Diagnosis and monitoring of liver disease

Abstract

The invention provides methods for determining or monitoring liver disease status. In particular, systems and methods are provided that employ a subjects age, sex, platelet count and concentrations of Golgi protein 73 (GP73) and laminin gamma-2 monomer (LG2m) to generate a liver disease score which is used to provide a liver disease status (e.g., absence of disease, presence, or stage of the disease).

Description

[0001] DIAGNOSIS AND MONITORING OF LIVER DISEASE CROSS REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Application No. 63 / 564,715, filed on March 13, 2024, the contents of which are herein incorporated by reference. FIELD OF THE INVENTION Provided herein are methods for determining or monitoring liver disease status. In particular, systems and methods are provided that employ a subjects age, sex, platelet count and concentrations of Golgi protein 73 (GP73) and laminin gamma-2 monomer (LG2m) to generate a liver disease score which is used to provide a liver disease status (e.g., absence of disease, presence, or stage of disease).BACKGROUNDProgressive diseases of the liver are a major cause of death throughout the world. These conditions can be inherited or result from several factors, including but not limited to, viruses, alcohol consumption, and obesity, which harm the liver. Over time, such liver damage can lead to fibrosis, chronic inflammation, scarring (cirrhosis), and eventually liver failure. Liver cancer ranks among the top three cancers in 46 countries, with approximately 1 million global diagnoses in 2020, and tragically, over 75% of those diagnosed succumbed to the disease. Alarmingly, the worldwide burden of primary liver cancer is projected to surge by more than 55% by 2040. Presently, early detection of liver disease can enhance the outcomes of survival and reduce the risk of malignancy progression. However, the challenge lies in the fact that over half of patients with chronic liver disease exhibit no symptoms, making it difficult to identify these cases in the initial stages. Consequently, intervention strategies and favorable outcomes are hampered. As of late, liver biopsies serve as the gold standard for assessing liver disease presence and status. However, this technique has its drawbacks, including but not limited to, invasiveness, sampling errors, and variability between observers, which have long highlighted the need for a non-invasive, cost-effective method with high sensitivity and specificity for early liver disease diagnosis and monitoring. Unfortunately, none of the available non-invasive diagnostic tests can accurately diagnose early chronic liver disease. SUMMARY OF THE INVENTION Provided herein are methods for determining liver disease status in a subject. In some embodiments, the methods comprise acquiring subject values for the subject, wherein the subject values comprise: a sex value, an age value, a platelet count from a sample from the subject, a laminin gamma-2 monomer (LG2m) concentration from a sample from the subject, and a Golgi protein 73 (GP73) concentration from a sample from the subject; generating a liver disease score based on the subject values; and providing a liver disease status based on the liver disease score. In some embodiments, the methods further comprise acquiring a LG2m concentration and a GP73 concentration in at least one additional subject sample and generating an updated liver disease score for the subject based on the subject values from the additional subject sample. In some embodiments, the subject sample comprises a blood, serum, or plasma samples. In some embodiments, the laminin gamma-2 monomer (LG2m) concentration and the Golgi protein 73 (GP73) concentration are from a single subject sample. In some embodiments, the methods further comprise treating the subject based on liver disease status. In some embodiments, the methods further comprises coating microparticles coating microparticles with anti-GP73 or anti-LG2m antibodies, producing a chemiluminescent signal in the subject sample and; measuring the concentration of GP73, LG2m, or GP73 and LG2m. Also provided herein are methods for monitoring a change in liver disease status in a subject. The method comprise acquiring at a first time point a first set of subject values comprising: a sex value of the subject; an age value of the subject; a platelet count from a sample from the subject; a laminin gamma-2 monomer (LG2m) concentration from a subject sample; and a Golgi protein 73 (GP73) concentration from a subject sample; calculating a liver disease score based on the subject values from the first time point; acquiring at a second time point a second set of subject values comprising: a sex value of the subject; an age value of the subject; a platelet count from a sample from the subject, a laminin gamma-2 monomer (LG2m) concentration from a subject sample; and a Golgi protein 73 (GP73) concentration from a subject sample; generating a liver disease score based on the subject values from the second time point; comparing the liver disease score from the first time point with the liver disease score of the second time point; and determining a change in liver disease status. In some embodiments, the methods further comprise treating the subject based on change in liver disease status. In some embodiments, the first time point and the second time point are separated by at least three months (e.g., at least three months, at least six months, at least nine months, at least 1 year, at least 2 years, at least 3 years, at least 4 years, at least 5 years, at least 6 years, at least 7 years, at least 8 years, at least 9 years, at least 10 years, or more). In some embodiments, the first time point is prior to the subject receiving a liver disease treatment and the second time point is obtained following the liver disease treatment. In some embodiments, the methods further comprise determining the efficacy of the liver disease treatment based on the change in liver disease status. In some embodiments the methods further comprise modifying the liver disease treatment. In some embodiments, the methods further comprise acquiring at one or more additional time points an additional set of subject values comprising: a sex value of the subject; an age value of the subject; a platelet count from a sample from the subject; a laminin gamma-2 monomer (LG2m) concentration from a subject sample; and a Golgi protein 73 (GP73) concentration from a subject sample; generating a liver disease score based on the subject values from the one or more additional time points; and determining a change in liver disease status from the first time point, second time point, or any previous time point. In some embodiments, the one or more additional time points are separated from an immediately preceding time point by at least three months. In some embodiments, the methods further comprise measuring the concentration of GP73, LG2m, or GP73 and LG2m at the first time point, the second time point, or any or all of the one or more additional time points. In some embodiments, the subject samples at the first time point, the second timepoint, or any or all of the one or more additional time points comprise a blood, serum, or plasma sample. In some embodiments, the liver disease status is the absence of a liver disease, the presence of a liver disease, or a liver disease stage, severity, or progression. In some embodiments, the liver disease is liver fibrosis. In some embodiments, the liver disease is liver cirrhosis. In some embodiments, generating the liver disease score comprises using a machine learning algorithm, regression analysis, predictive probability, multivariate survival analysis, or combinations thereof. In some embodiments, acquiring the subject values comprises receiving the subject values from a testing lab, from the subject, from an analytical testing system, and / or from a hand-held or point of care testing device. In some embodiments, acquiring the subject values comprises electronically receiving the subject values. Further provided are systems comprising one or more processors and a non-transitory computer readable media configured to: receive subject values for a subject, wherein the subject values comprise a sex value; an age value; a platelet count concentration; a laminin gamma-2 monomer (LG2m) concentration; and a Golgi protein 73 (GP73) concentration; and generate a liver disease score for the subject based on the subject values. Other embodiments and embodiments of the disclosure will be apparent in light of the following detailed