WO2024191712A1

WO2024191712A1 - Neurofilament light chain biomarker compositions and methods of use thereof

Info

Publication number: WO2024191712A1
Application number: PCT/US2024/018769
Authority: WO
Inventors: Arejas James UZGIRIS
Original assignee: Siemens Healthcare Diagnostics Inc
Current assignee: Siemens Healthcare Diagnostics Inc
Priority date: 2023-03-15
Filing date: 2024-03-07
Publication date: 2024-09-19
Anticipated expiration: 2025-09-15
Also published as: CN120752707A; MX2025010756A; AU2024234846A1

Abstract

Methods, non-transitory computer readable media, and computer systems are disclosed that predict heart disease with improved efficiency and accuracy. In some examples, this technology includes obtaining a biomarker profile comprising a first level of one or more biomarkers in a first sample obtained from a subject. The one or more biomarkers comprise neurofilament light chain (NfL). A first machine learning model is applied to an input to generate a biomarker score for the subject. The input comprises at least the biomarker profile and the biomarker score is indicative of a probability that the subject is at risk of, or is suffering from, a heart disease. The biomarker score or an indication of the heart disease determined from the biomarker score is then output to a computing device via one or more communication networks and in response to the biomarker profile.

Description

NEUROFILAMENT LIGHT CHAIN BIOMARKER COMPOSITIONS AND METHODS OF USE THEREOF

[0001] This application claims priority to U.S. Provisional Patent Application No. 63/490,493, filed March 15, 2023, which is incorporated herein by reference in its entirety.

FIELD

[0002] The disclosed technology generally relates to molecular biology and cardiac health and, more particularly, to neurofilament light chain biomarker compositions and methods of use thereof.

BACKGROUND

[0003] Heart disease is a significant health concern, as it is the leading cause of death for men, women, and people of most racial and ethnic groups in the United States. For example, one person dies every 34 seconds in the United States from cardiovascular disease. About 697,000 people in the United States died from heart disease in 2020 — that is 1 in every 5 deaths. Heart disease cost the United States about $229 billion each year from 2017 to 2018, which includes the cost of health care sendees, medicines, and lost productivity due to death.

[0004] Current methods for detecting heart disease are inconvenient, uncomfortable, and/or inaccurate. Accordingly, there is a need in the art for compositions, kits, and methods for detecting heart disease with an acceptable level of specificity and in a manner that aids patient compliance.

SUMMARY

[0005] The present disclosure provides compositions, kits, methods, and computer systems for detecting and/or identifying heart disease (e.g., acute coronary syndrome, aortic aneurysm, aortic dissection, aortic stenosis, arrhythmia, atherosclerosis, atrial fibrillation, coronary artery' disease (e.g., angina (e.g., stable angina or unstable angina) or heart attack), cardiac dysrhythmia, cardiomyopathy (e.g., dilated, hypertrophic, arrhythmogenic, or restrictive cardiomyopathy), carditis (e.g., endocarditis, infective endocarditis, myocarditis, pericarditis, pancarditis, or reflux carditis), congenital heart defect or disease, eosinophilic myocarditis, heart failure, heart murmurs, heart valve disease, heart valve stenosis, hypertension, hypertensive heart disease, inflammatory cardiomegaly, Kawasaki disease, myocardial infarction, Marfan syndrome, metabolic syndrome, peripheral arterial disease (PAD), rheumatic heart disease, thromboembolic disease, transthyretin amyloidosis (ATTR- CM). venous thrombosis, or valvular heart disease).

[0006] Further, the present disclosure provides methods of classifying heart disease patients compared to normal individuals. Additionally, the present disclosure recognizes that certain biomarkers (e.g., neurofilament light chain (NfL)) can assist in detecting and/or diagnosing heart disease, and/or assist in classification of heart disease patients. The present disclosure further recognizes that these biomarkers (e.g.. NfL) in compositions, kits, and methods can be useful for classifying, detecting and/or diagnosing heart disease without the need for performing invasive or costly tests, which represents a significant advancement in patient care. Specifically, heart disease can be detected and identified by the methods of this technology that are more comfortable for the patient, inflict less harm to the patient, and/or decrease the amount of time a patient needs to recover following the detection and/or diagnosis. [0007] In addition, the present disclosure provides that certain biomarkers (e.g., NfL) are useful in detecting heart disease with improved sensitivity. The present disclosure provides that certain biomarkers (e.g., NfL) are useful in detecting heart disease with improved selectivity. The present disclosure further provides that combinations of one or more demographic factors, especially age and/or sex, and NfL, do unexpectedly well at detecting heart disease with improved sensitivity and/or specificity⁷. In addition, the present disclosure further provides that combinations of one or more imaging-based biomarkers, especially left ventricle septal wall thickness and/or ejection fraction, and NfL, are surprisingly beneficial for detecting heart disease with improved sensitivity and/or specificity.

[0008] The increased sensitivity⁷ achieved with biomarkers (e.g., NfL) described herein decreases the number of false negatives obtained when detecting and/or identifying heart disease. The decrease in false negatives will, in turn, help to ensure that more heart disease patients receive earlier treatments critical for reducing signs, symptoms, and conditions associated with heart disease, as well as promoting long-term survival of heart disease patients. [0009] Thus, described herein in some examples are methods for heart disease prediction that are implemented by a computer system. In some examples, this technology includes obtaining a biomarker profile comprising a first level of one or more biomarkers in a first sample obtained from a subject. The one or more biomarkers comprise neurofilament light chain (NfL). A first machine learning model is applied to an input to generate a biomarker score for the subject. The input comprises at least the biomarker profile and the biomarker score is indicative of a probability that the subject is at risk of, or is suffering from, a heart disease. The biomarker score or an indication of the heart disease determined from the biomarker score is then output to a computing device via one or more communication networks and in response to the biomarker profile.

[0010] In one example, the method further includes obtaining from the computing device and via the communication networks demographic data corresponding to one or more demographic factors for the subject. The input in these examples further comprises the demographic data and the demographic factors comprise at least one or more of sex or age of the subject. In another example, one or more imaging-based biomarkers are obtained for the subject from the computing device and via the communication networks. The input in these examples further comprises the imaging-based biomarkers and the imaging-based biomarkers comprise at least a left ventricle septal wall thickness or ejection fraction.

[0011] In yet other examples, to determine the imaging-based biomarkers, one or more obtained images associated with the subject are analyzed to obtain one or more measurements. In these examples, the analysis comprises one or more of a pattern recognition performed on the obtained images or a segmentation and classification with the first machine learning model or a second machine learning model of one or more features extracted from the obtained images.

[0012] In some examples, the machine learning model is derived from a bagged, boosted, or additive decision tree methodology, a neural boosted methodology, a bootstrap forest methodology, a boosted tree methodology, or a support vector machine methodology. In other examples, the first machine learning model is a classifier for heart disease and the method further comprises classifying the subject as having or not having heart disease based on the biomarker score. The indication of heart disease comprises a binary indication determined based on the classification in these examples. Optionally, one or more of a sensitivity or a specificity of the classifier is more than eighty percent.

[0013] In yet other examples, the subject is a human subject, and the first sample comprises one or more of blood, serum, plasma, or cardiac tissue. Additionally, at least one of (i) a heart disease state for the subject, (ii) whether the subject has or does not have a heart disease, or (iii) a probability that the subject has a heart disease is determined based on the biomarker score in some examples.

[0014] In another example, the first machine learning model can be trained using obtained training data comprising biomarker profiles for a plurality of subjects and a health status for the subjects corresponding to the biomarker profiles in some examples. In these examples, each of the biomarker profiles comprises levels of two or more biomarkers comprising at least NfL.

[0015] In some examples, the first sample is obtained from the subject at a first time and the method further comprises determining that the subject is at risk of, or is suffering from, a heart disease when a second level of NfL detected in a second sample obtained from the subject at a second time later than the first time exceeds the first level of NfL by a threshold amount. In other examples, the first sample is obtained from the subject at a first time and the method further comprises determining whether the subject is at risk of, or is suffering from, a heart disease based on a first NfL level change determined based on a comparison of the first level of NfL to a second level of NfL detected in a second sample obtained from the subject at a second time later than the first time.

[0016] In yet other examples, the first NfL level change is compared to a second NfL change determined for a control subject over a first time period corresponding to a difference between the second time and the first time. The control subject in these examples has an age within three years of the subject and the control subject does not have a heart disease. In some examples, the subject is determined to be at risk of, or suffering from, a heart disease based on a second NfL level change determined over a second time period during which a series of samples was obtained from the subject based on a third level of NfL detected in each of the series of samples, wherein the series of samples includes the first sample.

[0017] The present disclosure also provides a non-transitory computer- readable medium comprising executable instructions that when executed by a processor cause the processor to perform a method disclosed herein.

[0018] The present disclosure also provides a computer system comprising memory and a processor, wherein the memory comprises a trained machine learning model and has executable instructions stored thereon that, when executed by the processor, cause the computer system to perform a method disclosed herein.

[0019] Any two or more of the features described in this specification, including in this summary section, may be combined to form implementations of the disclosure, whether specifically expressly described as a separate combination in this specification or not.

BRIEF DESCRIPTION OF THE DRAWINGS

[0020] FIG. 1 depicts a block diagram of an exemplary computer system. [0021] FIG. 2 depicts a flow chart of an exemplary method identifying a subject for further testing, as being at risk or having heart disease, and/or to receive medication.

[0022] FIG. 3 depicts a flow chart of an exemplary method for generating a biomarker score indicative of heart disease risk.

[0023] FIG. 4 is a block diagram of an example of a network environment.

[0024] FIG. 5 is a plot demonstrating performance of machine learning models in classifying heart disease using various neurofilament light chains (NfLs).

[0025] FIG. 6 is a plot demonstrating correlation between NfL and age for subjects with various disease states.

DEFINITIONS

[0026] Antibody agent: As used herein, the term “antibody agent” refers to an agent that specifically binds to a particular antigen. In some embodiments, the term encompasses any polypeptide or polypeptide complex that includes immunoglobulin structural elements sufficient to confer specific binding. Such polypeptide may be naturally produced (e.g., generated by an organism reacting to an antigen), or produced by recombinant engineering, chemical synthesis, or other artificial system or methodology. Exemplary antibody agents include, but are not limited to, human antibodies, primatized antibodies, chimeric antibodies, bi-specific antibodies, humanized antibodies, conjugated antibodies (e g., antibodies conjugated or fused to other proteins, radiolabels, cytotoxins). Small Modular ImmunoPharmaceuticals (“SMIPs™”), single chain antibodies, cameloid antibodies, and antibody fragments. As used herein, the term “antibody agent” also includes intact monoclonal antibodies, polyclonal antibodies, single domain antibodies (e.g., shark single domain antibodies (e.g., IgNAR or fragments thereof)), multispecific antibodies (e.g., bi-specific antibodies) formed from at least two intact antibodies, and antibody fragments so long as they exhibit the desired biological activity. An antibody agent can have antibody constant region sequences that are characteristic of mouse, rabbit, primate, or human antibodies. In some embodiments, the term antibody agent encompasses stapled peptides. In some embodiments, the term antibody agent encompasses one or more antibody-hke binding peptidomimetics, or one or more antibody-like binding scaffold proteins, monobodies, or adnectins. In some embodiments, an antibody agent is or includes a polypeptide whose amino acid sequence includes one or more structural elements comprising a complementarity determining region (CDR). In some embodiments, an antibody agent is or includes a polypeptide whose amino acid sequence includes at least one CDR (e.g., at least one heavy chain CDR and/or at least one light chain CDR) that is substantially identical to one found in a reference antibody. In some embodiments, an antibody agent is or includes a polypeptide whose amino acid sequence includes structural elements comprising an immunoglobulin variable domain. In some embodiments, an antibody agent is a polypeptide protein having a binding domain which is homologous or largely homologous to an immunoglobulin-binding domain. In some embodiments, an antibody agent may contain a covalent modification (e.g., attachment of a glycan, a payload (e.g., a detectable moiety, a therapeutic moiety, a catalytic moiety’, etc ), or other pendant group (e.g., poly-ethylene glycol, etc.).)

[0027] Biomarker: The term “biomarker” or “biological marker” is used herein, consistent with its use in the art, to refer to an entity whose presence, level, or form, correlates with a particular biological event or state of interest, so that it is considered to be a “marker” of that event or state. To give but a few examples, in some embodiments, a biomarker may be or include a marker for a particular disease state, or for likelihood that a particular disease, disorder or condition may develop, occur, or reoccur. In some embodiments, a biomarker may be or include a marker for a particular disease or therapeutic outcome, or likelihood thereof. Thus, in some embodiments, a biomarker is predictive, prognostic, or diagnostic of the relevant biological event or state of interest. In some embodiments, a biomarker is a possible marker of the relevant biological event or state of interest. A biomarker may be an entity of any chemical class. For example, in some embodiments, a biomarker may be or include a nucleic acid, a polypeptide, a small molecule, or a combination thereof. In some embodiments, a biomarker is a cell surface marker. In some embodiments, a biomarker is intracellular. In some embodiments, a biomarker is found in a particular tissue (e.g., cardiac tissue). In some embodiments, a biomarker is found outside of cells (e.g., is secreted or is otherwise generated or present outside of cells (e.g., in a body fluid such as blood, urine, tears, saliva, cerebrospinal fluid, etc.).)

