Systems and methods for risk-based diagnostic monitoring of neurodegenerative disease

Abstract

A system and method for risk-based diagnostic monitoring of neurodegenerative disease, wherein the system includes at least a processor, and a memory communicatively connected to the at least a processor. The memory may contain instructions configuring the at least a processor to receive a biological extraction wherein the biological extraction includes biomarker data, select a plurality of case data, wherein selecting a plurality of case data includes selecting, as the plurality of case data, medical data pertaining to a cohort associated with both cognitive impairment and at least a neurodegenerative-related pathology, generate a neurodegenerative risk model as a function of the selected plurality of case data, input the plurality of patient data including the biomarker data into the neurodegenerative risk model, generate, using the neurodegenerative risk mode, a neurodegenerative risk score, and output the neurodegenerative risk score to a requesting party.

Description

Attorney Docket No. 35944-100110SYSTEMS AND METHODS FOR RISK-BASED DIAGNOSTIC MONITORING OF NEURODEGENERATIVE DISEASE CROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of priority of U.S. Nonprovisional Application No. 19 / 034,972 filed on January 23, 2025 and entitled “SYSTEMS AND METHODS FOR RISK-BASED DIAGNOSTIC MONITORING OF NEURODEGENERATIVE DISEASE” the entirety of which is herein incorporated by reference in its entirety.FIELD OF THE INVENTION

[0002] The present invention generally relates to the field of medicine. In particular, the present invention is directed to systems and methods for risk-based diagnostic monitoring of neurodegenerative disease.BACKGROUND

[0003] Alzheimer's Disease (AD) is the #1 cause of dementia, affecting 6 million Americans. As such, 60-70% of dementia cases in the United States are due to AD, affecting nearly 1 in 9 Americans over 65. Up to 45% of AD cases may be preventable through lifestyle modification alone, which would impact more than 46 million Americans with preclinical AD, but only if the disease is detected early enough. Despite decades of research, AD incidence is increasing at a greater rate than would be predicted from aging alone and falls disproportionately on historically underrepresented communities — data have shown that Black populations see fewer AD diagnoses despite having higher risk factors, suggesting systemic issues in making dementia care equitable. While monoclonal antibody therapies (such as donanemab and lecanemab) may slow cognitive decline in some patients, they have not been shown to halt or reverse symptoms; the field now views cognitive impairment as a late stage of disease progression, occurring decades after previously undetected biological changes begin. For disease-slowing therapies to be used to their maximum effect, potential patients must be identified early and accurately. While nearly half of AD cases may be associated with modifiable risk factors, such as mid-life obesity, hypertension, alcohol intake, smoking, social isolation, or diabetes, potentially effective interventions are rarely put into place as early identification of individuals at risk is not widespread. There exists a significant need for preclinical tests that can identify individuals at risk so that prevention efforts can succeed along the spectrum of clinical care and research.Attorney Docket No. 35944-100110 SUMMARY OF THE DISCLOSURE

[0004] In an aspect, a system for risk-based diagnostic monitoring of neurodegenerative disease includes at least a processor and a memory communicatively connected to the at least a processor. Wherein the memory contains instructions configuring the at least a processor to receive a plurality of patient data including a biological extraction, wherein the biological extraction includes biomarker data, select a plurality of case data, wherein selecting the plurality of case data includes selecting, as the plurality of case data, medical data pertaining to a cohort associated with both cognitive impairment and at least a neurodegenerative-related pathology, generate a neurodegenerative risk model as a function of the selected plurality of case data, input the plurality of patient data including the biomarker data into the risk model, generate, using the risk model, a neurodegenerative risk score, and output the neurodegenerative risk score to a requesting party.

[0005] In another aspect, a method for risk-based diagnostic monitoring of neurodegenerative disease includes receiving a plurality of patient data including a biological extraction, wherein the biological extraction includes biomarker data, selecting a plurality of case data, wherein selecting the plurality of case data includes selecting, as the plurality of case data, medical data pertaining to a cohort associated with both cognitive impairment and at least a neurodegenerative-related pathology, generating a neurodegenerative risk model as a function of the selected plurality of case data, inputting the plurality of patient data including the biomarker data into the risk model, generating, using the risk model, a neurodegenerative risk score, and outputting the neurodegenerative risk score to a requesting party.

[0006] These and other aspects and features of non-limiting embodiments of the present invention will become apparent to those skilled in the art upon review of the following description of specific non-limiting embodiments of the invention in conjunction with the accompanying drawings.

[0007] For the purpose of illustrating the invention, the drawings show aspects of one or more embodiments of the invention. However, it should be understood that the present invention is not limited to the precise arrangements and instrumentalities shown in the drawings, wherein: FIG. 1 is a block diagram illustrating an exemplary system for risk-based diagnostic monitoring of neurodegenerative disease;FIG. 2 is a chart illustrating sensitivity and / or specificity for odds ratio based diagnostic algorithms; FIG. 3 illustrates a comparison of an index biomarker versus risk modeling;FIG. 4 illustrates a comparison of two different diagnostic models;FIG. 5 is an exemplary patient workflow;Attorney Docket No. 35944-100110 FIG. 6 is an exemplary patient interface illustrating a tracking visual based on snapshots of various interventions over time;FIG. 7 is a block diagram of an exemplary machine-learning process;FIG. 8 is a diagram of an exemplary embodiment of a neural network;FIG. 9 is a diagram of an exemplary embodiment of a node of a neural network;FIG. 10 is a flow diagram illustrating an exemplary method for risk-based diagnostic monitoring of neurodegenerative disease; andFIG. 11 is a block diagram of a computing system that can be used to implement any one or more of the methodologies disclosed herein and any one or more portions thereof. The drawings are not necessarily to scale and may be illustrated by phantom lines, diagrammaticrepresentations and fragmentary views. In certain instances, details that are not necessary for an understanding of the embodiments or that render other details difficult to perceive may have been omitted.DETAILED DESCRIPTION

[0008] At a high level, aspects of the present disclosure are directed to systems and methods for risk-based diagnostic monitoring of neurodegenerative diseases, such as AD. In an embodiment, the present system provides a key tool in AD diagnosis and prevention.

[0009] Aspects of the present disclosure can be used to model an individual's risk of developing AD. Aspects of the present disclosure can also be used to monitor disease progression before symptoms occur, opening the door to preventative interventions. This is so, at least in part, because by re-measuring risk periodically, it is possible to monitor how an individual's risk changes over time or in response to preventative interventions, making it a valuable tool for personalizing dementia prevention.

[0010] Diagnosis of AD before cognitive decline is an unmet need. An estimated 20% of individuals over the age of 50 have detectable amyloid or tau biomarkers, putting 46 million Americans at direct risk for developing AD-related cognitive decline. However, there are currently no diagnostics on the market indicated for use without self-reported cognitive decline. Clinicians are unable to determine a patient's risk of developing AD-related dementia and are only able to diagnose once symptoms have begun, which leaves patients unable to reach preventive interventions when they may be most effective, in the presymptomatic stage. Indeed, the diagnostic market is effectively confirmatory but not prospective and is able only to return results to patients after the window of intervention has mostly closed. Furthermore, many confirmatory diagnostics are deemedAttorney Docket No. 35944-100110 experimental by payers and are not covered fully by insurance. The development of a rigorous and regulated early AD diagnostic would be pivotal for making preventive dementia care accessible and equitable.

[0011] Recent advances in blood-based biomarkers have made it possible to use plasma sampling to reliably correlate early-stage AD cases with cerebrospinal fluid (CSF) biomarkers, which represents monumental strides in early biomarker detection. By using plasma rather than CSF or brain imaging methods, these diagnostics have lower requirements and cost than those of the past, which is an important step toward accessibility. However, because individual plasma biomarkers show imperfect differentiation between affected subjects and controls — that is, the distribution of concentrations overlap — they are unable to perfectly sort patients into a correct diagnosis. To get around this, many diagnostics rely on an "intermediate zone" of biomarker concentrations that is neither positive nor negative. In these cases, no diagnosis is made, and patients in this zone are recommended for more invasive or intensive follow-up testing to confirm a diagnosis.Unfortunately, individuals with indeterminate, slightly elevated biomarker levels may benefit most from preventive efforts.

[0012] Finally, these diagnostics are still built upon correlation with brain biomarker neuroimaging, itself an imperfect predictor of cognitive decline. Without a widely accepted mechanistic link between the measured biomarkers and cognitive decline or eventual disease state, exposure to radiation, and high cost, these measurements are unlikely to see wide-spread clinical implementation. Given this, diagnosis based on biomarkers alone has been criticized for a lack of applicability and potential harm for patients, and recent guidance documents have recommended against testing for AD biomarkers in the absence of cognitive complaints. Despite these technological advances, there still exists a strong clinical need for diagnostics which can be used to preserve cognition.

[0013] Early diagnosis must be risk-based rather than discriminatory. The current state of the market means that if we wait until we can diagnose symptomatic AD, it is already too late to prevent it. Our experiences over the last 15 years of developing and testing AD prevention strategies have shown that patients want to know and manage their risk of cognitive decline. This means that the most useful early diagnosis must be able to assess and monitor a patient's risk of developing AD, not only provide a confirmatory diagnosis. By shifting from a binary diagnostic product to one that can monitor patient risk as it changes over time, preclinical diagnosis becomes not only a possibility, but a welcome shift in the field, allowing patients and clinicians to work together to prevent dementia.Attorney Docket No. 35944-100110

[0014] Developing a risk model from biomarker data also shows promise as a discriminatory diagnostic. By integrating a single biomarker measurement — pTau217 — with prior AD risk, it is possible to develop a rudimentary risk score with higher sensitivity and specificity than traditional multivariate regression or machine learning models, while also eliminating the need for an "intermediate zone." A risk-based model of AD progression is more flexible and carries more clinical utility than a binary diagnostic model.

[0015] Aspects of the present disclosure allow for modeling an individual's risk of developing dementia as well as monitoring changes in risk and disease progression. Exemplary embodiments illustrating aspects of the present disclosure are described below in the context of several specific examples.

[0016] Referring now to FIG. 1, an exemplary embodiment of a system 100 for risk-based diagnostic monitoring of neurodegenerative disease is illustrated. In an embodiment, system 100 includes at least a processor 108 and a memory 112 communicatively connected to at least a processor 108. Memory 112 may contain instructions 116 configuring at least a processor 108 to receive a plurality of patient data 124 including a biological extraction 128, wherein the biological extraction 128 includes biomarker data 132, select a plurality of case data 136, wherein selecting the plurality of case data 136 includes selecting, as the plurality of case data 136, medical data 140 pertaining to a cohort associated with both cognitive impairment and at least a neurodegenerative-related pathology, generate a neurodegenerative risk model 144 as a function of the selected plurality of case data 136, input the plurality of patient data 124 including the biomarker data 132 into the risk model 144, generate, using the risk model 144, a neurodegenerative risk score 152, and output the neurodegenerative risk score 152 to a requesting party. In an embodiment, system 100 for risk-based diagnostic monitoring of neurodegenerative disease may monitor presymptomatic and / or symptomatic cases.

[0017] Still referring to FIG. 1, system 100 may include a computing device 104. Computing device 104 includes a processor 108 communicatively connected to a memory 112. As used in this disclosure, "communicatively connected" means connected by way of a connection, attachment or linkage between two or more relata which allows for reception and / or transmittance of information therebetween. For example, and without limitation, this connection may be wired or wireless, direct or indirect, and between two or more components, circuits, devices, systems, and the like, which allows for reception and / or transmittance of data and / or signal(s) therebetween. Data and / or signals therebetween may include, without limitation, electrical, electromagnetic, magnetic, video, audio,Attorney Docket No. 35944-100110 radio and microwave data and / or signals, combinations thereof, and the like, among others. A communicative connection may be achieved, for example and without limitation, through wired or wireless electronic, digital or analog, communication, either directly or by way of one or more intervening devices or components. Further, communicative connection may include electrically coupling or connecting at least an output of one device, component, or circuit to at least an input of another device, component, or circuit. For example, and without limitation, via a bus or other facility for intercommunication between elements of a computing device. Communicative connecting may also include indirect connections via, for example and without limitation, wireless connection, radio communication, low power wide area network, optical communication, magnetic, capacitive, or optical coupling, and the like. In some instances, the terminology "communicatively coupled" may be used in place of communicatively connected in this disclosure.

[0018] With continued reference to FIG. 1, memory 112 may include a primary memory and a secondary memory. "Primary memory" also known as "random access memory" (RAM) for the purposes of this disclosure is a short-term storage device in which information is processed. In one or more embodiments, during use of computing device 104, instructions 116 and / or information may be transmitted to primary memory wherein information may be processed. In one or more embodiments, information may only be populated within primary memory while a particular software is running. In one or more embodiments, information within primary memory is wiped and / or removed after the computing device 104 has been turned off and / or use of a software has been terminated. In one or more embodiments, primary memory may be referred to as "Volatile memory" wherein the volatile memory only holds information while data is being used and / or processed. In one or more embodiments, volatile memory may lose information after a loss of power. "Secondary memory" also known as "storage," "hard disk drive" and the like for the purposes of this disclosure is a long-term storage device in which an operating system and other information is stored. In one or remote embodiments, information may be retrieved from secondary memory and transmitted to primary memory during use. In one or more embodiments, secondary memory may be referred to as non-volatile memory wherein information is preserved even during a loss of power. In one or more embodiments, data within secondary memory cannot be accessed by processor 108. In one or more embodiments, data is transferred from secondary to primary memory wherein processor 108 may access the information from primary memory.

[0019] Still referring to FIG. 1, system 100 may include a database 120. The database 120 may include a remote database. The database 120 may be implemented, without limitation, as aAttorney Docket No. 35944-100110 relational database, a key -value retrieval database such as a NOSQL database, or any other format or structure for use as database that a person skilled in the art would recognize as suitable upon review of the entirety of this disclosure. The database 120 may alternatively or additionally be implemented using a distributed data storage protocol and / or data structure, such as a distributed hash table or the like. The database 120 may include a plurality patient data entries and / or records as described above. Data entries in database 120 may be flagged with or linked to one or more additional elements of information, which may be reflected in data entry cells and / or in linked tables such as tables related by one or more indices in a relational database. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which data entries in database 120 may store, retrieve, organize, and / or reflect data and / or records.

[0020] With continued reference to FIG. 1, system 100 may include and / or be communicatively connected to a server, such as but not limited to, a remote server, a cloud server, a network server and the like. In one or more embodiments, the computing device 104 may be configured to transmit one or more processes to be executed by server. In one or more embodiments, server may contain additional and / or increased processor power wherein one or more processes as described below may be performed by server. For example, and without limitation, one or more processes associated with machine learning may be performed by network server, wherein data is transmitted to server, processed and transmitted back to computing device 104. In one or more embodiments, server may be configured to perform one or more processes as described below to allow for increased computational power and / or decreased power usage by the system 100. In one or more embodiments, computing device 104 may transmit processes to server wherein computing device 104 may conserve power or energy.