description and related figures. BRIEF DESCRIPTION OF THE DRAWINGS Having thus described the presently disclosed subject matter in general terms, reference will now be made to the accompanying Figures, which are not necessarily drawn to scale, and wherein: FIG.1A-D: Box dot plots of the distribution of GP73 and LG2m by disease state (green; healthy, yellow; Fibrosis Only, magenta; Cirrhosis, blue; Fibrosis / Cirrhosis and maroon; CLD) in the development (A, B) and validation cohorts (C, D). FIG. 2A-B: ROC curves for the GLAS algorithm in the development (A) and validation (B) cohorts for Fibrosis / Cirrhosis versus healthy subjects. FIG 3A-B:Violin plots of the distribution of GLAS algorithm predicted probabilities by disease state (green; healthy, yellow; Fibrosis Only, magenta; Cirrhosis, blue; Fibrosis / Cirrhosis and maroon; CLD) in the development (A) and validation (B) cohorts. FIG 4A-D: Violin scatter plots comparing F0-F1 and F2-F4 Fibroscan patients (A) GP73 levels, (B) LG2m levels, (C) Age (years) and (D) platelet count levels (F0-F1: none to low fibrosis risk; F2-F4: medium to high fibrosis risk). FIG 5A-C: Scatter plots comparing Fibroscan kPas and (A) GP73 levels, (B) LG2m levels, and (C) platelet count levels. FIG 6: A Random Forest modeling diagram showing a Random Forest models were run in R and looped (n=500) and after each loop the variable weights were pulled and the metrics of the random forest that was generated were pulled from this data the means, median, SD, CV, etc. were calculated for these values and the median was reported. FIG 7: A table of the output data of the Random Forest modeling diagram predicting the probability of HCC within 2 years Random Forest Modeling FIG 8A-B: (A) GLAS Comparison chart and (B) a table of the output data of the Random Forest modeling diagram predicting the probability Fibroscan severity within 2 years Random Forest Modeling in F2 patients FIG 9A-B: (A) GLAS Comparison chart and (B) a table of the output data of the Random Forest modeling diagram predicting Fibroscan severity within 5 years Random Forest Modeling in F2 patients. DETAILED DESCRIPTION Most diagnostic tests are not sensitive or specific enough to aid in early detection, monitoring, staging, and aiding in liver chronic diseases and advancing liver diseases. Liver biopsies are presently considered the gold standard of diagnostic tests for evaluating liver fibrosis and cirrhosis, but they have significant drawbacks. Since it is an invasive procedure, it has the potential to result in infection, bleeding, and death. Therefore, various methods for the evaluation of non-invasive liver fibrosis / cirrhosis have been developed recently. Unfortunately, the non-invasive methodologies are not sensitive or specific enough to detect early liver diseases. Serum biomarkers GP73 and LG2m, when combined with age and sex to create the GLAS algorithm, showed superior sensitivity and specificity for early detection of liver fibrosis and cirrhosis. Analysis of the GLAS algorithm in an independent validation cohort showed similar clinical performance, although with lower AUC, sensitivities, and specificities. Differences in the demographics and disease classifications and etiologies between the development and validation cohorts may account for differences in biomarker levels and model performance; for example, the development cohort had a smaller number of patients with cirrhosis and a more diverse patient population than the validation cohort. Nevertheless, the GLAS algorithm remained robust for distinguishing between healthy subjects and patients with fibrosis or cirrhosis in these two highly different cohorts. The new GLAS algorithm outperformed other algorithms used for diagnosing liver disease that are reported in the literature. In this study, Model 5 had an area under the curve (AUC) of 0.92, sensitivity of 88.8%, and specificity of 75.9% in the development cohort and an AUC 0.93, sensitivity of 91.1%, and specificity of 80.2% in the validation cohort for detection of fibrosis or cirrhosis. These AUC values are much higher than those for the FIB-4 algorithm (platelet count, AST, ALT, age) (AUC 0.751) and Aspartate Platelet Ratio Index (APRI) algorithms (AUC 0.737) for significant fibrosis. The diagnostic accuracy of the Enhanced liver fibrosis (ELF) algorithm, which combines detection of hyaluronic acid, type III procollagen peptide (PIIINP), and tissue inhibitor of metalloproteinase-1 (TIMP1), was evaluated in recent meta-analysis of studies including nearly 20,000 individuals with or at risk of developing a wide variety of viral and non- viral liver diseases. The analysis reported an AUC of 0.811 for detecting fibrosis, 0.812 for advanced fibrosis, and 0.810 for advanced cirrhosis. In patients with chronic hepatitis C virus (HCV), the Fibrotest / FibroSure algorithm, which includes α2-macroglobulin, haptoglobin, gamma-glutamyltransferase, gamma-globulin, total bilirubin, and apolipoprotein A1, had an AUC of 0.74, sensitivity of 75.4%, and specificity of 71.4% for detection of fibrosis. In a meta-analysis, the algorithm was found to have suboptimal diagnostic accuracy for fibrosis and cirrhosis in patients with hepatitis B virus (HBV) (AUC 0.84, sensitivity 61%, and specificity 80%). Fibrometer, which combines age, weight, platelet count, AST, ALT, ferritin, and glucose, has been evaluated for the detection of fibrosis in NAFLD. In a recent meta-analysis of 7 studies including 1616 patients with NAFLD, Van Dijk et al. reported an AUC of 0.82 (sensitivity 83.5, specificity 91.1%) for Fibrometer in detecting advanced fibrosis, and lower accuracy (0.62-0.78) for detecting significant fibrosis in 3 studies. In a study of 134 patients with various autoimmune liver diseases, Fibrometer was found to have an AUC of 0.66 for severe fibrosis, which increased to 0.77 when combined with liver stiffness measured by transient elastography. Compared to individual biomarkers, the combination of GP73 and LG2m with age and sex significantly improved the accuracy of detecting fibrosis and cirrhosis liver disease in two large and diverse patient cohorts. Described herein are methods using patient demographic (e.g., age, sex) and biomarkers (e.g., GP73, LG2m) patterns for discriminating liver disease stages that would be helpful in monitoring of liver disease progression, staging, and aid in the diagnosis of liver disease. This algorithmic-based test can non-invasively and accurately diagnose early chronic liver disease, monitor progression, aid in assessing liver disease staging, and aid in diagnosis of a staged liver disease. DEFINITIONS The terms "comprise(s)," "include(s)," "having," "has," "can," "contain(s)," and variants thereof, as used herein, are intended to be open-ended transitional phrases, terms, or words that do not preclude the possibility of additional acts or structures. The singular forms "a," "and," and "the" include plural references unless the context clearly dictates otherwise. The present disclosure also contemplates other embodiments "comprising," "consisting of," and "consisting essentially of," the embodiments or elements presented herein, whether explicitly set forth or not. For the recitation of numeric ranges herein, each intervening number there between with the same degree of precision is explicitly contemplated. For example, for the range of 69, the numbers 7 and 8 are contemplated in addition to 6 and 9, and for the range 6.0-7.0, the number 6.0, 6.1, 6.2, 6.3, 6.4, 6.5, 6.6, 6.7, 6.8, 6.9, and 7.0 are explicitly contemplated. Unless otherwise defined herein, scientific, and technical terms used in connection with the present disclosure shall have the meanings that are commonly understood by those of ordinary skill in the art. The meaning and scope of the terms should be clear; in the event, however of any latent ambiguity, definitions provided herein take precedent over any dictionary or extrinsic definition. Further, unless otherwise required by context, singular terms shall include pluralities and plural terms shall include the singular. The "area under curve" or "AUC" refers to area under a receiver operating characteristic curve (ROC curve), plotting the true positive rate (TPR) or sensitivity against the false positive rate (FPR) at various threshold settings. AUC under a ROC curve is a measure of accuracy. An area of 1 represents a perfect test, whereas an area of 0.5 represents an insignificant test. A preferred AUC may be at least about 0.700, at least about 0.750, at least about 0.800, at least about 0.850, at least about 0.900, at least about 0.910, at least about 