[0028] Characteristic fragment: The term “characteristic fragment” as used herein refers to a fragment of a biomarker (e.g., NIL) that is sufficient to identify the biomarker from which the fragment was derived. For example, in some embodiments, a “characteristic fragment” of a biomarker is one that contains an amino acid sequence, or a collection of amino acid sequences, which collectively allow for the biomarker from which the fragment was derived to be distinguished from other possible biomarkers, proteins, or polypeptides. In some embodiments, a characteristic fragment includes at least 10, at least 20, at least 30, at least 40, or at least 50 amino acids, although other numbers of amino acids can also be used.

[0029] Gene product or expression product: As used herein, the term ‘gene product” generally refers to an RNA transcribed from a gene (pre-and/or post-processing) or a polypeptide (pre- and/or post-modification) encoded by an RNA transcribed from the gene.

[0030] Hybridization: The term “hybridization” as used herein refers to the physical property of single-stranded nucleic acid molecules (e.g.. DNA or RNA) to anneal to complementary nucleic acid molecules. Hybridization can typically be assessed in a variety of context- including where interacting nucleic acid molecules are studied in isolation or in the context of more complex systems (e.g., while covalently or otherwise associated with a carrier entity and/or in a biological system or cell). In some embodiments, hybridization can be detected by a hybridization technique, such as in situ hybridization (ISH), microarray, Northern blot, or Southern blot. In some embodiments, hybridization refers to 100% annealing between the single-stranded nucleic acid molecules and the complementary nucleic acid molecule. In some embodiments, annealing is less than 100% (e.g.. at least 95%, at least 90%, at least 85%, at least 80%. at least 75%. at least 70% of a single-stranded nucleic acid molecule anneals to a complementary nucleic acid molecule). Hybridization techniques, and methods for evaluating hybridization, are well known in the art. See, e.g., Sambrook, et al., 1989, Molecular Cloning: A Laboratory Manual, Second Edition, Cold Spring Harbor Press, Plainview. N.Y. and AusubeL F. M. et al. 1994. Current Protocols in Molecular Biology. John Wiley & Sons, Secaucus, N.J., each of which is incorporated by reference herein in its entirety.

[0031] Detection agent: The term “detection agent” as used herein refers to any element, molecule, functional group, compound, fragment or moiety that is detectable. In some embodiments, a detection agent is provided or utilized alone. In some embodiments, a detection agent is provided and/or utilized in association with (e.g., joined to) another agent. Examples of detection agents include, but are not limited to: various ligands, radionuclides (e.g., ³H, ¹⁴C, ¹⁸F, ¹⁹F, ³²P, ³⁵S, ¹³⁵I, ¹²⁵I, ¹²³I, ⁶⁴CU, ¹⁸⁷Re, ^mIn, ⁹⁰Y, "^mTc, ¹⁷⁷Lu, ⁸⁹Zr etc.), fluorescent dyes, chemiluminescent agents (e.g., acridinum esters, stabilized dioxetanes, and the like), bioluminescent agents, spectrally resolvable inorganic fluorescent semiconductors nanocrystals (i.e., quantum dots), metal nanoparticles (e g., gold, silver, copper, platinum, etc.) nanoclusters, paramagnetic metal ions, enzymes, colorimetric labels (e.g., dyes, colloidal gold, and the like), biotin, dioxigenin, haptens, and proteins for which antisera or monoclonal antibodies are available. [0032] Diagnostic test: As used herein, the term “diagnostic test'’ is a step or series of steps that is or has been performed to attain information that is useful in determining whether a patient has a disease, disorder or condition and/or in classifying a disease, disorder or condition into a phenotypic category or any category having significance with regard to prognosis of a disease, disorder or condition, or likely response to treatment (either treatment in general or any particular treatment) of a disease, disorder or condition. Similarly, “diagnosis” as used herein refers to providing any type of diagnostic information, including, but not limited to, whether a subject is likely to have or develop a disease, disorder or condition, state, staging or characteristic of a disease, disorder or condition as manifested in the subject, information related to the nature or classification of a tumor, information related to prognosis and/or information useful in selecting an appropriate treatment or additional diagnostic testing. Selection of treatment may include the choice of a particular therapeutic agent or other treatment modality such as surgery', radiation, etc., a choice about whether to withhold or deliver therapy, a choice relating to dosing regimen (e.g., frequency or level of one or more doses of a particular therapeutic agent or combination of therapeutic agents), etc. Selection of additional diagnostic testing may include more specific testing for a given disease, disorder, or condition.

[0033] Sample: As used herein, the term “sample” refers to a biological sample obtained or derived from a human subject, as described herein. In some embodiments, a biological sample includes biological tissue or fluid. In some embodiments, a biological sample may include blood, blood cells, tissue or fine needle biopsy samples, cell -containing body fluids, free floating nucleic acids, cerebrospinal fluid, lymph, tissue biopsy specimens, surgical specimens, other body fluids, secretions, and/or excretions, and/or cells therefrom. In some embodiments, a biological sample includes cells obtained from an individual (e.g.. from a human or animal subject). In some embodiments, obtained cells are or include cells from an individual from whom the sample is obtained. In some embodiments, a sample is a “primary sample” obtained directly from a source of interest by any appropriate means. For example, in some embodiments, a primary biological sample is obtained by biopsy (e.g., fine needle aspiration or tissue biopsy), surgery, or collection of body fluid (e.g.. blood). In some embodiments, a sample is cardiac tissue obtained from the subject. In some embodiments, the term “sample” refers to a preparation that is obtained by processing (e.g., by removing one or more components of and/or by adding one or more agents to) a primary sample. For example, filtering using a semi-permeable membrane. As another example of sample processing, the sample may be a plasma sample that is treated with an anticoagulant (e.g., EDTA, heparin, or citrate). As another example of sample processing, the sample may be processed to isolate one or more proteins (e.g., by capturing proteins with one or more antibodies). A '‘processed sample” may include, for example, nucleic acids or polypeptides extracted from a sample or obtained by subjecting a primary sample to techniques such as amplification or reverse transcription of mRNA, isolation and/or purification of certain components.

[0034] Subject: As used herein, the term ‘'subject” refers to an organism, for example, a mammal (e.g., a human). In some embodiments a human subject is an adult, adolescent, or pediatric subject. In some embodiments, a subject is at least 50, at least 55, at least 60, at least 65, at least 70, at least 75, or at least 80 years of age, although other threshold ages can also be used. In some embodiments, a subject is suffering from a disease, disorder or condition (e.g., a disease, disorder or condition that can be treated as provided herein). In some embodiments, a subject is susceptible to a disease, disorder, or condition. In some embodiments, a susceptible subject is predisposed to and/or shows an increased risk (as compared to the average risk observed in a reference subject or population) of developing the disease, disorder or condition. In some embodiments, a subject displays one or more symptoms of a disease, disorder or condition. In some embodiments, a subject does not display a particular symptom (e.g., clinical manifestation of disease) or characteristic of a disease, disorder, or condition. In some embodiments, a subject does not display any symptom or characteristic of a disease, disorder, or condition. In some embodiments, a subject is a patient. In some embodiments, a subject is an individual to whom diagnosis and/or therapy is and/or has been administered.

[0035] Therapeutically effective amount: As used herein, the term “therapeutically effective amount” refers to an amount that produces a desired effect for which it is administered. In some embodiments, the term “therapeutically effective amount” refers to an amount that is sufficient, when administered to a population suffering from or susceptible to a disease, disorder, and/or condition in accordance with a therapeutic dosing regimen, to treat the disease, disorder, and/or condition. In some embodiments, a therapeutically effective amount is one that reduces the incidence and/or severity of, and/or delays onset of, one or more symptoms of the disease, disorder, and/or condition. The term "therapeutically effective amount" as used herein does not require successful treatment be achieved in a particular individual. Rather, a therapeutically effective amount may be an amount that provides a particular desired pharmacological response in a significant number of subjects when administered to patients in need of such treatment. In some embodiments, reference to a therapeutically effective amount may be a reference to an amount as measured in one or more specific tissues (e.g., a tissue affected by the disease, disorder or condition) or fluids (e.g., blood, saliva, serum, sweat, tears, urine, etc.) In some embodiments, a therapeutically effective amount of a particular agent or therapy may be formulated and/or administered in a single dose. In some embodiments, a therapeutically effective agent may be formulated and/or administered in a plurality of doses (e.g., as part of a dosing regimen).

[0036] Threshold value: As used herein, the term ‘"threshold value” refers to a value (or values) that are used as a reference to attain information on and/or classify the results of a measurement (e.g., the results of a measurement attained in an assay). A threshold value can be determined based on one or more control samples. A threshold value can be determined prior to, concurrently with, or after the measurement of interest is taken. In some embodiments, a threshold value can be a range of values. In some embodiments, a threshold value can be a value (or range of values) reported in a relevant field (e.g., a value found in a standard table).

DETAILED DESCRIPTION OF CERTAIN EMBODIMENTS

Heart Disease

[0037] Methods and devices disclosed herein may be used to, for example, identify, diagnose, monitor, or treat heart disease. Heart disease may be or include acute coronary⁷ syndrome, aortic aneurysm, aortic dissection, aortic stenosis, arrhythmia, atherosclerosis, atrial fibrillation, coronary artery disease (e.g.. angina (e.g., stable angina or unstable angina) or heart attack), cardiac dysrhythmia, cardiomyopathy (e g., dilated, hypertrophic, arrhythmogenic, or restrictive cardiomyopathy), carditis (e.g., endocarditis, infective endocarditis, myocarditis, pericarditis, pancarditis, or reflux carditis), congenital heart defect or disease, eosinophilic myocarditis, heart failure, heart murmurs, heart valve disease, heart valve stenosis, hypertension, hypertensive heart disease, inflammatory⁷ cardiomegaly, Kawasaki disease, myocardial infarction, Marfan syndrome, metabolic syndrome, peripheral arterial disease (PAD), rheumatic heart disease, thromboembolic disease, transthyretin amyloidosis (ATTR- CM), venous thrombosis, or valvular heart disease. Heart disease may be a heart condition or heart disorder. Heart disease may cause and/or exacerbate one or more neurological symptoms in a subject (e.g., neuropathy, such as, for example, peripheral neuropathy). Heart disease may lead to (e.g., cause), directly or indirectly, an increase in level of NfL in a subject. Such increase may occur whether the subject has a neurological disease, disorder, or condition or not. In some embodiments, a neurological condition of a subject (e.g., whether a subject has one or more neurological diseases, disorders, or conditions) is considered when comparing, monitoring, or determining change in level of NfL for the subj ect over time, for example, in determining whether the subject has (e.g., is suffering from) or is at risk ofhaving heart disease. In some embodiments, heart disease is treated by administering a therapeutically effective amount of a medication or therapy for heart disease, such as, for example, an angiotensinconverting enzyme (ACE) inhibitor, an angiotensin II receptor blocker, an angiotensin receptor-neprilysin inhibitor, an anticoagulant or blood thinner, an antiplatelet agent, aspirin, a beta blocker, a calcium channel blocker, a cholesterylester transfer protein (CETP) inhibitor, a cholesterol absorption inhibitor, a digitalis preparation (e.g., a digitalis glycosides), a diuretic, a dual anti platelet therapy, a fibrate, niacin, a statin, a vasodilator, or a combination thereof. For example, a therapy may be apixaban. dabigatran, edoxaban, heparin, rivaroxaban, warfarin, aspirin, clopidogrel, dipyridamole, prasugrel, ticagrelor, benazepril, captopril, enalapril, fosinopril, moexipril, perindopril, quinapril, ramipril, trandolapril, azilsartan, candesartan, eprosartan, irbesartan, losartan, olmesartan, telmisartan, valsartan, sacubitril, sacubitril/valsartan, acebutolol, atenolol, betaxolol, bisoprolol/hydrochlorothiazide. bisoprolol, metoprolol, nadolol, propranolol, sotalol, carvedilol, labetalol hydrochloride, amlodipine, diltiazem, felodipine, nifedipine, nimodipine, nisoldipine, verapamil, atorvastatin. fluvastatin, lovastatin, pitavastatin, pravastatin, rosuvastatin, simvastatin, niacin, ezetimibe, ezetimibe/simvastatin, digoxin, acetazolamide, amiloride, bumetanide, chlorothiazide, chlorthalidone, furosemide, hydro-chlorothiazide, indapamide, metalozone, spironolactone, torsemide, isosorbide dinitrate, isosorbide mononitrate, hydralazine, nitroglycerin, minoxidil, or a combination thereof.

