computer system, generating, by the computer system, first data including genetic, epigenetic, and / or other biomarker test results for a patient to evaluate whether the patient has a disease, disorder, or risk, displaying the user interface on the display device, and displaying the first data within the user interface.

[0005] In some embodiments, the data is selected from: measurements (e.g., weight, blood pressure, etc.), test results (e.g., genetic, epigenetic, protein, metabolic assays, etc.), financial (e.g., cost of surgery, cost of medication, cost of claim, etc.), industry / prevalence (e.g., heart disease prevalence in a particular geographic region, number of heart attacks per year for truck drivers, etc.), interventions (e.g., surgery, etc.), medical (e.g., ICD10 codes, medication usage, etc.), clinical (e.g., blood pressure, etc.), therapeutic (e.g., statin cost, anti-inflammatory medication, etc.), lifestyle (e.g., smoking, drinking, exercise frequency, etc.), supplement usage (e.g., herbal, vitamin D, vitamin B12, iron, etc.), electronic data (e.g., imaging, electronic health records, publicly available data (e.g., repositories, etc.), publications, pharmaceuticals, clinical trials, etc.), and diagnostic, intervention, management, monitoring, and / or therapeutic implications thereof. In some embodiments, the data includes independent data, aggregated data, imputed data, derived data, numerical data, textual data, image data, and combinations thereof.

[0006] In some embodiments, the data is displayed in the user interface in one or more plots. In some embodiments, the data is compared to corresponding genetic, epigenetic, and / or other biomarker test results from a cohort population. In some embodiments, the data is overlaid on the genetic, epigenetic, and / or other biomarker test results of the population.

[0007] In some embodiments, the user interface displays diagnostic information, prognostic information, uncertainty quantification, clinical and / or business risk management or decision making, regulatory and / or policy making, intervention, monitoring, and / or therapeutic decisions and strategies related to the patient or group of patients or the user or group of users.

[0008] In some embodiments, the genetic, epigenetic, and / or other biomarker test results of the patient population include a bar chart showing age of the patient population on the X-axis and probability of patients of different ages having the disease, disorder, or risk on the Y-axis, wherein the test results of the patient include the probability of the patient having the disease.

[0009] In some embodiments, the patient is associated with an age, wherein the method further includes displaying the probability of the patient having the disease adjacent to the probability of a population of patients of the same age as the patient.

[0010] In some embodiments, the patient is associated with a gender, wherein the method further includes displaying the probability of the patient having the disease adjacent to the probability of a population of patients of the same gender as the patient.

[0011] In some embodiments, the method further comprises: receiving a ranking of the plurality of genetic, epigenetic, and / or other biomarkers for their contribution to the presence of the disease in the patient; generating a chart comprising the names of the plurality of markers on the X-axis and the normalized ranking of the plurality of genetic, epigenetic, and / or other biomarkers for their contribution to the patient; superimposing the chart with another chart showing the normalized ranking of the plurality of genetic, epigenetic, and / or other biomarkers for their contribution to a population of patients to obtain a second plot of the relationship of the ranking to the markers; and displaying the second plot adjacent to the plot within the user interface.

[0012] In some embodiments, the method further comprises: generating a plot of the distribution of genetic, epigenetic, and / or other biomarker measurements associated with a particular genetic, epigenetic, and / or other biomarker; superimposing the measured genetic, epigenetic, and / or other biomarker measurements for the patient on the plot; and displaying the plot with the superimposed genetic, epigenetic, and / or other biomarker measurements within the user interface.

[0013] In some embodiments, the method further comprises: determining an upper and lower bound of uncertainty associated with the measured genetic, epigenetic, and / or other biomarker measurements for the patient; and displaying the upper and lower bounds defining the genetic, epigenetic, and / or other biomarker measurements within the plot.

[0014] In some embodiments, the method further comprises: detecting a selection of data displayed within the user interface; in response to detecting the selection, displaying a window adjacent to the data within the user interface; and displaying a hyperlink to additional information within the window.

[0015] In some embodiments, the additional information comprises literature related to the genetic, epigenetic, and / or other biomarker test results or literature related to the disease, disorder, or risk.

[0016] In some embodiments, the literature is selected from publications, clinical data, clinical trials, and pharmaceuticals.

[0017] In another aspect, there is provided a computer-readable medium storing computer instructions that, when executed by one or more computer processors, are configured to cause the one or more computer processors to perform operations comprising any of the methods described herein.

[0018] In yet another aspect, a computer system is provided, the computer system comprising: one or more computer processors; and a computer-readable medium storing computer instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising any of the methods described herein.

[0019] The term "genome" as used herein refers to the totality of an organism's genetic information, encoded in its primary DNA sequence. The genome includes both genes and non-coding sequences. For example, the genome can represent a microbial genome or a mammalian genome.

[0020] "Nucleic acid," "oligonucleotide," and "polynucleotide" refer to deoxyribonucleic acid (DNA) or ribonucleic acid (RNA) and polymers thereof in either single- or double-stranded form. Unless specifically limited, the term encompasses nucleic acids containing known analogues of natural nucleotides which have similar binding properties as the reference nucleic acid. The term nucleic acid is used interchangeably with genetic material, cDNA, mRNA, and gene.

[0021] Reference to a "DNA region" is understood to refer to a specific segment of DNA. These DNA regions are specified by reference to a gene name, a set of chromosomal coordinates, or a reference single nucleotide polymorphism (SNP). Both chromosomal coordinates and gene or genomic regions are well known and understood by those skilled in the art. In general, a gene or genomic region can be routinely determined by reference to its name (from which both its sequence and chromosomal location can be routinely obtained), by reference to its chromosomal coordinates (from which both the gene or genomic region name and its sequence can be routinely obtained), or by sequence (from which both gene and genomic regions can be routinely obtained).

[0022] Reference to each of the genes / DNA regions detailed herein is understood to refer to all forms of these molecules and fragments or variants thereof. As will be appreciated by those skilled in the art, some genes are known to exhibit allelic variation. Allelic variation encompasses single nucleotide polymorphisms, insertions and deletions of varying sizes, and simple sequence repeats such as di- and tri-nucleotide repeats. Variants include nucleic acid sequences from the same region that share at least 90%, 95%, 98%, 99% sequence identity (i.e., have one or more deletions, additions, substitutions, inverted sequences, etc. relative to the DNA regions described herein). Thus, the compositions and methods described herein are understood to extend to such variants. Thus, the compositions and methods described herein are understood to extend to all forms of DNA resulting from any other mutation, polymorphism, or allelic variation.

[0023] As used herein, the term "sequencing" refers to a sequencing method used to determine the precise sequence of nucleotide bases (e.g., adenine, guanine, cytosine, and thymine) in a nucleic acid molecule (e.g., DNA or RNA nucleic acid molecule). The term includes any method or technique used to determine the sequence of four bases in a DNA strand.

[0024] As used in this article, the term "barcode" refers to any unique, non-naturally occurring nucleic acid sequence that can be used to identify nucleic acid molecules.

[0025] Real-time, derived, and predictive data (e.g., collected from samples, electronic health records, devices, etc.) can be collected and stored, and thus become historical data for current or future decision-making regarding processes, settings, or applications.

[0026] A "computer-readable medium" is an information storage medium that can be accessed by a computer using a commercially available or custom-made interface. Exemplary computer-readable media include memory (e.g., RAM, ROM, flash memory, etc.), optical storage media (e.g., CD-ROM), magnetic storage media (e.g., computer hard disk drives, floppy disks, etc.), punched cards, or other commercially available media. Information can be transferred between a computer system and the medium, between computer systems, or between a computer system and the computer-readable medium for the purpose of storing or accessing the stored information. Such transfer can be electrical or via other available methods, such as an IR link, wireless connection, etc.

[0027] Where a range of values ​​is provided, it should be understood that every intermediate value between the upper and lower limits of that range, as well as any other stated value or intermediate value within that range, is covered herein. It will be understood that test results, data, measurements, and biomarkers (or markers) are used interchangeably. For example, a measurement may be obtained from or measured by a patient (e.g., genetic biomarkers, epigenetic biomarkers, inflammatory biomarkers, lipids, weight, etc.). For example, a biomarker may be measurable (e.g., percentage of methylation) or may be represented by binary data (e.g., yes or no; present or absent; adenine (A) or guanine (G)). For example, data may include one or more measurements from, for example, test results, biomarker information (e.g., measured or binary), lifestyle information (e.g., lifestyle (e.g., smoker, drinker), medication or supplement use, etc.), and / or any number of other information sources (e.g., from public databases, publications, insurance claims, demographic data, costs or cost estimates, etc.).

[0028] Details of one or more implementations of the subject matter described in this specification are set forth in the accompanying drawings and the following description. Further features, aspects, and advantages of the subject matter will become clear from the description, drawings, and claims. BRIEF DESCRIPTION OF DRAWINGS

[0029] Figure 1 is a schematic diagram of a computer system configured to display a dashboard described in the present disclosure.

[0030] FIG. 2 is an example user interface that can be displayed in a display device.

[0031] FIG. 3 is an example user interface that can be displayed in a display device.

[0032] FIG. 4 is an example user interface that can be displayed in a display device.

[0033] FIG. 5 is an example user interface that can be displayed in a display device.

[0034] FIG. 6 is an example user interface that can be displayed in a display device.

[0035] FIG. 7 is an example user interface that can be displayed in a display device.

[0036] FIG. 8 is an example user interface that can be displayed in a display device.

[0037] FIG. 9 is an example user interface that can be displayed in a display device.

[0038] FIG. 10 is an example user interface that can be displayed in a display device.

[0039] FIG. 11 is an example user interface that can be displayed in a display device.

[0040] FIG. 12 is an example user interface that can be displayed in a display device.

[0041] FIG. 13 is an example user interface that can be displayed in a display device.

[0042] FIG. 14 is an example user interface that can be displayed in a display device.

[0043] FIG. 15 is an example user interface that can be displayed in a display device.

[0044] FIG. 16 is an example user interface that can be displayed in a display device.

[0045] FIG. 17 is an example user interface that can be displayed in a display device.

[0046] FIG. 18 is an example user interface that can be displayed in a display device.

[0047] FIG. 19 is an example user interface that can be displayed in a display device.

[0048] FIG. 20 is a block diagram showing an example computer system for providing computing functionality associated with the algorithms, methods, functions, processes, flows, and procedures described in the present disclosure, according to some implementations of the present disclosure.

[0049] Like reference numbers and designations in the various drawings indicate like elements. DETAILED DESCRIPTION

[0050] The present disclosure describes a platform through which an individual (e.g., a patient), a clinician (e.g., a physician, a nurse practitioner), or another user (e.g., a pharmacist, a researcher, an employer, an insurer) can receive and understand independent or aggregated information relating to: measurements (e.g., weight, blood pressure, etc.), test results (e.g., genetic, epigenetic, protein, metabolic assays, etc.), financial (e.g., cost of surgery, cost of medication, cost of claim, etc.), industry / prevalence (e.g., heart disease prevalence in a particular geographic region, number of heart attacks per year for truck drivers, etc.), interventions (e.g., surgery, etc.), medical (e.g., ICD10 codes, medication usage, etc.), clinical (e.g., blood pressure, etc.), therapeutic (e.g., statin cost, anti-inflammatory medication, etc.), lifestyle (e.g., smoking, drinking, exercise frequency, etc.), supplement usage (e.g., herbal, vitamin D, vitamin B12, iron, etc.), electronic data (e.g., imaging, electronic health records, publicly available data (e.g., repositories, etc.), publications, pharmaceuticals, clinical trials, etc.), and / or their diagnostic, intervention, management, monitoring, and / or therapeutic implications.