0.920, at least about 0.930, at least about 0.940, at least about 0.950, at least about 0.960, at least about 0.970, at least about 0.980, at least about 0.990, or at least about 0.995. “Antibody” and “antibodies” as used herein refers to monoclonal antibodies, monospecific antibodies (e.g., which can either be monoclonal, or may also be produced by other means than producing them from a common germ cell), multispecific antibodies, human antibodies, humanized antibodies (fully or partially humanized), animal antibodies such as, but not limited to, a bird (for example, a duck or a goose), a shark, a whale, and a mammal, including a non-primate (for example, a cow, a pig, a camel, a llama, a horse, a goat, a rabbit, a sheep, a hamster, a guinea pig, a cat, a dog, a rat, a mouse, etc.) or a non-human primate (for example, a monkey, a chimpanzee, etc.), recombinant antibodies, chimeric antibodies, single-chain Fvs (“scFv”), single chain antibodies, single domain antibodies, Fab fragments, F(ab’) fragments, F(ab’)2 fragments, disulfide-linked Fvs (“sdFv”), and anti-idiotypic (“anti-Id”) antibodies, dual- domain antibodies, dual variable domain (DVD) or triple variable domain (TVD) antibodies (dual- variable domain immunoglobulins and methods for making them are described in Wu, C., et al., Nature Biotechnology, 25(11):1290-1297 (2007) and PCT International Application WO 2001 / 058956, the contents of each of which are herein incorporated by reference), or domain antibodies (dAbs) (e.g., such as described in Holt et al., Trends in Biotechnology 21:484-490 (2014)), and including single domain antibodies sdAbs that are naturally occurring, e.g., as in cartilaginous fishes and camelid, or which are synthetic, e.g., nanobodies, VHH, or other domain structure), and functionally active epitope-binding fragments of any of the above. In particular, antibodies include immunoglobulin molecules and immunologically active fragments of immunoglobulin molecules, namely, molecules that contain an analyte-binding site. Immunoglobulin molecules can be of any type (for example, IgG, IgE, IgM, IgD, IgA, and IgY), class (for example, IgG1, IgG2, IgG3, IgG4, IgA1, and IgA2), or subclass. For simplicity sake, an antibody against an analyte is frequently referred to herein as being either an “anti-analyte antibody” or merely an “analyte antibody”. The "Golgi protein 73" or "GP73," also known as "Golgi membrane protein 1", "Golgi phosphoprotein 2" and "Golgi membrane protein GP73", refers to a protein that processes protein synthesized in the rough endoplasmic reticulum and assists in the transport of protein cargo through the Golgi apparatus. Human GP73 is a 400 amino acid protein encoded by the GOLMJ gene. GP73 is widely expressed in normal epithelial cells from several tissues. Upregulated intracellular GP73 expression enhances its intracellular trafficking through the endosomal pathway, which provides the opportunity for endoproteolytic cleavage of GP73, resulting in the secretion of truncated GP73. GP73 may be fucosylated or non-fucosylated. "Laminin gamma-2 monomer," "LG2m," "laminin-5 gamma-2 monomer," "LN-5 gamma-2 monomer," "gamma-2 monomer," "gamma-2," "g-2 monomer" or any of the preceding terms with the "y" symbol in place of the word "gamma" or the letter "g" or "G" are all interchangeable and refer to one of the polypeptide chains, the gamma (y) chain (as opposed to the alpha (a) and beta ((3) chains), that constitutes laminin-5 (also known as "kalinin" and "nicein" among other synonyms) and is identified as of the gamma-2 molecular species (contrasting from the gamma-1 species). "Liver cancer" as used herein refers to cancer that originates in the liver. Liver cancer includes hepatocellular carcinoma (HCC) and fibrolamellar carcinoma. In most cases, the cause of liver cancer is usually scarring of the liver (e.g., cirrhosis). "Liver cirrhosis" as used herein refers to the consequence of chronic liver disease characterized by replacement of liver tissue by fibrosis, scar tissue, and regenerative nodules, lumps that occur because of a process in which damaged tissue is regenerated, leading to loss of liver function. The architectural organization of the functional units of the liver becomes so disrupted that blood flow through the liver and liver function become disrupted. Cirrhosis is most commonly caused by alcoholism, hepatitis B and C, and fatty liver disease, but has many other probable causes. Some cases are idiopathic (e.g., of unknown cause). Once cirrhosis has developed, the serious complications of liver disease may occur including portal hypertension, liver failure, and liver cancer. The risk of liver cancer is greatly increased once cirrhosis develops, and cirrhosis should be considered to be a pre-malignant condition. Cirrhosis may be caused by alcohol abuse, autoimmune diseases of the liver, hepatitis B or C virus infection, inflammation of the liver that is long-term (chronic), and iron overload in the body (hemochromatosis). Patients with hepatitis B or C are at risk for liver cancer, even if they have not developed cirrhosis. "Liver disease" as used herein refers to damage to or disease of the liver. Such diseases include but are not limited to cirrhosis, alcoholic liver disease, hepatic steatosis, steatohepatitis, nonalcoholic liver disease including nonalcoholic steatohepatitis, liver infections caused by viral infections such as hepatitis B and hepatitis C infections, responses to other pathogens such as schistosomiasis, hereditary haemochromatosis, primary biliary cirrhosis and primary sclerosing cholangitis, reactions to drugs such as methotrexate and congenital disorders such as biliary atresia. Symptoms of liver dysfunction include both physical signs and a variety of symptoms related to digestive problems, blood sugar problems, immune disorders, abnormal absorption of fats, and metabolism problems. In some embodiments, liver disease includes liver fibrosis, liver cirrhosis, and liver cancer. All chronic liver diseases can lead to liver fibrosis. Chronic liver disease may be caused by chronic viral hepatitis B and alcoholic liver disease. "Liver fibrosis" as used herein refers to an excessive accumulation of extracellular matrix proteins including collagen that occurs in most types of chronic liver diseases. Liver fibrosis is the scarring process that represents the liver's response to injury or illness. Liver fibrosis may be caused by infections due hepatitis B and C, parasites, excessive alcohol use and exposure to toxic chemicals, including pharmaceutical drugs and blocked bile ducts. Advanced liver fibrosis results in cirrhosis, liver failure, and portal hypertension and often requires liver transplantation. “Microparticles” as used herein refers to small particles with dimensions typically ranging from 0.1 to 100 micrometers (μm). These particles can be solid or colloidal in nature Microparticles can include, but are not limited to, polymeric microparticles, liposomes, microspheres, nanoparticles, magnetic microparticles, protein microparticles, biodegradable microparticles, ceramic microparticles, hollow microparticles, Janus particles, nanospheres, microcapsules, and nanocapsules. In some cases, microparticle can include one or more of the following: a poly (lactide-co-glycolide), aliphatic polyesters including, but not limited to, poly- glycolic acid and poly-lactic acid, hyaluronic acid, modified polysaccharides, chitosan, cellulose, dextran, polyurethanes, polyacrylic acids, pseudo-poly(amino acids), polyhydroxybutyrate- related copolymers, polyanhydrides, polymethylmethacrylate, poly(ethylene oxide), lecithin and phospholipids – in any combination thereof. A "subject" or "patient" may be human or non-human and may include, for example, animal strains or species used as "model systems" for research purposes, such a mouse model as described herein. Likewise, the subject may include either adults or juveniles (e.g., children). Moreover, patient may mean any living organism, preferably a mammal (e.g., humans and non- humans) that may benefit from the administration of compositions contemplated herein. Examples of mammals include, but are not limited to, any member of the Mammalian class: humans, non-human primates such as chimpanzees, and other apes and monkey species; farm animals such as cattle, horses, sheep, goats, swine; domestic animals such as rabbits, dogs, and cats; laboratory animals including rodents, such as rats, mice and guinea pigs, and the like. Examples of non-mammals include, but are not limited to, birds, fish, and the like. In one embodiment, the mammal is a human. ABBREVIATIONS