Heart Disease Biomarker

[0038] Embodiments described herein provide a number of advantages over the prior techniques discussed herein. For example, technologies of the present disclosure are non- invasive, require minimal patient discomfort, are quick to perform, and are relatively cost- effective. Accordingly, technologies described herein offer advantages over these prior techniques including, but not limited to providing a non-invasive in vitro diagnostic (IVD) test for heart disease, one or more specific in vitro biomarkers suitable for use in an IVD testing, alternatives to a single marker IVD test including more than one marker to effectively rule in or rule out candidates for the more costly and invasive procedures in the diagnosis of the disease. [0039] The present disclosure relates particularly to NfL as a biomarker for heart disease. In some embodiments. NfL as described herein is or includes NfL protein, nucleic acid sequences encoding NfL, characteristic fragments thereof, and/or variants thereof.

[0040] As provided herein, NfL includes gene products associated with NfL. For example, NfL can include a protein or nucleotide (e.g., RNA or mRNA). NfL also encompasses full-length proteins, as well as fragments (e.g., characteristic fragments) of NfL. In some embodiments. NfL includes a fragment having an amino acid sequence identical to a contiguous span of at least 10 amino acids, at least 20 amino acids, at least 30 amino acids, at least 40 amino acids, at least 50 amino acids, at least 60 amino acids, at least 70 amino acids, at least 80 amino acids, at least 90 amino acids, or at least 100 amino acids of an amino acid sequence provided in Table 1, although other numbers of amino acids can also be used. In some embodiments, NfL includes a fragment having at least 70%, at least 75%, at least 80%, at least 85%, at least 90%, at least 95%, at least 96%, at least 97%, at least 98%, or at least 99% identity to an amino acid sequence provided in Table 1, although other percentages can also be used. In some embodiments. NfL includes a nucleic acid fragment having a nucleic acid sequence identical to a contiguous span of at least 10 nucleic acids, at least 20 nucleic acids, at least 30 nucleic acids, at least 40 nucleic acids, at least 50 nucleic acids, at least 60 nucleic acids, at least 70 nucleic acids, at least 80 nucleic acids, at least 90 nucleic acids, or at least 100 nucleic acids of a nucleic acid sequence provided in Table 2. although other numbers of nucleic acids can also be used. In some embodiments, NfL includes a fragment having at least 70%, at least 75%, at least 80%, at least 85%, at least 90%, at least 95%, at least 96%, at least 97%, at least 98%, or at least 99% identity to a nucleic acid sequence provided in Table 2, although other percentages can also be used. Variant or alternative forms of NfL include, for example, polypeptides encoded by any splice-variants of transcripts encoding NfL.

[0041] Biomarkers contemplated herein also include truncated forms or polypeptide fragments of NfL as described herein. Truncated forms or polypeptide fragments of NfL can include N-terminally deleted or truncated forms and C-terminally deleted or truncated forms. Truncated forms or fragments of NfL can include fragments arising by any mechanism, such as, without limitation, by alternative translation, exo- and/or endo-proteolysis and/or degradation, for example, by physical, chemical and/or enzymatic proteolysis. Without limitation, a biomarker may include a truncated or fragment of NfL may include at least 10%, at least 15%, at least 20%, at least 25%, at least 30%, at least 35%, at least 40%, at least 45%, at least 50%. at least 55%. at least 60%, at least 65%, at least 70%, at least 75%, at least 80%, at least 85%, at least 90%, at least 95%, at least 96%, at least 97%, at least 8%, or at least 99% of the amino acid sequence of an NfL protein, although other percentages can also be used.

[0042] In some instances, a fragment is N-terminally and/or C-terminally truncated by 1-20 amino acids, such as, for example, by 1-15 amino acids, by 1-10 amino acids, or by 1-5 amino acids, compared to the corresponding mature, full-length NfL protein.

[0043] NfL protein of the present disclosure (e.g., an NfL protein or fragment(s) thereof) may also encompass modified forms of NfL such as bearing post-expression modifications including but not limited to, modifications such as phosphorylation, glycosylation, lipidation, methylation, selenocystine modification, cysteinylation, sulphonation, glutathionylation, acetylation, and/or oxidation of methionine to methionine sulphoxide, or methionine sulphone.

[0044] In some embodiments, NfL can be a nucleotide (also referred to herein as a nucleic acid or polynucleotide). In some embodiments, a nucleotide can be RNA or DNA (e.g., cDNA). In some cases, corresponding RNA or DNA may exhibit better discriminatory power in diagnosis than the full-length protein.

Neurofilament Light Chain (NfL)

[0045] Neurofilaments are cytoskeletal components of neurons that are particularly abundant in axons. The functions of neurofilaments include provision of structural support and maintenance of the size, shape, and caliber of axons. Neurofilaments include three subunits: neurofilament light chain (NfL), neurofilament medium chain, and neurofilament heavy chain. NfL levels increase in cerebrospinal fluid (CSF) and blood proportionally to the degree of axonal damage in a variety of neurological disorders, including inflammatory, neurodegenerative. traumatic and cerebrovascular diseases.

[0046] In some embodiments, NfL can be useful for detecting and diagnosing heart disease and is a heart disease biomarker. In some embodiments, detection of NfL, a characteristic fragment of NfL, and/or a variant of NfL is used in a method for assessing a subject’s risk of developing heart disease, diagnosing a subject with heart disease, or recommending a subject for additional cardiomyopathy testing. In some embodiments, NfL is detected in a sample with anti- NfL agents (e.g., anti- NfL antibody agents, probes, etc.) In some embodiments, detection of nucleotides that encode NfL, nucleotides that encode a characteristic fragment of NfL, and/or nucleotides that encode variants of NfL is used in a method for assessing a subject’s risk of developing heart disease, diagnosing a subject with heart disease, or recommending a subject for additional cardiomyopathy testing. In some embodiments, nucleotides that encode NfL are detected in a sample with anti-NfL nucleotide sequence agents (e.g., anti- NfL nucleotide sequence antibody agents, probes, complementary nucleic acids, etc.)

[0047] An exemplar}' amino acid sequence for NfL is included in Table 1 below.

Table 1: Exemplary NfL Amino Acid Sequence

[0048] An exemplar}' nucleic acid sequence for NfL is included in Table 2 below.

Table 2: Exemplary NfL Nucleic Acid Sequence

[0049] In some embodiments, additional biomarkers may be analyzed or assessed. In some embodiments, biomarkers can include imaging-based biomarkers (e.g., left ventricle septal wall thickness and/or ejection fraction) of a subject from which a sample was obtained. In some embodiments, biomarkers can include factors, including but not limited to demographic factors (e.g., one or more of age. weight, biological sex, ethnicity, BMI, medical history, risk factors, family history, or geographic location).

Exemplary Heart Disease Biomarker Combinations

[0050] As provided herein, NfL may be a full-length protein or a fragment thereof. In some embodiments, a fragment of NfL is a characteristic protein fragment. In some embodiments, NfL (e.g.. in a sample) can include a subset of full-length NfL proteins and a subset of characteristic protein fragments of NfL.

[0051] In some embodiments, NfL has a wild-type amino acid sequence. In some embodiments, NfL has a variant amino acid sequence (e.g., an amino acid sequence including one or more mutations). In some embodiments, a subset of NfL proteins have a wild-type amino acid sequence and a subset of NfL proteins have a variant amino acid sequence.

[0052] As provided herein, NfL may be a full-length nucleotide (e.g., DNA, cDNA, or RNA) that encodes NfL or a fragment thereof. In some embodiments, a fragment of NfL is a characteristic nucleotide fragment. In some embodiments, NfL (e.g., in a sample) can include a subset of full-length NfL nucleotides (e.g., DNA, cDNA, or RNA) and a subset of characteristic nucleotide fragments of NfL.

[0053] In some embodiments, NfL has a wild-type nucleic acid sequence. In some embodiments, NfL has a variant nucleic acid sequence, e.g., a nucleic acid sequence including one or more mutations. In some embodiments, a subset of NfL comprises a wild-type nucleic acid sequence that encodes NfL and a subset comprises a variant nucleic acid sequence that encodes NfL. Exemplary Methods

[0054] Exemplary methods of the disclosed technology allow for earlier identification of more patients who are at risk of heart disease, while minimizing the number of false negatives. In some embodiments, methods disclosed herein provide an advantage of an early screen for the presence of heart disease. In some embodiments, methods disclosed herein can assist in the detection or diagnosis of heart disease (e.g.. after genetic testing rules out heart disease). In some embodiments, methods disclosed herein reduce or eliminate the need for initiating screening for heart disease (e.g., with costly and complex process of an echocardiogram, CMR, and/or scintigraphy). In some embodiments, if methods disclosed herein result in detection of possible heart disease in a subject, the subject can undergo subsequent confirmatory testing (e.g.. echocardiogram, cardiac magnetic resonance imaging (CMR), scintigraphy, and/or cardiac biopsy).

[0055] In some embodiments, a method disclosed herein includes determining a subject’s risk of developing heart disease. In some embodiments, a method disclosed herein includes diagnosing a subject with heart disease, and the sample was obtained from the subject. In some embodiments, a method disclosed herein includes treating heart disease in a subject at risk of or suffering from heart disease. In some embodiments, a method disclosed herein includes determining a patient does not have or is not at risk of developing heart disease.

[0056] In some embodiments, a method disclosed herein includes selecting a subject to receive one or more doses of a heart medication, and the sample was obtained from the subject. In some embodiments, a method disclosed herein includes administering to the subject one or more doses a heart medication. In some embodiments, a heart medication comprises an anticoagulant, an antiplatelet agent, an ACE inhibitor, an angiotensin II receptor blockers, an angiotensin receptor-neprilysin inhibitor, a beta blocker, a calcium channel blocker, a cholesterol-lowering medication, a digitalis preparation, a diuretic, a vasodilator, or a combination thereof.

[0057] In some embodiments, a method disclosed herein includes selecting a subject for one or more cardiomyopathy tests, and the sample was obtained from the subject. In some embodiments, one or more cardiomyopathy tests include an echocardiogram, an advanced imaging method, or both. In some embodiments, an advanced imaging method includes cardiac magnetic resonance imaging (CMR), scintigraphy, or both. In some embodiments, scintigraphy includes use of a radioisotope conjugate such as 99m Tc-Pyrophosphate. In some embodiments, scintigraphy is performed using single photon emission computed tomography (SPECT).

[0058] The present disclosure provides diagnostic tests for heart disease characterized by detection of NfL according to the methods described and illustrated herein.

[0059] In some embodiments, methods of detecting, diagnosing, or identifying a risk of heart disease as disclosed herein have one or more of the following benefits: improved sensitivity for identifying heart disease, improved specificity for identifying heart disease, improved accuracy for identifying heart disease, reduced time to diagnosis for heart disease, and/or reduced cost of screening patients for heart disease.

[0060] In some embodiments. NfL can be used for an in-vitro diagnostic (IVD) or screening test for the condition of heart disease. In some embodiments, a diagnostic test as taught by the present disclosure detects whether NfL is present in a sample obtained from a subject. In some embodiments, a diagnostic test as disclosed herein can assist in the detection or diagnosis of heart disease in a subject.

[0061] In some embodiments, a diagnostic test as disclosed herein is adapted to an immunoassay platform. In some embodiments, such an immunoassay platform includes a semi-automated or automated immunoassay platform. In some embodiments, a diagnostic test as disclosed herein is adapted for semi-automated testing of one or more biomarkers.

[0062] In some embodiments, a diagnostic test as disclosed herein is an improved diagnostic for heart disease as compared to standard techniques in that the diagnostic test of the present disclosure includes one or more of the following benefits: improved sensitivity for identifying heart disease, improved specificity for identify ing heart disease, improved accuracy for identifying heart disease, reduced time to diagnosis for heart disease, and/or reduced cost of screening patients for heart disease.

[0063] In some embodiments, a diagnostic test as disclosed herein can be a plasmabased screening assay. In some embodiments, a diagnostic test is adapted for the Siemens Atellica® system or the Siemens Advia Centaur® system, by way of example only.

[0064] In some embodiments, methods provided herein include detecting a level of NfL present in a sample to obtain a biomarker profile and using the biomarker profile to compute a biomarker score. In some embodiments, methods provided herein include detecting a level of NfL in a sample to obtain a biomarker profile and using the biomarker profile and demographic factors to compute a biomarker score. In some embodiments, methods provided herein include detecting a level of NfL in a sample to obtain a biomarker profile and using the biomarker profile and imaging-based biomarkers to compute a biomarker score. In some embodiments, methods provided herein include detecting a level of NfL in a sample to obtain a biomarker profile, and using the biomarker profile, demographic factors, and imaging-based biomarkers to compute a Biomarker score.

[0065] In some embodiments, methods provided herein including receiving a level of NfL, demographic factors, and/or imaging-based biomarkers in a sample. In some embodiments, receiving includes electronically receiving. In some embodiments, demographic factors include one or more of age, weight, biological sex, ethnicity, BMI, medical history, risk factors, family history, or geographic location. In some embodiments, imaging-based biomarkers include left ventricle septal wall thickness and/or ejection fraction.

[0066] In some embodiments, methods described herein include using a biomarker score to select a subject for further cardiomyopathy tests. In some embodiments, methods described herein include using a biomarker score to select a subject to receive one or more doses of a heart medication. In some embodiments, methods described herein include using a biomarker score to identify a subject as having or being at risk of having heart disease.

