Machine learning algorithm improves the detection of NASH (NAS-based) and at-risk NASH: A development and validation study.

BACKGROUND AND AIMS: Detecting NASH remains challenging, while at-risk NASH (steatohepatitis and F≥ 2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning techniques, with clinical data and biomarkers to stage and grade patients with NAFLD. APPROACH AND RESULTS: Learning data were collected in the Liver Investigation: Testing Marker Utility in Steatohepatitis metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH CRN. Conditions of interest were the clinical trial definition of NASH (NAS ≥ 4;53%), at-risk NASH (NASH with F ≥ 2;35%), significant (F ≥ 2;47%), and advanced fibrosis (F ≥ 3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputations. Data were randomly split into training/validation (75/25) sets. A gradient boosting machine was applied to develop 2 models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.Clinical gradient boosting machine models for steatosis/inflammation/ballooning had AUCs of 0.94/0.79/0.72. There were no improvements when biomarkers were included. The direct NASH model produced AUCs (clinical/extended) of 0.61/0.65. The composite NASH model performed significantly better (0.71) for both variants. The composite at-risk NASH model had an AUC of 0.83 (clinical and extended), an improvement over the direct model. Significant fibrosis models had AUCs (clinical/extended) of 0.76/0.78. The extended advanced fibrosis model (0.86) performed significantly better than the clinical version (0.82). CONCLUSIONS: Detection of NASH and at-risk NASH can be improved by constructing independent machine learning models for each component, using only clinical predictors. Adding biomarkers only improved the accuracy of fibrosis.

Defining the serum proteomic signature of hepatic steatosis, inflammation, ballooning and fibrosis in non-alcoholic fatty liver disease.

BACKGROUND & AIMS: Despite recent progress, non-invasive tests for the diagnostic assessment and monitoring of non-alcoholic fatty liver disease (NAFLD) remain an unmet need. Herein, we aimed to identify diagnostic signatures of the key histological features of NAFLD. METHODS: Using modified-aptamer proteomics, we assayed 5,220 proteins in each of 2,852 single serum samples from 636 individuals with histologically confirmed NAFLD. We developed and validated dichotomized protein-phenotype models to identify clinically relevant severities of steatosis (grade 0 vs. 1-3), hepatocellular ballooning (0 vs. 1 or 2), lobular inflammation (0-1 vs. 2-3) and fibrosis (stages 0-1 vs. 2-4). RESULTS: The AUCs of the four protein models, based on 37 analytes (18 not previously linked to NAFLD), for the diagnosis of their respective components (at a clinically relevant severity) in training/paired validation sets were: fibrosis (AUC 0.92/0.85); steatosis (AUC 0.95/0.79), inflammation (AUC 0.83/0.72), and ballooning (AUC 0.87/0.83). An additional outcome, at-risk NASH, defined as steatohepatitis with NAFLD activity score ≥4 (with a score of at least 1 for each of its components) and fibrosis stage ≥2, was predicted by multiplying the outputs of each individual component model (AUC 0.93/0.85). We further evaluated their ability to detect change in histology following treatment with placebo, pioglitazone, vitamin E or obeticholic acid. Component model scores significantly improved in the active therapies vs. placebo, and differential effects of vitamin E, pioglitazone, and obeticholic acid were identified. CONCLUSIONS: Serum protein scanning identified signatures corresponding to the key components of liver biopsy in NAFLD. The models developed were sufficiently sensitive to characterize the longitudinal change for three different drug interventions. These data support continued validation of these proteomic models to enable a "liquid biopsy"-based assessment of NAFLD. CLINICAL TRIAL NUMBER: Not applicable. IMPACT AND IMPLICATIONS: An aptamer-based protein scan of serum proteins was performed to identify diagnostic signatures of the key histological features of non-alcoholic fatty liver disease (NAFLD), for which no approved non-invasive diagnostic tools are currently available. We also identified specific protein signatures related to the presence and severity of NAFLD and its histological components that were also sensitive to change over time. These are fundamental initial steps in establishing a serum proteome-based diagnostic signature of NASH and provide the rationale for using these signatures to test treatment response and to identify several novel targets for evaluation in the pathogenesis of NAFLD.

Serum Proteomics and Plasma Fibulin-3 in Differentiation of Mesothelioma From Asbestos-Exposed Controls and Patients With Other Pleural Diseases.