AFP, alpha fetoprotein; APRI, aspartate platelet ratio index; AUC, area under the curve; CLD, chronic liver disease; ELF, enhanced liver fibrosis; ELISA, enzyme-linked immunosorbent assay; HAMA, human anti-mouse antibodies; HBV, hepatitis B virus; HCC, hepatocellular carcinoma; HCV, hepatitis C virus; JHU, Johns Hopkins University School of Medicine; LG2m, laminin-gamma 2 monomer; Ln, laminin; LoBDQ, limit of blank, limit of detection, and limit of quantitation; LR, logistic regression; MRE, magnetic resonance elastography; muhuFab, murine human chimeric Fab; PIIINP, type III procollagen peptide; TIMP1, and tissue inhibitor of metalloproteinase-1; PIVKA-II, protein induced by vitamin K absence / antagonist-II; PUMCH, Peking Union Medical College Hospital; ROC, receiver operating curve; SE, sensitivity; SP, specificity; UTSMC, University of Texas Southwestern Medical Center. Preferred methods and materials are described below, although methods and materials similar or equivalent to those described herein can be used in practice or testing of the present disclosure. All publications, patent applications, patents and other references mentioned herein are incorporated by reference in their entirety. The materials, methods, and examples disclosed herein are illustrative only and not intended to be limiting. LIVER DISEASE STATUS The invention provides systems and methods for determining and monitoring liver disease status in a subject. The disclosed methods employ four subject values: a sex value, an age value, a platelet count from a sample from the subject, a laminin gamma-2 monomer (LG2m) concentration from a subject sample and a Golgi protein 73 (GP73) concentration from a subject sample, to calculate a liver disease score using a machine learning algorithm. The liver disease score may be used to determine liver disease status and inform or change intervention strategy (e.g., a treatment plan) for the subject based on the liver disease status. Accordingly, methods of the invention can be used to diagnose or aid in the diagnosis of a liver disease or progression or severity thereof (e.g., progression of fibrosis or cirrhosis), monitor a liver disease progression (e.g., progression of fibrosis or cirrhosis), or distinguish between two or more liver diseases. In some embodiments, the methods comprise acquiring the subject values from a subject at single time point. In some embodiments, the methods comprise acquiring the subject values (e.g., the LG2m concentration or the GP73 concentration) at an initial time point and one or more additional or subsequent time points. As such, the methods may allow identification of an initial liver disease status or monitoring of the progression of the liver disease status over a period of time. The progression (or regression) of the liver disease or severity thereof may be monitored while the subject is undergoing a treatment. The monitoring may comprise determining the liver disease status e.g., the presence or the severity of the liver disease in the subject at two or more time points (e.g., before commencing the treatment, during a first and / or second time point during the treatment, and / or after completing all or a portion of a therapeutic regimen). In some embodiments, the methods comprise: acquiring at a first time point a first set of subject values comprising: a sex value of the subject; an age value of the subject; a platelet count from a sample from the subject; a laminin gamma-2 monomer (LG2m) concentration from a subject sample; and a Golgi protein 73 (GP73) concentration from a subject sample; calculating a liver disease score based on the subject values from the first time point; acquiring at a second time point a second set of subject values comprising: a sex value of the subject; an age value of the subject; a platelet count from a sample from the subject; a laminin gamma-2 monomer (LG2m) concentration from a subject sample; and a Golgi protein 73 (GP73) concentration from a subject sample; generating a liver disease score based on the subject values from the second time point; comparing the liver disease score from the first time point with the liver disease score of the second time point; and determining a change in liver disease status. Generally, for methods in which multiple time points are used to assay for a disease (e.g., monitoring disease progression and / or response to treatment), a second or additional subject samples are obtained at a period of time after the first subject sample has been obtained. Specifically, a second subject sample can be obtained minutes, hours, days, weeks, months, or years after the first subject sample was obtained. For example, the second, or additional, subject sample can be obtained from the subject at a time period of about 1 week, about 2 weeks, about 3 weeks, about 1 month, about 2 months, about 3 months, about 4 months, about 5 months, about 6 months, about 7 months, about 8 months, about 9 months, about 10 months, about 11 months, about 12 months, about 15 months, about 18 months, about 21 months, about 2 years, about 2.5 years, about 3.0 years, about 3.5 years, about 4.0 years, about 4.5 years, about 5.0 years, about 5.5 years, about 6.0 years, about 6.5 years, about 7.0 years, about 7.5 years, about 8.0 years, about 8.5 years, about 9.0 years, about 9.5 years, about 10.0 years, or more after the first, or previous, subject sample was obtained. In some embodiments, the methods further comprise treating the subject based on the change in liver disease status, or modifying an existing treatment regimen based on the change in liver disease status. 1. Subject Values The method generates a liver disease score based on subject values: a sex value; an age value; a platelet count from a sample from the subject; and concentrations of LG2m and GP73. In certain embodiments, the age value is addressed by determining the impact of the age decile of the subject. In some embodiments, the subject age value is either the subject's age in years or a set value based on range of ages. For example, the set value may be determined based on ranges such as: 0-29 years old, 30-39 years old, 40-49 years old, 50-59 years old, 60-69 years old, 70-79 years old, and 80 years or older. In some embodiments, the sex value is addressed by categorizing the patients into male and female sex profiles. In select embodiments, the sex value is one number for males (e.g., 1.0) and another number for females (e.g., 0).The methods may further use additional medical information other than those expressly described herein, particularly those associated with liver disease or risks associated with liver disease. For example, additional medical information may include the height and / or weight of the subject, recent or acute weight gain or loss, ethnicity, occupational history, family history, the presence of a genetic marker(s), clinical symptom, diagnosis of hepatitis B or C virus or viral infection, alcohol use history, diagnosis of non- alcoholic liver disease, medical history of diabetes or other metabolic syndrome, medication status, prior test result indicative of liver fibrosis (e.g., a FibroTest, a AST to ALT ratio, an APRI index), and imaging information such as ultrasonic (US), computed tomography (CT) and magnetic resonance imaging (MRI), and transient elastography (TE) (FibroScan). Additional biomedical information can be obtained from an individual using routine techniques known in the art, such as from the individual themselves by use of a routine patient questionnaire or health history questionnaire, or from a medical practitioner. In some embodiments, the subject has or is suspected of having the liver disease. In some embodiments, the subject has or has previously had a fatty liver, liver fibrosis, liver inflammation, or another liver condition. In some embodiments, the subject is undergoing or has undergone treatment for a liver disease. In some embodiments, the subject has diabetes or is at high risk of having diabetes. In some embodiments, the subject is overweight or obese. 