[0051] The platform can provide diagnostic information, prognostic information, relevant risk factors, uncertainty quantification, etc. The platform can allow an individual (e.g., a patient), clinician, or another user to drill down into additional information deemed relevant based on measurements (e.g., weight, blood pressure, etc.), tests (e.g., genetic, epigenetic, protein, metabolic assays, etc.), financial (e.g., procedure costs, medication costs, claims, etc.), industry / prevalence (e.g., heart disease prevalence in a particular geographic region, number of heart attacks per year for truck drivers, etc.), interventions (e.g., surgical procedures, etc.), medical (e.g., ICD10 codes, medication usage, etc.), clinical (e.g., blood pressure, etc.), therapeutic (e.g., statin costs, anti-inflammatory medications, etc.), lifestyle (e.g., smoking, alcohol consumption, exercise frequency, etc.), supplements (e.g., herbal, vitamin D, vitamin B12, iron, etc.), and / or additional data (imaging, electronic health records, publicly available data (e.g., repositories, etc.), publications, pharmaceuticals, clinical trials, etc.) to assist physicians or others in, for example, understanding and implementing diagnostic, clinical, and / or business risk management or decision making, regulatory and / or policy making, interventions, monitoring, and / or treatment decisions and strategies related to a patient or group of patients or a user or group of users. Further, the platform can provide the ability to assist in drilling down into, searching, interpreting, collating, communicating, and providing additional information (e.g., journal articles, clinical guidelines, raw or transformed data, etc.) using artificial intelligence or other algorithms (e.g., large language models). Although “patient” is frequently used throughout this disclosure, the term is not limited to individuals who have previously been diagnosed with a disease or disorder and is also not intended to be mutually exclusive with “stakeholder” or “user.”

[0052] The compositions and methods described herein can be used to provide changes in management, outcomes (e.g., health, cost, etc.), or other decision making by users (e.g., clinicians, payers, employers, researchers, insurers, governments, etc.) for patients or groups of patients or users with or without a disease, disorder, or risk. The compositions and methods described herein are discussed in the context of cardiovascular disease (e.g., coronary heart disease, stroke, etc.) and cardiovascular risk factors or comorbidities (e.g., obesity, smoking, alcohol consumption, etc.), but the compositions and methods described herein can be similarly applied in the context of cardiometabolic disorders (e.g., high blood pressure, high lipoprotein, etc.), insulin-related health conditions (e.g., prediabetes, type 2 diabetes, etc.); dementia (e.g., Alzheimer’s disease, etc.), cerebrovascular disease, mortality, cancer (e.g., breast cancer, etc.), other complex disorders or diseases (e.g., autism, mental health, COPD, kidney disease, etc.), and any number of other diseases, disorders, or risks.

[0053] Figure 1FIG. 1 is a schematic diagram of a computer system 100 configured to run and display the platforms described in this disclosure. The computer system 100 includes one or more processors and a computer-readable medium (e.g., a non-transitory computer-readable medium) storing computer instructions that, when executed by the one or more processors, can perform the operations described in this disclosure. The computer system 100 can generate a“dashboard” including one or more user interfaces (see, e.g., FIGS. 2-19) for display on a display device 105 operatively coupled to the computer system 100.

[0054] As described herein, the genetics, epigenetics, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described herein of a patient, a population of patients, or a user can be represented and displayed (e.g., graphically, textually) on the display device 105 by the computer system 100 via any number of user interfaces. For example, the genetics, epigenetics, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described herein of a population (e.g., a population of patients) to which a patient belongs (e.g., based on age, gender, race, ethnicity, etc.) can be represented and depicted in isolation or aggregated and for individual patients, for non-patient users (e.g., clinicians, technicians, etc.), or relative to a population (e.g., a cohort population). The same genetics, epigenetics, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or data described herein can be obtained for a population and can be categorized into individual (e.g., patient or non-patient) cohorts within the same or different individual demographic characteristics (e.g., age, gender, race, ethnicity, etc.). As used herein, test results or measurements refer to, but are not limited to, results or data obtained from genetic and / or epigenetic tests, but can also refer to the presence or absence or amount of a protein, feature detection during imaging, blood pressure, lifestyle (e.g., smoking, drinking, etc.), results from metabolic assays, blood test results, financial (e.g., cost of surgery, cost of medication, claims, etc.), industry / prevalence (e.g., heart disease prevalence in a particular geographic region, number of heart attacks per year for truck drivers, etc.), interventions (e.g., surgical procedures, etc.), medical (e.g., ICD10 codes, medication usage, etc.), clinical (e.g., blood pressure, etc.), treatment (e.g., statin cost, anti-inflammatory medication, etc.), supplements (e.g., herbal, vitamin D, vitamin B12, iron, etc.), and / or additional data (electronic health records, publicly available data (e.g., repositories, etc.), publications, pharmaceuticals, clinical trials, etc.).

[0055] As described herein, the compositions and methods involve processing various different types of data (e.g., lifestyle, medical history, prior and current diagnoses (e.g., according to International Classification of Diseases, Tenth Revision (ICD10)), indication occurrences (e.g., by age, by gender, etc.)) that can be used for risk assessment or quality control, or for creating training, test validation datasets and / or iterative training for machine learning, training, testing or validating machine learning or one or more other algorithms. Additionally, in some embodiments, the compositions and methods described herein are capable of rapidly and / or high-throughput processing of samples and data generated from processing of samples, which can be used to rapidly generate individualized care / intervention / management / monitoring / treatment program components.

[0056] User interface

[0057] Examples of user interfaces shown in screenshot displays are illustrated in FIGS. 2-19, however, these are not intended to be limiting. The computer system 100 can display user interfaces in static or dynamic forms. The computer system 100 can display a variety of different forms of data (e.g., standalone, aggregated, interpolated, derived, numerical, textual, image, or combinations thereof), plots, test results, publications, or hyperlinks to any of the foregoing within one or more user interfaces to assess the presence or absence of a disease or disorder or risk in a patient or population. The user can interact with plots in the user interface using the input device 110, for example, to view different items of information included in the plots (e.g., in drop-down menus, embedded links, etc.); to drill down into results, data, methods, analyses, and / or interpretations; to overlay or superimpose data, test results, etc. of a patient or user or group of patients or users onto corresponding data, test results, etc. of a population; and / or to search, interpret, collate, transmit, and provide additional information (e.g., journal articles, clinical guidelines, raw or transformed data, etc.) using artificial intelligence or other algorithms (e.g., large language models); to provide an artificial intelligence assistant (e.g., a large language model) for providing reference (e.g., journal articles, clinical guidelines), background, and / or query information, etc.

[0058] By employing the user interfaces described in greater detail below, a patient, physician or other individual or user or group of users can review patient information, as a whole or grouped by age and / or gender or other confounding variables, for comparison to a population. Patient information can be provided as de-identified material. In addition, users can compare population information, as a whole or grouped by age and / or gender or other confounding variables. Methods of determining genetic, epigenetic, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described herein for one or more patients or one or more users are known in the art or can be input into the computer system 100 if such information is known for one or more patients or one or more users.

[0059] The computer system 100 described herein can be configured to perform univariate biomarker analysis, which is primarily used to compare results for one or more users to a data source (e.g., an external source, such as but not limited to a third party study). The computer system 100 described herein can also be configured to perform multivariate risk and diagnostic predictions using a large number of data sources (e.g., measurements, electronic health records, lifestyle, etc.). The system can perform both univariate and multivariate analysis on the same source for one or more users.

[0060] FIGS. 2A and 2B illustrate example user interfaces that can be displayed by a display device. In the user interfaces, the computer system 100 can display patient information (e.g., patient ID, name, age, gender, etc.), user information (e.g., name, ID, and contact information for a physician or other user requesting and / or reviewing the information), and / or sample information (e.g., type of sample, date obtained from patient, etc.). While “clinician” is used in both of the user interfaces illustrated in FIGS. 2A and 2B, the same or different information can be similarly or differently configured in the user interfaces for any number of users as discussed herein.

[0061] FIGS. 3A and 3B illustrate example user interfaces that can be displayed by a display device. In the user interfaces, patient information can be hierarchically presented using different graphical formats. For example, computer system 100 can generate a plot as a vertical bar chart showing age of a patient population on the X-axis and probability of patients of different ages having a disease or disorder on the Y-axis (FIG. 3A), or conversely, as a horizontal bar chart showing probability (e.g., score) of patients of different ages having a disease or disorder on the X-axis and age of the patient population on the Y-axis (FIG. 3B). A patient's genetics, epigenetics, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described herein can include a probability value of the patient having a disease or disorder (or not having a disease or disorder), and computer system 100 can display the probability determined for the patient on the bar chart of population probabilities. This allows a user to compare the probability of the patient having a disease or disorder relative to the age-related probability of the disease or disorder in the population.

[0062] In some implementations, computer system 100 can generate a plot (e.g., a bar chart) showing gender of a patient population on the X-axis and probability of patients of the same gender having a disease on the Y-axis, and the gender shown can be selected to match the gender of the patient. Computer system 100 can display the probability determined for the patient relative to the population probability of individuals of the same gender as the patient. Similarly, computer system 100 can present the probability determined for the patient relative to the population probability of individuals of the same race, ethnicity, or other characteristic as the patient.

[0063] FIG. 4 is an example user interface that can be displayed by a display device. The user interface in FIG. 4 is a graph showing coronary heart disease (CHD) risk for male patients relative to a male cohort population. For example, when the disease, disorder, or risk involves CHD, cohort data can be obtained from the Framingham Heart Study Offspring Study, Intermountain Healthcare (IM) Inquiry, and / or Iowa Study, which are well known in the art.

[0064] FIG. 5 is an exemplary user interface that can be displayed by the display device. In some implementations, results can be obtained from more than one (e.g., multiple) genetic, epigenetic, and / or other biomarkers from the patient. Different genetic, epigenetic, and / or other biomarkers can have different levels of contribution to the association or cause of the patient’s disease, disorder, indication, condition, or risk. The contribution can be obtained from one or more models or from other methods such as SHapley Additive exPlanations (SHAP). In some implementations, the computer system 100 receives a ranking of the contribution of each of the plurality of genetic markers to the presence of the disease in the patient. The computer system 100 can generate a user interface that includes the name of each marker on the X-axis and the ranking or score of the contribution of each biomarker to the disease, disorder, or risk (e.g., normalized between 0 and 1) on the Y-axis. For example, the computer system 100 can generate a graph that shows the biomarker that contributes the most to the disease or disorder or risk and the genetic marker that contributes the least to the disease, disorder, or risk, with the remaining genetic markers arranged in decreasing rank therebetween (FIG. 5). In general, the contribution can be provided in comparison to the population as a whole, or for a particular individual or aggregated by group (not accounting for age or gender). In some implementations, the computer system 100 can generate Table 1 (see below) that describes the relevant genetic and / or epigenetic biomarkers displayed in the user interface.

[0065] Table 1

[0066]

[0067] The computer system 100 superimposes the test results of the genetic, epigenetic, and / or other markers of the individual patient on the corresponding ranking of the test of the genetic and / or epigenetic and / or other markers determined for the population as a whole. The computer system 100 displays the resulting plot in the user interface.