[0067] In some embodiments, methods described herein include comparing a biomarker score to a reference biomarker score. In some embodiments, methods described herein include administering one or more doses of a heart medication to a subject. In some embodiments, methods described herein include performing one or more cardiomyopathy tests on a subject.

Detecting NfL and Obtaining a Biomarker Profile

[0068] Among other things, methods provided herein include assessment of a level of NfL detected in a sample. Exemplary methods for detecting a level of NfL are described herein. However, a level of NfL can also be provided, for example, in electronic form from, e.g., a laboratory that has detected a level of NfL in sample.

[0069] In some embodiments, the present disclosure provides technologies according to which NfL is detected, analyzed, and/or assessed in a sample. In some embodiments, NfL is in a sample obtained from a subject and a diagnosis or therapeutic decision is made based on such detection, analysis, and/or assessment.

[0070] In some embodiments, a level of NfL, as described herein, encompasses the presence of NfL, the absence of NfL, an amount of NfL, an absolute amount of NfL, a relative amount of NfL, or a concentration of NfL. [0071] Methods of detecting NfL include detecting biomarkers as proteins. Proteinbased methods of detecting biomarkers include, for example, mass spectrometry (MS), immunoassays (e.g., immunoprecipitation), Western blots, ELISAs, immunohistochemistry, immunocytochemistry, flow cytometry, and/or immuno-PCR.

[0072] In some embodiments, mass spectrometry' includes MS, MS/MS, MALDI-TOF, electrospray ionization mass spectrometry (ESIMS), ESI-MS/MS, ESI-MS/(MS)_n, matrix- assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF-MS). surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF- MS), tandem liquid chromatography -mass spectrometry (LC-MS/MS) mass spectrometry, desorption/ionization on silicon (DIOS), secondary' ion mass spectrometry' (SIMS), quadrupole time-of-flight (Q-TOF), atmospheric pressure chemical ionization mass spectrometry (APCI- MS), APCI-MS/MS, APCI-(MS), atmospheric pressure photoionization mass spectrometry (APPI-MS), APPI-MS/MS, and APPI-(MS)_n, quadrupole mass spectrometry, Fourier transform mass spectrometry (FTMS), and ion trap mass spectrometry. Often, the MS approach quantifies a fragment of a biomarker rather than the full-length protein. MS approaches, however, can be sufficient to determine the protein level of the biomarker to an accuracy sufficient for methods and/or assessments as disclosed.

[0073] In some embodiments, an immunoassay can be a chemiluminescent immunoassay, a high-throughput, and/or an automated immunoassay platform. For example, a high-throughput and/or automated immunoassay platform can be used to analyze at least 240 tests per hour or at least 440 tests per hour, although any other number of tests per hour can also be used in other examples.

[0074] In some embodiments, methods of detecting NfL in a sample include contacting a sample with one or more antibody agents directed to NfL. In some embodiments, such methods also include contacting the sample with a first set of one or more detection agents. In some embodiments, the antibody agents are labeled with the first set of one or more detection agents. In some embodiments, the first set of one or more detection agents includes one or more acridinium ester (AE) molecules.

[0075] AE molecules can be used to label proteins and nucleic acids. Acridimum- labeled proteins can be used for detection in immunoassays. Exposing AE to an alkaline H2O2 (hydrogen peroxide) produces chemiluminescence. Light is emitted at a wavelength maximum in the range of 430 to 480 nm, depending on the specific AE variant. Such light can be detected, for example, by high-efficiency photomultiplier tubes. The light emission is rapid and completes within 1 to 5 seconds. Diversity in AE forms contributes to better assay performance, including improved sensitivity and robustness. AE molecules can be used to label small molecules, large analytes, and antibodies.

[0076] Additional methods of detecting biomarkers (e.g., NfL) include methods for detecting biomarkers as nucleic acids. Nucleic acid-based methods of detecting NfL include performing nucleic acid amplification methods, such as polymerase chain reaction (PCR), reverse transcription polymerase chain reaction (RT-PCR), transcription-mediated amplification (TMA), ligase chain reaction (LCR), strand displacement amplification (SDA), and nucleic acid sequence-based amplification (NASBA). In some embodiments, a nucleic acid-based method of detecting biomarkers includes detecting hybridization between one or more nucleic acid probes and one or more nucleotides that encode NfL. In some embodiments, the nucleic acid probes are each complementary to at least a portion of one of the one or more nucleotides that encode NfL. In some embodiments, the nucleotides that encode NfL include DNA (e.g., cDNA). In some embodiments, the nucleotides that encode NfL include RNA (e.g., mRNA).

Exemplary Samples

[0077] In some embodiments, a sample as disclosed herein is a biological sample. In some embodiments, a biological sample is a blood sample (e.g., drawn from an artery or vein of a subject). A blood sample can be a whole blood sample, a plasma sample, or a serum sample. In some embodiments, a biological sample includes cardiac tissue.

[0078] In some embodiments, a sample is obtained from a subject (e.g., via a biopsy). In some embodiments, a subject from which a sample was obtained is being assessed for heart disease. In some embodiments, a subject from which a sample was obtained is suffering from or is at risk of developing heart disease.

Exemplary Subjects

[0079] In some embodiments, a subject as disclosed herein is a mammal (e.g., a human). In some embodiments, a subject as disclosed herein is a biological male. In some embodiments, a subject as disclosed herein is a biological female. In some embodiments, a subject as disclosed herein is overweight. In some embodiments, a subject has a body mass index (BMI) of 25 or more. In some embodiments, a subject has a body mass index (BMI) of 30 or more, although another threshold BMI can also be used. In some embodiments, a subject is at least 50 years old, at least 55 years old, at least 60 years old, or at least 65 years old, although other age thresholds can also be used. Other types of subjects, subject characteristics, BMIs, and/or ages can also be used with the disclosed technology.

Exemplary Methods Utilizing Thresholds

[0080] In some methods disclosed herein, a level of NIL can be compared to a threshold. In some embodiments, methods disclosed herein include a comparison of a level of NfL to respective thresholds. In some embodiments, methods disclosed herein include a comparison of a level of NfL to reference thresholds.

[0081] A reference threshold may be a threshold from a subject known or independently verified to have good cardiac health, or from a subject known or independently verified to have poor cardiac health, such as is the case for a subject having heart disease. Alternately or in combination a subject’s biomarker profile can be compared to a reference threshold determined from a plurality⁷ of subjects of known status (e.g., healthy, not diagnosed with heart disease, or diagnosed with heart disease). In some embodiments, a reference threshold is an average of known level of NfL from a plurality of subjects or alternately is a range defined by the range of levels of NfL observed in reference subjects.

[0082] In more complex assessment approaches, a subject’s biomarker level can be compared to a reference biomarker level constructed from a larger number of subjects of a known status (e.g.. healthy, not diagnosed with heart disease, or diagnosed with heart disease), such as at least 10, at least 50, at least 100, at least 500, at least 1000 or more subjects, although another threshold number of subjects can also be used. Reference subjects can be evenly distributed in status between (1) healthy/not diagnosed with heart disease and (2) diagnosed with heart disease in some examples. Assessment includes in some cases iterative or simultaneous comparison of a subject’s biomarker (e.g., NfL) level to a plurality of profiles of known status.

[0083] A plurality⁷ of known reference biomarker profiles (e.g., detected levels of NfL in a reference sample, demographic factors, and/or imaging-based biomarkers) can also be used to train a computational assessment algorithm (e.g., a machine learning model), such that a single comparison between a subject’s biomarker profile and a reference biomarker profile provides an outcome that integrates or aggregates information from a large number of subjects of known health status (e.g., healthy, not diagnosed with heart disease, or diagnosed with heart disease), such as at least 10, at least 50, at least 100, at least 500, at least 1000 or more individuals, although another number of individuals can also be used. Generation of such a reference biomarker profile can facilitate faster assessment of a subject's risk of heart disease and/or assessment using less computational power.

[0084] A reference biomarker profile can be generated from a plurality of reference biomarker profiles through any of a number of computational approaches. Machine learning models in accordance with the present technology can be constructed using any number of statistical programming languages such as R, scripting languages such as Python and associated machine learning packages, data mining software such as Weka or Java, Mathematica, Matlab™ or SAS, for example.

[0085] A subject’s biomarker profile can be compared to a reference biomarker profile (e.g., generated as explained above), and an output assessment can be generated. A number of output assessments are consistent with the disclosure herein. Output assessments include a single assessment, optionally narrowed by a sensitivity⁷, specificity' or sensitivity and specificity parameter, indicating a health status assessment (e.g., probability subject has heart disease, subject is not at risk of heart disease, subject is at risk of heart disease, subject has heart disease). Alternately or in combination, additional parameters are provided, such as the subject’s demographic factors (e.g., one or more of age, weight, biological sex, ethnicity, BMI, medical history', risk factors, family history', and geographic location) and/or the subject’s imaging-based biomarkers (e.g., left ventricle septal wall thickness and/or ejection fraction).

[0086] In some embodiments, methods disclosed herein further include diagnosing a subject with heart disease when the level of NfL that is detected is above a threshold value. In some embodiments, methods disclosed herein include diagnosing a subject with heart disease when the level ofNfL that is detected is at least 1.3, at least 1.4, at least 1.5, at least 1.6, at least 1.7, at least 1.8, or at least 1.9-fold greater than a threshold value, although other factors of the threshold value can also be used.

[0087] In some embodiments, methods disclosed herein include recommending a subject for one or more cardiomyopathy tests when the level of NfL is above threshold value. In some such methods, the subject is recommended for one or more cardiomyopathy tests when the level of NfL that is detected is at least 1.3. at least 1.4, at least 1.5, at least 1.6, at least 1.7. at least 1.8, or at least 1.9-fold greater than a threshold value, although other factors of the threshold value can also be used.

[0088] As explained above, in some embodiments, methods of detecting NfL in a sample include contacting a sample with one or more antibody agents directed to NfL. In some embodiments, such methods also include contacting the sample with a first set of one or more detection agents. In some embodiments, the antibody agents are labeled with the first set of one or more detection agents. In some embodiments, the first set of one or more detection agents include one or more acridinium ester (AE) molecules.

[0089] AE molecules can be used to label proteins and nucleic acids. Acridinium- labeled proteins can be used for detection in immunoassays. Exposing AE to an alkaline H2O2 (hydrogen peroxide) produces chemiluminescence. Light is emitted at a wavelength maximum in the range of 430 to 480 nm, depending on the specific AE variant. Such light can be detected, for example, by high-efficiency photomultiplier tubes.

[0090] In some embodiments, detecting binding between NfL and one or more antibody agents directed against NfL includes determining absorbance values or emission values for the first set of one or more detection agents. For example, the absorbance values are indicative of the level of binding (e.g., higher absorbance is indicative of more binding). In some embodiments, the absorbance values or emission values for the first set of one or more detection agents are above a threshold value. In some embodiments, the absorbance values or emission values for the first set of one or more detection agents are at least 1.3, at least 1.4, at least 1.5, at least 1.6, at least 1.7, at least 1.8, or at least 1.9-fold greater than a threshold value, although other factors of the threshold value can also be used. In some embodiments, the threshold value is an average of absorbance values or emission values determined for a second set of one or more detection agents that label two or more control samples. In some such embodiments, the second set of one or more detection agents is similar to or the same as the first set of one or more detection agents.

[0091] In some embodiments, the methods disclosed herein further include diagnosing the subject with heart disease when the level of NfL that is detected is above a threshold value. In some embodiments, the method includes diagnosing a subject with heart disease when the level of NfL that is detected is at least 1.3, at least 1.4, at least 1.5, at least 1.6, at least 1.7, at least 1.8, or at least 1.9-fold greater than a threshold value, although other factors of the threshold value can also be used.

[0092] In some embodiments, the methods disclosed herein include diagnosing the subject with heart disease when the absorbance values or emission values for the first set of one or more detection agents is above a threshold value. In some embodiments, the method includes diagnosing a subject with heart disease when the absorbance values or emission values for the first set of one or more detection agents is at least 1.3, at least 1.4, at least 1.5, at least 1.6, at least 1.7, at least 1.8, or at least 1.9-fold greater than a threshold value, although other factors of the threshold value can also be used. In some embodiments, the threshold value is an average of absorbance values or emission values determined for a second set of one or more detection agents that label two or more control samples. In some such embodiments, the second set of one or more detection agents is similar to or the same as the first set of one or more detection agents.

[0093] In some embodiments, methods disclosed herein include recommending a subject for one or more cardiomyopathy tests when the level of NfL is above threshold value. In some such methods, the subject is recommended for one or more cardiomyopathy tests if the level of NfL that is detected is at least 1.3, at least 1.4, at least 1.5, at least 1.6, at least 1.7, at least 1.8, or at least 1.9-fold greater than a threshold value, although other factors of the threshold value can also be used.

[0094] In some embodiments, methods disclosed herein include recommending the subject for one or more cardiomyopathy tests when the absorbance values or emission values for the first set of one or more detection agents is above a threshold value. In some such methods, the subject is recommended for one or more cardiomyopathy tests when the absorbance values or emission values for the first set of one or more detection agents is at least 1.3, at least 1.4, at least 1.5, at least 1.6, at least 1.7, at least 1.8, or at least 1.9-fold greater than a threshold value, although other factors of the threshold value can also be used.