2. Liver Disease Score Any algorithm (e.g., machine learning algorithms) known in the art can be used in the methods of the present disclosure to generate a liver disease score. In some embodiments, the algorithm comprises logistic regression, multiple linear regression (MLR), dimensionality reduction, partial least squares (PLS) regression, principal component regression, predictive probability, autoencoders, variational autoencoders, singular value decomposition, Fourier bases, wavelets, discriminant analysis, support vector machine, decision tree, classification and regression trees (CART), tree-based methods, random forest, gradient boost tree, logistic regression, matrix factorization, multidimensional scaling (MDS), t-distributed stochastic neighbor embedding (t-SNE), multilayer perceptron (MLP), network clustering, neuro-fuzzy, neural networks (shallow and deep), artificial neural networks, Pearson product-moment correlation coefficient, Spearman's rank correlation coefficient, Kendall tau rank correlation coefficient, or any combination thereof. In some embodiments, a Cox proportional hazard model or other parametric models may be used, including exponential, Weibull, log-normal, and log- logistic models. For clinical applications, the main focus is to determine if the subject has a liver disease and, if so, what is the severity or progression of the disease. Of additional interest may be the risk of a subject for having or developing a liver disease, for example over a period of time. In some embodiments, the liver disease score informs of the presence or absence of a liver disease. In some embodiments, the liver disease score informs of the severity or progression of a liver disease. In some embodiments, the liver disease score informs of the risk of developing a liver disease. In some embodiments, a clinician or other medical personnel can compare the liver disease score for the subject with a metric. The metric can be provided in a product insert or other publication, or on a website or on a mobile device (e.g., such as through an app). The metric may provide values, ranges, correlations, or cut-offs for liver disease scores which relate to presence versus absence of a liver disease, stage or progression of a liver disease, or risk levels (e.g., very high, high, moderate, low, or very low risk) for developing or having a liver disease. In some embodiments, the liver disease is fibrosis. Fibrosis can optionally be classified or stratified by stage or progression. As such, certain liver disease scores may be correlated with certain stages of fibrosis. For example, fibrosis stages can include 5 stages: 05. Stage 0 can be characterized by an absence, substantial absence, or minor presence of fibrosis. Stage 1 can be characterized by mild fibrosis or fibrosis only present (or only substantially present) at the portal area, so called portal fibrosis. Stage 2 can be characterized by moderate fibrosis, or fibrosis present between portal areas, or periportal or portal septa but having intact architecture, or fibrosis without the substantial damage to the lobular structure. Stage 3 can be characterized as severe fibrosis, or fibrosis bridging between portal areas and between portal areas and center veins, or architectural distortion but no obvious cirrhosis. Stage 4 can be characterized as cirrhosis, or the formation of pseudo-lobules, or the deformation of liver structure. These classifications were historically defined by liver biopsy. As fibrosis can progress in a gradual increase in fibrosis over long periods of time, the present invention can optionally be used to provide new fibrosis classifications that are defined according to changes in biomarker levels (e.g., by a liver disease score) and that might not necessarily directly correspond to the biopsy-based stage classifications. For example, fibrosis can optionally be stratified into mild, moderate, or severe stages; or early, intermediate, or late stage fibrosis. Alternatively, the liver disease score can be used to create a continuous grading of fibrosis based on increasing or decreasing liver disease scores. In some embodiments, the liver disease is cirrhosis. Cirrhosis can optionally be classified by progression or severity, for example, as classified by Child-Pugh grade (e.g., A, B and C). As such, certain liver disease scores may be correlated with certain stages of Cirrhosis. Similar to the explanation of fibrosis above, the present invention can stratify cirrhosis in a manner that corresponds to previously formed classification schemes (e.g., Child-Pugh grade) or in alternative manners. For example, cirrhosis can be classified using a model stratifying into 2 discrete stages, 3, discrete stages, or 4 or more discrete stages, or classified using a continuous stage model, for example, a higher or lower liver disease score indicates a greater or lesser degree of cirrhosis. The methods described herein can be implemented as a system including one or more processors and a computer-readable medium storing instructions executable by the one or more processors to perform the method, as described above. The system may comprise at least one computer system comprising the one or more processors and / or the computer- readable media. The system may further comprise one or more local servers or databases connected to or integrated with the one or more computer system. The system may further comprise one or more devices (e.g., diagnostic devices) integrated with the computer systems. The one or more processors may be configured to communicate via wired or wireless communications with each other or other processors. The one or more processors may be configured to operate on one or more processor- controlled devices that can be similar or different devices. As such, also provided herein are systems comprising a computer processor and a non- transitory computer readable media configured to generate the liver disease score from the subject values. The present disclosure also provides non-transitory computer-readable media. The non-transitory computer-readable media stores instructions that when executed by one or more processors performs some or all of the operations described in the disclosed methods. The system may further comprise a database for storing clinical data of at least one subject, wherein the clinical data comprises subject values (e.g., age, sex, and one or more concentrations of GP73 and / or LG2m) associated with the subject. In some embodiments, the subject values are manually input into the database. In some embodiments, the subject values are automatically or electronically input into the database from a testing device or transferred from an electronic medical records system. In some embodiments, the system further comprises an analytical testing, or a hand-held or point-of-care testing device, as described. The system may further comprise reporting module, configured to prepare and deliver a report comprising the liver disease score. Thus, in some embodiments, the methods further comprise reporting or delivering the liver disease score for the subject. In some embodiments, the methods described herein are integrated into a treatment method for a subject. For example, in some embodiments, the subject sample(s) is analyzed by the systems and methods described herein, a report of the results is generated, and the subject is treated based on the results (e.g., commence a new treatment, continue existing treatment, change in treatment (e.g., change in intervention type, dose, timing, etc.), hospitalization, watchful waiting, etc.). Treatments for liver disease include, but are not limited to: medications (e.g., apical sodium-dependent bile acid transporters (ASBT)-inhibitors, bile acid-binding resins, steroid acid (e.g., bile acid), bile acid derivatives, anti-cholesterol agents, anti-diabetic agents, diuretic medicines, antibiotics, beta-blocker medicines, vasoconstrictor medicines); instructions on exercise regimen; alcohol cessation plan; diet modification plan; surgery (e.g., paracentesis with or without a protein (albumin) infusion, endoscopic variceal banding or sclerotherapy, balloon tamponade, transjugular intrahepatic portosystemic shunt (TIPS)); and, for severe cases, liver transplant. 