[0068] The plot shown in the user interface shows the contribution of each marker to the disease in the cluster compared to the contribution in the individual patient. For example, if a first genetic and / or epigenetic and / or other marker (e.g., cgO) is ranked as having the greatest contribution to the disease in the general population, but the same genetic and / or epigenetic and / or other marker has a relatively low contribution to the disease in the individual patient, the physician knows that the first genetic and / or epigenetic and / or other marker is likely to be less important for treating the individual patient. Conversely, if a different genetic and / or epigenetic and / or other marker (e.g., cg3) is ranked as having the lowest contribution to the disease in the general population, but the same genetic and / or epigenetic and / or other marker has the highest contribution to the disease in the individual patient, the physician knows that the different genetic and / or epigenetic and / or other marker is likely to be the most important for treating the individual patient. In this way, the risk contributions can be used to determine which markers significantly contribute to the disease or condition or indication of the individual patient.

[0069] As discussed herein, the computer system 100 can display each of the normalized rankings as selectable objects. The user can select the normalized ranking of one of the genetic, epigenetic, and / or other biomarkers using the input device 115. In response to detecting the selection (e.g., a mouse click, a hover, a touch input, or any other input), the computer system 100 can display, for example, information related to the genetic, epigenetic, and / or other biomarker (e.g., hyperlinks, publications, clinical data, clinical trials, pharmaceuticals, etc.).

[0070] FIG. 6 is another example user interface that can be displayed by a display device. In some implementations, the computer system 100 can generate a box plot of the distribution of genetic, epigenetic, and / or other biomarker measurements associated with a particular genetic, epigenetic, and / or other biomarker (e.g., for the entire patient population). The computer system 100 can display the box plot within the user interface with the patient’s genetic, epigenetic, and / or other biomarker measurements superimposed. For example, the computer system 100 can display the patient’s genetic, epigenetic, and / or other biomarker measurements as a dashed line across the box plot of the distribution of genetic, epigenetic, and / or other biomarker measurements. The computer system 100 can similarly generate and display multiple box plots, each corresponding to a respective genetic, epigenetic, and / or other biomarker, each box plot displaying the patient’s genetic, epigenetic, and / or other biomarker measurements. In some implementations, for each box plot, and in particular for the genetic, epigenetic, and / or other biomarker measurement taken for the patient, the computer system 100 can determine upper and lower bounds of uncertainty associated with the measurement. The computer system 100 can display the upper and lower bounds as solid lines on either side (e.g., above and below) of the dashed line representing the patient’s genetic, epigenetic, and / or other biomarker measurement. The computer system 100 can similarly generate and display uncertainty bounds for multiple box plots corresponding to multiple distributions of genetic, epigenetic, and / or other biomarker measurements. The user interface can be used to ensure robustness of the measurements and allow a user to compare individual patient and patient population measurements.

[0071] FIG. 7 is an example user interface that can be displayed by a display device. In some implementations, the computer system 100 can display a selectable object (e.g., a drop-down box) that a user can use to select a particular marker (e.g., the biomarker“rs1”). In response to the selection (e.g., using the input device 115), the computer system 100 can retrieve (from, e.g., a publicly available database or a private database) allele frequencies for different populations (e.g., European, Asian, East Asian, etc.) and provide as part of the user interface (see Table 2). A patient, physician, or other user can interact with the user interface to learn additional context about, e.g., ethnicity, age, gender, etc. Within the user interface, the computer system 100 can also display publicly available genome-wide association study (GWAS) data that can show the association of the biomarker with a risk factor and whether the disease, disorder, or risk was detected in independent studies.

[0072] Table 2

[0073]

[0074] FIG. 8 is an example user interface that can be displayed by a display device. As shown in FIG. 8, computer system 100 can produce cost analysis data for cardiovascular diseases over time (X-axis) (Y-axis) displayed by various populations based on national and regional data or statistics on prevalence rates and other data or factors (disease types include hypertension, coronary heart disease, congestive heart failure, stroke, other cardiovascular diseases, and hypertension). As discussed herein, the data can be further aggregated based on, for example, demographic information (e.g., age, gender, geographic location, etc.). In some embodiments, the user interface can display cost analyses (e.g., cost minimization, cost effectiveness, cost utility, cost benefit, cost consequences, budget impact, information value, pharmacoeconomics, incremental cost effectiveness ratio, etc.) and / or test utilization information, such as shown in Table 3 below, which can include hyperlinks to further review cost analysis data based on month, year, employee population, test population, etc. The cost analyses displayed in the user interface can help estimate treatment costs and outcomes at the individual, individual group, and / or population level.

[0075] Table 3. Representative cost utilization

[0076]

[0077] FIG. 9 is an example user interface that can be displayed by a display device in which computer system 100 causes the user interface to display coronary heart disease prevalence in the U.S. population based on age and gender. As discussed herein, the data used to create such a user interface can be obtained from available national and regional statistics, and can be displayed based on any number of factors (e.g., demographic characteristics; disease, disorder, or risk; ethnicity; geographic location, institution, etc.).

[0078] FIG. 10 is another example user interface that can be displayed by a display device. FIG. 10 shows an example in which mortality due to coronary heart disease is geographically depicted via a color-coded map based on age-standardized rates (per 100,000 people). The illustrated FIG. 10 is independent of race, ethnicity, gender, but the user interface can be configured to display data showing the contribution of those factors.

[0079] FIG. 11 is an exemplary user interface that can be displayed by a display device. In this example, uncertainty measures (e.g., uncertainty quantification (UQ)) are graphically represented for various biomarkers, although uncertainty can also be assessed for measurements, models, costs, etc. This type of user interface allows a patient, physician, or another user to assess the risk due to, for example, potential bias or error in measurements or modeling (due to, for example, differences in manufacturing assays, equipment, technicians, and / or sample collection and availability, etc.). In some cases, the user interface can allow the user to review and evaluate the uncertainty of measurements, uncertainty of modeling, or net uncertainty (defined as the aggregation of measurement and modeling uncertainty). In some embodiments, uncertainty can be used as a criterion for assessing the reliability of measurements in a quality control process. In some embodiments, uncertainty can be utilized in conjunction with data, metrics, and / or requirements provided by the user to ensure that target outcomes (e.g., costs, likelihood of events, etc.) fall within acceptable ranges. For example, this approach can be employed to ensure that treatment costs do not exceed a prescribed limit or the probability of a coronary heart disease (CHD) event remains below a defined threshold.

[0080] FIGS. 12A and 12B are exemplary user interfaces that can be displayed by a display device to demonstrate a quality control process in a method involving obtaining genetic, epigenetic, and / or other biomarker measurements (e.g., digital PCR (dPCR)) and / or modeling resulting data. This type of user interface can demonstrate whether all sample measurements fall within (FIG. 12A) or outside of (FIG. 12B) expected reference measurements and are therefore considered failed tests.

[0081] FIG. 13 is an exemplary user interface that can be displayed by a display device. In this example, the user interface displays a line graph showing changes in genetic, epigenetic, one or more other biomarkers (e.g., protein, metabolic assays, etc.), one or more measurements, test results, and / or other data described herein (Y-axis) over time (X-axis). This type of user interface can allow a patient, physician, or another user to assess changes in an individual patient or individual patients over time (e.g., significant changes) relative to a particular specified population.

[0082] FIG. 14 is an example user interface that can be displayed by a display device. In this example, the user interface displays a line graph that shows the change in score (Y-axis) over time (X-axis) based on, for example, one or more genetics, epigenetics, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described above. In this example, the graph in the user interface indicates a threshold score that distinguishes between patients with low scores and patients with high scores, as well as trends observed from population data. As discussed herein, the computer system 100 allows a user to manipulate and configure the display to present information in any number of different formats (e.g., display low and high score ranges for different patient populations). Changes in patient scores over time can identify whether a patient is responding to a treatment strategy. In addition, uncertainty (e.g., in measurements, modeled, and / or aggregated measurements and models) can be used to further inform one or more users about the confidence in one or more risk groups of results. In some implementations, uncertainty can not be included.

[0083] FIG. 15 is an example user interface that can be displayed by a display device. FIG. 15 shows scores based on, for example, genetics, epigenetics, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described herein that were used to compute the scores. This type of user interface allows a user to evaluate the contribution of individual genetics, epigenetics, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described herein to the scores (e.g., risk probabilities, diagnostic probabilities, etc.).

[0084] FIG. 16 is an example user interface that can be displayed by a display device. The user interface example shown in FIG. 16 illustrates the change in contribution of a particular measurement and / or other data described herein (Y-axis) for a user or group of users over time (X-axis).

[0085] FIG. 17 is an example user interface that can be displayed by a display device. This example depicts a graphical illustration of the contribution of several different contributions of genetics, epigenetics, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described herein (Y-axis) to the contribution of genetics, epigenetics, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described herein (e.g., SHAP values, model weights, etc.) (X-axis) in a population. As discussed herein, this user interface can be integrated with, overlaid, superimposed, etc. with one or more user interfaces that, for example, display the change in contribution of a particular biomarker over time.

[0086] FIG. 18 is another example user interface that can be displayed by a display device. FIG. 18 depicts a pie chart that, in combination with information such as contained in Table 4 below, can be used to perform univariate or multivariate analysis of various disease pathways in an individual and / or a population. This type of user interface can also be used to inform treatment and / or intervention recommendations.

[0087] Table 4

[0088]

[0089] FIGS. 19A and 19B are example user interfaces that can be displayed by a display device. In FIG. 19A, computer system 100 generates a graph corresponding to an individual’s treatment response (Y-axis) over time (X-axis) based on, for example, genetics, epigenetics, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described above. In FIG. 19B, computer system 100 generates a graph corresponding to an individual’s score (e.g., risk probability, diagnostic probability, etc.) (Y-axis) over time (X-axis). In addition, uncertainty (e.g., of measurements, modeling, and / or aggregated measurements and modeling) can be used to further inform one or more users of the confidence of a risk group with respect to one or more outcomes. In some implementations, uncertainty can not be included.

[0090] The example user interfaces shown in the previously referenced and described figures show data associated with coronary heart disease measurements. The underlying data used to generate such figures was measured by testing genetic and epigenetic markers of coronary heart disease (CHD). In some implementations, the underlying data can be obtained by testing or compiling or querying or aggregating other diseases or disorders (such as stroke, heart failure, diabetes, etc.) appropriate genetic, epigenetic, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described above. User interfaces can be generated based on such underlying data. In this way, the online platform described herein can be used not only to present data related to cardiovascular diseases, but also to present data related to other diseases and associated comorbidities. Genetic and epigenetic markers associated with CHD and many other indicators can be found, for example, in WO 2017 / 214397, WO 2022 / 051630, and WO 2022 / 051641, which are hereby incorporated by reference.

[0091] As used herein, a genetic biomarker generally refers to a single nucleotide polymorphism (SNP), but can also refer to any type of genetic change (e.g., deletion, insertion, substitution, etc.). As used herein, an epigenetic biomarker generally refers to methylation of a cytosine nucleotide, which is typically adjacent to a guanine nucleotide (CpG). As used herein, other biomarkers refer to proteins, metabolic assays, lipids, family history information, images, biochemistry, other data described herein, etc.