[0095] Cardiomyopathy tests that may be used according to the methods of the present disclosure include echocardiogram or advanced imaging methods, for example. In some embodiments, the advanced imaging methods include cardiac magnetic resonance imaging (CMR) or scintigraphy (e.g., using a radioisotope conjugate such as 99m Tc-Pyrophosphate and/or using single photon emission computed tomography (SPECT)).

[0096] In any of the embodiments described and illustrated herein, a threshold value may be an average of values detected for two or more control samples. In some such embodiments, the values detected for the two or more control samples represent control levels for NfL. In some embodiments, the control samples include recombinant NfL. In some embodiments, the two or more control samples are each a sample obtained from a subject who does not have heart disease. In some embodiments, the threshold value is a value reported in a standard table. Exemplary Methods Utilizing Biomarker Profiles

[0097] An algorithm-based assay and associated information provided by the practice of any of the methods described herein can facilitate improved treatment and decision making for subjects. For example, methods described herein can enable a physician or caretaker to identify patients who have a low likelihood of having heart disease and therefore would not need treatment, would not need additional cardiac tests, or would not need increased monitoring for heart disease, or who have a high likelihood of having heart disease, would need treatment, would need additional cardiac tests, or would need increased monitoring for heart disease, for example.

[0098] A biomarker score can be determined by the application of a specific algorithm in some cases. In some embodiments, a biomarker score is quantitative. An algorithm used to calculate a biomarker score in some methods disclosed herein may group the expression level values of NfL or groups of biomarkers including NfL. The formation of a particular group of biomarkers, in addition, can facilitate a mathematical weighting of the contribution of various expression levels of biomarker or biomarker subsets (e.g., classifier) to the quantitative score. [0099] Some methods described herein, as well as kits and systems provided herein, can utilize an algorithm-based diagnostic assay for predicting if a subject from which the sample was obtained is at risk of or suffering from heart disease, selecting a subject from which the sample was obtained for one or more cardiomyopathy tests, and/or selecting a subject from which the sample was obtained to receive one or more doses of a heart medication.

[0100] Levels of NfL, and optionally one or more demographic factors (e g., one or more of age, weight, biological sex, ethnicity, BMI, medical history, risk factors, family history, and geographic location) and/or imaging-based biomarkers (e.g., left ventricle septal wall thickness and/or ejection fraction) can be used alone or arranged into functional subsets to calculate a biomarker score that is used to predict if a subject from which the sample was obtained is at risk of or suffering from heart disease, select a subject from which the sample was obtained for one or more cardiomyopathy tests, and/or select a subject from which the sample was obtained to receive one or more doses of a heart medication.

[0101] Some methods disclosed herein include using a biomarker profile to compute a biomarker score. In some embodiments, using a biomarker profile to compute a biomarker score includes applying an algorithm to the biomarker profile to compute a biomarker score. In some embodiments, an algorithm is derived from a decision tree methodology, a neural boosted methodology, a bootstrap forest methodology, a boosted tree methodology, a K nearest neighbors methodology, a generalized regression forward selection methodology, a generalized regression pruned forward selection methodology, a fit stepwise methodology, a generalized regression lasso methodology, a generalized regression elastic net methodology, a generalized regression ridge methodology, a nominal logistic methodology, a support vector machines methodology, a discriminant methodology, a naive Bayes methodology', or a combination thereof. In some embodiments, an algorithm is or is derived from a decision tree methodology, a neural boosted methodology, a bootstrap forest methodology, a boosted tree methodology, a generalized regression lasso methodology, a generalized regression elastic net methodology, a generalized regression ridge methodology⁷, a nominal logistic methodology, a support vector machines methodology, a discriminant methodology, or a combination thereof. In some embodiments, an algorithm is or is derived from a decision tree methodology, a neural boosted methodology, a bootstrap forest methodology, a boosted tree methodology, a support vector machines methodology, or a combination thereof.

[0102] A machine learning model may use data corresponding to one or more (e.g., two or more) demographic factors and a biomarker profile that includes data corresponding to a level of NIL in a sample from a subject. In some embodiments, the one or more demographic factors include one or more of age, weight, biological sex, ethnicity, BMI, medical history-, risk factors, family history', and geographic location. In some embodiments, the one or more demographic factors include age, biological sex, or both age and biological sex. In some embodiments, the one or more demographic factors is two demographic factors. In some embodiments, the two demographic factors are age and biological sex.

[0103] In some embodiments, a method includes providing data corresponding to one or more demographic factors of a subject and a corresponding biomarker profile as input to a machine learning model. In some embodiments, the one or more demographic factors include biological sex, age, or both biological sex and age. The corresponding biomarker profile includes data for a level of NfL in a sample of a subject characterized by the demographic factor(s). Performance (e.g., predictive power, sensitivity and/or selectivity', and/or classification accuracy) of a machine learning model may be improved by using a machine learning model that considers a combination of NfL with one or more (e.g., two or more) demographic factors, as compared to a machine learning model that does not consider any demographic factor.

[0104] Additional algorithms can be used in methods provided herein, and the algorithms provided herein are merely exemplary of the types of algorithms that can be used to generate a biomarker score. Exemplary algorithms have been described by Duda, 2001, Pattern Classification, John Wiley & Sons, Inc.. New York. pp. 396-408 and pp. 411-412 and Hastie et al., 2001, The Elements of Statistical Learning, Springer-Verlag, New York, Chapter 9, each of which is hereby incorporated by reference herein in its entirety, for example. Moreover, as indicated above, combinations of algorithms can be used in methods provided herein. For example, a boosted tree methodology can be a combination of a decision tree methodology and a boosting methodology. Further combinations are possible and are contemplated for use in methods provided herein. Exemplary algorithms that can be used in the methods provided herein are further described below.

Decision Tree

[0105] One methodology that can be used to calculate a biomarker score from a Biomarker profile is a decision tree. A decision tree can be constructed using a training population and specific data analysis algorithms. Decision trees are described generally byDuda, 2001, Pattern Classification, John Wiley & Sons, Inc.. New York. pp. 395-396. Treebased methods partition the feature space into a set of rectangles, and then fit a model (like a constant) in each one.

[0106] A training population data can include biomarker profiles (e.g., including a level of NIL in a sample) across a training set population. One specific algorithm that can be used to construct a decision tree is a classification and regression tree (CART). Other specific decision tree algorithms include, but are not limited to, ID3, C4.5, MART, and Random Forests. CART, ID3, and C4.5 are described in Duda, 2001, Pattern Classification, John Wiley & Sons, Inc., New York. pp. 396-408 and pp. 411-412. CART, MART, and C4.5 are described in Hastie et al., 2001, The Elements of Statistical Learning. Springer-Verlag, New York, Chapter 9. Random Forests are described in Breiman, 1999, "Random Forests — Random Features,” Technical Report 567, Statistics Department, U.C. Berkeley, September 1999, which is also hereby incorporated by reference herein in its entirety.

[0107] An aim of a decision tree is to induce a classifier (i.e., a tree) from real-world example data. This tree can be used to classify unseen examples that have not been used to derive the decision tree. As such, a decision tree can be derived from training data. Exemplary training data contains data for a plurality of subjects (e.g., a training population). A biomarker profile can be provided and/or used for each respective subj ect. In some embodiments, training data includes biomarker profiles for the training population. Exemplary Decision Tree

[0108] The following algorithm describes an exemplary derivation of a decision tree: Create a root node

If all Examples have the same Class value, give the root this label

Else if Features is empty label the root according to the most common value

Else begin

Calculate the information gain for each Feature

Select the Feature A with highest information gain and make this the root Feature

For each possible value, v, of this Feature

Add a new branch below the root, corresponding to A = v

Let Examples(v) be those examples with A = v

If Examples(v) is empty, make the new branch a leaf node labeled with the most common value among Examples

Else let the new branch be the tree created by

Tree(Examples(v), Class, Features - {A}) end

[0109] In univariate decision trees, each split is based on a feature value (e.g., a level) for a corresponding biomarker. Further, multivariate decision trees can be implemented in a method described herein. In some embodiments, a split is based on a feature value corresponding to a demographic factor, either alone or in combination with a feature value for a corresponding biomarker. For example, a split may be based on a combination of feature values corresponding to sex and level(s) of one or more biomarkers, to age and level(s) of one or more biomarkers, or to both age and sex and level(s) of one or more biomarkers. Multivariate decision trees are described in Duda, 2001, Pattern Classification, John Wiley & Sons, Inc., New York, pp. 408-409. In such multivariate decision trees, some or all of the decisions include a linear combination of feature values (e.g., levels) for a plurality of biomarkers of a profile. Such a linear combination can be trained using known techniques such as gradient descent on a classification or by the use of a sum-squared-error criterion.

[0110] As an illustrative example, the following equation is used: 0.05(Xl) + 0.2(X2) < 500. In this example, XI and X2 refer to two different features (e.g., levels) for two different biomarkers (e.g., including NIL). To apply the methodology', the values of features XI and X2 (e.g., as part of a biomarker profile) are obtained from the measurements obtained from an unclassified subject. These values are then inserted into the equation. If a value of less than 500 is computed, then a first branch in the decision tree is taken. Otherwise, a second branch in the decision tree is taken.

[OHl] Biomarker profiles may be used to train a machine learning model. Biomarker profiles may be from different subjects, a same subject at different times, or a combination thereof. Biomarker profiles may be associated with (e.g., labelled with) corresponding data indicative of health status. For example, a biomarker profile for a subject used as training data may be labelled with data indicative of health status for the subject. Such corresponding data may be a probability or a score (e.g., a biomarker score). The health status may be a probability that a subject has heart disease, whether a subject is at risk of heart disease, or whether a subj ect has heart disease (e.g., is healthy, not diagnosed with heart disease, or diagnosed with heart disease). Health status may be determined manually, for example by a physician. Labelling biomarker profiles with corresponding data indicative of health status may be performed manually (e.g., by the physician who determines health status) or automatically based on stored correlations.

[0112] Demographic factor data may be used in combination with biomarker profiles to train a machine learning model. For example, biomarker profiles and data for one or more demographic factors for each of a set of subjects may be used to train a machine learning model. The set may be, for example, at least 10 subjects, at least 20 subjects, at least 50 subjects, at least 100 subjects, at least 200 subjects, at least 300 subjects, at least 500 subjects, at least 1.000 subjects, at least 1 ,500 subjects, at least 2,000 subjects, at least 5,000 subjects, or at least 10,000 subjects, although another number of subjects can also be used in other examples. In some embodiments, a combination of one or more demographic factors of age, sex, or both age and sex and a biomarker profile for each of a set of subjects is used for training a machine learning model. The biomarker profile may include data corresponding to the level of NfL.

[0113] In some embodiments, training a machine learning model includes determining one or more feature values. Each feature value may correspond to a biomarker (e.g., NfL). One or more feature values may be determined based on biomarker profiles and/or a linear combination thereof. One or more feature values may correspond to a level of NfL. Training a machine learning model may include determining one or more decision rules based on biomarker profiles used as training data. The one or more decision rules may be based on one or more demographic factors corresponding to subject(s) associated with the biomarker profiles. The one or more decision rules may be based one or more feature values (e.g., determined during training). The one or more decision rules may be used in one or more decision trees.

[0114] Bagging, boosting, and additive trees can be combined with a decision methodology to improve weak decision rules. These techniques are designed for decision trees, such as the decision trees described herein. In some embodiments, a machine learning model may include at least 25 decision trees, at least 50 decision trees, or at least 100 decision trees, although any number of decision trees can be used. In addition, such techniques can also be useful in decision rules developed using other types of data analysis algorithms such as linear discriminant analysis.

[0115] In bagging, a training set is sampled, generating random independent bootstrap replicates, constructing a decision rule on each of these, and aggregating them by a simple majority vote in the final decision rule. See e.g., Breiman, 1996, Machine Learning 24, 123- 140; and Efron & Tibshirani, An Introduction to Boostrap, Chapman & Hall, New York, 1993, which is hereby incorporated herein by reference in its entirety.

[0116] In boosting, decision rules are constructed on weighted versions of the training set. which are dependent on previous classification results. Initially, all features under consideration have equal weights, and the first decision rule is constructed on this data set. Then, weights are changed according to the performance of the decision rule. Erroneously classified features get larger weights, and the next decision rule is boosted on the reweighted training set. In this way, a sequence of training sets and decision rules is obtained, which is then combined by majority voting or by weighted majority voting in the final decision rule. See e.g., Freund & Schapire, “Experiments with a new boosting algorithm,” Proceedings 13th International Conference on Machine Learning, 1996, 148-156, which is hereby incorporated herein by reference in its entirety’.

[0117] Measurement data used in the technology' disclosed herein are optionally normalized. Normalization refers to a process to correct differences in the amount of genes or protein levels assayed and variability’ in the quality⁷ of the template used, to remove unwanted sources of systematic variation measurements involved in the processing and detection of genes or protein expression, for example. Other sources of systematic variation are attributable to laboratory processing conditions.