[0021] Further referring to FIG. 1, Computing device 104 may include any computing device as described in this disclosure, including without limitation a microcontroller, microprocessor, digital signal processor (DSP) and / or system on a chip (SoC) as described in this disclosure.Computing device 104 may include, be included in, and / or communicate with a mobile device such as a mobile telephone or smartphone. Computing device 104 may include a single computing device operating independently, or may include two or more computing device operating in concert, in parallel, sequentially or the like; two or more computing devices may be included together in a single computing device or in two or more computing devices. Computing device 104 may interface or communicate with one or more additional devices as described below in further detail via a network interface device. Network interface device may be utilized for connecting computing deviceAttorney Docket No. 35944-100110 104 to one or more of a variety of networks, and one or more devices. Examples of a network interface device include, but are not limited to, a network interface card (e.g., a mobile network interface card, a LAN card), a modem, and any combination thereof. Examples of a network include, but are not limited to, a wide area network (e.g., the Internet, an enterprise network), a local area network (e.g., a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a data network associated with a telephone / voice provider (e.g., a mobile communications provider data and / or voice network), a direct connection between two computing devices, and any combinations thereof. A network may employ a wired and / or a wireless mode of communication. In general, any network topology may be used. Information (e.g., data, software etc.) may be communicated to and / or from a computer and / or a computing device. Computing device 104 may include but is not limited to, for example, a computing device or cluster of computing devices in a first location and a second computing device or cluster of computing devices in a second location. Computing device 104 may include one or more computing devices dedicated to data storage, security, distribution of traffic for load balancing, and the like. Computing device 104 may distribute one or more computing tasks as described below across a plurality of computing devices of computing device, which may operate in parallel, in series, redundantly, or in any other manner used for distribution of tasks or memory between computing devices. Computing device 104 may be implemented, as a non-limiting example, using a "shared nothing" architecture.

[0022] With continued reference to FIG. 1, computing device 104 may be designed and / or configured to perform any method, method step, or sequence of method steps in any embodiment described in this disclosure, in any order and with any degree of repetition. For instance, computing device 104 may be configured to perform a single step or sequence repeatedly until a desired or commanded outcome is achieved; repetition of a step or a sequence of steps may be performed iteratively and / or recursively using outputs of previous repetitions as inputs to subsequent repetitions, aggregating inputs and / or outputs of repetitions to produce an aggregate result, reduction or decrement of one or more variables such as global variables, and / or division of a larger processing task into a set of iteratively addressed smaller processing tasks. Computing device 104 may perform any step or sequence of steps as described in this disclosure in parallel, such as simultaneously and / or substantially simultaneously performing a step two or more times using two or more parallel threads, processor cores, or the like; division of tasks between parallel threads and / or processes may be performed according to any protocol suitable for division of tasks between iterations. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various ways inAttorney Docket No. 35944-100110 which steps, sequences of steps, processing tasks, and / or data may be subdivided, shared, or otherwise dealt with using iteration, recursion, and / or parallel processing.

[0023] In continued reference to FIG. 1, in an embodiment, at least a processor 108 may be configured to receive a plurality of patient data 124 including a biological extraction 128. In some embodiments, the biological extraction 128 may include biomarker data 132. "Patient data" refers to information collected about a patient throughout the patient's healthcare journey. Patient data may include personal information, medical history, family health history, clinical data, treatment records, diagnostic information, vital signs, medications, patient preferences, billing and insurance information, and / or the like. Furthermore, patient data may include a biological extraction 128, which may include biomarker data 132. A "biological extraction," as used throughout this disclosure, refers to the process of isolating or obtaining specific biological materials, compounds, or substances from living organisms or biological samples using various techniques. For example, and without limitation, a biological extraction 128 may include the extraction of biomolecules, which may include isolating proteins, nucleic acids (DNA / RNA), enzymes, lipids, or metabolites from biological samples using methods like centrifugation, chromatography, or solvent-based extraction methods. Biological materials obtained from biological extraction 128 may include blood, plasma, mucus, spit, and / or the like. In an embodiment, obtaining a biological extraction 128 may include the use of plasma separation cards (PSCs), which are commercially available medical devices that combine dried blood spot technology with capillary plasma separation to quickly and consistently create a sampling and transfer method that does not requiring trained phlebotomist or have hazardous material shipping restrictions. Further, in some embodiments, immunoassays, mass spectrometry, polymerase chain reaction, western blotting, fluorescence-based detection, microarray analysis, flow cytometry, electrochemical biosensors, cytokine, and chemokine measurements, immunohistochemistry, and / or the like may be used to obtain biomarker data 132 from biological extraction 128. As used throughout this disclosure, "biomarker data" refers to information derived from specific biological markers (biomarkers) that provide insights into an individual's health, disease status, or response to treatment. A "biomarker" is any measurable indicator found in the body that can reflect physiological or pathological processes, or the effects of a treatment. For example, and without limitation biomarkers may include genetic biomarkers, proteomic biomarkers, metabolic biomarkers, immunological biomarkers, and / or radiological biomarkers. Biomarkers may be found in various biological samples, for example, biomarkers may be found in blood, urine, tissue, saliva,Attorney Docket No. 35944-100110 and / or the like. Biomarkers may be used in disease diagnosis and monitoring, predictions of disease risk, personalized medicine, and / or monitoring treatment efficacy.

[0024] Further referencing FIG. 1, in an embodiment, biomarker data 132 may include a biomarker selected from a list including Af340, Af342, Neurofilament Light-chain [NFL], Glial Fibrillary Acidic Protein [GFAP], pTaul81, pTau217, and pTau231. In an embodiment, biomarker data may additionally and / or alternatively include the biomarkers ab40, ab42, ACHE, AGRN, ANXA5, APOE, APOE4, ARSA, BACE1, BASP1, BDNF, CALB2, Eotaxin, MCP4, TARC / CCL17, MCP1, MDC, Eotaxin-3, MIPla / CCL3, Miplb / CCL4, CD40L / TNFSF5, CD63, YKL40, CHIT1, CNTN2, CRH, CRP, GM-CSF, CST3, CX3CL1 / Fractalkine, CXCLl / GROa, IP-10, IL8, DDC, ENO2, FABP3, FCN2, FGF basic, VEGF Rl, FOLR1, GDF15, GDI1, GDNF, GFAP, GOT1, HBal; HBa2, HTT, ICAM1, IFN-gamma, IGF1R, IGFBP7, IL-10, IL12p70, IL-13, IL-15, IL-16, IL-17A, IL-18, IL-1 beta, IL-2, IL-33, IL-4, IL-5, IL-6, IL6R a, IL-7, IL9, VEGF R2, KLK6, MDH1, MME, MSLN, NEFH, NfL, NGF, NPTX1, NPTX2, NPTXR, NPY, NRGN, SNCAagg, PARK 7, PDGFRB, PDLIM5, PLGF, PGK1, POSTN, PRDX6, PSEN1, pTaul81, pTau 217, pTau231, PTN, REST, RUVBL2, S100A12, SIOOB, SAA1, SFRP1, SFTPD, SLIT2, SNAP25, pSNCA-129, a-Syn, fi-syn, SOD1, SQSTM1, TAFA5, TDP43 (both TAR DNA-binding protein 43 and / or TDP-43 with phosphorylation on serine 409), Tie-2 / TEK, TIMP3, TNF-a, sTREMl, TREM2, total Tau, UBB, UCHL1, VCAM1 / CD106, VEGF-A, VEGF-D, VGF, VILIP-1, YWHAG, and / or YWHAZ, PSEN2, pTau205, pTau 212, APOEe2, APOE3, alpha-synuclein, phosphorylated alpha-synuclein, PINK1, Parkin, LRRK2, and / or the like.

[0025] In continued reference to FIG. 1, in some embodiments, each of the biomarkers from the list may be selected for measurement. Integrating multiple biomarkers into a single assay can enhance diagnostic effectiveness, potentially due to increased sensitivity when more than one biomarker is included. For instance, a biomarker panel consisting of the seven biomarkers described above may be tested on a clinically characterized cohort with known cognitive profiles. Certain biomarkers are linked to neurodegenerative diseases. For example, and without limitation, amyloid beta and tau are linked to Alzheimer's disease, alpha-synuclein is linked to Parkinson's disease, neurofilament light chain (NfL) is a marker for neurodegeneration in general, and inflammatory markers such as elevated levels of cytokines or other inflammatory markers can be indicative of neurodegeneration. In some instances, an expanded panel of about 120 biomarkers related to central nervous system (CNS) diseases may be measured to broaden the search for biomarkers of interest beyond those with strong correlations to pathology. This may allow even low-fidelity biomarkers toAttorney Docket No. 35944-100110 inform neurodegenerative risk model 144 by treating every biomarker as an updated risk calculation. Use of a Bayesian risk model 172 may be pertinent in such an embodiment to account for weaker correlations with disease state, without diluting the overall strength of the model. Biomarker data 132 may be gathered using neuroimaging techniques, such as MM, PET scans, and / or the like. These imaging techniques may show structural changes in the brain, such as atrophy, amyloid plaques, and / or tau tangles. Imaging data may be incorporated into the risk model 144 as discussed in more detail below.

[0026] In continued reference to FIG. 1, a "Bayesian risk model" is a statistical model that uses Bayesian inference to assess and predict the risk of an event or outcome based on observed data, prior knowledge, and probability distributions. Bayesian risk models 12 may allow for quantification of uncertainty and to make predictions based on both prior beliefs (prior distributions) and new evidence (data observations). Bayesian risk models 172 may be especially useful when dealing with uncertainty and incomplete data, as they provide a structured way to update beliefs about the likelihood of risks as new information becomes available. Key concepts of a Bayesian risk model 172 include prior distribution, likelihood function, posterior distribution, and risk assessment. Prior distribution represents the prior belief or knowledge about a system before any new data is observed. In the present context, this may include an initial estimate of a risk factor, such as the probability of an individual developing a neurodegenerative disease. A likelihood function represents the probability of observing the data given a specific model or hypothesis. For example, the likelihood function may describe how likely it is to observe a set of symptoms in a patient if they have a particular disease. Posterior distribution updates prior beliefs after observing data using Bayes' Theorem, which incorporates new evidence to revise the likelihood of an event or outcome. The posterior distribution reflects the updated knowledge of risk after factoring in the observed data. Bayes' Theorem forms the foundation of a Bayesian model and is P(Risk OutcomelData) = (P(DatalRisk Outcome) * P(Risk Outcome)) / P(Data). Wherein: P(Risk OutcomelData) is the posterior probability (the updated belief about risk after observing data), P(DatalRisk Outcome) is the likelihood (how likely the observed data is given a risk outcome), P(Risk Outcome) is the prior probability (the initial belief about the risk), and P(Data) is the marginal likelihood (the probability of observing the data across all possible outcomes).

[0027] Further referring to FIG. 1, in an embodiment, Bayesian risk model 172 may begin with prior knowledge about a risk, which may be derived from historical data, expert opinions, and / or established theories. Bayesian risk model 172 may incorporate observed data by collecting orAttorney Docket No. 35944-100110 receiving new data and using it to calculate the likelihood of different risk outcomes. The beliefs may be updated using Bayes' Theorem, wherein the prior beliefs are updated with the likelihood of observing the new data, resulting in an updated posterior distribution that represents the new beliefs about the risk. Based on the posterior distribution, predictions about the likelihood of future events may be made. Bayesian risk model may be generated by defining a problem, gathering data, specifying probability distributions, applying Bayes' Theorem, and making predictions and decisions based on the posterior distribution. Specifying probability distributions may include choosing appropriate probability distributions for both the prior and likelihood. For example, a prior distribution might be a normal distribution reflecting historical data on risk factors, and the likelihood function may be based on conditional probabilities.

[0028] Still referring to FIG. 1, in an embodiment, at least a processor 108 may be configured to receive the plurality of patient data 124 from database 120. Database 120 may be local and / or remote. Database 120 may include one or more databases that likewise may be local and / or remote.

[0029] With further reference to FIG. 1, in an embodiment, the at least a processor 108 may be configured to select a plurality of case data 136, wherein selecting the plurality of case data 136 includes selecting, as the plurality of case data 136, medical data 140 pertaining to a cohort associated with both cognitive impairment and at least a neurodegenerative-related pathology. As used herein, "case data" refers to information collected about an individual case or instance within a study, clinical trial, or medical context. For example, case data may describe a wide range of data points that detail the circumstances, conditions, and outcomes related to that specific case. Case data may be used for analysis, diagnosis, and / or research purposes. For example, and without limitation case data may related to clinical case data or case data in research or studies, such as patient demographics, symptoms, diagnostic test results, treatment plans and responses, medical imaging or other diagnostic information, outcomes, baseline characteristics, interventions 188 or exposures experienced, observations and measurements during the study, responses to treatment or interventions 188, data on outcomes or endpoints of the study and / or the like. "Medical data" relates to any information related to a patient's health, medical history, treatments, and clinical encounters. For example, this may include personal information such as demographic details, medical history, clinical data, laboratory results imaging data, treatment and medications, vital signs, patient observations, insurance and billing information, genetic and molecular data, treatment outcomes, and / or the like. A "cohort" refers to a group of individuals who share a common characteristic orAttorney Docket No. 35944-100110 experience within a defined period. Here, the cohort may be associated with both cognitive impairment and at least a neurodegenerative-related pathology. As used herein, "cognitive impairment" is a noticeable decline in cognitive functions such as memory, attention, reasoning, problem-solving, and decision-making, which can interfere with an individual's ability to perform everyday tasks and function independently. Key features of cognitive impairment may include memory problems, attention and concentration issues, executive functioning decline, language and communication issues, and issues with judgement and decision-making. Types of cognitive impairment may include MCI, dementia, acquired cognitive impairment, and / or the like."Neurodegenerative- related pathology," as used throughout this disclosure, refers to the progressive and often irreversible damage to the structure and function of the nervous system, particularly the brain, caused by neurodegenerative diseases. Neurodegenerative diseases are characterized by the gradual degeneration of neurons, which impair various cognitive, motor, and sensory functions. For example, common neurodegenerative diseases may include Alzheimer's Disease, Parkinson's Disease, Huntington's Disease, Amyotrophic Lateral Sclerosis (ALS), Frontotemporal Dementia (FTD), and / or the like. Neurodegenerative-related pathology may involve a range of mechanisms, which may include neuroinflammation, oxidative stress, and / or mitochondrial dysfunction.