[0092] Computer system

[0093] FIG. 20 is a block diagram of an example computer system for providing computing functionality associated with the algorithms, methods, functions, processes, flows, and procedures described in the present disclosure, according to some implementations of the present disclosure. The illustrated computer is intended to encompass any computing device such as a server, desktop computer, laptop / notebook computer, wireless data port, smart phone, personal data assistant (PDA), tablet computing device, or one or more processors within these devices, including physical instances, virtual instances, or both. The computer can include input devices that can accept user information, such as a microphone, keyboard, and touch screen. Also, the computer can include output devices that can convey information associated with the operation of the computer. The information can include digital data, visual data, audio information, or a combination of information. The information can be presented in a graphical user interface (UI) (or GUI).

[0094] The computer can act as a client, network component, server, database, persistent device, or component of a computer system for performing the subject matter described in the present disclosure. The illustrated computer is communicatively coupled with a network. In some implementations, one or more components of the computer can be configured to operate within different environments, including cloud-computing based environments, local environments, global environments, and combinations of environments.

[0095] At a top level, the computer is an electronic computing device operable to receive, transmit, process, store, and manage the data and information associated with the subject matter described. According to some implementations, the computer can also include, or be communicatively coupled with, an application server, an email server, a web server, a cache server, a streaming data server, or a combination of servers.

[0096] The computer can receive requests from a client application (e.g., executing on another computer) over a network. The computer can respond to the received requests by processing the received requests using a software application. The requests can also be sent to the computer from an internal user (e.g., from a command console), an external (or third) party, an automated application, an entity, an individual, a system, and a computer.

[0097] Each of the components of the computer can communicate using a system bus. In some implementations, any or all of the components of the computer, including hardware or software components, can interface with each other and / or the interfaces (or a combination of the two) through a system bus. The interfaces can use application programming interfaces (APIs), service layer interfaces, or a combination of APIs and service layer interfaces. APIs can include specifications for routines, data structures, and object classes. APIs can be either language-dependent or language-independent. An API can refer to entire interfaces, single functions, or a group of APIs.

[0098] A service layer can provide software services to the computer and other components that can be communicatively coupled to the computer, whether directly connected to or indirectly connected to the computer via another system. All service consumers that use this service layer can access the functionality of the computer. Software services, such as those provided by a service layer, can provide reusable, defined functionalities that are exposed using a defined interface. For example, the interface can be software written in JAVA, C++, or a language that provides data in extensible markup language (XML) format. While shown as an integrated component of the computer, in alternative implementations, the API or service layer can be separate from the other components of the computer and the other components that are communicatively coupled to the computer. Moreover, any or all parts of the API or service layer can be implemented as child or sub-modules of another software module, enterprise application, or hardware module without departing from the scope of this disclosure.

[0099] The computer can include an interface. Although illustrated as a single interface in FIG. 20, two or more interfaces can be used according to particular needs, desires, or particular implementations of the computer and the functionality described. In a distributed environment, interfaces can be used by the computer to communicate with other systems that are connected to a network, whether directly connected through a permanent connection or indirectly connected over a network employing wireless or wired communication protocols. Generally, an interface can include logic encoded in software or hardware in a software-hardware combination, or a combination of the two, operable to cause the system to perform various functions as described. More specifically, the interface can include software supporting one or more communication protocols associated with the communication of one or more other systems. In this manner, the network or a hardware aspect of the interface can be operable to communicate physical signals between the computer and other systems. Any of the user interfaces and / or other interfaces described herein that are based on genetics, epigenetics, one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measurements, test results, and / or other data described herein can be displayed, tracked, and shared via the computer by way of an application environment (e.g., a mobile application environment, a web application environment, etc.), a guidance, and / or a connected device.

[0100] The computer can include a processor. Although illustrated as a single processor in FIG. 20, two or more processors can be used according to the particular needs, desires, or particular implementations of the computer and the described functionality. Generally, the processor(s) can execute instructions and can manipulate data to perform the operations of the computer, including the algorithms, methods, functions, processes, flows, and procedures as described in the present disclosure.

[0101] The computer can also include a database, which can hold data for the computer or a combination of components connected to a network, whether illustrated or not. For example, the database can be an in-memory, conventional, or database that stores data consistent with the present disclosure. In some implementations, the database can be a combination of two or more different database types (e.g., a hybrid in-memory database and conventional database) according to the particular needs, desires, or particular implementations of the computer and the described functionality. Although illustrated as a single database in FIG. 20, two or more databases (of the same type, different types, or a combination of types) can be used according to the particular needs, desires, or particular implementations of the computer and the described functionality. While the database is illustrated as an internal component of the computer, in alternative implementations, the database can be external to the computer.

[0102] The computer can also include a memory, which can hold data for the computer or a combination of components connected to a network, whether illustrated or not. The memory can store any data consistent with the present disclosure. In some implementations, the memory can be a combination of two or more different types of memory (e.g., a combination of semiconductor and magnetic memory) according to the particular needs, desires, or particular implementations of the computer and the described functionality. Although illustrated as a single memory in FIG. 20, two or more memories (of the same type, different types, or a combination of types) can be used according to the particular needs, desires, or particular implementations of the computer and the described functionality. While the memory is illustrated as an internal component of the computer, in alternative implementations, the memory can be external to the computer.

[0103] The application can be an algorithmic software engine that provides functionality according to the particular needs, desires, or particular implementations of the computer and the described functionality. For example, the application can function as one or more components, modules, or applications. Further, although illustrated as a single application, the application can be implemented as multiple applications on the computer. Additionally, although illustrated as internal to the computer, in alternative implementations, the application can be external to the computer.

[0104] The computer can also include a power supply. The power supply can include a rechargeable or non-rechargeable battery that can be configured to be either user- replaceable or non-user- replaceable. In some implementations, the power supply can include power conversion and management circuitry including charging, standby, and power management functionality. In some implementations, the power supply can include a power plug to allow the computer to be plugged into a wall socket or power supply to, for example, power the computer or charge a rechargeable battery.

[0105] There can be any number of computers associated with or external to a computer system that includes the computer, with each computer communicating over a network. Further, the terms "client," "user," and other appropriate terminology can be used interchangeably as appropriate, without departing from the scope of the present disclosure. Moreover, the present disclosure contemplates that many users can use a computer, and that a single user can use multiple computers.

[0106] To achieve the described performance characteristics, models for processing the described one or more inputs and returning the described one or more outputs can include classification models structured to receive input data and return an indication of a subset of features with high predictive power (e.g., sensitivity, specificity, cost, etc.).

[0107] Different types of models (e.g., linear, non-linear, classification, etc.) can be built with one or more markers for different objectives (e.g., cost, diagnosis, etc.). Multiple models can be built with one or more markers for different objectives (e.g., cost, diagnosis, etc.).

[0108] Model architectures can include statistics (e.g., linear regression, logistic regression, proportional hazards model, etc.), machine learning (e.g., random forest, support vector machine, neural network, Bayesian classifier, etc.), deep learning (e.g., convolutional neural network, recurrent neural network, autoencoder, large language model, etc.), and time series (e.g., ARIMA, etc.), Bayesian models (e.g., Bayesian network, etc.), finance (decision tree, discrete event simulation, budget impact, etc.).

[0109] The input data can be conditioned or otherwise pre-processed prior to fitting one or more models, such that the conditioned data elements (e.g., genomic reads associated with loci of interest, functional data, sensor data, other lifestyle data, etc.) are suitable for further processing. As described herein, conditioning can include filtering of data (e.g., sensor data output having a confidence value below a threshold, etc.). One or more pre-processing steps, such as dimensionality reduction (e.g., principal component analysis, linear discriminant analysis, autoencoders, uniform manifold approximation and projection, partial least squares regression, etc.), can be performed on one or more model inputs prior to training one or more models.

[0110] Transforming the output data can be used to enhance the interpretability of the previously described models. For example, Shapley Additive exPlanations (SHAP), model-agnostic Local Interpretable Model-agnostic Explanations, Integrated Gradients, Partial Dependence Plots, Global Surrogate Models, etc. can be used to enhance the interpretability of the output to the user. One or more of these methods can be utilized simultaneously. In a specific example, SHAP can be used to identify one or more most significant contributing markers to a condition or indication.

[0111] The output data is transformed into digital objects (such as visualizations) in order to facilitate the generation of representations, interventions for condition prevention, interventions for condition treatment, and / or other actions (e.g., computer-generated and machine- implementable instructions) for improving and / or maintaining metrics (diagnoses, risk scores, costs, etc.). In a specific example, digital objects and visualizations can be generated after transforming the input data using various software (e.g., Rstats, ggplotz, matplotlib, etc.) in sequence and / or in parallel.

[0112] One or more model predictions (e.g., risk scores, diagnoses, etc.) uncertainty can be computed. Methods for estimation can include bootstrapping methods, Bayesian methods, Monte Carlo dropout, ensemble methods, sensitivity analysis, etc. The uncertainty of the methods and / or models described herein can be aggregated to provide an overall system uncertainty.

[0113] In some variations, the methods described herein can further include refining one or more models: collecting a training data stream set derived from a population of one or more patients, the training data stream set capturing data (e.g., genetic, epigenetic, lifestyle, etc.) paired with one or more interventions, one or more treatments, one or more management information from the population of one or more patients; creating a training data set derived from the training data stream set and a set of transformation operations; and training one or more models in one or more stages based on the training data set.

[0114] Data / signals inputs and / or other inputs (e.g., contextual inputs, derived inputs, combined inputs, etc.) can be used to train one or more models. In more detail, markers can be transformed individually or in combination prior to being processed by one or more models. Combined markers can include genetic, epigenetic, metabolic assays, lipids, proteins, lifestyle, demographic features, and / or other data described herein.

[0115] Additionally or alternatively, dynamic aspects of features derived from a sample (e.g., changes in markers over time, frequency changes between instances of a respective feature, other temporal aspects, other frequency-related aspects, etc.) can be used to predict or otherwise anticipate a health status state for generating a personalized intervention plan component.

[0116] Inputs can be aggregated from patient populations associated with different demographic characteristics, health statuses, health conditions, lifestyles, and / or other suitable factors.

[0117] With respect to model architectures, inputs to one or more models described herein can produce outputs that are subsequently used as inputs to an overall model (e.g., a classification model with multiple layers, a reinforcement learning model, etc.) that returns a diagnosis, a characterization of one or more patients (e.g., with respect to a health status, a disease state, etc.), aspects of a personalized intervention plan, and / or other aspects based on processing data in stages. However, one or more models can implement other suitable architectures with other suitable processes for processing data derived from inputs.

[0118] Classification, regression, and / or other outputs returned by one or more models can include a confidence associated parameter in such classifications. In particular, a confidence associated parameter can have a score (e.g., a percentile, other score) that indicates a confidence in a returned output. Confidence can be estimated by aggregating measurements and / or modeling uncertainty.

[0119] Further, a refined version of one or more models can be configured to process fewer inputs (e.g., only a subset of inputs described herein) in order to return accurate outputs for generating a personalized intervention plan component. Further, during model refinement, previous data derived from inputs (e.g., new signal / marker features, signal / marker features of interest, etc.) can be returned by a computing component.

[0120] While embodiments, variations, and examples of one or more models are described herein (e.g., with respect to inputs, outputs, and training), models can additionally or alternatively include other machine learning architectures.

[0121] The statistical analysis and / or the one or more machine learning algorithms can be characterized by a learning style that includes any one or more of: supervised learning (e.g., using backpropagation neural networks), unsupervised learning (e.g., K-means clustering), semi-supervised learning, reinforcement learning (e.g., using a Q-learning algorithm, using temporal difference learning, etc.), and any other suitable learning style.