[0118] In some instances, normalization methods are used for the normalization of laboratory⁷ processing conditions. Non-limiting examples of normalization of laboratory processing that may be used with this technology include but are not limited to: accounting for systematic differences between the instruments, reagents, and/or equipment used during the data generation process, and/or the date and/or time or lapse of time in the data collection.

[0119] Assays can provide for normalization by incorporating the expression of certain normalizing standard genes or proteins, which do not significantly differ in expression levels under the relevant conditions, and are known to have a stabilized and consistent expression level in that particular sample type. Suitable normalization genes and proteins that can be used with the present disclosure include housekeeping genes. See e.g., E. Eisenberg, et al.. Trends in Genetics 19(7): 362-365 (2003), which is hereby incorporated herein by reference in its entirety. In some examples, the normalizing biomarkers (genes and/or proteins), also referred to as reference genes, are known not to exhibit meaningfully different expression levels in subjects with heart disease as compared to control subjects without heart disease. In some examples, it may be useful to add a stable isotope labeled standard, which can be used and represent an entity with known properties for use in data normalization. In other examples, a standard, fixed sample can be measured with each analytical batch to account for instrument and day-to-day measurement variability.

[0120] Machine learning models for sub-selecting discriminating biomarkers and optionally subject characteristics, and for building classification models, are used in some methods and systems herein to determine clinical outcome scores. Examples of such algorithms are described above. These algorithms can aid in selection of important biomarker features and transform the underlying measurements into a score or probability relating to. for example, clinical outcome, disease risk, disease likelihood, presence or absence of disease, treatment response, and/or classification of disease status.

[0121] A machine learning model may output a biomarker score. A machine learning model may determine if a subject is at risk of or is suffering from heart disease. In some embodiments, an output of a machine learning model is a determination of whether a subject is at risk of or is suffering from heart disease. A machine learning model may be a classifier for heart disease. In some embodiments, a machine learning model can be used to classify whether a subject has heart disease, for example based on a biomarker profile for the subject. In some embodiments, the classifier or the classifying has a sensitivity and a specificity each of more than 80% (e g., at least one or both of more than 90%).

[0122] A biomarker score can be determined by comparing a subject-specific biomarker profile to a reference biomarker profile. A reference biomarker profile can be representative of a known diagnosis. For example, a biomarker profile can represent a positive diagnosis of heart disease. As another example, a reference biomarker profile can represent a negative diagnosis of heart disease. In some examples, an increase in a score indicates an increased likelihood of one or more of: a poor clinical outcome, good clinical outcome, high risk of disease, low risk of disease, complete response, partial response, stable disease, nonresponse, or recommended treatments for disease management. In some examples, a decrease in the quantitative score indicates an increased likelihood of one or more of: a poor clinical outcome, good clinical outcome, high risk of disease, low risk of disease, complete response, partial response, stable disease, non-response, or recommended treatments for disease management.

[0123] A similar biomarker profile from a subject to a reference biomarker profile often indicates an increased likelihood of one or more of: a poor clinical outcome, good clinical outcome, high risk of disease, low risk of disease, complete response, partial response, stable disease, non-response, or recommended treatments for disease management. In some applications, a dissimilar biomarker profile between a subject and a reference indicates an increased likelihood of one or more of: a poor clinical outcome, good clinical outcome, high risk of disease, low risk of disease, complete response, partial response, stable disease, nonresponse, or recommended treatments for disease management.

[0124] Results can be provided to a subject, a health care professional, or other professional. Results are optionally accompanied by a heath recommendation, such as a recommendation to confirm or independently assess heart disease risk, for example using one or more cardiomyopathy tests.

[0125] A recommendation optionally includes information relevant to a treatment regimen. Efficacy of a regimen can be assessed in some cases by comparison of a subject’s biomarker profile at a first time point, optionally prior to a treatment and a later second time point, optionally subsequent to a treatment instance. Biomarker profiles can be compared to one another, each to a reference, or otherwise assessed to determine whether a treatment regimen demonstrates efficacy such that it should be continued, increased, replaced with an alternate regimen, or discontinued because of its success in addressing heart disease or associated signs and symptoms. Some assessments rely upon comparison of a subject’s biomarker profile at multiple time points, such as at least one time point prior to a treatment and at least one time point following a treatment. Biomarker profiles can be compared one to another or to at least one reference biomarker panel level or both to one another and to at least one reference biomarker panel level. Treatment for Amyloid Transthyretin Cardiomyopathy

[0126] In some embodiments, the present disclosure includes a method for selecting a patient for treatment with a heart medication including the step of detecting a level of NfL in a sample obtained from the subject.

[0127] In some embodiments, the present disclosure includes a method of treating heart disease in subject at risk of or suffering from heart disease, the method including administering to the subject a therapeutically effective amount of a heart medication. In some embodiments, the subject expresses a level of NfL above a threshold value. In some embodiments, the method further includes determining that the subject expresses a level of NfL above a threshold value. In some embodiments, prior to administration, the subject has been determined to express a level of NfL above a threshold value. In some embodiments, a heart medication is an angiotensin-converting enzyme (ACE) inhibitor, an angiotensin II receptor blocker, an angiotensin receptor-neprilysin inhibitor, an anticoagulant or blood thinner, an antiplatelet agent, aspirin, a beta blocker, a calcium channel blocker, a cholesterylester transfer protein (CETP) inhibitor, a cholesterol absorption inhibitor, a digitalis preparation (e.g.. a digitalis glycosides), a diuretic, a dual antiplatelet therapy, a fibrate, niacin, a statin, a vasodilator, or a combination thereof. For example, a heart medication may be apixaban, dabigatran, edoxaban, heparin, rivaroxaban, warfarin, aspirin, clopidogrel, dipyridamole, prasugrel, ticagrelor, benazepril, captopril, enalapril, fosinopril. moexipril, perindopril, quinapril, ramipril, trandolapril, azilsartan, candesartan, eprosartan, irbesartan, losartan, olmesartan, telmisartan, valsartan, sacubitril, sacubitril/valsartan, acebutolol, atenolol, betaxolol, bisoprolol/hydrochlorothiazide, bisoprolol, metoprolol, nadolol, propranolol, sotalol, carvedilol, labetalol hydrochloride, amlodipine, diltiazem, felodipine, nifedipine, nimodipine, nisoldipine, verapamil, atorvastatin, fluvastatin, lovastatin, pitavastatin, pravastatin, rosuvastatin, simvastatin, niacin, ezetimibe, ezetimibe/simvastatin, digoxin, acetazolamide, amiloride, bumetanide, chlorothiazide, chlorthalidone, furosemide, hydro-chlorothiazide, indapamide, metalozone, spironolactone, torsemide, isosorbide dinitrate, isosorbide mononitrate, hydralazine, nitroglycerin, minoxidil, or a combination thereof.

[0128] In some embodiments, the biomarkers disclosed herein can be used for screening patients for effective therapies for heart disease. In some embodiments, a therapy for heart disease is an ACE inhibitor, an angiotensin II receptor blocker, an angiotensin receptor-neprilysin inhibitor, an anticoagulant or blood thinner, an antiplatelet agent, aspirin, a beta blocker, a calcium channel blocker, a CETP inhibitor, a cholesterol absorption inhibitor, a digitalis preparation (e.g.. a digitalis glycosides), a diuretic, a dual antiplatelet therapy, a fibrate, niacin, a statin, a vasodilator, or a combination thereof. For example, a therapy may be apixaban, dabigatran, edoxaban, heparin, rivaroxaban, warfarin, aspirin, clopidogrel, dipyridamole, prasugrel, ticagrelor, benazepril, captopril, enalapril, fosinopril, moexipril, perindopril, quinapril, ramipril, trandolapril, azilsartan, candesartan, eprosartan, irbesartan, losartan, olmesartan, telmisartan, valsartan, sacubitriL sacubitril/valsartan. acebutoloL atenolol, betaxolol, bisoprolol/hydrochlorothiazide, bisoprolol, metoprolol, nadolol, propranolol, sotalol, carvedilol, labetalol hydrochloride, amlodipine, diltiazem, felodipine, nifedipine, nimodipine, nisoldipine, verapamil, atorvastatin, fluvastatin, lovastatin, pitavastatin, pravastatin, rosuvastatin. simvastatin, niacin, ezetimibe, ezetimibe/simvastatin, digoxin, acetazolamide, amiloride, bumetanide, chlorothiazide, chlorthalidone, furosemide, hydro-chlorothiazide, indapamide, metalozone, spironolactone, torsemide, isosorbide dinitrate, isosorbide mononitrate, hydralazine, nitroglycerin, minoxidil, or a combination thereof.

Exemplary Kits

[0129] Also provided by the present disclosure are kits including one or more anti-NfL agents and instructions for use (e.g., treatment, prophylactic, or diagnostic use). In some embodiments, the kit is used for an in vitro diagnostic assay to diagnose heart disease. In some embodiments, the kits of the disclosure further include a heart medication.

[0130] In some embodiments, the one or more anti-NfL agents include antibody agents. In some embodiments, one or more of the antibody agents are labeled with a detectable moiety. In some embodiments, the kit includes a detection agent (e.g., one or more acridinium ester molecules). In some embodiments, one or more of the antibody agents are labeled with one or more of the acridinium ester molecules. In some embodiments, the kit further includes one or more secondary antibody agents that bind to one or more of the anti-NfL antibody agents.

[0131] In some embodiments, the one or more anti-NfL agents include nucleic acid probes. In some embodiments, at least a portion of each nucleic acid probe hybridizes to one or more portions of a nucleotide that encodes NfL. Nucleotides that encode NfL can be DNA (e.g., cDNA) or RNA (e.g., mRNA). In some embodiments, the nucleic acid probes are labeled with one or more detection agents (e.g., wherein the detection agents indicate presence of nucleotides that encode NfL). [0132] In some embodiments, a kit includes one or more control samples. In some embodiments, the control samples include one or more standards. In some embodiments, a standard includes recombinant NfL. In some embodiments, a standard includes synthetic NfL nucleic acids.

[0133] A kit in accordance with the disclosed technology also can include other ingredients, such as a solvent or buffer, a stabilizer or a preservative, and/or an agent for treating a condition or disorder. Alternatively, other ingredients can be included in a kit, but in different compositions or containers than the anti -NfL agents. In such embodiments, a kit can include instructions for admixing the anti -NfL agents and the other ingredients or for using the anti-NfL together with the other ingredients. In some embodiments, kits for use in accordance with the present disclosure may include a reference or control sample(s), instructions for processing samples, performing tests on samples, instructions for interpreting the results, and/or buffers and/or other reagents necessary for performing tests.

[0134] Single biomarkers can be helpful for detecting and/or diagnosing heart disease as explained herein. The present disclosure further provides the insight that NfL is especially useful for detecting and/or diagnosing heart disease. Thus, methods, compositions, and kits described herein can be used for assays to assess the risk of heart disease, assess whether a subject should undergo further cardiac tests, and/or diagnose heart disease based on detection or measurement of NfL in a sample (e g., a biological sample obtained from a subject).

[0135] Methods and kits provided herein can detect heart disease in a sample with a sensitivity and a specificity that renders the outcome of the test sufficiently reliable to be medically actionable. Methods and kits described herein for detection and/or diagnosis of heart disease in a subject detects heart disease with a sensitivity greater than 75%, greater than 80%, greater than 85%, greater than 90%, greater than 95%, greater than 96%. greater than 97%, greater than 98%, greater than 99%, or about 100%. In some embodiments, methods and kits provided herein can detect heart disease with a sensitivity that is between about 70%-100%, between about 80%-100%, or between about 90-100%. In some embodiments, methods and kits provided herein can detect heart disease with a specificity greater than 70%, greater than 75%. greater than 80%, greater than 85%, greater than 90%, greater than 95%. greater than 96%, greater than 97%, greater than 98%, greater than 99%, or about 100%. In some embodiments, methods and kits provided herein can detect heart disease with a specificity that is between about 50%-100%, between about 60%-100%, between about 70%-100%, between about 80%-100%, or between about 90-100%. In some embodiments, methods and kits provided herein can detect heart disease with a sensitivity and a specificity that is 50% or greater, 60% or greater, 70% or greater. 75% or greater, 80% or greater, 85% or greater. 90% or greater. In some embodiments, methods and kits provided herein can detect heart disease with a sensitivity and a specificity that is between about 50%-100%, between about 60%-100%, between about 70%-100%, between about 80%-100%, or between about 90-100%.

Exemplary Compositions

[0136] Also provided herein are compositions. In some embodiments, a composition includes NfL and one or more anti-NfL agents. In some embodiments, one or more anti-NfL agents in a composition provided herein include antibody agents. In some embodiments, one or more of the antibody agents are labeled with a detectable moiety. In some embodiments, a composition includes a detection agent (e.g., one or more acridinium ester molecules). In some embodiments, one or more of the antibody agents are labeled with one or more of the acridinium ester molecules. In some embodiments, a composition includes one or more secondary antibody agents that bind to one or more of the anti-NfL antibody agents.