[0030] In further reference to FIG. 1, in an embodiment, selecting a plurality of case data 136 may include purposive or judgmental sampling. Wherein purposive or judgmental sampling includes selecting cases that meet specific criteria or have particular characteristics relevant to an end goal or question. For example, here, cases are selected based on their association with a cohort having both cognitive impairment and at least a neurodegenerative-related pathology. This may ensure that the plurality of patient data 124 is related to the purpose of the study or training, namely modeling the relationship between particular medical data 140 and cognitive impairment and neurodegenerative-related pathology.

[0031] Continuing to reference FIG. 1, in some embodiments, at least a processor 108 may be configured to generate a neurodegenerative risk model 144 as a function of the selected plurality of case data 136. As used herein, a "neurodegenerative risk model" is a mathematical model used to estimate the likelihood of developing a neurodegenerative disease based on one or more factors. For example, and without limitation the at least a processor 108 may transform the biomarker data 132 using a logistic regression model 148 to generate odds ratios for each individual biomarker with binary bins of no impairment and preclinical disease against mild cognitive impairment (MCI) and dementia. The at least a processor 108 may then generate a threshold cutoff value by maximizing theAttorney Docket No. 35944-100110 area under a receiver-operator characteristic curve (AUROC) for each biomarker. Further, the at least a processor 108 may sum the effective hazard ratio for each biomarker which generates an algorithm capable of differentiating individuals with and without cognitive impairment. The effective hazard ratio may be defined by the measured biomarker concentration minus the cutoff value times the hazard ratio. In one or more embodiments, additional biomarker data 132 may be integrated into the algorithm for diagnostic testing.

[0032] Still referring to FIG. 1, in some embodiments, the neurodegen erative risk model 144 may include statistical methods, such as logistic regression, survival analysis, and / or the like. In other embodiments, neurodegenerative risk model 144 may include machine-learning techniques such as decision trees, neural networks, random forests, and / or the like. In an embodiment, neurodegenerative risk model 144 may be trained using historical data from clinical studies or patient registries, where the relationships between various risk factors and the onset of neurodegenerative diseases has been established. For example, neurodegenerative risk model 144 may be trained using exemplary historical pluralities of patient data, including biomarkers correlated with cognitive impairment and at least a neurodegenerative-related pathology. Further, neurodegenerative risk model 144 may be retrained with new or updated patient data as time goes on. Retraining may include an iterative retraining using updated and new patient data. Training and / or retraining of neurodegenerative risk model 144 may occur at system 100 and or remotely.

[0033] With further reference to FIG. 1, in an embodiment, the at least a processor 108 may be configured to input the plurality of patient data 124 including the biomarker data 132 into the neurodegenerative risk model 144. In one or more embodiments, inputting a plurality of patient data 124 may include one or more inputs of a user. In other embodiments, inputting a plurality of patient data 124 may be automated. Wherein, the at least a processor 108 receives a plurality of patient data 124 passively and inputs the relevant data from the plurality of patient data 124 into neurodegenerative risk model 144 as a function of being available to system 100.

[0034] Continuing to reference FIG. 1, in an embodiment, the at least a processor 108 may be configured to generate, using neurodegenerative risk model 144, a neurodegenerative risk score 152. As used throughout this disclosure, a "neurodegenerative risk score" is a numerical or categorical value generated by a risk model that estimates the likelihood or probability of a patient developing a neurodegenerative disease. The neurodegenerative risk score 152 may combine various biomarkers to determine an individual's risk for developing a specific neurodegenerative disease. In some embodiments, the neurodegenerative risk score 152 may be presented as a number orAttorney Docket No. 35944-100110 percentage. Whereas, in other embodiments, the neurodegenerative risk score 152 may be presented as a categorical value. For example, this may include low, medium, high risk, or some other similar variation.

[0035] In continued reference to FIG. 1, in an embodiment, the at least a processor 108 may be further configured to integrate patient indicators of health risk 156 with the neurodegenerative risk score 152 to generate an integrated risk score 190. Wherein integrating the patient indicators of health risk 156 with the neurodegenerative risk score 152 may include receiving a plurality of patient indicators of health risk 156 including genomic data 160, biographical data 164, and lifestyle risk scores 168, receiving the neurodegenerative risk score 152, inputting the patient indicators of health risk 156 and the neurodegenerative risk score 152 into the neurodegenerative risk model 144 generating, at the risk model 144, an integrated risk score 190, and outputting the integrated risk score 190 to a requesting party. An "integrated risk score" is a composite score that combines multiple health risk indicators to assess the overall risk of a particular health outcome or disease in a patient. For example, here integrated risk score 190 integrates patient health risk 156 indicators with neurodegenerative risk scores 152 to generate a comprehensive score. As used throughout this disclosure, "patient indicators of health risk" are measurable factors or signs that suggest an individual's likelihood of developing a particular health condition, disease, or experiencing a negative health event in the future. For example, this may include genetic indicators, behavioral indicators, environmental indicators, psychosocial indicators, clinical indicators, sociodemographic indicators, and / or the like. Genetic indicators may include certain genetic variations or mutations that are known to increase a patient's risk for specific diseases. For example, the presence of APOE c4 allele may indicate a genetic risk factor for Alzheimer's Disease, BRCA1 And BRCA2 gene mutations may be associated with an increased risk for breast and ovarian cancer, SNCA gene mutations may be associated with Parkinson's disease, and Tau gene mutations may contribute to tauopathies. Behavioral indicators may include lifestyle choices such as diet, physical activity, tobacco use, alcohol consumption, sleep patterns and / or the like. Environmental indicators may include air quality, chemical exposure, and / or living conditions. Psychosocial indicators may include mental health and stress levels which may influence health risks. For example, chronic stress, depression, or anxiety can increase an individual's risk of heart disease, weakened immune system, and chronic diseases. Clinical indicators and demographic data may include age, family history, gender, cognitive function, clinical symptoms, comorbidities, and / or the like. In an embodiment, patient indicators of health risk 156 may be included in the plurality of patient data 124. In otherAttorney Docket No. 35944-100110 embodiments, patient indicators of health risk 156 may be generated or obtained through one or more processes. For example, indicators of health risk may be generated or obtained through one or more comprehensive questionnaires or in-person physician visits.

[0036] In continued reference to FIG. 1, "genomic data" refers to information about an individual's genome — the complete set of genetic material in an organism. Genomic data 160 may include DNA sequencing, genetic variants, gene expression data, chromosomal information, epigenetic data, mitochondrial DNA, and / or the like. Further, genomic data 160 may be sourced from Whole Genome Sequencing (WGS), Exome sequencing, and / or targeted gene panels. As used herein, "biographical data" refers to information about an individual's personal history and life experiences. For example, biographical data 164 may include personal information such as name, date of birth, gender, etc., family and social background, educational and professional history, life events and experiences, behavioral and lifestyle information, and / or the like.

[0037] Still referring to FIG. 1, "lifestyle risk score" is a numerical or categorical value that reflects an individual's risk for developing certain health conditions or diseases based on their lifestyle behaviors. A lifestyle risk score 168 may be calculated by evaluating various lifestyle factors, such as diet, physical activity, smoking, alcohol consumption, and other personal habits, and scoring them based on their association with health risks. The higher the score, the greater an individual's risk for certain adverse health outcomes. This area of analysis can be quite important due to the nature and ability to change habits that increase one's risk fir adverse health outcomes. Important factors contributing to lifestyle risk score 168 may include evaluating physical activity, diet and nutrition, tobacco use, alcohol consumption, sleep habits, mental health and stress, body weight and BMI, and other risk behaviors. Such data may be collected from surveys and questionnaires, medical records, and / or physical assessments. Each lifestyle factor may be assigned a score based on how it relates to an individual's health risk. For example, a high level of physical activity may be assigned a low-risk score, while sedentary behavior may be assigned a high-risk score. Further, some lifestyle factors may be weighed differently than others as some lifestyle factors have a stronger influence on health outcomes than others. For example, smoking might be given a higher weight than sleep duration due to its stronger link with diseases like lung cancer and cardiovascular disease. In some embodiments, statistical models or risk prediction algorithms may be used to determine the relative importance of each lifestyle factor. Once each factor is scored, the individual scores may be summed and averaged to create an overall lifestyle risk score 168. In some embodiments, the resulting score may be placed into a risk category such as low risk, moderate risk,Attorney Docket No. 35944-100110 and high risk. In other embodiments, a point system may be used wherein different behaviors contribute a fixed number of points to an overall score. For example, smoking 20 cigarettes a day may contribute 10 points; while engaging in 30 minutes of exercise a day might contribute -5 points. Lifestyle risk scores 168 may provide for areas of improvement for an individual's integrated neurodegenerative risk score 152.

[0038] In further reference to FIG. 1, a "requesting party," as used throughout this disclosure, refers to a system or component that initiates a request for data, resources, or services from another system or component. For example, and without limitation, a requesting party may include GUI 185, database 120, application programming interfaces (APIs), and / or the like. GUI 185 may be a requesting party when a patient or user requests to view their integrated risk score 190 at a user interface. Further, in some cases database 120 may be a requesting party when for example, an application sends a request to a database to retrieve customer records based on certain search criteria, and database 120 acts as the requesting party in initiating the retrieval of the required information. Database may also be a requesting party when system 100 is run, and integrated risk score 190 is stored at database 120. In some embodiments, an API may be a requesting party, for example a mobile app might send a request to database 120 to retrieve integrated scores 190 over a period of time, making the mobile app the requesting party.

[0039] With continued reference to FIG. 1, in an embodiment, neurodegenerative risk model 144 may be trained on biomarker data 132, genomic data 160, biographical data 164, and lifestyle risk scores 168. In an embodiment, the neurodegenerative risk model 144 may include a Bayesian risk model 172 configured to integrate innate and mutable risk factors into the integrated risk score 190. "Innate" refers to characteristics or conditions that are inherited or present from birth, typically influenced by genetics or biological factors. Whereas, "mutable" refers to factors that can be changed or influenced by an individual's behavior, environment, or medical interventions. For example, diet, sleeping patterns, physical activity and / or the like. The method has been criticized for use of priors (these are often unsubstantiated beliefs, or "gut feelings") to inform statistical models; here, system 100 leverages data-driven insights from genomic and population health to develop empirical priors. The unique value of this alternate statistical method is in its ability to continuously update risk as data is fed into the model, while accounting for any uncertainty in that data and returning not a single probability but a posterior distribution of probabilities, allowing confidence interpretation of results. Because there is inherent variability in the distribution of these biomarkers both between individuals and within an individual measured at different times, this method accountsAttorney Docket No. 35944-100110 for natural variability without weakening the model. By treating every biomarker as an updated risk calculation, system 100 can integrate even low-fidelity biomarkers into the overall risk calculation turning a weakness of neurological biomarkers into a strength of the model. This allows for building a robust risk assessment for potential of developing a neurodegenerative disease, even in the absence of a clear etiological link between analyte and pathology.

[0040] In further reference to FIG. 1, in an embodiment, concentration distributions for each biomarker may be characterized among affected and unaffected individuals, building dueling distributions for each biomarker. Further, when tested on later timepoints for the same patients (who were either followed longitudinally over time without any risk reduction interventions 188, as well as in those who were given personalized care based on their own modifiable risk), the model is able to update the risk output, reflecting individualized clinical interventions 188 which were reported between the timepoints — the model may accurately monitor the effectiveness of preventive interventions 188 in as little as 4 weeks. This method may also allow for an increased amount of patient data to be integrated into the model. While one of the main criticisms of Bayesian statistics is that prior risk is often based on nonquantifiable metrics such as experience or expert opinion, the prior risk calculation is formalized through genetic and age-based risk. APOE genotyping can readily be integrated into the model. One of system 100's benefits is its ability to integrate low-fidelity biomarkers, biomarkers without a strong unaffected disease state, while avoiding degradation in statistical analysis quality. For example, GFAP is a biomark for biomarker axiomal, no matter the difference in distribution between people affected and those not affected, the Bayesian risk model 172 may integrate the distribution while taking into account that it is not a perfect biomarker. In an embodiment, Bayesian risk model 172 may modify confidence levels and risk spread based on the distributions integrated into the system.

[0041] With further reference to FIG. 1, Bayesian risk model 172 may utilize one or more algorithms, including a biomarker algorithm. In an embodiment, developing a biomarker algorithm may include measuring a panel of seven biomarkers (Al 340 and Af342; Neurofilament Light-chain [NFL]; Glial Fibrillary Acidic Protein [GFAP]; and phospo-tau species pTaul81, pTau217, and pTau231) on a cognitively characterized clinical cohort (demographics for n=49: 65% male, 39% aged >65, 67% APOE4 carriers, and 22% with cognitive complaint as defined by clinician as having mild cognitive impairment [MCI] or dementia). These data may be transformed via logistic regression to generate odds ratios for each individual biomarker with binary bins of no impairment and preclinical disease against MCI and dementia. A threshold "cutoff value may then be generatedAttorney Docket No. 35944-100110 by maximizing the area under a receiver-operator characteristic curve (AUROC) for each biomarker. An algorithm for differentiating individuals with and without cognitive impairment may be generated summing the effective hazard ratio for each biomarker (as defined by the measured biomarker concentration minus the cutoff value times the hazard ratio). The sensitivity and specificity of these combined algorithms (with clinical diagnosis as standard) may be compared to pTau217 with an ROC-optimized cutoff as well as pTau217 with the Quanterix-defined positive cutoff of 0.63pg / mL, outperforming both. In an embodiment, the panel of biomarkers may be expanded to the 120 central nervous system (CNS) biomarkers that Alamar Biosciences offers on its NUcleic acid Linked Immunosorbent Assay (NULISA) platform which can be integrated into diagnostic testing. In integrating multiple biomarkers yields increased diagnostic effectiveness.

[0042] Further referencing FIG. 1, NULISA may allow for attomolar sensitivity multiplex proteomics. AD biomarker concentrations may be low in plasma, particularly in early stages of disease, which may require highly sensitive assays. The Alamar NULISA assay may be used for gathering proteomic data as it has high sensitivity for both low and high biomarker levels, and is run in multiplex from a small volume (10 pL) of plasma. The low sample volume requirement may allow sampling to be completed by patients using plasma separation cards (PSCs), commercially available medical devices that combine dried blood spot technology with capillary plasma separation to quickly and consistently create a sampling and transfer method that does not require a trained phlebotomist or have hazardous material shipping restrictions. Alamar Biosciences' multiplex proteomic platform may allow for testing of up to 250 inflammatory biomarkers or 120 CNS disease biomarkers at attomolar sensitivity from a single 10-pL plasma sample across a 12-log dynamic range. This poses a significant improvement over existing technologies in target sensitivity and specificity, as well as offering massive multiplex capabilities to prevent inter-sample errors. The low-volume requirement of NULISA means that one may circumvent the need for venipuncture and centrifugal plasma separation performed by a trained phlebotomist.