[0122] Further, any one or more algorithms can implement any one or more of: a regression algorithm, an instance-based method (e.g., k-nearest neighbor algorithm, learning vector quantization, self-organizing map, etc.), a regularization method, a decision tree learning method (e.g., classification and regression tree, chi-squared method, random forest method, multivariate adaptive regression method, gradient boosting machine method, etc.), a Bayesian method (e.g., Naive Bayes, Bayesian belief network, etc.), a kernel method (e.g., support vector machine, linear discriminant analysis, etc.), a clustering method (e.g., k-means clustering), an association rule learning algorithm (e.g., apriori algorithm), an artificial neural network model (e.g., backpropagation method, hopfield network method, learning vector quantization method, etc.), a deep learning algorithm (e.g., Boltzmann machine, convolutional network method, stacked autoencoder method, etc.), a dimensionality reduction method (e.g., principal component analysis, partial least squares regression, etc.), an ensemble method (e.g., boosting, bootstrap aggregating, gradient boosting machine method, etc.), and any suitable form of algorithm.

[0123] In an example, the model training can be based on a cohort of patients who are taking one or more medications (e.g., statins) and / or who are losing > 5% body weight while receiving personalized digital weight loss care and presenting with concomitant reduction in cardiovascular symptoms and / or risk. With respect to the likelihood of a patient having a cardiovascular event, a diagnostic signature can be constructed based on predictive variables identified in one or more models. Example variables include demographic features, genomic variables (e.g., SNPs and / or methylation associated with inflammation, associated with obesity, associated with other factors described, etc.), and any other type of variable.

[0124] The one or more interventions, one or more treatments, one or more managements, and / or monitoring can also include modified variants of operations for training and refining other model architectures configured for improving other conditions.

[0125] A system / platform for one or more interventions, diagnostics, one or more treatments, one or more managements, and / or monitoring includes a computing platform including one or more processing subsystems including a non-transitory computer readable medium including instructions stored thereon that, when executed by the processing subsystems, perform one or more steps of the methods described herein; and one or more execution subsystems configured to perform components of a personalized intervention plan dictated by the processing of the computing platform. In variations, the execution subsystems can be configured to execute control instructions generated by the computing platform, where the control instructions can involve instructions for controlling operational modes of one or more of: application interfaces (e.g., mobile application interfaces, web application interfaces, etc.) for signal reception, data aggregation, and / or retrieval of other inputs to be processed by the system architecture; sample processing architecture (e.g., by automated / robotic subsystems); communication interfaces for performing remote health operations, providing group therapy, providing counseling (e.g., by human entities, by digital entities); interfaces for providing rewards and / or other incentives to patients; interfaces for providing and monitoring tasks provided to patients; interfaces for connecting patient devices (e.g., biometric monitoring devices) to patient accounts within the system / platform; interfaces for providing medicaments to patients; interfaces for providing dietary suggestions / tracking dietary behaviors of patients; and / or other suitable functionality for delivering components of a personalized intervention plan.

[0126] Embodiments of the system are configured to perform one or more portions of the methods described herein; however, variations of the system can be configured to perform other suitable methods.

[0127] The computing platform can include one or more processing subsystems including a non-transitory computer readable medium including instructions stored thereon that, when executed by the processing subsystems, perform one or more steps of the methods described herein; and one or more execution subsystems configured to perform components of one or more personalized interventions, one or more treatments, one or more management, and / or monitoring plans dictated by the processes of the computing platform.

[0128] The execution subsystem can be configured to execute control instructions generated by the computing platform, where the control instructions can involve instructions for controlling operational modes of one or more of: application interfaces (e.g., mobile application interfaces, web application interfaces, etc.) for signal reception, data aggregation, and / or retrieval of other inputs to be processed by the system architecture; sample processing architecture (e.g., by automated / robotic subsystems); communication interfaces for performing remote health operations, providing group therapy, for providing counseling (e.g., by human entities, by digital entities); interfaces for providing rewards and / or other incentives to patients; interfaces for providing and monitoring tasks provided to patients; interfaces for connecting patient devices (e.g., biometric monitoring devices) to patient accounts within the system / platform; interfaces for providing medicaments to patients; interfaces for providing suggestions / tracking patient lifestyle / behavior or one or more other measures or one or more biomarkers; and / or other suitable functionality for delivering components of a personalized intervention, treatment, management, and monitoring plan.

[0129] In particular, the execution subsystem can be structured to implement next generation prescription level digital therapy or use artificial intelligence (AI) to analyze genetics, epigenetics, and / or one or more other biomarkers (e.g., proteins, metabolic assays, etc.), one or more measures, test results, and / or other items described herein to create evidence-based personalized care, intervention, treatment, management, monitoring items to improve targeted outcomes (e.g., risk reduction, cost reduction, etc.).

[0130] Uses and Benefits

[0131] The compositions and methods described herein provide for generating, curating, aggregating, evaluating, analyzing, displaying, tracking, and sharing independent or integrated (genomic, epigenomic, proteomic, RNA, imaging, electrocardiogram, lifestyle factors, clinical markers, social determinants of health, etc.) diagnostics, risk assessments, treatment pathways, cost estimates, prognostics, health outcomes (e.g., with respect to prevention, diagnosis, treatment, and / or management) for care or for understanding, managing, and mitigating risk (e.g., with respect to implementing cost reduction initiatives) for various conditions or indications. In examples, the characterizations can be used to provide actionable insights, where one or more interventions include lifestyle changes and / or treatments (e.g., pharmaceuticals, medical devices, nutritional therapies, stem cell therapies) and / or interventions (e.g., gene editing, base editing, epigenetic silencing, epigenetic editing). Additionally or alternatively, the data from the patients, analysis of the data, and interpretation of the data can also reveal more complex diagnostic pathways and pinpoint potential treatment and / or intervention options. Additionally or alternatively, the systems and methods can be used to continuously monitor and assess the effectiveness of such treatments and / or interventions, providing data and actionable insights for further optimization of conditions, indications, health outcomes, or costs.

[0132] In some embodiments, the compositions and methods described herein can be used for risk assessment, prevention, prognosis, management, intervention, treatment, and / or monitoring of one or more diseases, disorders, or risks. In some embodiments, the compositions and methods described herein can be used for risk assessment, prevention, prognosis, management, intervention, treatment, and / or monitoring of an indication at more than one time point.

[0133] The compositions and methods described herein can be used to suggest one or more lifestyle changes and / or one or more treatments and / or one or more interventions and / or one or more management strategies to optimize a target outcome (e.g., reduce costs, reduce likelihood of heart attack). The compositions and methods described herein can also be used to monitor or optimize the effectiveness of one or more lifestyle changes and / or one or more treatments and / or one or more interventions and / or one or more management strategies over time to optimize a target outcome (e.g., reduce costs, reduce likelihood of heart attack).

[0134] The compositions and methods described herein can also estimate the benefit of new interventions, such as new drugs and / or other compositions, including but not limited to chemical compositions (e.g., small molecule modulators), biological compositions (e.g., pre / pro / post biotics), gene editing, base editing, epigenetic silencing, and epigenetic editing. Additionally, the compositions and methods described herein can be used to apply the output of the analysis to implement one or more actions (e.g., suggest new health initiatives) to achieve an intended outcome (e.g., address obesity in employees).

[0135] The compositions and methods described herein encompass a comprehensive system designed to manage marker data (e.g., genomic, epigenomic, and / or other biomarkers) and other data or measurements derived from one or more processed samples. The system also includes mechanisms for deriving insights and for facilitating personalized care / intervention / management / treatment strategies by analyzing these biomarkers using models (e.g., linear regression, machine learning). As discussed herein, these processes can be integrated and data and insights can be delivered to patients or other users in a customized manner by way of computer system 100 and display devices.

[0136] The compositions and methods described herein can be used to query, curate, aggregate, evaluate, analyze information from one or more of the following: financial (e.g., procedure costs, medication costs, claims, etc.), industry / prevalence (e.g., heart disease prevalence in a particular geographic region, number of heart attacks per year for truck drivers, etc.), publications (e.g., journal articles, clinical guidelines, etc.), lab tests (e.g., epigenetic assessments, inflammatory biomarkers, etc.), imaging (e.g., FFR from CCTA, etc.), medical (e.g., ICD10 codes, electronic medical records, medication usage, etc.), clinical (e.g., blood pressure, weight, etc.), therapeutic (e.g., cost of statins, anti-inflammatory medications, etc.), lifestyle (e.g., smoking, exercise frequency, etc.), supplement usage (e.g., vitamin D, vitamin B12, iron, etc.), data to display, track, derive insights for users in a customized manner.

[0137] The methods can be used to generate, curate, aggregate, evaluate, analyze, display, track, and share standalone or integrated (genomic, epigenomic, proteomic, RNA, imaging, electrocardiogram, lifestyle factors, clinical markers, social determinants of health, etc.) diagnostics, risk assessments, treatment pathways, cost estimates, prognostics, health outcomes (e.g., with respect to prevention, diagnosis, treatment, and / or management) for care or for understanding, managing, and mitigating risk for various conditions or indications (e.g., with respect to implementing cost reduction initiatives). Thus, these methods have the potential to enhance outcomes with respect to one or more health conditions or indications, thereby providing a nuanced approach to precision medicine, personalized risk assessment, prevention, management, treatment, and monitoring.

[0138] The received or generated measurements can be data or information (e.g., data sets) including, but not limited to, clinical diagnoses; demographic characteristics (e.g., gender, race); lifestyle; cost; claims (e.g., health insurance); imaging (e.g., cardiac CT scan, cardiac MRI, coronary angiogram); features derived from imaging (e.g., FFR from CT scan, percent stenosis); results from electrocardiogram or echocardiogram testing; results from stress testing; blood tests (e.g., for metabolic assays, genetics, epigenetics, proteins, etc.); blood pressure; results from carotid ultrasound; and the like. The received or generated data or information can also include publications (e.g., journal articles) and, for example, clinical guidelines.

[0139] One or more data sets can be received from the patient or those associated with the patient (e.g., clinicians) that further act to enable generation of a baseline or subsequent state and from which one or more measurements can be generated in subsequent portions of the method for return diagnosis, risk assessment, personalized treatment pathway, cost estimate, prognosis, health outcome, one or more risks, other insights of interest, recommendations.

[0140] The data sets can include data derived from one or more of the following: body weight (e.g., receiving a patient’s body weight value generated from a digital body scale), body fat percentage, muscle mass, body water, height or other length measurement (e.g., via a ruler or measuring tape), other body mass index (BMI) related parameters, blood chemistry and biochemistry information, inflammation markers, fasting blood glucose, high-density lipids, low-density lipids, blood interleukins, c-reactive protein, blood cell counts, electrophysiological signals (e.g., electroencephalogram signals, electromyogram signals, galvanic skin response signals, electrocardiogram signals, etc.), heart rate, body temperature, cardiovascular parameters, continuous glucose monitoring (glucose response), respiratory parameters (e.g., respiratory rate, respiratory depth / shallowness, etc.), blood oxygen signals, exercise parameters, and any other suitable physiologically related parameters of the patient. Additionally and alternatively, the data sets can include data derived from one or more of the following: electronic health records, health plan claims, questionnaires, surveys, wearable devices, public sources (e.g., repositories), and any other data directly or indirectly related to the patient or user. Additionally and alternatively, the data sets can include raw, imputed, transformed, longitudinal, cross-sectional, or temporal data.

