Fuchs, Michael A.

ABSTRACT Background Metabolic dysfunction‐associated steatotic liver disease (MASLD) exhibits marked heterogeneity in fibrosis progression and liver‐related outcomes. Liver biopsy is not feasible for longitudinal risk stratification at scale, creating a need for validated non‐invasive biomarkers, particularly imaging biomarkers, that can predict clinically meaningful disease progression and liver‐related outcomes. Aims To describe the design and rationale of the GOLDMINE study, established to determine whether non‐invasive imaging biomarkers predict MASLD progression and liver‐related clinical outcomes. Methods GOLDMINE is an investigator‐initiated, multi‐centre, international longitudinal cohort enrolling up to 1000 adults with either biopsy‐proven MASLD or MASLD cirrhosis across the full fibrosis spectrum. Participants are recruited from 15 sites in the US and 4 international sites (Japan, Singapore and France). At baseline, participants undergo clinical phenotyping, vibration‐controlled transient elastography, and advanced magnetic resonance imaging (MRI), including proton‐density‐fat‐fraction and magnetic resonance elastography (MRE). MRI (and biospecimen banking) is repeated at 2‐year intervals (years 2 and 4), with annual follow‐up visits for up to 10 years. Baseline liver histology is centrally processed, digitized and reviewed by a single expert hepatopathologist; all MRI/MREs are centrally interpreted. Results The prespecified clinical outcomes include progression to cirrhosis, clinically significant portal hypertension, major adverse liver‐related outcomes (ascites, hepatic encephalopathy, portal hypertensive bleeding, liver transplantation/qualification), hepatocellular carcinoma, major adverse cardiovascular events, and all‐cause mortality, with independent central adjudication of all events. Conclusions GOLDMINE establishes a rigorously phenotyped MASLD cohort integrating centralized histology, advanced MRI‐based biomarkers, longitudinal biobanking, and adjudicated outcomes, providing a platform to validate imaging and blood‐based prognostic biomarkers in MASLD.

Lactulose-based hepatic encephalopathy treatment requires bowel movements/day titration, which is improved with Bristol stool scale (BSS) incorporation. Dieta app evaluates artificial intelligence (AI)-based BSS (AI-BSS) with stool images. Initially, controls (N = 13) and cirrhosis patients on lactulose/not on lactulose (n = 33) were trained on the app. They entered self-reported BSS (self-BSS) with AI-BSS communicated. Lactulose dose changes were tracked. A subset (n = 12) was retested with AI communication blocked. Most subjects were comfortable with the app. Self/AI-BSS and lactulose dose/AI-BSS correlation increased with app use. AI-BSS communications improved insight into self-BSS over time. Dieta app to gauge stool AI characteristics was acceptable and increased insight into lactulose dose and BSS in cirrhosis.