[0043] In further reference to FIG. 1, Bayesian risk model 172 may provide increased utility without sacrificing sensitivity and / or specificity. Current assays are not indicated for use in diagnosing AD before symptom onset. To circumvent the poor predictive value these biomarkers have for cognitive decline, a training dataset may be developed on samples that have AD via both cognitive assessment and pathological diagnosis. In an embodiment system 100 may integrate patient indicators of health risk, such as age, APOE status, and lifestyle risk scores, to encapsulate data that cannot be measured solely from blood. An expanded panel of — 120 biomarkers related toAttorney Docket No. 35944-100110 CNS disease may be tested to broaden the search for biomarkers of interest beyond those with strong correlations to pathology. So that any lower-fidelity biomarkers do not skew our calculations, Bayesian statistical methods may be used to integrate these measurements, as well as the mutable and immutable risk factors, without integrating more noise into our projections. The Bayesian approach is purposefully built for risk modeling, is robust to low-fidelity or missing data, and is sensitive to unexpected data — better mirroring clinical judgement process. Further, Bayesian analyses return a posterior distribution rather than a single probability statistic, which allows for interpretation not only of risk but of conviction in that metric. Integrating more biomarkers within a Bayesian framework may provide the highest fidelity test currently available.

[0044] With continued reference to FIG. 1, in an embodiment, Bayesian risk model 172 may be built by characterizing concentration distributions for each biomarker among affected and unaffected individuals, building dueling distributions for each biomarker. The way in which each individual's biomarker measurements fit in to each distribution may be integrated in the Bayesian risk model 172.

[0045] Continuing to reference FIG. 1, in an embodiment, the neurodegenerative risk model 144 may include one or more machine-learning models 176, wherein the neurodegenerative risk model 144 is trained using exemplary biomarker data and exemplary patient indicators of health risk correlated with exemplary positive indicators of neurodegenerative disease. In an embodiment, one or more machine-learning models 176 may be nested and / or individual. Nested and / or individual machine-learning models may be used to calculate neurodegenerative risk score 152, lifestyle risk score 168, and / or a baseline risk score. Training data may include data from at least three areas of a patient's life, biomarker data, lifestyle risks, and baseline risks. For example, machine-learning model 176 to generate neurodegenerative risk score 152 may include training data such as, without limitation, biomarker data in affected and non-affected patients correlated to neurodegenerative disease presence. Further, in an embodiment, machine-learning model 176 to generate lifestyle risk score 168 may include training data such as, but not limited to, lifestyle factors, such as diet, physical activity, smoking, alcohol consumption, and other personal habits in affected and unaffected patients correlated to neurodegenerative disease presence. In some embodiments, machine-learning model 176 for generating a baseline risk score may be trained using training data such as, without limitation, one or more genomic indicators, family history of disease, and / or the like of affected and unaffected patients correlated to neurodegenerative disease presence. The one or more machine-learning models 176 may be trained at system 100 and / or remotely. In anAttorney Docket No. 35944-100110 embodiment each of the one or more machine-learning models 176 may be integrated to embody neurodegenerative risk model 144. Further, in some embodiments, neurodegenerative risk model 144 may be retrained using an iteratively updated plurality of patient data 180. Retraining may occur at system 100 and / or remotely. Iterative updates of a plurality of patient data 124 may occur as a function of a patient or individual's treatment plan. Measurements of biomarker data 132 may occur in intervals based on a temporal element. For example, biomarker measurements may be taken every 3 months, every 6 months, every year, and so on and so forth. The updated plurality of data may be updated with the biomarker measurements and with any intervention 188 data as described in further detail below.

[0046] In further reference to FIG. 1, in an embodiment, the at least a processor 108 may be configured to output the neurodegenerative risk score 152 to a requesting party. In an embodiment, a requesting party may include one or more databases 120. In some cases, a requesting party may include a display device 184. Display device 184 may be configured to display a graphical user interface 185 (GUI). In an embodiment, outputting the integrated risk score 190 may include generating a user interface including the integrated risk score 190, and transmitting an integrated risk score 190 to a display device 184, wherein the display device 184 is configured to display a GUI 185.

[0047] With continued reference to FIG. 1, a "GUI" is a visual interface that allows users to interact with electronic devices through graphical elements rather than or in addition to text- based commands. Features of a GUI 185 may include, but are not limited to windows, icons, menus, buttons, sliders and controls, and / or any other graphical content configured to assist a user in interacting with an electronic device. As used in this context, "manipulation" refers to actions or interactions a user may perform to modify, control, or navigate through an interface. Such manipulations may require the use of input devices such as, but not limited to mouses, keyboards, and / or touchscreens. For example, manipulations may include clicking, dragging, scrolling, resizing, zooming, hovering, right-clicking, keyboard shortcuts, inputting data, removing data, and / or modifying data. "Visual elements" refer to the various components or building blocks that make up the interface and allow users to interact with a software application. These elements are designed to provide users with an intuitive and efficient way to access the functionality of the application.

[0048] In continued reference to FIG. 1, in an embodiment, GUI 185 may include one or more event handlers. As used throughout this disclosure, "input event handler" refers to functions or methods designed to respond to specific events in a program, particularly in user interface contexts.Attorney Docket No. 35944-100110 An "event" is an occurrence that is detected by the program. For example, this may include a mouse click, keyboard input, and / or a change in a form field. In an embodiment, event handlers may include a listener and or binding process. A listener is a function that listens for specific events on an element. For instance, a button or an input field. A binding process is the process of associating an event with its handler. When an event occurs, an event object may be passed to the handler, containing details about the event. Event handlers allow for interactivity, modularity, and reusability. In such that, event handlers enable applications to respond dynamically to user actions, organize code by separating event handling logic from other program logic, and the same handler may be used for multiple elements and / or events. Further, in an embodiment, the feedback from an event handler may be utilized as training data in the training or retraining of models and / or modules as described here within.

[0049] Continuing to reference FIG. 1, as used in this disclosure, a "display device" refers to an electronic device that visually presents information to the entity. In some cases, display device 184 may be configured to project or show visual content generated by computers, video devices, or other electronic mechanisms. In some cases, display device 184 may include a liquid crystal display (LCD), a cathode ray tube (CRT), a plasma display, a light emitting diode (LED) display, and any combinations thereof. In a non-limiting example, one or more display devices 184 may vary in size, resolution, technology, and functionality. Display device 184 may be able to show any data elements and / or visual elements in various formats such as, textural, graphical, video among others, in either monochrome or color. Display device 184 may include, but is not limited to, a smartphone, tablet, laptop, monitor, tablet, and the like. Display device 184 may include a separate device that includes a transparent screen configured to display computer generated images and / or information. In some cases, display device 184 may be configured to present a GUI 185 to a user, wherein a user may interact with the GUI 185. In some cases, a user may view a GUI 185 through display. Additionally, or alternatively, processor 108 may be connected to display device 184. In some embodiments, GUI 185 may be updated based on user inputs and the integrated neurodegenerative risk score.

[0050] A "GUP" is a visual interface that allows users to interact with electronic devices through graphical elements rather than text-based commands. Features of a GUI 185 may include, but are not limited to windows, icons, menus, buttons, sliders and controls, and / or any other graphical content configured to assist a user in interacting with an electronic device. As used in this context, "manipulation" refers to actions or interactions a user may perform to modify, control, or navigate through an interface. Such manipulations may require the use of input devices such as, butAttorney Docket No. 35944-100110 not limited to mouses, keyboards, and / or touchscreens. For example, manipulations may include clicking, dragging, scrolling, resizing, zooming, hovering, right-clicking, keyboard shortcuts, inputting data, removing data, and / or modifying data.

[0051] In continued reference to FIG. 1, in an embodiment, GUI 185 may include one or more event handlers. As used throughout this disclosure, "event handler" refers to functions or methods designed to respond to specific events in a program, particularly in user interface contexts. An "event" is an occurrence that is detected by the program. For example, this may include a mouse click, keyboard input, and / or a change in a form field. In an embodiment, event handlers may include a listener and or binding process. A listener is a function that listens for specific events on an element. For instance, a button or an input field. A binding process is the process of associating an event with its handler. When an event occurs, an event object may be passed to the handler, containing details about the event. Event handlers allow for interactivity, modularity, and reusability. In such that, event handlers enable applications to respond dynamically to user actions, organize code by separating event handling logic from other program logic, and the same handler may be used for multiple elements and / or events. Further, in an embodiment, the feedback from an event handler may be utilized as training data in the training or retraining of models and / or modules as described here within.

[0052] In further reference to FIG. 1, in an embodiment, at least a processor 108 may be configured to generate a GUI 185 using the integrated risk score 190, receive an updated plurality of patient data 180 and at least an intervention 188, regenerate an integrated risk score 190 as a function of the updated plurality of patient data 180, and update the GUI 185 as a function of the regenerated integrated risk score 192 and the at least an intervention 188. An "intervention," as used throughout this disclosure, refers to any action, procedure, or treatment performed to improve health, prevent disease, manage a medical condition, or modify the course of an illness or injury. Interventions 188 are aimed at improving patient outcomes, alleviating symptoms, and / or preventing complications. These actions can range from preventative measures to therapeutic treatments or even surgical procedures. Interventions 188 may include lifestyle changes medications, and / or the like. In an embodiment, updating the GUI 185 as a function of the regenerated integrated risk score 192 may include plotting the integrated risk score 190 the regenerated integrated risk score 192 with respect to a temporal attribute, labeling the integrated risk score 190 and the regenerated integrated risk score 192 with a respective intervention 188, updating the GUI 185, and displaying, at a display device 184, the updated GUI 185. As used here, a "temporal attribute" refers to a characteristic orAttorney Docket No. 35944-100110 feature that relates to time. Here, an individual's plurality of patient data 124 is tracked over time, allowing a user to view changes in an individual's neurodegen erative risk score 152 over time and provide feedback and insight into at least an intervention 188 taken since the last measurement. The feedback and insights available to a user may include a plot of data points, wherein a user may view the plot at a GUI 185 and take notice of changes, either increases, decreases, or no change, in an individual's neurodegenerative risk score 152. This may allow, for example, a healthcare provider to review a patient's neurodegenerative risk score 152 after prescribing a medication. If the patient's neurodegenerative risk score 152 increases, then the healthcare provider may determine that a new medication is necessary. In some embodiments, GUI 185 may be integrated with electronic medical records (EMR), so that a primary care provider (PCP) may use, service, and / or receive personalized notes based on a patient's interactions with GUI 185. This may provide a way for a user to interface with PCP's, which may allow for increased interactions between a PCP and their patients. Further, in some embodiments, GUI 185 may provide for a platform to order testing, which may include a biological extraction 128. In some cases, testing may be on a schedule, in which case GUI may provide a user the ability to schedule testing at their convenience within a specified period of time within a scheduling window. This may also allow for flexibility in location. For example, if a user is unable to make it to a certain location for testing, GUI 185 may suggest other locations in their vicinity.

[0053] In continued reference to FIG. 1, a patient's compliance to interventions 188 is key to modifying their neurodegenerative risk factors. Therefore, tracking a patient's compliance may be beneficial in determining an intervention's effectiveness. In an embodiment, GUI 185 may be accessible on a variety of computing devices. For example, GUI 185 may be accessible on a smartphone, a tablet, and / or any other mobile device. This may allow a user to track intervention 188 statuses, which may include components of a patient's compliance with said intervention 188. For example, system 100 may incorporate interfaces such as RETAIN HEALTH' s platformRET AINYOURB RAIN to help patient's track and meet goals related to interventions 188. The ability to track and monitor a patient's compliance with an intervention 188 may provide an internal validation of neurodegenerative risk model by providing additional data related to compliance with a given intervention 188.

[0054] Still referring to FIG. 1, in an embodiment, at least a processor 108 may be further configured to determine an intervention efficacy score 196 as a function of the integrated risk score 190 and the regenerated integrated risk score 192. The integrated risk score 190 and the regeneratedAttorney Docket No. 35944-100110 integrated risk score 192 may be used to calculate the change in risk after a certain intervention 188 or group of interventions 188. This may, for example, provide the difference between the integrated risk score 190 and the regenerated risk score, which may be a reduction in risk, no change in risk, or an increase in risk. As used here, an "intervention efficacy score" quantifies the effectiveness of a given intervention 188 in terms of risk reduction. It may be expressed as a percentage of reduction and / or as a simple absolute difference. In some embodiments an intervention efficacy score 196 may be presented in a format such as a report, graphically shown over an axis of time, or provide next steps or suggestions for intervention 188 adjustments. Intervention efficacy scores 196 may be stored at database 120 and used to train or retrain neurodegenerative risk model 144.

[0055] Now referring to FIG. 2, illustrated is a chart describing sensitivity and / or specificity for odds ratio based diagnostic algorithms. "ClinDx" is clinician-based assessment of whether a patient has moderate cognitive impact and / or dementia due to Alzheimer's Disease (AD). Integrating multiple biomarkers (A., our initial algorithm) outperforms single biomarkers (B., pTau217 with ROC-optimized cutoff) as well as commercially available diagnostic methods (C., SimoaDx, with established 0.63pg / mL cutoff).

[0056] Now referring to FIG. 3, illustrated is an index biomarker versus risk modeling. A) illustrates a Binary diagnostic algorithm using five biomarkers for four patients, where a negative score is negative for AD and a positive score is positive. B) illustrates affected and unaffected biomarker distributions as used in a binary diagnostic. The overlapping range is indeterminate as it cannot be decided which distribution a measurement in that range belongs to, and no result can be returned. In recent publications, up to 15% of cases fall within this range. High quality binary diagnostics require individual biomarkers with the least overlap between distributions. C) illustrates a risk modeling algorithm using the same data determines the same patient to be positive for AD, while also providing usable risk data for the other three patients. D) illustrates a Bayesian inference, which may leverage the likelihood that a biomarker measurement belongs to either distribution and updates a patient's prior risk distribution accordingly. Lower fidelity data can be integrated into this model without reducing its power.

[0057] Now referring to FIG. 4, illustrated, is a comparison of two diagnostic models. Head-to-head comparison of summary statistics and ROC curves for A) the Bayesian algorithm created by our group and B) the traditional biomarker algorithm, as measured on a cohort associated with both cognitive impairment and at least a neurodegenerative-related pathology, showed no difference in diagnostic capacity between the two models, and little difference in area under the ROC curves. C)Attorney Docket No. 35944-100110 Two patients with multiple biomarker timepoints were analyzed for risk over time using the Bayesian model on 5 biomarkers (A(342 / 40, NFL, GFAP, and pTau217) without posterior distributions included. One patient (PT01) with clinically diagnosed preclinical AD showed an increase in risk between the first two timepoints with noted low compliance to interventions. After the 2nd timepoint, compliance with Suvorexant (FDA approved for AD-related sleep disturbance) increased, and the model returned lower risk. One patient (PT02) with clinically diagnosed moderate cognitive impairment due to AD and no major interventions showed no change to their overall risk.