3. Subject Sample The subject sample used for acquiring the concentration of GP73 and / or LG2m may be the same or different. For example, a single sample may be analyzed GP73 and / or LG2m. Alternatively, two different subject samples may utilize: a first for determining the concentration of GP73 and a second for determining the concentration of LG2m. When two different subject samples are utilized, the subject samples may be the same type (e.g., from the same fluid or tissue) or may be a different sample type. The at least one additional subject sample may be a single sample or multiple samples and may be the same or different type as described for the initial subject sample. When the methods comprise at least one additional subject sample, they are preferably the same type and number as the initial sample but are not limited as such. Subject samples include, but are not necessarily limited to, bodily fluids such as blood- related samples (e.g., whole blood, serum, plasma, and other blood-derived samples), urine, cerebral spinal fluid, bronchoalveolar lavage, and the like. Another example of a biological sample is a tissue sample. A biological sample may be fresh or stored (e.g., blood or blood fraction stored in a blood bank). The biological sample may be a bodily fluid expressly obtained for the assays of this invention or a bodily fluid obtained for another purpose which can be sub-sampled for the assays of this invention. In certain embodiments, the biological sample is whole blood. Whole blood may be obtained from the subject using standard clinical procedures. In other embodiments, the biological sample is plasma. Plasma may be obtained from whole blood samples by known means, including but not limited to, centrifugation (e.g., of anti-coagulated blood), membrane- or filter-based separation, agglutination-based plasma separation, acoustic force, and microfluidics. This process provides a buffy coat of white cell components and a supernatant of the plasma. In certain embodiments, the biological sample is serum. Serum may be obtained by centrifugation of whole blood samples that have been collected in tubes that are free of anti-coagulant. The blood is permitted to clot prior to centrifugation. The yellowish-reddish fluid that is obtained by centrifugation is the serum. In another embodiment, the sample is urine. The sample may be pretreated as necessary by dilution in an appropriate buffer solution, heparinized, concentrated if desired, or fractionated by any number of methods including but not limited to ultracentrifugation, fractionation by fast performance liquid chromatography (FPLC), or precipitation of apolipoprotein B containing proteins with dextran sulfate or other methods. Any of a number of standard aqueous buffer solutions at physiological pH, such as phosphate, Tris, or the like, can be used. In some embodiments, the initial samples are blood, serum, or plasma sample. In some embodiments, first, second, or additional samples comprise blood, serum, or plasma samples. The sample(s) can be obtained using techniques known to those skilled in the art, and the sample(s) may be used directly as obtained from the source or following a pretreatment to modify the character of the sample. Such pretreatment may include, for example, preparing plasma from blood, diluting viscous fluids, filtration, precipitation, dilution, distillation, mixing, concentration, inactivation of interfering components, the addition of reagents, lysing, and the like. The sample(s) may be obtained in a medical facility, e.g., at an Emergency Room, urgent care clinic, walk-in clinic, a long-term care facility, or another appropriate site of medical practice. The sample(s) may be obtained in a home or residential setting (e.g., a senior living or hospice setting), at the site of the suspected myocardial infarction, or during transportation to a medical facility (e.g., ambulance). 4. Assay Methods The present invention is not limited by the type of assay used to detect and / or quantify LG2m and / or GP73. The nature of methods and the test can be any assay known in the art such as, for example, immunoassays, point-of-care assays, clinical chemistry assay, protein immunoprecipitation, immunoelectrophoresis, chemical analysis, SDS-PAGE and Western blot analysis, or protein immunostaining, a protein assay, a competitive binding assay, a lateral flow assay, a functional protein assay, or chromatography or spectrometry methods, such as high-performance liquid chromatography (HPLC) or liquid chromatography—mass spectrometry (LC / MS). Also, the assay can be employed in a clinical chemistry format such as would be known by one of ordinary skill in the art. In certain embodiments, an immunoassay is employed for detecting LG2m and / or GP73. Examples of such assays include, but are not limited to, immunoassay, such as sandwich immunoassay (e.g., monoclonal-polyclonal sandwich immunoassays, including radioisotope detection (radioimmunoassay (RIA)) and enzyme detection (enzyme immunoassay (EIA) or enzyme-linked immunosorbent assay (ELISA) (e.g., Quantikine ELISA assays, R&D Systems, Minneapolis, Minn.)), competitive inhibition immunoassay (e.g., forward and reverse), fluorescence polarization immunoassay (FPIA), enzyme multiplied immunoassay technique (EMIT), bioluminescence resonance energy transfer (BRET), and homogeneous chemiluminescent assay, one-step antibody detection assay, homogeneous assay, heterogeneous assay, capture on the fly assay, single molecule detection assay, lateral flow assay, etc. LG2m and / or GP73 can be detected or quantified in a sample with the help of one or more separation methods. For example, suitable separation methods may include a mass spectrometry method, such as electrospray ionization mass spectrometry (ESI-MS), ESI- MS / MS, ESI-MS / (MS)n (n is an integer greater than zero), 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), 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)n, or atmospheric pressure photoionization mass spectrometry (APPI-MS), APPI-MS / MS, and APPI-(MS)n. Other suitable separation methods include chemical extraction partitioning, column chromatography, ion exchange chromatography, hydrophobic (reverse phase) liquid chromatography, isoelectric focusing, one-dimensional polyacrylamide gel electrophoresis (PAGE), two-dimensional polyacrylamide gel electrophoresis (2D-PAGE), or other chromatographic techniques, such as thin-layer, gas or liquid chromatography, or any combination thereof. In one embodiment, the biological sample to be assayed may be fractionated prior to application of the separation method. Determining the concentration of LG2m and / or GP73 by an immunoassay can be adapted for use in a variety of automated and semi-automated systems or platforms (including those wherein the solid phase comprises a microparticle) known in the art. The following adaptations of automated and / or semi-automated systems are included herein as merely exemplary. Specifically, the methods can utilize automated and semi-automated systems or platforms such as those described, e.g., U.S. Patent No. 5,063,081, U.S. Patent Application Publication Nos. 2003 / 0170881, 2004 / 0018577, 2005 / 0054078, and 2006 / 0160164 and as commercially marketed e.g., by Abbott Laboratories (Abbott Park, IL) as Abbott Point of Care (i-STAT® or i-STAT Alinity, ID Now®, Abbott Laboratories) as well as those described in U.S. Patent Nos. 5,089,424 and 5,006,309, and as commercially marketed, e.g., by Abbott Laboratories (Abbott Park, IL) as ARCHITECT® or the series of Abbott Alinity devices. In certain embodiments, the methods for detecting GP73 are as described in U.S. Patent No. 9,469,686 incorporated herein by reference in its entirety but with particular focus on the assay methods. In certain embodiments, the methods for detecting LG2m are as described in U.S. Patent No. 11,340,229 incorporated herein by reference in its entirety but with particular focus on the assay methods. Other methods of detection include the use of or adaptation for use on a nanopore device or nanowell device, e.g., for single molecule detection. As used herein the term "single molecule detection" refers to the detection and / or measurement of a single molecule of an analyte in a test sample at very low levels of concentration (such as pg / mL or femtogram / mL levels). A number of different single molecule analyzers or devices are known in the art and include nanopore and nanowell devices. Examples of nanopore devices are described in PCT International Application WO 2016 / 161402, which is hereby incorporated by reference in its entirety. Examples of nanowell device are described in PCT International Application WO 2016 / 161400, which is hereby incorporated by reference in its entirety. The methods are not limited by the method of acquiring the subject values. In some embodiments, the methods comprise receiving the subject values from a testing lab, from the subject, from an analytical testing system, and / or from a hand-held or point of care testing device. In select embodiments, the methods comprise receiving the subject values from an analytical testing system. In some embodiments, the methods comprise receiving the subject values from a hand-held or point of care testing device. "Point-of-care device" refers to a device used to provide medical diagnostic testing at or near the point-of-care (namely, outside of a laboratory), at the time and place of patient care (such as in a hospital, physician's