[0141] The dataset can involve behavioral information of the patient for one or more of the following: energy level (e.g., morning energy level, evening energy level, daytime energy level, etc.), eating behavior, sleep behavior, stress level, stress-related events, cravings, exercise behavior, meditation behavior, perceived progress toward health-related goals, actual progress toward health-related goals, symptom status, social determinants of health, family determinants of health, and work determinants of health, and / or other behavioral information. In an example, the lifestyle dataset can capture one or more of the following lifestyle characteristics of the patient: energy level, food intake (e.g., through food photos (which are subsequently evaluated and scored by a coaching entity or other entity), through diet journal entries, through an application programming interface (API) of a diet monitoring application, etc.), sleep behavior, stress level, cravings, exercise behavior, and weight loss progress. However, variants of the example can alternatively capture other types of lifestyle information from the patient.

[0142] The dataset can include data derived from one or more of the following: blood chemistry and biochemistry profiles, saliva chemistry and biochemistry profiles, medication usage, supplement usage, fasting blood glucose, blood glucose response, high-density lipid values, low-density lipid values, and any other similar parameters. The dataset can capture one or more of the following: morning energy level, eating behavior, sleep behavior, stress level, cravings, exercise behavior, meditation behavior, symptom status of the patient, medication usage, social determinants of health, family determinants of health, and work determinants of health.

[0143] The dataset can capture background and supplemental information at one or more of the following levels: population, location or geographic location, employer, health plan, government entity, non-profit organization, health care organization, and any other similar parameters. Additionally or alternatively, the dataset can include or otherwise detect periodic biometrics or biometrics that occur in some pattern (e.g., from user input, from biometric monitoring devices worn by the user, or from algorithms that track the physical, emotional, or neurological state of the user). The dataset can include data sampled from the device at one time (e.g., at a single point in time, at the time of patient enrollment) or at multiple points in time (e.g., at random points, at regular points, in relation to triggering events, at other frequencies, etc.).

[0144] Other supplemental or contextual data can be received in connection with generating actionable insights. For example, the method can include capturing current treatment methods (e.g., existing medications, existing supplements, etc.) engaged in by the patient, trends in use or adherence to current treatment methods engaged in by the patient (e.g., increasing use, decreasing use, stable use, etc.), medical history, family medical history, and / or other information. Additionally or alternatively, additional data can include information related to the user’s environment, such as the user’s location (e.g., as determined from a global positioning device, from a triangulation device), the user’s environmental temperature, the user’s environmental audio, and any other suitable environmental information related to potential stimuli that affect health and / or environmental devices that can be used in connection with outputs (e.g., diagnoses, treatments, etc.) associated with subsequent blocks of the method. Additionally or alternatively, additional data can include information from assessments or procedures experienced by the user, such as imaging (e.g., information from an angiogram or a coronary calcium scan or CCTA, etc.), interventions (e.g., gene editing, epigenetic silencing, etc.), and any other similar techniques or methods.

[0145] The compositions and methods described herein can be adapted to different populations (e.g., Midwestern Americans, Native Americans, etc.), different demographic characteristics (e.g., age, sex, etc.), different health conditions (e.g., diabetes, known risk factors, etc.), different lifestyles (e.g., smoking, diet type, etc.), different users (e.g., clinicians, employers, insurance companies, etc.), different interventions (e.g., drug A versus drug B), and / or other factors (e.g., social determinants of health, family history, etc.). These adaptations are intended to enhance health outcomes, improve care and / or understanding, manage and mitigate risk.

[0146] Methods of personalized intervention

[0147] Once one or more measurements are received in connection with a patient, the compositions and methods described herein can include: (A) performing uncertainty quantification of the markers; (B) performing quality control of the samples and / or markers; (C) performing risk assessment and / or diagnosis; (D) performing uncertainty quantification to assess confidence of the assessment; (E) determining contribution of one or more biomarkers; (F) identifying causal relationships or associations of biomarkers to disease and treatment pathways; (G) generating one or more personalized interventions, one or more treatments, management, and / or monitoring for the patient or user; (H) predicting one or more estimated outcomes and / or costs associated with one or more personalized interventions, one or more treatments, management, and / or monitoring; (I) and / or performing one or more personalized interventions, one or more treatments, management, and / or monitoring for the patient. See Table 5.

[0148] Table 5

[0149]

[0150] The order of operations can be changed, and some steps are not essential for system operation. This process can be repeated multiple times to monitor and assess the effectiveness of the intervention, treatment(s), management, and / or monitoring, and to update the intervention, treatment(s), management, and / or monitoring recommendations. The following description with respect to Table 5 is merely exemplary and is not intended to be limiting.

[0151] Row (A) relates to uncertainty quantification, which can encompass all aspects of marker measurement. For example, in epigenetic measurements, uncertainty quantification can include, but is not limited to, sampling error, reagent quality, instrument, and human error.

[0152] Row (B) relates to uncertainty quantification mentioned herein, which can be used to perform quality control. For example, one or more known reference samples and / or one or more known reference measurements can be compared to one or more new measurements. The difference between the one or more known measurements and the one or more new measurements, and their uncertainty, can be used to assess one or more errors and / or one or more uncertainties and how they compare to defined acceptable thresholds. This process aids in identifying sources of errors and / or uncertainties and minimizing such one or more errors and / or one or more uncertainties to ensure the reliability of the one or more measurements. For example, it can be used to determine whether one or more samples need to be re-measured one or more times or re-collected one or more times to meet defined acceptable thresholds for the one or more measurements and / or one or more markers.

[0153] Row (C) relates to returning one or more baseline states or one or more subsequent states and identifying feature sets (e.g., diagnostic and / or therapeutic identification features associated with one or more patients’ genomic and demographic features) when processing data (e.g., imaging, lifestyle, etc.) and / or measurements (e.g., DNA methylation, genetic biomarkers, etc.). Row (C) includes transforming data into various identification features, which can be used to characterize one or more patients and generate a personalized intervention, treatment, management, and / or monitoring plan for one or more patients based on the characterization of the one or more patients.

[0154] The one or more transformation operations can include one or more of: graph-based methods, linear and non-linear dimensionality reduction, application of supervised, semi-supervised, and unsupervised machine or statistical inference methods for deriving informative features from the one or more measurements and / or data, imputation of missing sites, determination of genetic ancestry of the patient, estimation of genetic parameters including genetic diversity and homozygosity, estimation of scores representing genetic risk, estimation of scores representing acquired risk, and estimation of values for qualitative, quantitative, continuous, and categorical traits normalized for biological sex, genetic ancestry, age, socioeconomic status, measurements, lifestyle variables, and any other suitable parameter or parameters. In some cases, the traits can be normalized for biological sex, genetic ancestry, age, socioeconomic status, measurements, lifestyle variables, and any other suitable parameter or parameters.

[0155] With respect to the one or more measurements and / or monitoring devices described herein, row (C) can also include signal processing operations including one or more of: denoising, filtering, smoothing, clipping, transforming discrete data points into continuous functions, and performing any other suitable signal conditioning process. For example, some variants of row (C) can additionally include performing windowing operations and / or performing signal cleaning operations. Signal cleaning can include removing signal anomalies by one or more filtering techniques. In particular examples, the filtering can include one or more of: Kalman filtering techniques, bootstrap filtering techniques, particle filtering techniques, Markov Chain Monte Carlo filtering techniques; and / or another suitable technique. Thus, signal cleaning can improve data quality for further processing with respect to one or more of: noise, sensor balance, sensor drift, environmental influences (e.g., humidity, physical interference, etc.), and any other suitable type of signal artifact.

[0156] The baseline state is used to establish a reference state against which progress is compared when the patient engages in the generated personalized intervention, treatment, management, and / or monitoring plan. The baseline state is preferably associated with the patient's state prior to engaging in the personalized intervention, treatment, management, and / or monitoring plan (e.g., epigenetic baseline state, coronary heart disease baseline state, etc.) such that the baseline state characterizes the patient's state prior to treatment or intervention or care in accordance with the personalized intervention, treatment, management, and / or monitoring plan. However, the baseline state can alternatively characterize another suitable state of the patient. Moreover, the methods described herein can include reestablishing the "baseline" state of the patient in coordination with the provision of the personalized intervention, treatment, management, and / or monitoring plan. As such, the baseline state can be updated as the patient progresses during engagement in the personalized intervention, treatment, management, and / or monitoring plan, at which point data, prognostic, outcome, cost, risk, diagnostic, and / or therapeutic identification features can direct the patient to a different personalized intervention, treatment, management, and / or monitoring plan.

[0157] The baseline state can also characterize the physiological state of the patient with respect to a condition or indication (e.g., health condition, disease state, etc.). As such, the baseline state can characterize a clinical diagnosis, a laboratory diagnosis, a radiological diagnosis, a histological diagnosis, a primary diagnosis, an admission diagnosis, a differential diagnosis, a prenatal diagnosis, an exclusion diagnosis, and / or other diagnostic criteria. Additionally or alternatively, the baseline state can characterize aspects associated with a condition or indication (e.g., high cholesterol, etc.). In some embodiments, the baseline state can characterize a risk assessment, a treatment pathway, a cost estimate, a prognosis, a health outcome, or any one or more other suitable parameters.

[0158] In some embodiments, the diagnostic identification features generated in row (C) can include one or more of the following: one or more measured values (e.g., genetic identification features, epigenetic identification features, epigenetic identification features associated with coronary heart disease, HbAlc, etc.), additional data (e.g., lifestyle, demographic features, imaging, etc.) indicative of a reduced or increased likelihood of developing a health condition or indication. In some embodiments, the identification features based on one or more of the factors and data outlined herein can be used for a risk assessment, a treatment pathway, a cost estimate, a prognosis, a health outcome, or any one or more other suitable parameters.

[0159] In some embodiments, the diagnostic signature generated in row (C) can include one or more of the following: one or more measured values (e.g., genetic signature, epigenetic signature, epigenetic signature associated with coronary heart disease, HbAlc, etc.), additional data (e.g., lifestyle, demographic features, imaging, etc.) indicative of a reduced / increased likelihood of improvement or remission of the health condition or indication. The signature can be used to develop lifestyle change recommendations and / or treatments (e.g., pharmaceutical, medical devices, nutritional, stem cell therapy) and / or interventions (e.g., gene editing, base editing, epigenetic silencing, epigenetic editing) and / or care and / or understanding, management and / or mitigation of one or more risks. Additionally or alternatively, one or more interventions can be used to generate a personalized intervention, treatment, management and / or monitoring plan with respect to implementing a personalized and combination treatment approach, care, intervention and risk management of different methods.

[0160] The biomarker signature and one or more baseline states or one or more subsequent states and diagnostics, risk assessments, personalized treatments, cost estimates, prognostics, health outcomes developed using the compositions and methods described herein can be for one or more health conditions or indications.

[0161] Row (G) indicates that upon processing one or more baseline states or one or more subsequent states, a set of diagnostic signatures, and a set of treatment and intervention signatures with a model for transforming the signatures into a customized combination of one or more treatments and / or one or more interventions and / or management and / or care methods tailored to improve or maintain and / or improve the health condition or indication of the patient, a personalized intervention, treatment, management and / or monitoring plan can be made for the patient. Instead of diagnostic signatures, the signatures can be risk assessments, treatment approaches, cost estimates, prognostics, health outcomes, or signatures of any one or more other suitable parameters.