[0058] Now referring to FIG. 5, illustrated is an exemplary patient workflow. A) Patient contact with our product begins with integrated risk analysis of three aspects of the patient's life. B) These aspects are integrated into a single baseline risk. C) Patients can then take these results to their healthcare provider to begin risk-reducing interventions. After a period, biomarkers are then retested and the risk score is updated. The patient's provider will then use the risk score to analyze efficacy of interventions and modify as necessary. The patient retention cycle represents a unique value for customers in their ability to re-test as their care is personalized.

[0059] Now referring to FIG. 6, illustrated is an exemplary patient interface 600. 2-5 may represent at least an intervention. For example, 1 may represent a baseline read, 2, may represent a started metformin, 3 may represent the beginning of a solo exercise, 4 may represent a change to GLP-1 agonist, and 5 may represent starting with a personal trainer. System 100 may track baseline and updated risk calculations and provide them as a visual for a patient or individual at patient interface 600. Each datapoint may provide an individual with a snapshot of their distinct interventions in order to monitor their effectiveness. By highlighting habitual interventions such as diet or exercise, the user experience may encourage adherence to these interventions, while providing back-end electronic medical record integration for providers' tracking purposes.

[0060] Still referring to FIG. 6, in an embodiment, patient interface may include a graphical user interface. For example, at least a processor may be configured to generate a graphical user interface using the neurodegenerative risk score, receive an updated plurality of patient data and at least an intervention, regenerate the neurodegenerative risk score as a function of the updated plurality of patient data, and update the graphical user interface. Further, in some cases an integrated risk score may be used in place of and / or in addition to the neurodegenerative risk score.

[0061] In continued reference to FIG. 6, in an embodiment, patient interface 600 may be dynamically updated to include new risk scores, neurodegenerative and / or integrated, over time. For example, and without limitation, at least a processor may be configured to update patient interfaceAttorney Docket No. 35944-100110 600 as a function of the regenerated neurodegenerative risk score. This may be accomplished by plotting the neurodegenerative risk score and the regenerated neurodegenerative risk score with respect to a temporal attribute, labeling the neurodegenerative risk score and the regenerated neurodegenerative risk score with a respective intervention, and displaying, at a display device, the updated patient interface 600. In some cases, an integrated risk score may be used in place of and / or in addition to the neurodegenerative risk score. Updates to patient interface 600 may occur in a scheduled manner based on a patient's checkups.

[0062] With further reference to FIG. 6, in an embodiment, at least a processor may be further configured to determine an intervention efficacy score as a function of the neurodegenerative risk score and the regenerated neurodegenerative risk score. This may also be accomplished using an integrated risk score in place of and / or in addition to the neurodegenerative risk score. The intervention efficacy score may be displayed at a display device in a pop-up window when a datapoint correlated to an intervention is hovered over. In other embodiments, the intervention efficacy score may be displayed in a chart form and / or a report, wherein a detailed description of the intervention and its effect on the neurodegenerative or integrated risk score is provided to a requesting party.

[0063] Referring now to FIG. 7, an exemplary embodiment of a machine-learning module 700 that may perform one or more machine-learning processes as described in this disclosure is illustrated. Machine-learning module may perform determinations, classification, and / or analysis steps, methods, processes, or the like as described in this disclosure using machine learning processes. A "machine learning process," as used in this disclosure, is a process that automatedly uses training data 704 to generate an algorithm instantiated in hardware or software logic, data structures, and / or functions that will be performed by a computing device / module to produce outputs 708 given data provided as inputs 712; this is in contrast to a non-machine learning software program where the commands to be executed are determined in advance by a user and written in a programming language.

[0064] Still referring to FIG. 7, "training data," as used herein, is data containing correlations that a machine-learning process may use to model relationships between two or more categories of data elements. For instance, and without limitation, training data 704 may include a plurality of data entries, also known as "training examples," each entry representing a set of data elements that were recorded, received, and / or generated together; data elements may be correlated by shared existence in a given data entry, by proximity in a given data entry, or the like. Multiple data entries in trainingAttorney Docket No. 35944-100110 data 704 may evince one or more trends in correlations between categories of data elements; for instance, and without limitation, a higher value of a first data element belonging to a first category of data element may tend to correlate to a higher value of a second data element belonging to a second category of data element, indicating a possible proportional or other mathematical relationship linking values belonging to the two categories. Multiple categories of data elements may be related in training data 704 according to various correlations; correlations may indicate causative and / or predictive links between categories of data elements, which may be modeled as relationships such as mathematical relationships by machine-learning processes as described in further detail below. Training data 704 may be formatted and / or organized by categories of data elements, for instance by associating data elements with one or more descriptors corresponding to categories of data elements. As a non-limiting example, training data 704 may include data entered in standardized forms by persons or processes, such that entry of a given data element in a given field in a form may be mapped to one or more descriptors of categories. Elements in training data 704 may be linked to descriptors of categories by tags, tokens, or other data elements; for instance, and without limitation, training data 704 may be provided in fixed-length formats, formats linking positions of data to categories such as comma-separated value (CSV) formats and / or self-describing formats such as extensible markup language (XML), JavaScript Object Notation (JSON), or the like, enabling processes or devices to detect categories of data.

[0065] Alternatively or additionally, and continuing to refer to FIG. 7, training data 704 may include one or more elements that are not categorized; that is, training data 704 may not be formatted or contain descriptors for some elements of data. Machine-learning algorithms and / or other processes may sort training data 704 according to one or more categorizations using, for instance, natural language processing algorithms, tokenization, detection of correlated values in raw data and the like; categories may be generated using correlation and / or other processing algorithms. As a nonlimiting example, in a corpus of text, phrases making up a number "n" of compound words, such as nouns modified by other nouns, may be identified according to a statistically significant prevalence of n-grams containing such words in a particular order; such an n-gram may be categorized as an element of language such as a "word" to be tracked similarly to single words, generating a new category as a result of statistical analysis. Similarly, in a data entry including some textual data, a person's name may be identified by reference to a list, dictionary, or other compendium of terms, permitting ad-hoc categorization by machine-learning algorithms, and / or automated association of data in the data entry with descriptors or into a given format. The ability to categorize data entriesAttorney Docket No. 35944-100110 automatedly may enable the same training data 704 to be made applicable for two or more distinct machine-learning algorithms as described in further detail below. Training data 704 used by machine-learning module 700 may correlate any input data as described in this disclosure to any output data as described in this disclosure. As a non-limiting illustrative example inputs may include a plurality of patient data which may include biomarker data and / or indicators of health risk.

[0066] Further referring to FIG. 7, training data may be filtered, sorted, and / or selected using one or more supervised and / or unsupervised machine-learning processes and / or models as described in further detail below; such models may include without limitation a training data classifier 716. Training data classifier 716 may include a "classifier," which as used in this disclosure is a machinelearning model as defined below, such as a data structure representing and / or using a mathematical model, neural net, or program generated by a machine learning algorithm known as a "classification algorithm," as described in further detail below, that sorts inputs into categories or bins of data, outputting the categories or bins of data and / or labels associated therewith. A classifier may be configured to output at least a datum that labels or otherwise identifies a set of data that are clustered together, found to be close under a distance metric as described below, or the like. A distance metric may include any norm, such as, without limitation, a Pythagorean norm. Machine-learning module 700 may generate a classifier using a classification algorithm, defined as a processes whereby a computing device and / or any module and / or component operating thereon derives a classifier from training data 704. Classification may be performed using, without limitation, linear classifiers such as without limitation logistic regression and / or naive Bayes classifiers, nearest neighbor classifiers such as k-nearest neighbors classifiers, support vector machines, least squares support vector machines, fisher's linear discriminant, quadratic classifiers, decision trees, boosted trees, random forest classifiers, learning vector quantization, and / or neural network-based classifiers. As a nonlimiting example, training data classifier 716 may classify elements of training data to cohorts of individuals presenting with both cognitive impairment and at least a neurodegenerative-related pathology and those who do not present which such proclivities.

[0067] Still referring to FIG. 7, a computing device may be configured to generate a classifier using a Naive Bayes classification algorithm. Naive Bayes classification algorithm generates classifiers by assigning class labels to problem instances, represented as vectors of element values. Class labels are drawn from a finite set. Naive Bayes classification algorithm may include generating a family of algorithms that assume that the value of a particular element is independent of the value of any other element, given a class variable. Naive Bayes classification algorithm may beAttorney Docket No. 35944-100110 based on Bayes Theorem expressed as P(A / B)= P(B / A) P(A)±13(B), where P(A / B) is the probability of hypothesis A given data B also known as posterior probability; P(B / A) is the probability of data B given that the hypothesis A was true; P(A) is the probability of hypothesis A being true regardless of data also known as prior probability of A; and P(B) is the probability of the data regardless of the hypothesis. A naive Bayes algorithm may be generated by first transforming training data into a frequency table. Computing device may then calculate a likelihood table by calculating probabilities of different data entries and classification labels. A computing device may utilize a naive Bayes equation to calculate a posterior probability for each class. A class containing the highest posterior probability is the outcome of prediction. Naive Bayes classification algorithm may include a gaussian model that follows a normal distribution. Naive Bayes classification algorithm may include a multinomial model that is used for discrete counts. Naive Bayes classification algorithm may include a Bernoulli model that may be utilized when vectors are binary.

[0068] With continued reference to FIG. 7, a computing device may be configured to generate a classifier using a K-nearest neighbors (KNN) algorithm. A "K-nearest neighbors algorithm" as used in this disclosure, includes a classification method that utilizes feature similarity to analyze how closely out-of-sample- features resemble training data to classify input data to one or more clusters and / or categories of features as represented in training data; this may be performed by representing both training data and input data in vector forms, and using one or more measures of vector similarity to identify classifications within training data, and to determine a classification of input data. K-nearest neighbors algorithm may include specifying a K-value, or a number directing the classifier to select the k most similar entries training data to a given sample, determining the most common classifier of the entries in the database, and classifying the known sample; this may be performed recursively and / or iteratively to generate a classifier that may be used to classify input data as further samples. For instance, an initial set of samples may be performed to cover an initial heuristic and / or "first guess" at an output and / or relationship, which may be seeded, without limitation, using expert input received according to any process as described herein. As a nonlimiting example, an initial heuristic may include a ranking of associations between inputs and elements of training data. Heuristic may include selecting some number of highest-ranking associations and / or training data elements.

[0069] With continued reference to FIG. 7, generating k-nearest neighbors algorithm may generate a first vector output containing a data entry cluster, generating a second vector output containing an input data, and calculate the distance between the first vector output and the secondAttorney Docket No. 35944-100110 vector output using any suitable norm such as cosine similarity, Euclidean distance measurement, or the like. Each vector output may be represented, without limitation, as an n-tuple of values, where n is at least two values. Each value of n-tuple of values may represent a measurement or other quantitative value associated with a given category of data, or attribute, examples of which are provided in further detail below; a vector may be represented, without limitation, in n-dimensional space using an axis per category of value represented in n-tuple of values, such that a vector has a geometric direction characterizing the relative quantities of attributes in the n-tuple as compared to each other. Two vectors may be considered equivalent where their directions, and / or the relative quantities of values within each vector as compared to each other, are the same; thus, as a nonlimiting example, a vector represented as [5, 10, 15] may be treated as equivalent, for purposes of this disclosure, as a vector represented as [1, 2, 3], Vectors may be more similar where their directions are more similar, and more different where their directions are more divergent; however, vector similarity may alternatively or additionally be determined using averages of similarities between like attributes, or any other measure of similarity suitable for any n-tuple of values, or aggregation of numerical similarity measures for the purposes of loss functions as described in further detail below. Any vectors as described herein may be scaled, such that each vector represents each attribute along an equivalent scale of values. Each vector may be "normalized," or divided by a "length" attribute, such as a length attribute 1 as derived using a Pythagorean norm: 1 = ai 2, where a, is attribute number i ofthe vector. Scaling and / or normalization may function to make vector comparison independent of absolute quantities of attributes, while preserving any dependency on similarity of attributes; this may, for instance, be advantageous where cases represented in training data are represented by different quantities of samples, which may result in proportionally equivalent vectors with divergent values.

[0070] With further reference to FIG. 7, training examples for use as training data may be selected from a population of potential examples according to cohorts relevant to an analytical problem to be solved, a classification task, or the like. Alternatively or additionally, training data may be selected to span a set of likely circumstances or inputs for a machine-learning model and / or process to encounter when deployed. For instance, and without limitation, for each category of input data to a machine-learning process or model that may exist in a range of values in a population of phenomena such as images, user data, process data, physical data, or the like, a computing device, processor, and / or machine-learning model may select training examples representing each possibleAttorney Docket No. 35944-100110 value on such a range and / or a representative sample of values on such a range. Selection of a representative sample may include selection of training examples in proportions matching a statistically determined and / or predicted distribution of such values according to relative frequency, such that, for instance, values encountered more frequently in a population of data so analyzed are represented by more training examples than values that are encountered less frequently.Alternatively or additionally, a set of training examples may be compared to a collection of representative values in a database and / or presented to a user, so that a process can detect, automatically or via user input, one or more values that are not included in the set of training examples. A computing device, processor, and / or module may automatically generate a missing training example; this may be done by receiving and / or retrieving a missing input and / or output value and correlating the missing input and / or output value with a corresponding output and / or input value collocated in a data record with the retrieved value, provided by a user and / or other device, or the like.

[0071] Continuing to refer to FIG. 7, computer, processor, and / or module may be configured to preprocess training data. "Preprocessing" training data, as used in this disclosure, is transforming training data from raw form to a format that can be used for training a machine learning model. Preprocessing may include sanitizing, feature selection, feature scaling, data augmentation and the like.