[0137] In some embodiments, one or more anti-NfL agents in a composition provided herein include nucleic acid probes. In some embodiments, at least a portion of each nucleic acid probe hybridizes to one or more portions of a nucleotide that encodes NfL. Nucleotides that encode NfL can be DNA (e.g., cDNA) or RNA (e.g., mRNA). In some embodiments, the nucleic acid probes are labeled with one or more detection agents (e.g., wherein the detection agents indicate presence of nucleotides that encode NfL).

[0138] In some embodiments, a composition includes one or more control samples. In some embodiments, the control samples include one or more standards. In some embodiments, a standard includes recombinant NfL. In some embodiments, a standard includes synthetic NfL nucleic acids. A composition in accordance with this technology can include other ingredients, such as a solvent or buffer, a stabilizer or a preservative, and/or an agent for treating a condition or disorder, for example.

Exemplary Computer Systems

[0139] FIG. 1 is a block diagram of a computer system 1100 that can be used in the operations described and illustrated herein and is disclosed in accordance with one embodiment. The system 1100 includes a processor 1110, a memory 1120, a storage device 1130 and an input/output device 1140. Each of the components 1110, 1120, 1130 and 1140 are interconnected using a system bus 1150. The system may include analyzing equipment 1160 for determining a level of NIL in a sample.

[0140] Methods described herein can be implemented by the computer system 1100 having the processor 1110 that executes specific instructions in a computer program stored in the memory 1120. In some embodiments, the computer system 1100 may be arranged to output a biomarker score based on receiving a biomarker profile and/or a level of NfL, demographic factors, and/or imaging-based biomarkers. The computer program may include instructions for the computer system 1100 to select appropriate next steps, including additional medication, a treatment, and/or additional testing (e.g., cardiomyopathy tests) for a subject.

[0141] In some embodiments, the computer program may be configured such that the computer system 1100 can identify a subject for further testing (e.g., cardiomyopathy tests), identify a subject as being at risk or having heart disease, and/or identify a subject to receive medication based on received data (e.g., a biomarker profile) and use the data to calculate a biomarker score. A computer system 100 according to this technology may rank-order identified next steps based on biomarker profile with demographic factors and/or imagingbased biomarkers. The computer system 1 100 may adjust the rank ordering based on. for example, a clinical response of a subject or of a family member of the subject who has or is suspected of having heart disease.

[0142] Thus, the processor 1110 is capable of processing instructions for execution within the computer system 1100. In one embodiment, the processor 1110 is a single-threaded processor. In another embodiment, the processor 1 1 10 is a multi-threaded processor. The processor 1110 is capable of processing instructions stored in the memory' 1120 or on the storage device 1130, including for receiving or sending information through the input/output device 1140.

[0143] The memory 1120 stores information within the system 1100. In one embodiment, the memory⁷ 1120 is a computer-readable medium. In one embodiment, the memory⁷ 1120 is a volatile memory⁷ unit. In another embodiment, the memory 1120 is a nonvolatile memory unit (e.g., a non-transitory computer-readable medium). The storage device 1130 can provide mass storage for the computer system 1100. In one embodiment, the storage device 1130 is a volatile or non-volatile computer-readable medium. Thus, the non-transitory computer readable media of the memory⁷ 1120 may contain executable instructions that w hen executed by the processor 1110 cause the processor 1110 to perform operations including a method as provided herein. For example, a non-transitory computer readable medium containing executable instructions that when executed by the processor 1110 cause the processor 1110 to perform operations including the method 1200 or 1300.

[0144] The input/ output device 1 140 provides input/output operations for the computer system 1100. In one embodiment, the input/output device 1140 includes a keyboard and/or pointing device. In one embodiment, the input/output device 1140 includes a display unit for displaying graphical user interfaces. In some examples, the input/output device 1140 is a touch screen.

[0145] The computer system 1100 can be used to build a database in some examples. FIG. 2 shows a flow chart of an exemplary method 1200 for generating a database for use in identifying a subject for further testing (e.g., cardiomyopathy tests), identifying a subject as being at risk or having heart disease, and/or identifying a subject to receive medication. Any of the methods described and illustrated herein, including method 1200 and/or method 1300, can be performed in whole or in part by computer system 1100. For example, a computer program product can include instructions that cause the processor 1110 to perform the steps of the method 1200 or the method 1300.

[0146] In step 1205 in this example, the computer system 1100 trains a machine learning model or obtains a trained machine learning model. In some examples, the machine learning model is trained using training data including biomarker profiles for subjects and a health status (e.g., healthy, suffering from heart disease, etc.) for the subjects corresponding to the biomarker profiles. Each of the biomarker profiles includes levels of two or more biomarkers includes at least NfL in this example. In some examples, the training data further includes demographic data and/or imaging-based biomarkers correlated to each of the subjects and their corresponding biomarker profiles and health statuses.

[0147] The machine learning model in some examples is derived from a bagged, boosted, or additive decision tree methodology, a neural boosted methodology, a bootstrap forest methodology, a boosted tree methodology, or a support vector machine methodology, although other methodologies and/or machine learning algorithms or models can also be used in other examples. In some examples, the machine learning model is a classifier for heart disease trained to provide an output indicative of whether a subject has or does not have a heart disease (e g., based on an output biomarker score), as explained in more detail below. Thus, the machine learning model is trained to leverage patterns and vector searches, for example, to correlate input data associated with a subject with a health status of a subject in the training data, to thereby analyze a probability that the subject is at risk of or is suffering from heart disease, as also explained in more detail below.

[0148] In step 1210, the computer system 1100 obtains a subject’s biomarker profile (e.g., levels of one or more biomarkers in a sample obtained from a subject, including at least a level of NfL) from a computing device (e.g., computer device 2404) via one or more communication networks (e.g., network 2408). In some examples, the machine learning model is trained on training data associated with human subjects and/or the biomarker profile obtained in step 1210 is associated with a human subject. In these examples, the sample can include one or more of blood, serum, plasma, or cardiac tissue, although other types of subjects and/or samples can also be used in other examples. Optionally, the sample can be obtained via the analyzing equipment 1160, for example.

[0149] Optionally, the computer system 1100 can further obtain additional data for the subject corresponding to the obtained biomarker profile, including demographic data and/or imaging-based biomarkers. The demographic data can correspond to one or more demographic factors for the subject (e.g.. age, sex, etc.), for example, although any other demographic factors can also be used, including those identified above. Additionally, the imaging-based biomarkers can include at least a left ventricle septal wall thickness or ejection fraction, although other imaging-based biomarkers can also be used.

[0150] In examples in which imaging-based biomarkers are obtained in step 1210, the computer system 1100 can be configured to determine the imaging-based biomarkers by analyzing one or more obtained images associated with the subject to obtain one or more measurements. For example, the analysis can include a pattern recognition performed on the obtained images and/or a segmentation and classification of one or more features extracted from the obtained images, for example, although other types of analyses can also be used in other examples. Optionally, the segmentation and classification can be performed by the first machine learning model, or a second machine learning model trained to extract the features from the images.

[0151] In some examples, a computer program in the computer system 1100 may include instructions for presenting a suitable graphical user interface (GUI) on input/output device 1140, and the GUI may prompt a user to enter NfL levels using the input/output device 1140, such as a keyboard. In other examples, the computer system 1100 may provide an application programming interface (API) or other integration to a third-party service or other device for obtaining a biomarker profile, demographic data, and/or imaging-based biomarkers for a subject.

[0152] In step 1220, the computer system 1100 applies the machine learning model trained in step 1205 to an input to generate a biomarker score for the subject. The input can include at least the biomarker profile received in step 1210, although demographic data and/or imaging-based biomarkers received in step 1210 can also form part of the input to the machine learning model. The biomarker score in this example is indicative of a probability that the subject is at risk of, or is suffering from, a heart disease. Thus, in some examples, the biomarker score is effectively calculated or determined from the biomarker profile, demographic data or factors, and/or imaging-based biomarkers for the subject. The biomarker score can be a binary value indicative of a classification of the subject into one of two classes. Alternatively, the biomarker score can include a range or can be a value within a range, and other types of biomarker scores can also be generated in step 1220.

[0153] In step 1230, the computer system 1100 provides the biomarker score, and/or an indication of heart disease derived therefrom, to the computing device via the communication networks and in response to the biomarker profile, and optionally stores the calculated biomarker score. The computer system 1100 may store a biomarker score in the storage device 1130, for example.

[0154] In some examples, the indication of heart disease comprises a binary- indication determined based on a classification by the machine learning model of the subject into one of two classes corresponding to having or not having heart disease. Optionally, one or more of a sensitivity or a specificity- of the classifier in these examples is more than eighty' percent, although another percentage can also be used or required before the machine learning model is deployed in production. In other examples, the biomarker score can be used by the computer system 1100 to determine at least one of (i) a heart disease state for the subject, (ii) whether the subject has or does not have a heart disease (e.g., a heart disorder or condition), or (iii) a probability that the subject has a heart disease.

[0155] Additionally, or alternatively, the computer system 1100 may provide a readout (e.g.. via the input/out device 1140) including the biomarker score and/or the indication of heart disease (e.g., a likelihood or probability that the subject is suffering from, or is at risk of, heart disease determined from the biomarker score). The readout may include proposed next steps for the subject associated with the received biomarker profile and/or a confidence level associated with the calculated biomarker score. For example, a biomarker score within a first range or exceeding a first threshold may be correlated with a next step of retesting after a recommended time period has elapsed to provide a comparison analysis to determine NfL level trends that may be indicative of increasing risk of heart disease, as explained in more detail below with reference to method 1300.

[0156] In another example, a biomarker score within a second range or exceeding a second threshold (e.g.. higher than the first threshold) may be correlated with a next step of confirmatory testing (e.g., echocardiogram, cardiac magnetic resonance imaging (CMR). scintigraphy, and/or cardiac biopsy). In this example, the biomarker score may be indicative of a subject likely to be suffering from heart disease. Other types of indicia and recommended next steps can also be used in other examples.

[0157] In the example method 1300 illustrated in FIG. 3, in step 1310, the computer system 1 100 detects biomarker levels in a sample (e.g., from a subject), including at least the level of NfL. The level of NfL can be detected using the analyzing equipment 1160 of the computer system 1100, for example, although other methods for detecting biomarker levels can also be used in other examples.

[0158] In step 1320. the computer system 1100 uses the levels of NfL to obtain a biomarker profile for a subject corresponding to the sample.

[0159] In step 1330, the computer system 1100 calculates a biomarker score from the biomarker profile. The biomarker score can be calculated from (i) the biomarker profile and (ii) demographic factors and/or imaging-based biomarkers. In some examples, the biomarker score for the subject can be generated using a trained machine learning model, as explained in more detail above with reference to method 1200.

[0160] In step 1340, the computer system 1100 stores the calculated biomarker score, such as in the storage device 1130, for example. Additionally, or alternatively, the computer system 1100 may provide a readout including the biomarker score, such as via the input/output device 1140, for example. The readout may also include proposed next steps for the subject associated with the received biomarker profile and/or a confidence level associated with the calculated biomarker score, as explained in more detail above.

[0161] In some examples, the sample from which the biomarker levels were detected in step 1310 is a second sample, or a subsequent sample in a series of samples, obtained from the subject and analyzed according to method 1200 or 1300. In this example, the biomarker score, and/or the indication of heart disease, can be generated based on a comparison of the level of NfL detected in the second sample, obtained from the subject at a second time later than the first time at which a first sample was obtained, to the level of NfL detected from the first sample. In some examples, the biomarker score, and/or the indication of heart disease, is generated based on the level of NfL detected from the second sample exceeding the level of NfL detected from the first sample (e.g., by a threshold amount, which can be any amount, percentage, or factor, for example).

[0162] In other examples, the computer system 1100 is configured to compare an NfL level change between two samples to a second NfL change determined for a control subject over a first time period corresponding to a difference between the time the two samples were obtained. In these examples, the control subject optionally has an age within three years of the subject and the control subject does not have a heart disease, although other age differences can also be used.

[0163] In yet other examples, the computer system 1100 can be configured to analyze a trend of NfL levels detected from a series of samples obtained from the subject to generate the biomarker score in step 1330 and/or the indication of heart disease in step 1340. By way of example only, a gradual increase in NfL over time could indicate a type of damage that would accumulate with lowered cerebral perfusion due to decline in cardiovascular function. Other methods for generating the biomarker score in step 1330 and/or the indication of heart disease in step 1340 can also be used in other examples.

[0164] Illustrative embodiments of the disclosed technology can be executed locally or over a network by the computer system 1100. FIG. 4 shows an illustrative network environment 2400 for use in the examples of this technology described herein. The network environment 2400 may include one or more resource providers 2402a, 2402b, 2402c (collectively, 2402). Each resource provider 2402 may include computing resources. In some implementations, computing resources may include any hardware (e.g., a computing resource may be computer system 1 100) and/or software used to process data in accordance with any of the methods described herein, including methods 1200 and 1300. For example, computing resources may include hardware and/or software capable of executing algorithms, computer programs, and/or computer applications. In some implementations, illustrative computing resources may include application servers and/or databases with storage and retrieval capabilities. Each resource provider 2402 may be connected to any other resource provider 2402 in the network environment 2400. In some implementations, the resource providers 2402 may be connected over a computer network 2408. Each resource provider 2402 may be connected to one or more computing device 2404a, 2404b, 2404c (collectively, 2404), over the computer network 2408.