[0162] One or more markers and / or one or more models can be used to provide one or more personalized interventions, one or more treatments, one or more managements, and / or monitoring of one or more patients and / or one or more users. One or more markers and / or one or more models can be used as a basis for designing and / or developing and / or optimizing one or more personalized interventions, one or more treatments, one or more managements, and / or monitoring of one or more patients. For example, one or more markers and / or one or more models can be used in drug development, drug development, understanding studies, or to understand or predict side effect profiles, define eligibility criteria for studies or clinical trials, effectiveness of drugs in a clinical or clinical trial setting.

[0163] One or more markers can be used to measure the impact of one or more personalized interventions, one or more treatments, one or more managements, and / or one or more monitoring of one or more patients and / or one or more users (e.g., cost reduction, improvement in health, etc.). The impact of one or more markers can be quantified for one or more personalized interventions, one or more treatments, one or more managements, and / or one or more monitoring of one or more patients and / or one or more users. By continuously monitoring (measuring and collecting data) one or more personalized interventions, one or more treatments, one or more managements, and / or one or more monitoring of one or more patients and / or one or more users, the impact of one or more markers can be re-evaluated over time. The re-evaluated impact of one or more markers can be used to optimize one or more personalized interventions, one or more treatments, one or more managements, and / or one or more monitoring of one or more patients and / or one or more users. For example, the re-evaluated impact of one or more markers can be used to optimize drug compounds and / or dosages, etc. The re-evaluated impact of one or more markers can be used to optimize one or more personalized interventions, one or more treatments, one or more managements, and / or one or more monitoring of one or more patients and / or one or more users. The re-evaluation of one or more markers and / or one or more models can be at regular intervals or one or more random time intervals.

[0164] The model is preferably constructed to process the identified features and / or one or more baseline states and / or one or more subsequent states generated from the rows (C) and return a personalized intervention, treatment, management, and / or monitoring plan customized for one or more patients and / or one or more users. The model can return a set of measurements (e.g., SNPs, methylation markers, etc.) and one or more insights (e.g., percentage of employees at high risk of heart attack, etc.) for the patients and / or users and generate its personalized intervention, treatment, management, and / or monitoring plan from the one or more measurements, data, and / or one or more insights.

[0165] The personalized intervention, treatment, management, and / or monitoring plan can have subparts (e.g., modules, phases) that can include portions comprising one or more of: a personalized medication regimen, a personalized supplement regimen, personalized lifestyle recommendations, medical procedures, testing recommendations, preventive health care treatment methods, and / or other suitable aspects. Further, the personalized intervention, treatment, management, and / or monitoring plan can be characterized with a duration, such that the patient can complete the program and achieve one or more health goals. As such, generating the personalized intervention, treatment, management, and / or monitoring plan can include returning recommendations (e.g., medication recommendations, gene editing, epigenetic silencing, target BMI, etc.) and / or care components, guidance components, risk management components delivered in-person and / or digitally based on one or more measurements and / or data and / or one or more insights of the patient(s). However, the personalized intervention, treatment, management, and / or monitoring plan can be configured in other ways.

[0166] The row (G) can include generation of instructions that can be executed by a system having a computing element. For example, one or more components of the personalized intervention, treatment, management, and / or monitoring plan can be delivered digitally by a mobile device application by way of an application interface between a care or guidance entity and the patient(s) being treated.

[0167] In one example, the personalized intervention, treatment, management, and / or monitoring plan can have a set duration (e.g., 36 weeks, 24 weeks, 12 weeks, another suitable number of weeks, etc.) and can be configured for delivery with one or more patients using one or more interfaces (e.g., a web interface, a mobile device interface, a wearable computing device interface, a telephone interface, a face-to-face interface, an interface with one or more robotic devices, etc.).

[0168] The example personalized intervention, treatment, management, and / or monitoring plan can have one or more phases configured to facilitate a change in a marker or a marker aggregate of the patient(s), provide a therapeutic intervention, and achieve a desired outcome with respect to the generated diagnosis and characterization (e.g., based on diagnostic features processed by the model, based on therapeutic features processed by the model, etc.). In some variations, the desired outcome can be with respect to a risk assessment, a treatment pathway, a cost estimate, a prognosis, a health outcome, or any one or more other suitable parameters.

[0169] In one example, the first phase has a duration (e.g., 4 weeks, another suitable number of weeks) configured to direct one or more patients to focus on establishing a baseline health status, indicators, insights, and / or habits, the function of which is to track lifestyle via a mobile device application. In an example, the second phase has a duration (e.g., 12 weeks, another suitable number of weeks) focused on individualized treatment, care, management approaches for one or more patients to produce a behavior change. In an example, the third phase has a duration (e.g., 8 weeks, another suitable number of weeks) focused on individualized treatment, care, management approaches for stabilizing a patient with respect to maintaining a desired state (e.g., establishing and maintaining healthy habits, preventing relapse, maintaining remission, etc.).

[0170] With respect to individualized intervention, treatment, management, and / or monitoring plans, the platform can provide a kit (e.g., genetic and epigenetic sampling kit, connected devices, biometric devices, instructions, etc.), and interaction by one or more patients with the kit facilitates establishment of a physiological baseline that can be used as a reference point with respect to progress of the individualized intervention, treatment, management, and / or monitoring plan. In an example, the kit can be mailed (e.g., as facilitated by the platform) to a patient’s residence or location. The kit also provides instructions for downloading an application having an interface to the platform, and functionality for receiving input related to the lifestyle data sets described herein. In one particular example, a patient is prompted to download a mobile application, complete a lifestyle collection form, and schedule a consultation session as part of the individualized treatment, care, management approach.

[0171] Subsequently, with respect to the personalized intervention, treatment, management, and / or monitoring plan, the platform can guide and support the patient over a period of time (e.g., weeks, months) using a counseling entity (e.g., a professional counselor, a clinician, an artificial intelligence counseling entity, etc.) through regular sessions (e.g., weekly and bi-weekly sessions), which can be pre-scheduled and / or ad-hoc. The counseling sessions in a particular example can be 15-20 minute phone behavioral counseling sessions, but variations of the example can have other durations and / or be provided in other forms. The personalized intervention, treatment, management, and / or monitoring plan provides a personalized treatment and intervention pathway that is configured to reconfigure the patient’s condition or indication to achieve a goal (e.g., a 5-10% reduction in risk score). With respect to the personalized intervention, treatment, management, and / or monitoring plan generated in line (G), the personalized and actionable insights are returned by the model and delivered to the patient (e.g., through an entity, through an application interface, through other interfaces with the platform, etc.) at stages of the personalized intervention, treatment, management, and / or monitoring plan that one or more patients complete (e.g., completing tasks, interacting with modules, interacting with tools for monitoring diet (e.g., by uploading photo records of their meals / diets / consumption), monitoring their lifestyle vitals (e.g., smoking cessation, exercise, weight loss, etc.) through a mobile application and wireless scale, etc.). The patient can participate in the personalized intervention, treatment, management, and / or monitoring plan at any time and place via their mobile device application and / or web application, which allows for flexible participation. Additionally or alternatively, the personalized intervention, treatment, management, and / or monitoring plan can provide timely tasks and / or prompt interactions in a timely manner with respect to more urgent states of the patient (e.g., triggering events such as heart attack, etc.).

[0172] The application environment (e.g., a mobile application environment, a web application environment, etc.) can support one or more of the following: a diet consumption log (e.g., a food log, a drink log, etc.), which can receive input from the patient and / or automatically track the patient’s consumption (e.g., in coordination with applications supported by Apple Health™, Google Health™, etc.); medication usage; personalized meal and exercise plans or any other parameters that are known or generated by the personalized intervention, treatment, management, and / or monitoring plan. Additionally or alternatively, the application environment can include an interface for connecting with (e.g., as described herein for automatic weight, cardiovascular parameter tracking, blood analyte parameter tracking, motion tracking, etc.) smart devices (e.g., using Bluetooth™, using another protocol).

[0173] The application environment can further support remote health interactions between the patient and a clinician providing counseling / healthcare. For example, the application environment can provide one or more of the following: a communication interface connecting and / or facilitating delivery of care to one or more patients (e.g., by automating processing of insurance claims, by generating appointments, by enabling counseling with a clinician, etc.); a communication interface providing constant or near-constant access (e.g., 24 hours, 7 days a week access, etc.) to trained coaches, nutritionists, counselors, etc.; a communication interface enabling remote health group coaching; exercise regimen components (e.g., group fitness content, exercise guidance content, such as yoga content, etc.); stress management materials (e.g., provided to the patient in response to a detected stress state and / or triggering event, provided to the patient such that the patient can access the content in a convenient manner, etc.); an interface to a private (e.g., invitation-only) social network or community; tasks (e.g., health habit challenges); an interface for reward offerings (e.g., community celebrations, incentives, other benefits, etc.); and other suitable interfaces. However, the application environment can support other suitable functionality associated with the individualized intervention, treatment, management, and / or monitoring plan.

[0174] Line (I) relates to executing an individualized intervention, treatment, management, and / or monitoring plan for a patient, where executing the individualized intervention, treatment, management, and / or monitoring plan can involve executing components of the intervention, treatment, management, and / or monitoring plan through the interfaces described herein and / or associated with the systems described below. As such, the execution can involve a mobile device application interface, a web application interface, an interface with an entity (e.g., a human care providing entity, a digital care providing entity, etc.), and / or other suitable interfaces.

[0175] The execution of the individualized intervention, treatment, management, and / or monitoring plan can be based on an individual, multiple, or aggregation of one or more of the following: financial (e.g., cost of care, cost of medication, etc.), prevalence (e.g., percentage risk of heart attack, etc.), lab test (e.g., DNA methylation level, change in inflammation level, etc.), imaging (e.g., FFR from CCTA, etc.), medical (e.g., risk score, data from electronic medical records, etc.), clinical (e.g., blood pressure level, presence of symptoms such as chest pain, etc.), comorbidity (e.g., obesity, diabetes, hypertension, hypercholesterolemia, etc.), treatment (e.g., type of statin available, etc.), supplement (e.g., vitamin D, vitamin B12, iron agent, etc.), lifestyle (e.g., smoking, drinking, exercise frequency, etc.), or other suitable data.

[0176] Execution of the personalized intervention, treatment, management, and / or monitoring plan produces outcomes for patients and / or other users (e.g., employers, payers, etc.) participating in their respective personalized intervention, treatment, management, and / or monitoring plan, examples of which include: improved engagement (e.g., 93% of participants enrolled; a significant proportion of participants still participating after 60 days); improved outcomes (e.g., significant weight loss, significant reduction in diabetes-associated A1C levels, significant reduction in cardiovascular symptoms, changes in one or more DNA methylation biomarkers associated with cardiovascular disease risk, status, or comorbidities, reduced mortality, etc.); reduced medication use / need; reduced health care costs; reduced events (e.g., reduced number of emergency room visits, reduced number of heart attacks, etc.); and other suitable benefits.

[0177] Additionally or alternatively, improved outcomes can be measured at an individual level or in aggregate numbers of patients within a cohort or relative to prior levels or compared to another cohort, and can include: percent weight loss, weight loss over a period of time, average number of months maintaining weight loss after completing a program, average reduction in HbA1C levels, average reduction in fasting glucose, percent change in DNA methylation, directionality of DNA methylation changes, and other improved outcomes.