[0072] Still referring to FIG. 7, computer, processor, and / or module may be configured to sanitize training data. "Sanitizing" training data, as used in this disclosure, is a process whereby training examples are removed that interfere with convergence of a machine-learning model and / or process to a useful result. For instance, and without limitation, a training example may include an input and / or output value that is an outlier from typically encountered values, such that a machinelearning algorithm using the training example will be adapted to an unlikely amount as an input and / or output; a value that is more than a threshold number of standard deviations away from an average, mean, or expected value, for instance, may be eliminated. Alternatively or additionally, one or more training examples may be identified as having poor quality data, where "poor quality" is defined as having a signal to noise ratio below a threshold value. Sanitizing may include steps such as removing duplicative or otherwise redundant data, interpolating missing data, correcting data errors, standardizing data, identifying outliers, and the like. In a nonlimiting example, sanitization may include utilizing algorithms for identifying duplicate entries or spell-check algorithms.Attorney Docket No. 35944-100110

[0073] As a non-limiting example, and with further reference to FIG. 7, images used to train an image classifier or other machine-learning model and / or process that takes images as inputs or generates images as outputs may be rejected if image quality is below a threshold value. For instance, and without limitation, computing device, processor, and / or module may perform blur detection, and eliminate one or more Blur detection may be performed, as a non-limiting example, by taking Fourier transform, or an approximation such as a Fast Fourier Transform (FFT) of the image and analyzing a distribution of low and high frequencies in the resulting frequency-domain depiction of the image; numbers of high-frequency values below a threshold level may indicate blurriness. As a further non-limiting example, detection of blurriness may be performed by convolving an image, a channel of an image, or the like with a Laplacian kernel; this may generate a numerical score reflecting a number of rapid changes in intensity shown in the image, such that a high score indicates clarity and a low score indicates blurriness. Blurriness detection may be performed using a gradient-based operator, which measures operators based on the gradient or first derivative of an image, based on the hypothesis that rapid changes indicate sharp edges in the image, and thus are indicative of a lower degree of blurriness. Blur detection may be performed using Wavelet -based operator, which takes advantage of the capability of coefficients of the discrete wavelet transform to describe the frequency and spatial content of images. Blur detection may be performed using statistics-based operators take advantage of several image statistics as texture descriptors in order to compute a focus level. Blur detection may be performed by using discrete cosine transform (DCT) coefficients in order to compute a focus level of an image from its frequency content.

[0074] Continuing to refer to FIG. 7, computing device, processor, and / or module may be configured to precondition one or more training examples. For instance, and without limitation, where a machine learning model and / or process has one or more inputs and / or outputs requiring, transmitting, or receiving a certain number of bits, samples, or other units of data, one or more training examples' elements to be used as or compared to inputs and / or outputs may be modified to have such a number of units of data. For instance, a computing device, processor, and / or module may convert a smaller number of units, such as in a low pixel count image, into a desired number of units, for instance by upsampling and interpolating. As a non-limiting example, a low pixel count image may have 100 pixels, however a desired number of pixels may be 128. Processor may interpolate the low pixel count image to convert the 100 pixels into 128 pixels. It should also be noted that one of ordinary skill in the art, upon reading this disclosure, would know the variousAttorney Docket No. 35944-100110 methods to interpolate a smaller number of data units such as samples, pixels, bits, or the like to a desired number of such units. In some instances, a set of interpolation rules may be trained by sets of highly detailed inputs and / or outputs and corresponding inputs and / or outputs downsampled to smaller numbers of units, and a neural network or other machine learning model that is trained to predict interpolated pixel values using the training data. As a non-limiting example, a sample input and / or output, such as a sample picture, with sample-expanded data units (e.g., pixels added between the original pixels) may be input to a neural network or machine-learning model and output a pseudo replica sample-picture with dummy values assigned to pixels between the original pixels based on a set of interpolation rules. As a non-limiting example, in the context of an image classifier, a machine-learning model may have a set of interpolation rules trained by sets of highly detailed images and images that have been downsampled to smaller numbers of pixels, and a neural network or other machine learning model that is trained using those examples to predict interpolated pixel values in a facial picture context. As a result, an input with sample-expanded data units (the ones added between the original data units, with dummy values) may be run through a trained neural network and / or model, which may fill in values to replace the dummy values. Alternatively or additionally, processor, computing device, and / or module may utilize sample expander methods, a low-pass filter, or both. As used in this disclosure, a "low-pass filter" is a filter that passes signals with a frequency lower than a selected cutoff frequency and attenuates signals with frequencies higher than the cutoff frequency. The exact frequency response of the filter depends on the filter design. Computing device, processor, and / or module may use averaging, such as luma or chroma averaging in images, to fill in data units in between original data units.

[0075] In some embodiments, and with continued reference to FIG. 7, computing device, processor, and / or module may down-sample elements of a training example to a desired lower number of data elements. As a non-limiting example, a high pixel count image may have 256 pixels, however a desired number of pixels may be 128. Processor may down-sample the high pixel count image to convert the 256 pixels into 128 pixels. In some embodiments, processor may be configured to perform downsampling on data. Downsampling, also known as decimation, may include removing every Nth entry in a sequence of samples, all but every Nth entry, or the like, which is a process known as "compression," and may be performed, for instance by an N-sample compressor implemented using hardware or software. Anti-aliasing and / or anti-imaging filters, and / or low-pass filters, may be used to clean up side-effects of compression.Attorney Docket No. 35944-100110

[0076] Further referring to FIG. 7, feature selection includes narrowing and / or filtering training data to exclude features and / or elements, or training data including such elements, that are not relevant to a purpose for which a trained machine-learning model and / or algorithm is being trained, and / or collection of features and / or elements, or training data including such elements, on the basis of relevance or utility for an intended task or purpose for a trained machine-learning model and / or algorithm is being trained. Feature selection may be implemented, without limitation, using any process described in this disclosure, including without limitation using training data classifiers, exclusion of outliers, or the like.

[0077] With continued reference to FIG. 7, feature scaling may include, without limitation, normalization of data entries, which may be accomplished by dividing numerical fields by norms thereof, for instance as performed for vector normalization. Feature scaling may include absolute maximum scaling, wherein each quantitative datum is divided by the maximum absolute value of all quantitative data of a set or subset of quantitative data. Feature scaling may include min-max scaling, in which each value X has a minimum value Xmin in a set or subset of values subtracted therefrom, with the result divided by the range of the values, give maximum value in the set or subset Xinax: Xnew = X — XmEn. . Feature scaling may include mean normalization, which Xmax — Xmln involves use of a mean value of a set and / or subset of values, )(mean with maximum and minimum values: Xnew = X-Xl leQn Feature scaling may include standardization, where a Xmax — Xmin difference between X and Xmean is divided by a standard deviation a of a set or subset of values:— X — Xme Xnew = an. Scaling may be performed using a median value of a a set or subset Xmedian and / or interquartile range (IQR), which represents the difference between the 25th percentile value and the 50th percentile value (or closest values thereto by a rounding protocol), such as: XXmeatan Xnew =• Persons skilled in the art, upon reviewing the entirety of this disclosure, will IQR be aware of various alternative or additional approaches that may be used for feature scaling.

[0078] Further referring to FIG. 7, computing device, processor, and / or module may be configured to perform one or more processes of data augmentation. "Data augmentation" as used in this disclosure is addition of data to a training set using elements and / or entries already in the dataset. Data augmentation may be accomplished, without limitation, using interpolation, generation of modified copies of existing entries and / or examples, and / or one or more generative Al processes, for instance using deep neural networks and / or generative adversarial networks; generative processes may be referred to alternatively in this context as "data synthesis" and as creating "synthetic data."Attorney Docket No. 35944-100110 Augmentation may include performing one or more transformations on data, such as geometric, color space, affine, brightness, cropping, and / or contrast transformations of images.

[0079] Still referring to FIG. 7, machine-learning module 700 may be configured to perform a lazy-leaming process 720 and / or protocol, which may alternatively be referred to as a "lazy loading" or "call-when-needed" process and / or protocol, may be a process whereby machine learning is conducted upon receipt of an input to be converted to an output, by combining the input and training set to derive the algorithm to be used to produce the output on demand. For instance, an initial set of simulations may be performed to cover an initial heuristic and / or "first guess" at an output and / or relationship. As a non-limiting example, an initial heuristic may include a ranking of associations between inputs and elements of training data 704. Heuristic may include selecting some number of highest-ranking associations and / or training data 704 elements. Lazy learning may implement any suitable lazy learning algorithm, including without limitation a K-nearest neighbors algorithm, a lazy naive Bayes algorithm, or the like; persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various lazy-leaming algorithms that may be applied to generate outputs as described in this disclosure, including without limitation lazy learning applications of machine-learning algorithms as described in further detail below.

[0080] Alternatively or additionally, and with continued reference to FIG. 7, machinelearning processes as described in this disclosure may be used to generate machine-learning models 724. A "machine-learning model," as used in this disclosure, is a data structure representing and / or instantiating a mathematical and / or algorithmic representation of a relationship between inputs and outputs, as generated using any machine-learning process including without limitation any process as described above, and stored in memory; an input is submitted to a machine-learning model 724 once created, which generates an output based on the relationship that was derived. For instance, and without limitation, a linear regression model, generated using a linear regression algorithm, may compute a linear combination of input data using coefficients derived during machine-learning processes to calculate an output datum. As a further non-limiting example, a machine-learning model 724 may be generated by creating an artificial neural network, such as a convolutional neural network comprising an input layer of nodes, one or more intermediate layers, and an output layer of nodes. Connections between nodes may be created via the process of "training" the network, in which elements from a training data 704 set are applied to the input nodes, a suitable training algorithm (such as Levenberg-Marquardt, conjugate gradient, simulated annealing, or other algorithms) is then used to adjust the connections and weights between nodes in adjacent layers ofAttorney Docket No. 35944-100110 the neural network to produce the desired values at the output nodes. This process is sometimes referred to as deep learning.

[0081] Still referring to FIG. 7, machine-learning algorithms may include at least a supervised machine-learning process 728. At least a supervised machine-learning process 728, as defined herein, include algorithms that receive a training set relating a number of inputs to a number of outputs, and seek to generate one or more data structures representing and / or instantiating one or more mathematical relations relating inputs to outputs, where each of the one or more mathematical relations is optimal according to some criterion specified to the algorithm using some scoring function. For instance, a supervised learning algorithm may include inputs as described above as inputs, outputs described above as outputs, and a scoring function representing a desired form of relationship to be detected between inputs and outputs; scoring function may, for instance, seek to maximize the probability that a given input and / or combination of elements inputs is associated with a given output to minimize the probability that a given input is not associated with a given output. Scoring function may be expressed as a risk function representing an "expected loss" of an algorithm relating inputs to outputs, where loss is computed as an error function representing a degree to which a prediction generated by the relation is incorrect when compared to a given input-output pair provided in training data 704. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various possible variations of at least a supervised machine-learning process 728 that may be used to determine relation between inputs and outputs. Supervised machinelearning processes may include classification algorithms as defined above.

[0082] With further reference to FIG. 7, training a supervised machine-learning process may include, without limitation, iteratively updating coefficients, biases, weights based on an error function, expected loss, and / or risk function. For instance, an output generated by a supervised machine-learning model using an input example in a training example may be compared to an output example from the training example; an error function may be generated based on the comparison, which may include any error function suitable for use with any machine-learning algorithm described in this disclosure, including a square of a difference between one or more sets of compared values or the like. Such an error function may be used in turn to update one or more weights, biases, coefficients, or other parameters of a machine-learning model through any suitable process including without limitation gradient descent processes, least-squares processes, and / or other processes described in this disclosure. This may be done iteratively and / or recursively to gradually tune such weights, biases, coefficients, or other parameters. Updating may be performed, in neural networks,Attorney Docket No. 35944-100110 using one or more back-propagation algorithms. Iterative and / or recursive updates to weights, biases, coefficients, or other parameters as described above may be performed until currently available training data is exhausted and / or until a convergence test is passed, where a "convergence test" is a test for a condition selected as indicating that a model and / or weights, biases, coefficients, or other parameters thereof has reached a degree of accuracy. A convergence test may, for instance, compare a difference between two or more successive errors or error function values, where differences below a threshold amount may be taken to indicate convergence. Alternatively or additionally, one or more errors and / or error function values evaluated in training iterations may be compared to a threshold.

[0083] Still referring to FIG. 7, a computing device, processor, and / or module may be configured to perform method, method step, sequence of method steps and / or algorithm described in reference to this figure, in any order and with any degree of repetition. For instance, a computing device, processor, and / or module may be configured to perform a single step, sequence and / or algorithm repeatedly until a desired or commanded outcome is achieved; repetition of a step or a sequence of steps may be performed iteratively and / or recursively using outputs of previous repetitions as inputs to subsequent repetitions, aggregating inputs and / or outputs of repetitions to produce an aggregate result, reduction or decrement of one or more variables such as global variables, and / or division of a larger processing task into a set of iteratively addressed smaller processing tasks. A computing device, processor, and / or module may perform any step, sequence of steps, or algorithm in parallel, such as simultaneously and / or substantially simultaneously performing a step two or more times using two or more parallel threads, processor cores, or the like; division of tasks between parallel threads and / or processes may be performed according to any protocol suitable for division of tasks between iterations. Persons skilled in the art, upon reviewing the entirety of this disclosure, will be aware of various ways in which steps, sequences of steps, processing tasks, and / or data may be subdivided, shared, or otherwise dealt with using iteration, recursion, and / or parallel processing.

[0084] Further referring to FIG. 7, machine learning processes may include at least an unsupervised machine-learning processes 732. An unsupervised machine-learning process, as used herein, is a process that derives inferences in datasets without regard to labels; as a result, an unsupervised machine-learning process may be free to discover any structure, relationship, and / or correlation provided in the data. Unsupervised processes 732 may not require a response variable;Attorney Docket No. 35944-100110 unsupervised processes 732may be used to find interesting patterns and / or inferences between variables, to determine a degree of correlation between two or more variables, or the like.

[0085] Still referring to FIG. 7, machine-learning module 700 may be designed and configured to create a machine-learning model 724 using techniques for development of linear regression models. Linear regression models may include ordinary least squares regression, which aims to minimize the square of the difference between predicted outcomes and actual outcomes according to an appropriate norm for measuring such a difference (e.g. a vector-space distance norm); coefficients of the resulting linear equation may be modified to improve minimization. Linear regression models may include ridge regression methods, where the function to be minimized includes the least-squares function plus term multiplying the square of each coefficient by a scalar amount to penalize large coefficients. Linear regression models may include least absolute shrinkage and selection operator (LASSO) models, in which ridge regression is combined with multiplying the least-squares term by a factor of 1 divided by double the number of samples. Linear regression models may include a multi-task lasso model wherein the norm applied in the least-squares term of the lasso model is the Frobenius norm amounting to the square root of the sum of squares of all terms. Linear regression models may include the elastic net model, a multi-task elastic net model, a least angle regression model, a LARS lasso model, an orthogonal matching pursuit model, a Bayesian regression model, a logistic regression model 148, a stochastic gradient descent model, a perceptron model, a passive aggressive algorithm, a robustness regression model, a Huber regression model, or any other suitable model that may occur to persons skilled in the art upon reviewing the entirety of this disclosure. Linear regression models may be generalized in an embodiment to polynomial regression models, whereby a polynomial equation (e.g. a quadratic, cubic or higher-order equation) providing a best predicted output / actual output fit is sought; similar methods to those described above may be applied to minimize error functions, as will be apparent to persons skilled in the art upon reviewing the entirety of this disclosure.