office, urgent or other medical care facility, a patient's home, a nursing home and / or a long-term care and / or hospice facility). Such point-of-care devices can also include portable, desktop sized devices. Examples of point-of-care devices include those produced by Abbott Laboratories (Abbott Park, IL) (e.g., i-STAT®, i-STAT® Alinity, ID Now®), Universal Biosensors (Rowville, Australia) (see US 2006 / 0134713), Axis-Shield PoC AS (Oslo, Norway) and Clinical Lab Products (Los Angeles, USA). As such, in some embodiments, the processing system further comprises a hand-held or point-of-care testing device. In some embodiments, the methods comprise obtaining subject values electronically. EXAMPLES The following examples are for the purposes of illustration only and are not intended to limit the scope of the claims.EXAMPLE 1Using serum samples collected from patients with hepatocellular carcinoma and chronic and progressing liver diseases, the concentration of LG2m and GP73 was determined, and the age and sex of the patient were gathered. Each sample was correlated with a liver disease or stage thereof. Random Forest (RF) classification models were used to explore the best combination of biomarkers with or without age and / or sex for the detection of liver disease. RF uses a resampling method to create a large collection of de-correlated trees, and then averages them. With the RF method, the bias of the full model is equivalent to the bias of a single decision tree, but the variance is much lower due to the nature of averaging a large collection of trees. As shown in Table 1, using age, sex, and concentrations of LG2m and GP73 resulted in the overall highest ROC AUC across the various comparisons of the liver diseases of interest (e.g., fibrosis and cirrhosis). Table 1. Liver Disease Sample Data EXAMPLE 2GP73 antibodies and immunoassay development Mice were immunized with recombinant GP73, and fusions were performed with an NSO myeloma cell line to produce monoclonal antibodies. Twelve IgG antibodies were produced in- house and were screened for use in a prototype GP73 ARCHITECT immunoassay, for a total of approximately 144 antibody pairs. The best antibody pairs were initially selected based on sensitivity, range, and reagent stability. The capture IgG1 (kappa) antibody was coated on magnetic microparticles. The conjugate antibody was murine human chimeric Fab (muhuFab) produced in CHO cells. This conjugate design minimized interference by human anti-mouse antibodies (HAMA) because it lacks the Fc region of the antibody and provided better sensitivity. Microparticle reagent bulk stability was tested under heat stress for 3 days at 45°C compared to controls at 2-8°C. The conjugate reagent bulk stability was tested with heat stress at 30°C and 37°C for 7 and 14 days compared to the 2-8°C control condition. Further prototype verification studies with the selected antibody pair included reagent stability, limit of blank, limit of detection, and limit of quantitation (LoBDQ), dilution linearity, 20-day precision, range, and interference testing. LG2m assay development A hybridoma of an anti-LG2m monoclonal antibody (Clone 1) used for capture was originally developed by Koshikawa et al. A hybridoma of an anti-LG2m monoclonal antibody (Clone 2) used for detection was developed by Abbott Laboratories (Lake County, IL, USA). Clone 1 detected only the LG2m monomer, and not LG2m as a component of Ln-332. Monoclonal antibodies were prepared and purified by Abbott Laboratories on a protein A column. The capture antibody (Clone 1) was produced in CHO cells and coated on magnetic microparticles. The conjugate antibody (Clone 2) was labeled with acridinium for the detection of LG2m. Assay prototype verification studies including LoBDQ, dilution linearity, 20-day precision, range, auto- dilution, and interference testing were performed. Study design and serum samples The prototype GP73 and LG2m ARCHITECT immunoassays were used to measure GP73 and LG2m concentrations in residual serum samples collected between 2003 and 2016 at JHU in Baltimore, MD, from patients with staged fibrosis and cirrhosis with viral or non-viral etiology, and healthy controls. The study was approved by the Johns Hopkins Medicine IRB. Additional residual serum samples were analyzed at JHU that had been collected after obtaining informed consent from patients with liver cirrhosis at the University of Texas Southwestern Medical Center (UTSMC) in Dallas, TX. For each residual serum sample, the following de-identified data was collected: age, sex, race / ethnicity, and etiology of liver disease. An additional set of serum samples (collectively referred to as the Western Vendor Cohort, WVC) were purchased from BioIVT (Wesbury, NY), Biomex GmbH (Heidelberg, Germany), Discovery Life Sciences (Huntsville, AL), and ProMedDx (Norton, MA). These three sample sets (JHU / UTSMC / WVC) were combined to develop and train the liver fibrosis and cirrhosis diagnostic algorithm (development cohort). For the validation cohort, samples were obtained from PUMCH (Bejing, China), from patients with liver disease (fibrosis, cirrhosis, or chronic liver disease) and healthy subjects. This cohort was used to validate the model derived from the development cohort. Patients with chronic liver disease included those with fatty liver disease, HBV-induced liver disease, and / or autoimmune hepatitis. For each serum sample, the following de-identified data was collected: age, sex, race / ethnicity, and etiology of liver disease. The study was approved by the PUMCH IRB (HS-2386). Sample storage and assays Serum samples were stored at approximately -80°C prior to analysis. GP73 and LG2m levels were measured using the prototype GP73 and LG2m ARCHITECT immunoassays on an ARCHITECT i2000SR analyzer (Abbott Laboratories, North Chicago, IL). Each two-step sandwich immunoassay utilizes paramagnetic microparticles coated with either anti-GP73 or anti- LG2m antibodies and produces a chemiluminescent signal for the quantitative measurement of GP73 or LG2m in human serum and plasma. The performance characteristics for the prototype ARCHITECT GP73 and LG2m assays as described in Table 2. Table 2. Performance Characteristics of the Prototype GP73 and LG2m Assay Statistical analysis Biomarker concentrations were stratified by disease category. The probability of each biomarker to detect non-cancer liver disease (chronic liver disease, fibrosis and / or cirrhosis) was determined and logistic regression (LR) classification models were used to explore the best combination of biomarkers for the detection of non-cancer liver disease. For biomarkers with skewed distribution, logarithmic transformation was applied prior to modeling. All of the samples from the development cohort (JHU / UTMSC / WVC), were used to train the models. The response variable for the models was the binary liver disease status (fibrosis and / or cirrhosis versus healthy). Multiple LR models were developed by selecting different combinations of age, sex, and the two biomarkers as the classifiers. The best model was selected based on the combination of classifiers with the highest ROC AUC. Confidence intervals for AUCs were calculated by taking 2000 stratified bootstrapped replicates. The sensitivities (SEs) and specificities (SPs) were reported at the default cutoff of 0.5 for LR. Additionally, sensitivity at a fixed specificity of 90% was reported as the median value across 2000 stratified bootstrapped replicates. Median values were also calculated from specificity at fixed sensitivities of 90% and 75%. AUCs were compared by pairing AUC curves as described by Delong et al. The best model selected from the development cohort was further assessed. To evaluate the generalizability of the best model in a different population, an independent validation cohort was used to validate model performance. Non-cancer liver disease was added to chronic liver disease (including fatty liver disease, HBV-induced liver disease, and / or autoimmune hepatitis) to better evaluate the performance in clinical practice. EXAMPLE 3 Algorithm development cohort demographics The development cohort consisted of serum samples from 78 patients with fibrosis (with or without hepatitis), 182 patients with cirrhosis (with or without hepatitis), and 133 healthy subjects as shown in Table 3. The median age for patients in the fibrosis, cirrhosis, and healthy control groups were 54, 56, and 40 years, respectively, with the majority of patients being White males (fibrosis / cirrhosis) or Black males (healthy). Table 3. Development Cohort Demographics (N=393)