[0165] The network environment 2400 may include a resource manager 2406. The resource manager 2406 may be connected to the resource providers 2402 and the computing devices 2404 over the computer network 2408. In some implementations, the resource manager 2406 may facilitate the provision of computing resources by one or more resource providers 2402 to one or more computing devices 2404. The resource manager 2406 may receive a request for a computing resource from a particular computing device 2404. The resource manager 2406 may identify one or more resource providers 2402 capable of providing the computing resource requested by the computing device 2404. The resource manager 2406 may select a resource provider 2402 to provide the computing resource. The resource manager 2406 may facilitate a connection between the resource provider 2402 and a particular computing device 2404. In some implementations, the resource manager 2406 may establish a connection between a particular resource provider 2402 and a particular computing device 2404. In some implementations, the resource manager 2406 may redirect a particular computing device 2404 to a particular resource provider 2402 with the requested computing resource.

EXEMPLIFICATION

Example 1: Machine Learning Model Performance Results

[0166] Machine learning models were trained and assessed for performance in classifying subjects as having heart disease or not. Biomarker profiles that included measured levels ofNfL were obtained for a population of subjects of varying race/ethnicity, sex, age, and geographic location. The population included subjects diagnosed as having heart disease and normal subjects. Bootstrap forest machine learning models were trained and evaluated utilizing k-fold cross-validation (k = 5). Results are shown in FIG. 6 as a box-and-whisker plot (with 95% confidence interval diamonds shown) of area under curve (AUC) of a receiver operating characteristic (ROC) curve on the y-axis. FIG. 5 illustrates that, averaged across the training folds, NfL-based machine learning models were able to distinguish patients having heart disease from patients who did not.

Example 2: Relationship Between NfL and Age

[0167] Biomarker profiles that included measured levels of NfL were obtained for populations of subjects having varying heart disease states. Subjects either had ATTR-CM, non-ATTR-CM HF-PEF, or normal heart function. FIG. 6 illustrates that NfL levels in blood increase with age for subjects with ATTR-CM and non-ATTR-CM HF-PEF, but not for subjects with normal heart function, at least for subjects of older age (i.e., ~60 and older). Therefore, changes in NfL levels over time may be used to predict whether an individual has heart disease and/or monitor progression of heart disease. For example, NfL levels of a subject may be monitored periodically, such as yearly, to compare. Monitoring may begin after a certain age at which NfL levels are expected to increase over time, for example at an age of at least 40 years old, at least 50 years old, at least 60 years old, or at least 65 years old, although other threshold ages can also be used.

[0168] While various illustrative embodiments incorporating the principles of the present teachings have been disclosed, the present teachings are not limited to the disclosed embodiments. Instead, this application is intended to cover any variations, uses, or adaptations of the present teachings and use its general principles. Further, this application is intended to cover such departures from the present disclosure that are within known or customary practice in the art to which these teachings pertain.

[0169] In the above detailed description, reference is made to the accompanying drawings, which form a part hereof. In the drawings, similar symbols typically identify similar components, unless context dictates otherwise. The illustrative embodiments described in the present disclosure are not meant to be limiting. Other embodiments may be used, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein. It will be readily understood that various features of the present disclosure, as generally described herein, and illustrated in the Figures, can be arranged, substituted, combined, separated, and designed in a wide variety of different configurations, all of which are explicitly contemplated herein.

[0170] Aspects of the present technical solutions are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the technical solutions. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.

[0171] These computer readable program instructions can be provided to a processor of a special purpose computer or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks.

[0172] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

[0173] As used herein, the terms “worker,"’ “algorithm,” “system,” “module,” “engine,” or “architecture,” if used herein, are not intended to be limiting of any particular implementation for accomplishing and/or performing the actions, steps, processes, etc., attributable to and/or performed thereby. An algorithm, system, module, engine, and/or architecture may be, but is not limited to, software, hardware and/or firmware or any combination thereof that performs the specified functions including, but not limited to, any use of a general and/or specialized processor in combination with appropriate software loaded or stored in a machine-readable memory and executed by the processor. Further, any name associated with a particular algorithm, system, module, and/or engine is, unless otherwise specified, for purposes of convenience of reference and not intended to be limiting to a specific implementation. Additionally, any functionality attributed to an algorithm, system, module, engine, and/or architecture may be equally performed by multiple algorithms, systems, modules, engines, and/or architectures incorporated into and/or combined with the functionality of another algorithm, system, module, engine, and/or architecture of the same or different type, or distributed across one or more algorithms, systems, modules, engines, and/or architectures of various configurations.

[0174] The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present technical solutions. In this regard, each block in the flowchart or block diagrams can represent a module, segment, or portion of instructions, which includes one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession can, in fact, be executed substantially concurrently, or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

[0175] A second action can be said to be "in response to’' a first action independent of whether the second action results directly or indirectly from the first action. The second action can occur at a substantially later time than the first action and still be in response to the first action. Similarly, the second action can be said to be in response to the first action even if intervening actions take place between the first action and the second action, and even if one or more of the intervening actions directly cause the second action to be performed. For example, a second action can be in response to a first action if the first action sets a flag and a third action later initiates the second action whenever the flag is set.

[0176] The present disclosure is not to be limited in terms of the particular embodiments described in this application, which are intended as illustrations of various features. Many modifications and variations can be made without departing from its spirit and scope, as will be apparent to those skilled in the art. Functionally equivalent methods and apparatuses within the scope of the disclosure, in addition to those enumerated herein, will be apparent to those skilled in the art from the foregoing descriptions. It is to be understood that this disclosure is not limited to particular methods, reagents, compounds, compositions or biological systems, which can, of course, vary. It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting.

[0177] With respect to the use of substantially any plural and/or singular terms herein, those having skill in the art can translate from the plural to the singular and/or from the singular to the plural as is appropriate to the context and/or application. The various singular/plural permutations may be expressly set forth herein for sake of clarity.

[0178] It will be understood by those within the art that, in general, terms used herein are generally intended as “open” terms (for example, the term “including” should be interpreted as “including but not limited to;’ the term “having” should be interpreted as “having at least,” the term “includes” should be interpreted as “includes but is not limited to,” et cetera). While various compositions, methods, and devices are described in terms of “comprising” various components or steps (interpreted as meaning “including, but not limited to”), the compositions, methods, and devices can also “consist essentially of’ or “consist of’ the various components and steps, and such terminology should be interpreted as defining essentially closed-member groups.

[0179] As used in this document, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise. Unless defined otherwise, all technical and scientific terms used herein have the same meanings as commonly understood by one of ordinary skill in the art. Nothing in this disclosure is to be construed as an admission that the embodiments described in this disclosure are not entitled to antedate such disclosure by virtue of prior invention.

[0180] In addition, even if a specific number is explicitly recited, those skilled in the art will recognize that such recitation should be interpreted to mean at least the recited number (for example, the bare recitation of “two recitations,” without other modifiers, means at least two recitations, or two or more recitations). Furthermore, in those instances where a convention analogous to “at least one of A, B, and C, et cetera” is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (for example, “a system having at least one of A, B, and C” would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, et cetera). In those instances where a convention analogous to “at least one of A, B, or C, et cetera” is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (for example, “a system having at least one of A, B, or C” would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, and C together, et cetera). It will be further understood by those within the art that virtually any disjunctive word and/or phrase presenting two or more alternative terms, whether in the description, sample embodiments, or drawings, should be understood to contemplate the possibilities of including one of the terms, either of the terms, or both terms. For example, the phrase “A or B” will be understood to include the possibilities of “A” or “B” or “A and B.” [0181] In addition, where features of the disclosure are described in terms of Markush groups, those skilled in the art will recognize that the disclosure is also thereby described in terms of any individual member or subgroup of members of the Markush group.

[0182] As will be understood by one skilled in the art, for any and all purposes, such as in terms of providing a written description, all ranges disclosed herein also encompass any and all possible subranges and combinations of subranges thereof. Any listed range can be easily recognized as sufficiently describing and enabling the same range being broken down into at least equal halves, thirds, quarters, fifths, tenths, et cetera. As a non-limiting example, each range discussed herein can be readily broken down into a lower third, middle third and upper third, et cetera. As will also be understood by one skilled in the art all language such as “up to." “at least,’⁷ and the like include the number recited and refer to ranges that can be subsequently broken down into subranges as discussed above. Finally, as will be understood by one skilled in the art, a range includes each individual member. Thus, for example, a group having 1-3 components refers to groups having 1, 2, or 3 components. Similarly, a group having 1-5 components refers to groups having 1. 2, 3, 4, or 5 components, and so forth.

[0183] Various of the above-disclosed and other features and functions, or alternatives thereof, may be combined into many other different systems or applications. Various presently unforeseen or unanticipated alternatives, modifications, variations or improvements therein may be subsequently made by those skilled in the art, each of which is also intended to be encompassed by the disclosed embodiments.

Claims

CLAIMS What is claimed is:

1. A method for heart disease prediction, the method implemented by a computer system and comprising: obtaining a biomarker profile comprising a first level of one or more biomarkers in a first sample obtained from a subject, wherein the one or more biomarkers comprise neurofilament light chain (NfL); applying a first machine learning model to an input to generate a biomarker score for the subject, wherein the input comprises at least the biomarker profile and the biomarker score is indicative of a probability that the subject is at risk of, or is suffering from, a heart disease; and outputting the biomarker score or an indication of the heart disease determined from the biomarker score to a computing device via one or more communication networks.

2. The method of claim 1 , further comprising obtaining, from the computing device and via the communication networks, demographic data corresponding to one or more demographic factors for the subject, wherein the input further comprises the demographic data and the demographic factors comprise at least one or more of sex or age of the subject.

3. The method of any one of claims 1-2, further comprising obtaining, from the computing device and via the communication networks, one or more imaging-based biomarkers for the subject, wherein the input further comprises the imaging-based biomarkers and the imaging-based biomarkers comprise at least a left ventricle septal wall thickness or ejection fraction.

4. The method of claim 3, further comprising, to determine the imaging-based biomarkers, analyzing one or more obtained images associated with the subject to obtain one or more measurements, wherein the analysis comprises one or more of: a pattern recognition performed on the obtained images; or a segmentation and classification with the first machine learning model or a second machine learning model of one or more features extracted from the obtained images.

5. The method of any one of claims 1-4, wherein the first machine learning model is derived from a bagged, boosted, or additive decision tree methodology, a neural boosted methodology, a bootstrap forest methodology, a boosted tree methodology, or a support vector machine methodology.

6. The method of any one of claims 1-5, wherein the first machine learning model is a classifier for heart disease and the method further comprises classifying the subject as having or not having heart disease based on the biomarker score, wherein the indication of heart disease comprises a binary' indication determined based on the classification and one or more of a sensitivity or a specificity of the classifier is more than eighty percent.

7. The method of any one of claims 1-6, wherein the subject is a human subject, and the first sample comprises one or more of blood, serum, plasma, or cardiac tissue.

8. The method of any one of claims 1-7, further comprising determining based on the biomarker score at least one of (i) a heart disease state for the subject, (ii) whether the subject has or does not have a heart disease, or (iii) a probability that the subject has a heart disease.

9. The method of any one of claims 1-8, further comprising training the first machine learning model using obtained training data comprising biomarker profiles for a plurality of subjects and a health status for the subjects corresponding to the biomarker profiles, wherein each of the biomarker profiles comprises levels of two or more biomarkers comprising at least NfL.

10. The method of any one of claims 1-9, wherein the first sample is obtained from the subject at a first time and the method further comprises determining that the subject is at risk of, or is suffering from, a heart disease when a second level of NfL detected in a second sample obtained from the subject at a second time later than the first time exceeds the first level of NfL by a threshold amount.

11. The method of any one of claims 1-10, wherein the first sample is obtained from the subject at a first time and the method further comprises determining whether the subject is at risk of. or is suffering from, a heart disease based on a first NfL level change determined based on a comparison of the first level of NfL to a second level of NfL detected in a second sample obtained from the subject at a second time later than the first time.

12. The method of claim 11, further comprising comparing the first NfL level change to a second NfL change determined for a control subject over a first time period corresponding to a difference between the second time and the first time, wherein the control subject has an age within three years of the subject and the control subject does not have a heart disease.

13. The method of any one of claims 1-12, further comprising determining that the subject is at risk of, or is suffering from, a heart disease based on a second NfL level change determined over a second time period during which a series of samples was obtained from the subject based on a third level of NfL detected in each of the series of samples, wherein the series of samples includes the first sample.

14. A non-transitory computer-readable medium comprising executable instructions that when executed by a processor cause the processor to perform the method of any one of claims 1-13.

15. A computer system comprising memory and a processor, wherein the memory comprises the first machine learning model and has executable instructions stored thereon that, when executed by the processor, cause the computer system to perform the method of any one of claims 1-13.