[0086] Continuing to refer to FIG. 7, machine-learning algorithms may include, without limitation, linear discriminant analysis. Machine-learning algorithm may include quadratic discriminant analysis. Machine-learning algorithms may include kernel ridge regression. Machinelearning algorithms may include support vector machines, including without limitation support vector classification-based regression processes. Machine-learning algorithms may include stochastic gradient descent algorithms, including classification and regression algorithms based on stochastic gradient descent. Machine-learning algorithms may include nearest neighbors algorithms.Attorney Docket No. 35944-100110 Machine-learning algorithms may include various forms of latent space regularization such as variational regularization. Machine-learning algorithms may include Gaussian processes such as Gaussian Process Regression. Machine-learning algorithms may include cross-decomposition algorithms, including partial least squares and / or canonical correlation analysis. Machine-learning algorithms may include naive Bayes methods. Machine-learning algorithms may include algorithms based on decision trees, such as decision tree classification or regression algorithms. Machinelearning algorithms may include ensemble methods such as bagging meta-estimator, forest of randomized trees, AdaBoost, gradient tree boosting, and / or voting classifier methods. Machinelearning algorithms may include neural net algorithms, including convolutional neural net processes.

[0087] Still referring to FIG. 7, a machine-learning model and / or process may be deployed or instantiated by incorporation into a program, apparatus, system and / or module. For instance, and without limitation, a machine-learning model, neural network, and / or some or all parameters thereof may be stored and / or deployed in any memory or circuitry. Parameters such as coefficients, weights, and / or biases may be stored as circuit-based constants, such as arrays of wires and / or binary inputs and / or outputs set at logic " 1 " and "0" voltage levels in a logic circuit to represent a number according to any suitable encoding system including twos complement or the like or may be stored in any volatile and / or non-volatile memory. Similarly, mathematical operations and input and / or output of data to or from models, neural network layers, or the like may be instantiated in hardware circuitry and / or in the form of instructions in firmware, machine-code such as binary operation code instructions, assembly language, or any higher-order programming language. Any technology for hardware and / or software instantiation of memory, instructions, data structures, and / or algorithms may be used to instantiate a machine-learning process and / or model, including without limitation any combination of production and / or configuration of non-reconfigurable hardware elements, circuits, and / or modules such as without limitation ASICs, production and / or configuration of reconfigurable hardware elements, circuits, and / or modules such as without limitation FPGAs, production and / or of non-reconfigurable and / or configuration non-rewritable memory elements, circuits, and / or modules such as without limitation non-rewritable ROM, production and / or configuration of reconfigurable and / or rewritable memory elements, circuits, and / or modules such as without limitation rewritable ROM or other memory technology described in this disclosure, and / or production and / or configuration of any computing device and / or component thereof as described in this disclosure. Such deployed and / or instantiated machine-learning model and / or algorithm mayAttorney Docket No. 35944-100110 receive inputs from any other process, module, and / or component described in this disclosure, and produce outputs to any other process, module, and / or component described in this disclosure.

[0088] Continuing to refer to FIG. 7, any process of training, retraining, deployment, and / or instantiation of any machine-learning model and / or algorithm may be performed and / or repeated after an initial deployment and / or instantiation to correct, refine, and / or improve the machinelearning model and / or algorithm. Such retraining, deployment, and / or instantiation may be performed as a periodic or regular process, such as retraining, deployment, and / or instantiation at regular elapsed time periods, after some measure of volume such as a number of bytes or other measures of data processed, a number of uses or performances of processes described in this disclosure, or the like, and / or according to a software, firmware, or other update schedule.Alternatively or additionally, retraining, deployment, and / or instantiation may be event-based, and may be triggered, without limitation, by user inputs indicating sub-optimal or otherwise problematic performance and / or by automated field testing and / or auditing processes, which may compare outputs of machine-learning models and / or algorithms, and / or errors and / or error functions thereof, to any thresholds, convergence tests, or the like, and / or may compare outputs of processes described herein to similar thresholds, convergence tests or the like. Event-based retraining, deployment, and / or instantiation may alternatively or additionally be triggered by receipt and / or generation of one or more new training examples; a number of new training examples may be compared to a preconfigured threshold, where exceeding the preconfigured threshold may trigger retraining, deployment, and / or instantiation.

[0089] Still referring to FIG. 7, retraining and / or additional training may be performed using any process for training described above, using any currently or previously deployed version of a machine-learning model and / or algorithm as a starting point. Training data for retraining may be collected, preconditioned, sorted, classified, sanitized or otherwise processed according to any process described in this disclosure. Training data may include, without limitation, training examples including inputs and correlated outputs used, received, and / or generated from any version of any system, module, machine-learning model or algorithm, apparatus, and / or method described in this disclosure; such examples may be modified and / or labeled according to user feedback or other processes to indicate desired results, and / or may have actual or measured results from a process being modeled and / or predicted by system, module, machine-learning model or algorithm, apparatus, and / or method as "desired" results to be compared to outputs for training processes as described above.Attorney Docket No. 35944-100110

[0090] Redeployment may be performed using any reconfiguring and / or rewriting of reconfigurable and / or rewritable circuit and / or memory elements; alternatively, redeployment may be performed by production of new hardware and / or software components, circuits, instructions, or the like, which may be added to and / or may replace existing hardware and / or software components, circuits, instructions, or the like.

[0091] Further referring to FIG. 7, one or more processes or algorithms described above may be performed by at least a dedicated hardware unit 736. A "dedicated hardware unit," for the purposes of this figure, is a hardware component, circuit, or the like, aside from a principal control circuit and / or processor performing method steps as described in this disclosure, that is specifically designated or selected to perform one or more specific tasks and / or processes described in reference to this figure, such as without limitation preconditioning and / or sanitization of training data and / or training a machine-learning algorithm and / or model. A dedicated hardware unit 736 may include, without limitation, a hardware unit that can perform iterative or massed calculations, such as matrixbased calculations to update or tune parameters, weights, coefficients, and / or biases of machinelearning models and / or neural networks, efficiently using pipelining, parallel processing, or the like; such a hardware unit may be optimized for such processes by, for instance, including dedicated circuitry for matrix and / or signal processing operations that includes, e.g., multiple arithmetic and / or logical circuit units such as multipliers and / or adders that can act simultaneously and / or in parallel or the like. Such dedicated hardware units 736 may include, without limitation, graphical processing units (GPUs), dedicated signal processing modules, FPGA or other reconfigurable hardware that has been configured to instantiate parallel processing units for one or more specific tasks, or the like, A computing device, processor, apparatus, or module may be configured to instruct one or more dedicated hardware units 736 to perform one or more operations described herein, such as evaluation of model and / or algorithm outputs, one-time or iterative updates to parameters, coefficients, weights, and / or biases, and / or any other operations such as vector and / or matrix operations as described in this disclosure.

[0092] Referring now to FIG. 8, an exemplary embodiment of neural network 800 is illustrated. A neural network 800 also known as an artificial neural network, is a network of "nodes," or data structures having one or more inputs, one or more outputs, and a function determining outputs based on inputs. Such nodes may be organized in a network, such as without limitation a convolutional neural network, including an input layer of nodes 804, one or more intermediate layers 808, and an output layer of nodes 812. Connections between nodes may be created via the process ofAttorney Docket No. 35944-100110 "training" the network, in which elements from a training dataset are applied to the input nodes, a suitable training algorithm (such as Levenberg-Marquardt, conjugate gradient, simulated annealing, or other algorithms) is then used to adjust the connections and weights between nodes in adjacent layers of the neural network to produce the desired values at the output nodes. This process is sometimes referred to as deep learning. Connections may run solely from input nodes toward output nodes in a "feed-forward" network, or may feed outputs of one layer back to inputs of the same or a different layer in a "recurrent network." As a further non-limiting example, a neural network may include a convolutional neural network comprising an input layer of nodes, one or more intermediate layers, and an output layer of nodes. A "convolutional neural network," as used in this disclosure, is a neural network in which at least one hidden layer is a convolutional layer that convolves inputs to that layer with a subset of inputs known as a "kernel," along with one or more additional layers such as pooling layers, fully connected layers, and the like.

[0093] Referring now to FIG. 9, an exemplary embodiment of a node 900 of a neural network is illustrated. A node may include, without limitation a plurality of inputs x, that may receive numerical values from inputs to a neural network containing the node and / or from other nodes. Node may perform one or more activation functions to produce its output given one or more inputs, such as without limitation computing a binary step function comparing an input to a threshold value and outputting either a logic 1 or logic 0 output or something equivalent, a linear activation function whereby an output is directly proportional to the input, and / or a non-linear activation function, wherein the output is not proportional to the input. Non-linear activation functions may include, without limitation, a sigmoid function of the form f (x) = given ex-e-x input x, a tanh (hyperbolic tangent) function, of the form ex+e-x' a tanh derivative function such as f (x) = tanh2(x), a rectified linear unit function such as f (x) = max (0, x), a "leaky" and / or "parametric" rectified linear unit function such as f (x) = max (ax, x) for some a, an x for x > 0exponential linear units function such as f (x) = a(ex — 1) f or x < 0 for some value of a(this function may be replaced and / or weighted by its own derivative in some embodiments), a softmax function such as f (xi) = — x where the inputs to an instant layer are xi, a swish Lixi function such as f (x) = x * sigmoid(x), a Gaussian error linear unit function such as f(x) = all + tanh (. lr(x + bxr))) for some values of a, b, and r, and / or a scaled exponential linear unit function such as f (x) = A {a(e x — 1) f or x < 0. Fundamentally, there is no limit to the x for x > 0 nature of functions of inputs x, that may be used as activation functions. As a non-limiting and illustrative example, node may perform a weighted sum of inputs using weights wi that are multiplied byAttorney Docket No. 35944-100110 respective inputs z. Additionally or alternatively, a bias b may be added to the weighted sum of the inputs such that an offset is added to each unit in the neural network layer that is independent of the input to the layer. The weighted sum may then be input into a function co, which may generate one or more outputs y. Weight wi applied to an input x, may indicate whether the input is "excitatory," indicating that it has strong influence on the one or more outputs y, for instance by the corresponding weight having a large numerical value, and / or a "inhibitory," indicating it has a weak effect influence on the one more inputs y, for instance by the corresponding weight having a small numerical value. The values of weights wi may be determined by training a neural network using training data, which may be performed using any suitable process as described above.

[0094] Now referring to FIG. 10, a flow diagram of an exemplary method 1000 for riskbased diagnostic monitoring of neurodegenerative disease is illustrated. Method 1000 for risk-based diagnostic monitoring of neurodegenerative disease may include a step 1005 of receiving a plurality of patient data including a biological extraction, wherein the biological extraction includes biomarker data. In an embodiment, biomarker data may include a biomarker selected from a list consisting of Af340, Af342, Neurofilament Light-chain [NFL], Glial Fibrillary Acidic Protein [GFAP], pTaul81, pTau217, and pTau231.This may be implemented, without limitation, as described in reference to FIGS. 1-9 above. Method 1000 for risk-based diagnostic monitoring of neurodegenerative disease may include a step 1010 of selecting a plurality of case data, wherein selecting the plurality of case data includes selecting, as the plurality of case data, medical data pertaining to a cohort associated with both cognitive impairment and at least a neurodegenerative related pathology. This may be implemented, without limitation, as described in reference to FIGS.1-9 above. Method 1000 for risk-based diagnostic monitoring of neurodegenerative disease may include a step 1015 of generating a neurodegenerative risk model as a function of the selected plurality of case data. This may be implemented, without limitation, as described in reference to FIGS. 1-9 above. Method 1000 for risk-based diagnostic monitoring of neurodegenerative disease may include a step 1020 of inputting the plurality of patient data including the biomarker data into the neurodegenerative risk model. This may be implemented, without limitation, as described in reference to FIGS. 1-9 above. Method 1000 for risk-based diagnostic monitoring of neurodegenerative disease may include a step 1025 of generating using the neurodegenerative risk model, a neurodegenerative risk score. This may be implemented, without limitation, as described in reference to FIGS. 1-9 above. Method 1000 for risk-based diagnostic monitoring of neurodegenerative disease may include a step 1030 of outputting the neurodegenerative risk score toAttorney Docket No. 35944-100110 a requesting party. This may be implemented, without limitation, as described in reference to FIGS.1-9 above.

[0095] Still referring to FIG. 10, method 1000 for risk-based diagnostic monitoring of neurodegenerative disease may further include integrating patient indicators of health risk with the neurodegenerative risk score to generate and integrated risk score. Integrating the patient indicators of health risk with the neurodegenerative risk score may include receiving a plurality of patient indicators of health risk including genomic data, biographical data, and lifestyle risk scores, receiving the neurodegenerative risk score, inputting the patient indicators of health risk and neurodegenerative risk score in to the neurodegenerative risk model, generating, at the neurodegenerative risk model, an integrated risk score, and outputting the integrated risk score to a requesting party. In some embodiments, outputting the integrated risk score may include generating a user interface including the integrated risk score, and transmitting the integrated risk score to a display device, wherein the display device is configured to display a graphical user interface. In some embodiments, the neurodegenerative risk model may include a Bayesian risk model configured to integrate innate and mutable risk factors into the integrated risk score. In some embodiments the neurodegenerative risk model may include a machine-learning model, wherein the machine-learning model is trained using exemplary biomarker data and exemplary patient indicators of health risk correlated with exemplary positive indicators for neurodegenerative disease. Further, in some embodiments, the neurodegenerative risk model is retrained using an iteratively updated plurality of patient data. This may be implemented, without limitation, as described in reference to FIGS. 1-9 above.

[0096] In continued reference to FIG. 10, in an embodiment method 1000 for risk-based diagnostic monitoring of neurodegenerative disease may include a step wherein the method further includes generating a graphical user interface using the neurodegenerative risk score, receiving an updated plurality of patient data and at least an intervention, regenerating the neurodegenerative risk score as a function of the updated plurality of patient data, and updating the graphical user interface as a function of the regenerated neurodegenerative risk score and the at least an intervention.Further, in some embodiments, updating the graphical user interface as a function of the regenerated neurodegenerative risk score may include plotting the integrated neurodegenerative risk score and the regenerated neurodegenerative risk score with respect to a temporal attribute, labeling the neurodegenerative risk score and the regenerated neurodegenerative risk score with a respective intervention, and displaying, at a display device, the updated graphical user interface. In someAttorney Docket No. 35944-100110 embodiments, method 1000 for risk-based diagnostics monitoring of neurodegenerative disease may include determining an intervention efficacy score as a function of the neurodegenerative risk score and the regenerated neurodegenerative risk score. This may be implemented, without limitation, as described in reference to FIGS. 1-9 above.

[0097] It is to be noted that any one or more of the aspects and embodiments described herein may be conveniently implemented using one or more machines (e.g., one or more computing devices that are utilized as a user computing device for an electronic document, one or more server devices, such as a document server, etc.) programmed according to the teachings of the present specification, as will be apparent to those of ordinary skill in the computer art. Appropriate software coding can readily be prepared by skilled programmers based on the teachings of the present disclosure, as will be apparent to those of ordinary skill in the software art. Aspects and implementations discussed above employing software and / or software modules may also include appropriate hardware for assisting in the implementation of the machine executable instructions of the software and / or software module.