[0002] JHU, Johns Hopkins University School of Medicine; UTSMC, University of Texas Southwestern Medical Center;

[0003] WVC, Western Vendor Cohort; IQR, interquartile range; HBV, hepatitis B virus; HCV, hepatitis C virus.

[0004] Algorithm validation cohort demographics

[0005] The validation cohort included 503 individuals; of these, 501 were included in this analysis and 2 were excluded for missing assay results. The validation cohort included 119 patients with cirrhosis, 129 patients with fibrosis, 147 patients with chronic liver disease, and 106 healthy subjects as shown in Table 4. Patient age varied from 19 to 88 years, with a greater proportion of men in the chronic liver disease and fibrosis groups and a greater proportion of women in the healthy and cirrhosis groups. All individuals in the validation cohort were Asian.

[0006] Table 4. Validation Cohort Demographics (n = 501)

[0007] CLD, chronic liver disease; IQR, interquartile range; HBV, hepatitis B virus; HCV, hepatitis C virus.

[0008] Biomarker concentrations

[0009] In the development cohort, GP73 and LG2M concentrations were found to be higher in patients with fibre sis / cirrho sis than in healthy controls, and on average, patients with cirrhosis had higher biomarker concentrations compared to patients with fibrosis (FIG. 1A, B). In the validation cohort, GP73 and LG2M levels were also higher overall in patients with fibrosis / cirrhosis compared to healthy controls (FIG. 1C, D); however, both GP73 and LG2M concentrations in the validation cohort were slightly higher for patients with fibrosis compared to patients with cirrhosis (FIG. 1C, D). On average, biomarker levels for patients with chronic liver disease fell between those in the fibrosis / cirrhosis and healthy groups (FIG. 1C, D). Model performance in the development cohort Five models were created and compared from the development cohort data using four potential variables: age, sex, GP73, and / or LG2m as shown in Table 5. The AUC for differentiating fibrosis / cirrhosis from healthy controls was slightly higher for GP73 alone (Model 1: 0.86, 95% CI: 0.82-0.89) compared to LG2m alone (Model 2: 0.83, 95% CI: 0.79-0.87), but the difference was not statistically significant. The addition of age and sex to either the GP73 or LG2m models increased AUCs (Model 3: 0.91, 95% CI: 0.89-0.94 and Model 4: 0.88, 95% CI: 0.85-0.92, respectively). The AUC values from both updated models were improved and statistically significant compared to the individual biomarkers alone (p < 0.0001 and p = 0.0003, respectively). Table 5. Diagnostic Performance of Biomarkers Alone and in Combination with Clinical Factors in the Development Cohort (JHU / UTSMC / WVC) and Model 5 in the Validation Cohort (PUMCH) The best model included all four variables, GP73, LG2m, age, and sex (the GLAS algorithm), and increased the AUC to 0.92 (Model 5: 95% CI: 0.90-0.95), with a sensitivity of 88.8% and a specificity of 75.9% (FIG. 2A). The increase was statistically significant compared to GP73 or LG2m alone (Models 1 and 2) and the model with LG2m, age, and sex (Model 4; all p-values <0.0001). The increase was not statistically different compared to Model 3 with GP73, age, and sex (p = 0.0621). Model validation in an independent cohort The best model from the development cohort (Model 5, the GLAS algorithm) was evaluated using the validation cohort data as an independent assessment of clinical performance (Table 4). The GLAS algorithm had an estimated AUC for fibrosis / cirrhosis of 0.93 (95% CI: 0.90-0.95) in the validation cohort (FIG. 2B). It had an estimated sensitivity of 91.1% and a specificity of 80.2%; when specificity was held to 90%, the median sensitivity was estimated to be 81.0%. The GLAS algorithm was further assessed using the validation cohort data set after stratification of fibrosis and cirrhosis etiology. AUCs were comparable for viral and non-viral liver disease, with an AUC of 0.91 (95% CI: 0.86-0.96) for viral induced fibrosis / cirrhosis and 0.94 (95% CI: 0.91-0.97) for non-viral induced fibrosis / cirrhosis compared to healthy subjects. As an exploratory analysis, the GLAS algorithm was also applied to the validation cohort to discriminate patients with chronic liver disease from healthy subjects. For this application, the model had an estimated AUC of 0.65 (95% CI: 0.58-0.71), with a sensitivity of 42.9% and specificity of 80.2%. GLAS algorithm performance by disease state The performance of the GLAS algorithm was assessed by disease state in both the development and validation cohorts (FIG.3A, B). In the development cohort, the GLAS algorithm predicted probability was higher overall in the fibrosis / cirrhosis group versus healthy controls, and patients with cirrhosis on average had higher predicted probabilities than patients with fibrosis (FIG. 3A). In the validation cohort, the GLAS algorithm predicted probability was also higher overall in the fibrosis / cirrhosis group versus healthy controls (FIG. 3B). In the validation cohort, the median predicted probability using the GLAS algorithm was slightly higher for patients with fibrosis versus cirrhosis, which matches the trend observed for GP73 and LG2m biomarker concentrations in these groups (FIG.3B, FIG.1). Additionally, the median GLAS prediction value for patients with chronic liver disease fell between that of the healthy controls and patients with fibrosis / cirrhosis, which again matches the trend seen in biomarker concentrations in each group (FIG. 3B, FIG. 1). Those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this disclosure. Accordingly, all such modifications and alternative are intended to be included within the scope of the invention as defined in the following claims. Those skilled in the art should also realize that such modifications and equivalent constructions or methods do not depart from the spirit and scope of the present disclosure, and that they may make various changes, substitutions, and alterations herein without departing from the spirit and scope of the present disclosure.

Claims

CLAIMSWe claim:

1. A method of determining liver disease status in a subject comprising: acquiring subject values for the subject, wherein the subject values comprise: a sex value, an age value, a platelet count from a sample from the subject, a laminin gamma-2 monomer (LG2m) concentration from a sample from the subject, and a Golgi protein 73 (GP73) concentration from a sample from the subject; generating a liver disease score based on the subject values; and providing a liver disease status based on the liver disease score.

2. The method of claim 1, wherein the liver disease status is the absence of a liver disease, the presence of a liver disease, or a liver disease stage, severity, or progression.

3. The method of claim 1 or 2, wherein the liver disease is liver fibrosis.

4. The method of claim 1 or 2, wherein the liver disease is liver cirrhosis.

5. The method of any of claims 1-4, wherein generating the liver disease score comprises using a machine learning algorithm, regression analysis, predictive probability, multivariate survival analysis, or combinations thereof.

6. The method of any of claims 1-5, wherein acquiring the subject values comprises receiving the subject values from a testing lab, from the subject, from an analytical testing system, and / or from a hand-held or point of care testing device.

7. The method of any of claims 1-6, wherein acquiring the subject values compriseselectronically receiving the subject values.

8. The method of any of claims 1-7, wherein the method further comprises: a. coating microparticles coating microparticles with anti-GP73 or anti-LG2m antibodies, b. producing a chemiluminescent signal in the subject sample and; c. measuring the concentration of GP73, LG2m, or GP73 and LG2m.

9. The method of any of claims 1-8, wherein the method further comprises treating the subject based on liver disease status.

10. The method of any of claims 1-9, wherein the subject sample comprises a blood, serum, or plasma sample.

11. The method of any of claims 1-10, wherein the laminin gamma-2 monomer (LG2m) concentration and the Golgi protein 73 (GP73) concentration are from a single subject sample.

12. The method of any of claims 1-11, further comprising acquiring a LG2m concentration and a GP73 concentration in at least one additional subject sample and generating an updated liver disease score for the subject based on the subject values from the additional subject sample.

13. A method for monitoring a change in liver disease status in a subject comprising: acquiring at a first time point a first set of subject values comprising: a sex value of the subject; an age value of the subject; a platelet count from a sample from the subject, a laminin gamma-2 monomer (LG2m) concentration from a subject sample; and a Golgi protein 73 (GP73) concentration from a subject sample; calculating a liver disease score based on the subject values from the first time point; acquiring at a second time point a second set of subject values comprising: a sex value of the subject; an age value of the subject; a platelet count from a sample from the subject;a laminin gamma-2 monomer (LG2m) concentration from a subject sample; and a Golgi protein 73 (GP73) concentration from a subject sample; generating a liver disease score based on the subject values from the second time point; comparing the liver disease score from the first time point with the liver disease score of the second time point; and determining a change in liver disease status.

14. The method of claim 13, wherein the first time point and the second time point are separated by at least three months.

15. The method of claim 13 or 14, wherein the first time point and the second time point are separated by at least 1 year.

16. The method of any of claims 13-15, further comprising treating the subject based on change in liver disease status.

17. The method of any of claims 13-15, wherein the first time point is prior to the subject receiving a liver disease treatment and the second time point is obtained following the liver disease treatment.

18. The method of claim 17, further comprising determining the efficacy of the liver disease treatment based on the change in liver disease status.

19. The method of claim 17 or 18, further comprising modifying the liver disease treatment.

20. The method of any of claims 13-19, further comprising acquiring at one or more additional time points an additional set of subject values comprising: a sex value of the subject; an age value of the subject; a platelet count from a sample from the subject,a laminin gamma-2 monomer (LG2m) concentration from a subject sample; and a Golgi protein 73 (GP73) concentration from a subject sample; generating a liver disease score based on the subject values from the one or more additional time points; and determining a change in liver disease status from the first time point, second time point, or any previous time point.

21. The method of claim 20, wherein the one or more additional time points are separated from an immediately preceding time point by at least three months.

22. The method of any of claims 13-21, wherein the change in liver disease status comprises a presence of a liver disease or a change in a liver disease stage, severity, or progression.

23. The method of any of claims 13-22, wherein the liver disease is liver fibrosis.

24. The method of any of claims 13-22, wherein the liver disease is liver cirrhosis.

25. The method of any of claims 13-24, wherein generating the liver disease score comprises using a machine learning algorithm, regression analysis, predictive probability, multivariate survival analysis, or combinations thereof.

26. The method of any of claims 13-25, wherein acquiring the subject values comprises receiving the subject values from a testing lab, from the subject, from an analytical testing system, and / or from a hand-held or point of care testing device.

27. The method of any of claims 13-26, wherein acquiring the subject values comprises electronically receiving the subject values.

28. The method of any of claims 13-27, wherein the method further comprises measuring the concentration of GP73, LG2m, or GP73 and LG2m at the first time point, the second time point, or any or all of the one or more additional time points.

29. The method of any of claims 13-28, wherein the subject samples at the first time point, the second time point, or any or all of the one or more additional time points comprise a blood, serum, or plasma sample. 30.A system comprising: one or more processors; and a non-transitory computer readable media configured to: receive subject values for a subject, wherein the subject values comprise a sex value; an age value; a platelet count concentration, a laminin gamma-2 monomer (LG2m) concentration; and a Golgi protein 73 (GP73) concentration; and generate a liver disease score for the subject based on the subject values.

Images