A Universal Gut-Microbiome-Derived Signature Predicts Cirrhosis

Dysregulation of the gut microbiome has been implicated in the progression of non-alcoholic fatty liver disease (NAFLD) to advanced fibrosis and cirrhosis. To determine the diagnostic capacity of this association, we compared stool microbiomes across 163 well-characterized participants encompassing non-NAFLD controls, NAFLD-cirrhosis patients, and their first-degree relatives. Interrogation of shotgun metagenomic and untargeted metabolomic profiles by using the random forest machine learning algorithm and differential abundance analysis identified discrete metagenomic and metabolomic signatures that were similarly effective in detecting cirrhosis (diagnostic accuracy 0.91, area under curve [AUC]). Combining the metagenomic signature with age and serum albumin levels accurately distinguished cirrhosis in etiologically and genetically distinct cohorts from geographically separated regions. Additional inclusion of serum aspartate aminotransferase levels, which are increased in cirrhosis patients, enabled discrimination of cirrhosis from earlier stages of fibrosis. These findings demonstrate that a core set of gut microbiome species might offer universal utility as a non-invasive diagnostic test for cirrhosis. [Display omitted] •Non-invasive detection of cirrhosis by using microbial species, age, and serum measures•Stool microbial and metabolite signatures independently predict NAFLD-cirrhosis•Machine-learning-based prediction of cirrhosis validated in independent cohorts Oh et al. identify diagnostic signatures for fibrosis from stool metagenomic and metabolomic profiling that, when combined with serum AST levels, distinguishes cirrhosis in mixed fibrosis cohort. Moreover, this combination signature was validated in racially and geographically independent cohorts.