[0098] Such software may be a computer program product that employs a machine-readable storage medium. A machine-readable storage medium may be any medium that is capable of storing and / or encoding a sequence of instructions for execution by a machine (e.g., a computing device) and that causes the machine to perform any one of the methodologies and / or embodiments described herein. Examples of a machine-readable storage medium include, but are not limited to, a magnetic disk, an optical disc (e.g., CD, CD-R, DVD, DVD-R, etc.), a magneto-optical disk, a read-only memory "ROM" device, a random access memory "RAM" device, a magnetic card, an optical card, a solid-state memory device, an EPROM, an EEPROM, and any combinations thereof. A machine-readable medium, as used herein, is intended to include a single medium as well as a collection of physically separate media, such as, for example, a collection of compact discs or one or more hard disk drives in combination with a computer memory. As used herein, a machine-readable storage medium does not include transitory forms of signal transmission.

[0099] Such software may also include information (e.g., data) carried as a data signal on a data carrier, such as a carrier wave. For example, machine-executable information may be included as a data-carrying signal embodied in a data carrier in which the signal encodes a sequence of instruction, or portion thereof, for execution by a machine (e.g., a computing device) and any related information (e.g., data structures and data) that causes the machine to perform any one of the methodologies and / or embodiments described herein.Attorney Docket No. 35944-100110

[0100] Examples of a computing device include, but are not limited to, an electronic book reading device, a computer workstation, a terminal computer, a server computer, a handheld device (e.g., a tablet computer, a smartphone, etc.), a web appliance, a network router, a network switch, a network bridge, any machine capable of executing a sequence of instructions that specify an action to be taken by that machine, and any combinations thereof. In one example, a computing device may include and / or be included in a kiosk.

[0101] FIG. 11 shows a diagrammatic representation of one embodiment of a computing device in the exemplary form of a computer system 1100 within which a set of instructions for causing a control system to perform any one or more of the aspects and / or methodologies of the present disclosure may be executed. It is also contemplated that multiple computing devices may be utilized to implement a specially configured set of instructions for causing one or more of the devices to perform any one or more of the aspects and / or methodologies of the present disclosure. Computer system 1100 includes a processor 1104 and a memory 1108 that communicate with each other, and with other components, via a bus 1112. Bus 1112 may include any of several types of bus structures including, but not limited to, a memory bus, a memory controller, a peripheral bus, a local bus, and any combinations thereof, using any of a variety of bus architectures.

[0102] Processor 1104 may include any suitable processor, such as without limitation a processor incorporating logical circuitry for performing arithmetic and logical operations, such as an arithmetic and logic unit (ALU), which may be regulated with a state machine and directed by operational inputs from memory and / or sensors; processor 1104 may be organized according to Von Neumann and / or Harvard architecture as a non-limiting example. Processor 1104 may include, incorporate, and / or be incorporated in, without limitation, a microcontroller, microprocessor, digital signal processor (DSP), Field Programmable Gate Array (FPGA), Complex Programmable Logic Device (CPLD), Graphical Processing Unit (GPU), general purpose GPU, Tensor Processing Unit (TPU), analog or mixed signal processor, Trusted Platform Module (TPM), a floating point unit (FPU), system on module (SOM), and / or system on a chip (SoC).

[0103] Memory 1108 may include various components (e.g., machine-readable media) including, but not limited to, a random-access memory component, a read only component, and any combinations thereof. In one example, a basic input / output system 1116 (BIOS), including basic routines that help to transfer information between elements within computer system 1100, such as during start-up, may be stored in memory 1108. Memory 1108 may also include (e.g., stored on one or more machine-readable media) instructions (e.g., software) 1120 embodying any one or more ofAttorney Docket No. 35944-100110 the aspects and / or methodologies of the present disclosure. In another example, memory 1108 may further include any number of program modules including, but not limited to, an operating system, one or more application programs, other program modules, program data, and any combinations thereof.

[0104] Computer system 1100 may also include a storage device 1124. Examples of a storage device (e.g., storage device 1124) include, but are not limited to, a hard disk drive, a magnetic disk drive, an optical disc drive in combination with an optical medium, a solid-state memory device, and any combinations thereof. Storage device 1124 may be connected to bus 1112 by an appropriate interface (not shown). Example interfaces include, but are not limited to, SCSI, advanced technology attachment (ATA), serial ATA, universal serial bus (USB), IEEE 1394 (FIREWIRE), and any combinations thereof. In one example, storage device 1124 (or one or more components thereof) may be removably interfaced with computer system 1100 (e.g., via an external port connector (not shown)). Particularly, storage device 1124 and an associated machine-readable medium 1128 may provide nonvolatile and / or volatile storage of machine-readable instructions, data structures, program modules, and / or other data for computer system 1100. In one example, software 1120 may reside, completely or partially, within machine-readable medium 1128. In another example, software 1120 may reside, completely or partially, within processor 1104.

[0105] Computer system 1100 may also include an input device 1132. In one example, a user of computer system 1100 may enter commands and / or other information into computer system 1100 via input device 1132. Examples of an input device 1132 include, but are not limited to, an alphanumeric input device (e.g., a keyboard), a pointing device, a joystick, a gamepad, an audio input device (e.g., a microphone, a voice response system, etc.), a cursor control device (e g., a mouse), a touchpad, an optical scanner, a video capture device (e.g., a still camera, a video camera), a touchscreen, and any combinations thereof. Input device 1132 may be interfaced to bus 1112 via any of a variety of interfaces (not shown) including, but not limited to, a serial interface, a parallel interface, a game port, a USB interface, a FIREWIRE interface, a direct interface to bus 1112, and any combinations thereof. Input device 1132 may include a touch screen interface that may be a part of or separate from display 1136, discussed further below. Input device 1132 may be utilized as a user selection device for selecting one or more graphical representations in a graphical interface as described above.

[0106] A user may also input commands and / or other information to computer system 1100 via storage device 1124 (e.g., a removable disk drive, a flash drive, etc.) and / or network interfaceAttorney Docket No. 35944-100110 device 1140. A network interface device, such as network interface device 1140, may be utilized for connecting computer system 1100 to one or more of a variety of networks, such as network 1144, and one or more remote devices 1148 connected thereto. Examples of a network interface device include, but are not limited to, a network interface card (e.g., a mobile network interface card, a LAN card), a modem, and any combination thereof. Examples of a network include, but are not limited to, a wide area network (e.g., the Internet, an enterprise network), a local area network (e.g., a network associated with an office, a building, a campus or other relatively small geographic space), a telephone network, a data network associated with a telephone / voice provider (e.g., a mobile communications provider data and / or voice network), a direct connection between two computing devices, and any combinations thereof. A network, such as network 1144, may employ a wired and / or a wireless mode of communication. In general, any network topology may be used.Information (e.g., data, software 1120, etc.) may be communicated to and / or from computer system 1100 via network interface device 1140.

[0107] Computer system 1100 may further include a video display adapter 1152 for communicating a displayable image to a display device, such as display 1136. Examples of a display device include, but are not limited to, a liquid crystal display (LCD), a cathode ray tube (CRT), a plasma display, a light emitting diode (LED) display, and any combinations thereof. Display adapter 1152 and display 1136 may be utilized in combination with processor 1104 to provide graphical representations of aspects of the present disclosure. In addition to a display device, computer system 1100 may include one or more other peripheral output devices including, but not limited to, an audio speaker, a printer, and any combinations thereof. Such peripheral output devices may be connected to bus 1112 via a peripheral interface 1156. Examples of a peripheral interface include, but are not limited to, a serial port, a USB connection, a FIREWIRE connection, a parallel connection, and any combinations thereof

[0108] The foregoing has been a detailed description of illustrative embodiments of the invention. Various modifications and additions can be made without departing from the spirit and scope of this invention. Features of each of the various embodiments described above may be combined with features of other described embodiments as appropriate in order to provide a multiplicity of feature combinations in associated new embodiments. Furthermore, while the foregoing describes a number of separate embodiments, what has been described herein is merely illustrative of the application of the principles of the present invention. Additionally, although particular methods herein may be illustrated and / or described as being performed in a specific order,Attorney Docket No. 35944-100110 the ordering is highly variable within ordinary skill to achieve methods, systems, and software according to the present disclosure. Accordingly, this description is meant to be taken only by way of example, and not to otherwise limit the scope of this invention.

[0109] Exemplary embodiments have been disclosed above and illustrated in the accompanying drawings. It will be understood by those skilled in the art that various changes, omissions and additions may be made to that which is specifically disclosed herein without departing from the spirit and scope of the present invention.

Claims

Attorney Docket No. 35944-100110 What is claimed is:

1. A system for risk-based diagnostic monitoring of neurodegenerative disease, wherein the system comprises: at least a processor; and a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to: receive a plurality of patient data comprising a biological extraction, wherein the biological extraction comprises biomarker data; select a plurality of case data, wherein selecting the plurality of case data comprises selecting, as the plurality of case data, medical data pertaining to a cohort associated with both cognitive impairment and at least a neurodegenerative-related pathology; generate a neurodegenerative risk model as a function of the selected plurality of case data; input the plurality of patient data comprising the biomarker data into the neurodegenerative risk model; generate, using the neurodegenerative risk model, a neurodegenerative risk score; and output the neurodegenerative risk score to a requesting party.

2. The system of claim 1, wherein the biomarker data comprises a biomarker selected from a list consisting of Af340, A1342, Neurofilament Light-chain [NFL], Glial Fibrillary Acidic Protein [GFAP], pTaul81, pTau217, and pTau231.

3. The system of claim 1, wherein the at least a processor is further configured to integrate patient indicators of health risk with the neurodegenerative risk score to generate an integrated risk score, wherein integrating the patient indicators of health risk with the neurodegenerative risk score comprises: receiving a plurality of patient indicators of health risk comprising genomic data, biographical data, and lifestyle risk scores; receiving the neurodegenerative risk score; inputting the patient indicators of health risk and the neurodegenerative risk score into the neurodegenerative risk model; generating, at the neurodegenerative risk model, an integrated risk score; and outputting the integrated risk score to a requesting party.

4. The system of claim 3, wherein outputting the integrated risk score comprises: generating a user interface comprising the integrated risk score; and transmitting the integrated risk score to a display device, wherein the display device is configured to display a graphical user interface.

5. The system of claim 3, wherein the neurodegenerative risk model comprises a Bayesian risk model configured to integrate innate and mutable risk factors into the integrated risk score.Attorney Docket No. 35944-100110 6. The system of claim 3, wherein the neurodegenerative risk model comprises a machinelearning model, wherein the machine-learning model is trained using exemplary biomarker data and exemplary patient indicators of health risk correlated with exemplary positive indicators for neurodegenerative disease.

7. The system of claim 6, wherein the at least a processor is further configured to iteratively retrain the neurodegenerative risk model using an updated plurality of patient data.

8. The system of claim 1, wherein the at least a processor is further configured to: generate a graphical user interface using the neurodegenerative risk score; receive an updated plurality of patient data and at least an intervention; regenerate the neurodegenerative risk score as a function of the updated plurality of patient data; and update the graphical user interface as a function of the regenerated neurodegenerative risk score and the at least an intervention.

9. The system of claim 8, wherein updating the graphical user interface as a function of the regenerated neurodegenerative risk score comprises: plotting the neurodegenerative risk score and the regenerated neurodegenerative risk score with respect to a temporal attribute; labeling the neurodegenerative risk score and the regenerated neurodegenerative risk score with a respective intervention; and displaying, at a display device, the updated graphical user interface.

10. The system of claim 8, wherein the at least a processor is further configured to determine an intervention efficacy score as a function of the neurodegenerative risk score and the regenerated neurodegenerative risk score.

11. A method for risk-based diagnostic monitoring of neurodegenerative disease, wherein the method comprises: receiving a plurality of patient data comprising a biological extraction, wherein the biological extraction comprises biomarker data; selecting a plurality of case data, wherein selecting the plurality of case data comprising selecting, as the plurality of case data, medical data pertaining to a cohort associated with both cognitive impairment and at least a neurodegenerative-related pathology; generating a neurodegenerative risk model as a function of the selected plurality of case data; inputting the plurality of patient data comprising the biomarker data into the risk model; generating, using the risk model, a neurodegenerative risk score; and outputting the neurodegenerative risk score to a requesting party.

12. The method of claim 11, wherein the biomarker data comprises a biomarker selected from a list consisting of Af340, Af342, Neurofilament Light-chain [NFL], Glial Fibrillary Acidic Protein [GFAP], pTaul81, pTau217, and pTau231.Attorney Docket No. 35944-100110 13. The method of claim 11, wherein the method further comprises integrating patient indicators of health risk with the neurodegenerative risk score to generate an integrated risk score, wherein integrating the patient indicators of health risk with the neurodegenerative risk score comprises: receiving a plurality of patient indicators of health risk comprising genomic data, biographical data, and lifestyle risk scores; receiving the neurodegenerative risk score; inputting the patient indicators of health risk and the neurodegenerative risk score into the neurodegenerative risk model; generating, at the neurodegenerative risk model, an integrated risk score; and outputting the integrated risk score to a requesting party.

14. The method of claim 13, wherein outputting the integrated risk score comprises: generating a user interface comprising the integrated risk score; and transmitting the integrated risk score to a display device, wherein the display device is configured to display a graphical user interface.

15. The method of claim 13, wherein the neurodegenerative risk model comprises a Bayesian risk model configured to integrate innate and mutable risk factors into the integrated risk score.

16. The method of claim 13, wherein the neurodegenerative risk model comprises a machinelearning model, wherein the machine-learning model is trained using exemplary biomarker data and exemplary patient indicators of health risk correlated with exemplary positive indicators for neurodegenerative disease.

17. The method of claim 16, wherein the at least a processor is further configured to iteratively retrain the neurodegenerative risk model using an updated plurality of patient data.

18. The method of claim 11, wherein the method further comprises: generating a graphical user interface using the neurodegenerative risk score; receiving an updated plurality of patient data and at least an intervention; regenerating the neurodegenerative risk score as a function of the updated plurality of patient data; and updating the graphical user interface as a function of the regenerated neurodegenerative risk score and the at least an intervention.

19. The method of claim 18, wherein updating the graphical user interface as a function of the regenerated neurodegenerative risk score comprises: plotting the neurodegenerative risk score and the regenerated neurodegenerative risk score with respect to a temporal attribute; labeling the neurodegenerative risk score and the regenerated neurodegenerative risk score with a respective intervention; and displaying, at a display device, the updated graphical user interface.Attorney Docket No. 35944-100110 20. The method of claim 18, wherein the method further comprises determining an intervention efficacy score as a function of the neurodegenerative risk score and the regenerated neurodegenerative risk score.

Images