INTRODUCTION: Malignant pleural mesothelioma (MPM) is difficult to diagnose. An accurate blood biomarker could prompt specialist referral or be deployed in future screening. In earlier retrospective studies, SOMAscan proteomics (Somalogic, Boulder, CO) and fibulin-3 seemed highly accurate, but SOMAscan has not been validated prospectively and subsequent fibulin-3 data have been contradictory. METHODS: A multicenter prospective observational study was performed in 22 centers, generating a large intention-to-diagnose cohort. Blood sampling, processing, and diagnostic assessment were standardized, including a 1-year follow-up. Plasma fibulin-3 was measured using two enzyme-linked immunosorbent assays (CloudClone [used in previous studies] and BosterBio, Pleasanton, CA). Serum proteomics was measured using the SOMAscan assay. Diagnostic performance (sensitivity at 95% specificity, area under the curve [AUC]) was benchmarked against serum mesothelin (Mesomark, Fujirebio Diagnostics, Malvern, PA). Biomarkers were correlated against primary tumor volume, inflammatory markers, and asbestos exposure. RESULTS: A total of 638 patients with suspected pleural malignancy (SPM) and 110 asbestos-exposed controls (AECs) were recruited. SOMAscan reliably differentiated MPM from AECs (75% sensitivity, 88.2% specificity, validation cohort AUC 0.855) but was not useful in patients with differentiating non-MPM SPM. Fibulin-3 (by BosterBio after failed CloudClone validation) revealed 7.4% and 11.9% sensitivity at 95% specificity in MPM versus non-MPM SPM and AECs, respectively (associated AUCs 0.611 [0.557-0.664], p = 0.0015) and 0.516 [0.443-0.589], p = 0.671), both inferior to mesothelin. SOMAscan proteins correlated with inflammatory markers but not with asbestos exposure. Neither biomarker correlated with tumor volume. CONCLUSIONS: SOMAscan may prove useful as a future screening test for MPM in asbestos-exposed persons. Neither fibulin-3 nor SOMAscan should be used for diagnosis or pathway stratification.

Plasma protein patterns as comprehensive indicators of health.

Proteins are effector molecules that mediate the functions of genes1,2 and modulate comorbidities3-10, behaviors and drug treatments11. They represent an enormous potential resource for personalized, systemic and data-driven diagnosis, prevention, monitoring and treatment. However, the concept of using plasma proteins for individualized health assessment across many health conditions simultaneously has not been tested. Here, we show that plasma protein expression patterns strongly encode for multiple different health states, future disease risks and lifestyle behaviors. We developed and validated protein-phenotype models for 11 different health indicators: liver fat, kidney filtration, percentage body fat, visceral fat mass, lean body mass, cardiopulmonary fitness, physical activity, alcohol consumption, cigarette smoking, diabetes risk and primary cardiovascular event risk. The analyses were prospectively planned, documented and executed at scale on archived samples and clinical data, with a total of ~85 million protein measurements in 16,894 participants. Our proof-of-concept study demonstrates that protein expression patterns reliably encode for many different health issues, and that large-scale protein scanning12-16 coupled with machine learning is viable for the development and future simultaneous delivery of multiple measures of health. We anticipate that, with further validation and the addition of more protein-phenotype models, this approach could enable a single-source, individualized so-called liquid health check.

Alternative splicing of the FGF antisense gene: differential subcellular localization in human tissues and esophageal adenocarcinoma.

Overexpression of FGF-2 is associated with tumor recurrence and reduced survival after surgical resection of esophageal cancer, and these risks are reduced in tumors co-expressing the FGF antisense (FGF-AS) RNA. The aim of this study was to characterize the expression of alternatively spliced FGF-AS transcripts and encoded nudix-motif proteins in normal human tissues and in esophageal adenocarcinoma, and to correlate their expression with clinicopathologic findings and outcome. Three alternatively spliced FGF-AS transcripts encoding GFG/NUDT6 isoforms with distinct N termini were detected in various human tissues including esophageal adenocarcinoma. Expression of each isoform as a fusion protein with enhanced green fluorescent protein revealed differential subcellular trafficking: hGFGa is localized to mitochondria by an N-terminal targeting sequence (MTS), whereas hGFGb and hGFGc were localized in the cytoplasm and nucleus. Mutation/deletion analysis confirmed that the predicted MTS was necessary and sufficient for mitochondrial compartmentalization. The predominant FGF-AS mRNA expressed in esophageal tumors was splice variant b. GFG immunoreactivity was detected in the cytoplasm of all esophageal adenocarcinomas and in 88% of tumor cell nuclei. Although we found a trend towards reduced disease-free survival in patients with FGF-2 overexpressing esophageal adenocarcinomas, significantly worse disease-free survival was noted among patients whose tumors did not also overexpress the FGF-AS b isoform (p = 0.03). Tetracycline-inducible FGF-AS b expression in stably transfected human Seg-1 esophageal adenocarcinoma cells resulted in a significant suppression of steady state FGF-2 mRNA content and cell proliferation. Our data implicate the FGF-AS b isoform in modulation of FGF-2 expression and clinical outcome in esophageal adenocarcinoma.