[0178] Execution of the personalized intervention, treatment, management, and / or monitoring plan in row (I) can include providing results presented in one or more sections of one or more reports generated from model output (e.g., within an application environment), determined based on one or more biomarkers of the same or different types. The reports can then be sent to relevant entities (e.g., patients, caregivers, insurance companies, etc.) through a mobile application and / or web application architecture. Execution of the personalized intervention, treatment, and / or monitoring plan in row (I) can further implement individual biomarkers and / or aggregate biomarker profiles to guide the process of precision care and / or monitoring and / or management and / or treatment and / or guidance for patients.

[0179] The implementation of the personalized intervention, treatment, management, and / or monitoring plan in line (I) can further include providing a personalized care program that implements physical markers, clinical markers, lifestyle markers, epigenetic and genetic profiles, and personalized health coaching to manage an outcome of interest (e.g., weight loss, reduction in risk of heart attack). According to the personalized care program, the patient can be provided with digital tools for tracking lifestyle and mind-body health markers (i.e., blood pressure, heart rate, weight, sleep, hunger, cravings, stress, meditation, superfoods, energy, foods to avoid, exercise, etc.), logging their habits and markers (e.g., through photo journal, through text journal, through wearable device, through app, etc.), and assigned a health coach who will work with the patient in person through guided sessions according to the patient’s schedule to interpret personalized reports generated from the patient’s tracking and data. According to the personalized care program, the reports can provide a breakdown of the markers being tracked (e.g., obesity risk, etc.) based on the individual’s data and one or more measurements (e.g., epigenetic profile, age, etc.). The program can be targeted to one or more outcomes of interest (e.g., reduce their blood pressure by 5% within 90 days of the start of the program, reduce the number of emergency department visits by employees). To achieve this outcome, example implementations of the program can include automated and manual tools for incentivizing participants to make gradual lifestyle changes, reminders for tracking progress, and tools for tracking progress.

[0180] In specific examples, the implementation of the personalized intervention, treatment, management, and / or monitoring plan based on the described model outputs and / or data can not include all elements (such as health coaching) or can be replaced with similar elements (e.g., health coaching replaced with a clinician) or can add other elements (e.g., add a clinician in addition to health coaching). Additionally, the outcomes measured in implementing the personalized intervention, treatment, management, and / or monitoring plan can be used to iterate, or optimize or change the personalized intervention, treatment, management, and / or monitoring plan.

[0181] In specific examples, personalized intervention, treatment, management, and / or monitoring plans based on the aforementioned model output and / or data can be used to quantitatively or qualitatively evaluate individual, multiple, aggregate, comparative, or simultaneous changes in one or more of the following at one or more time points: financial (e.g., care costs, medication costs, etc.), prevalence (e.g., percentage of employees at risk of heart attack, etc.), laboratory tests (e.g., changes in DNA methylation levels, inflammation levels, etc.), imaging (e.g., FFR from CCTA, etc.), medical (e.g., changes in indicators reported in electronic medical records, etc.), clinical (e.g., changes in blood pressure, reduction in the severity of symptoms such as chest pain, etc.), comorbidities (e.g., obesity, diabetes, hypertension, hypercholesterolemia, etc.), treatments (e.g., type of statin associated with the largest change in lipid levels, etc.), supplements (e.g., vitamin D, vitamin B12, iron, etc.), lifestyle (e.g., smoking, alcohol consumption, exercise frequency, etc.), or one or more other suitable parameters, said evaluation at or against one or more baseline states of the patient or patient group or user or user group undergoing the personalized intervention, treatment, management, and / or monitoring plan.

[0182] A set of cardiovascular symptoms may include one or more of the following: pain levels (e.g., chest pain, limb pain, neck pain, throat pain, abdominal pain, back pain, etc.), chest tightness, chest pressure, angina, respiratory distress (e.g., tachypnea, blood oxygen saturation, respiratory rate, etc.), limb numbness, limb strength, degree of vascular stenosis, cardiovascular parameters (e.g., heart rate, heart rate variability, blood pressure, cardiac output, ECG markers, stroke volume, cardiac index, etc.), cholesterol levels (e.g., HDL levels), blood glucose levels, HbA1c levels, percentage of stenosis, degree of occlusion, fractional flow reserve, DNA methylation value, genetic profile, and other cardiovascular symptoms. Cardiovascular symptoms may be associated with one or more of the following: coronary artery disease, coronary artery disease, hypertension, cardiac arrest, congestive heart failure, arrhythmia, peripheral artery disease, stroke, congenital heart disease, and / or other diseases or comorbidities.

[0183] The methods described herein can induce individual and / or simultaneous changes in one or more of the factors described herein over a duration of less than 30 days, 30–60 days, 60–90 days, 90–120 days, any intermediate number of days, or more than 120 days. Variations of the methods described herein can induce individual and / or simultaneous changes in one or more of the factors described herein in a patient's body.

[0184] Additionally or alternatively, the methods described herein can be used to evaluate changes in one or more of the factors described herein, alone and / or simultaneously, at one time (e.g., at a single point in time) or at multiple points in time (e.g., at random points, at periodic points, in relation to a triggering event, at other frequencies, etc.).

[0185] While this specification contains many specifics, these should not be construed as limitations on the scope of any invention, but rather as descriptions of particular implementations of the inventions. Certain features that are described in the context of separate implementations can also be implemented in combination with each other. Conversely, various features that are described in the context of a single implementation can also be implemented separately from that single implementation or in any other suitable combination. Moreover, although features can be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination and the claimed combination can be directed to a sub-combination or a variation of a sub-combination.

[0186] While certain implementations of methods and compositions described herein have been described herein for illustrative purposes, it can be recognized that various modifications can be made of the described implementations without deviating from the spirit and scope of the methods and compositions. It will be understood by those within the art that, in light of the preceding disclosure, modifications and / or changes can be made by those skilled in the art without departing from the scope of this disclosure. It will be appreciated that some embodiments can be comprised of one or more generic steps or operations, without departing from the scope of the claims.

[0187] Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring such order, nor that all illustrated operations be performed, to implement the desired results. In certain circumstances, multitasking and parallel processing can be advantageous. Moreover, the separation of various system components in the implementations described herein should not be understood as requiring such separation in all implementations, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0188] Accordingly, particular implementations of the subject matter have been described. Other implementations can fall within the scope of the claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the process depicted in the accompanying figures can not require the particular order shown, or sequential order, to achieve the desired results. In some implementations, multitasking and parallel processing can be advantageous.

Claims

1. A method comprising: generating, by a computer system, a user interface for display on a display device operatively coupled to the computer system; generating, by the computer system, first data comprising genetic, epigenetic, and / or other biomarker test results of a patient to evaluate whether the patient has a disease, disorder, or risk; displaying the user interface on the display device; and displaying the first data within the user interface. the data is selected from the group consisting of: measurements (e.g., weight, blood pressure, etc.), test results (e.g., genetic, epigenetic, protein, metabolic assays, etc.), financial (e.g., cost of surgery, cost of medication, cost of claim, etc.), industry / prevalence (e.g., heart disease prevalence in a particular geographic region, number of heart attacks per year for truck drivers, etc.), interventions (e.g., surgery, etc.), medical (e.g., ICD10 codes, medication usage, etc.), clinical (e.g., blood pressure, etc.), therapeutic (e.g., statin cost, anti-inflammatory medication, etc.), lifestyle (e.g., smoking, drinking, exercise frequency, etc.), supplement usage (e.g., herbal, vitamin D, vitamin B12, iron, etc.), electronic data (e.g., imaging, electronic health records, publicly available data (e.g., repositories, etc.), publications, pharmaceuticals, clinical trials, etc.), and diagnostic, intervention, management, monitoring, and / or therapeutic implications thereof.

2. The method of claim 1, wherein, the data comprises independent data, aggregated data, interpolated data, derived data, numerical data, textual data, image data, and combinations thereof.

3. The method of claim 1 or 2, wherein, the data is displayed in the user interface in one or more plots.

4. The method of any one of claims 1 to 3, wherein, the data is compared to corresponding genetic, epigenetic, and / or other biomarker test results from a cohort population.

5. The method of any one of claims 1 to 4, wherein, the data is overlaid on genetic, epigenetic, and / or other biomarker test results of a population.

6. The method of any one of claims 1 to 5, wherein, the user interface displays diagnostic information, prognostic information, uncertainty quantification, clinical and / or business risk management or decision making, regulatory and / or policy making, intervention, monitoring, and / or therapeutic decisions and strategies related to a patient or group of patients or a user or group of users.

7. The method of any one of claims 1 to 6, wherein, genetic, epigenetic, and / or other biomarker test results of a population of patients comprise a bar chart showing ages of the population of patients on an X-axis and probabilities of patients of different ages having the disease, disorder, or risk on a Y-axis, wherein the test results of the patient comprise a probability of the patient having the disease.

8. The method of any one of claims 1 to 7, wherein, the patient is associated with an age, wherein the method further comprises displaying the probability of the patient having the disease adjacent to the probability of a population of patients of the same age as the patient.

9. The method of any one of claims 1 or 8, wherein, the patient is associated with a gender, wherein the method further comprises displaying the probability of the patient having the disease adjacent to the probability of a population of patients of the same gender as the patient.

10. The method of any one of claims 1 to 9, wherein, 11. The method of any one of claims 1-10, further comprising: ​ receiving a plurality of genetic, epigenetic, and / or other biomarker contributions of the genetic, epigenetic, and / or other biomarkers to the disease in the patient; generating a chart comprising, on an X-axis, names of the plurality of markers, and a normalized ranking of the plurality of genetic, epigenetic, and / or other biomarker contributions to the patient; superimposing the chart with another chart showing normalized rankings of the plurality of genetic, epigenetic, and / or other biomarker contributions to the patient population, resulting in a second plot of the ranking versus the marker; and displaying the second plot adjacent to the plot within the user interface.

12. The method of any one of claims 1-11, further comprising: generating a plot of a distribution of genetic, epigenetic, and / or other biomarker measurements associated with a particular genetic, epigenetic, and / or other biomarker; superimposing the genetic, epigenetic, and / or other biomarker measurements measured for the patient on the plot; and displaying the plot with the superimposed genetic, epigenetic, and / or other biomarker measurements within the user interface.

13. The method of any one of claims 1-12, further comprising: determining an upper limit and a lower limit of uncertainty associated with the genetic, epigenetic, and / or other biomarker measurements measured for the patient; and displaying the upper limit and the lower limit defining the genetic, epigenetic, and / or other biomarker measurements within the plot.

14. The method of any one of claims 1-13, further comprising: detecting a selection of the data displayed within the user interface; in response to detecting the selection, displaying a window adjacent to the data within the user interface; and displaying a hyperlink to additional information within the window.

15. The method of claim 14, wherein, The additional information comprises literature related to the genetic, epigenetic, and / or other biomarker test results, or related to the disease, disorder, or risk.

16. The method of any one of claims 1 to 15, wherein, The literature is selected from publications, clinical data, clinical trials, and pharmaceuticals.

17. A computer-readable medium storing computer instructions configured to cause one or more computer processors to perform operations comprising the method of any one of claims 1-16 when executed by the one or more computer processors.

18. A computer system comprising: one or more computer processors; and a computer-readable medium storing computer instructions configured to cause the one or more processors to perform operations comprising the method of any one of claims 1-16 when executed by the one or more processors. ​

Images