Journal Article

Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis

Baxi, Vipul, Sejling, Anne-Sophie, Chung, Chuhan, Pulaski, Hanna, Resnick, Murray, Egger, Robert, Manigat, Laryssa C., Madasu Christudoss, Susan P., Patel, Neel, Sanyal, Arun J., Hoffman, Sara M., Stanford-Moore, Adam, Glickman, Jonathan, Montalto, Michael C., Beck, Andrew H., Hou, Hypatia, Vitali, Marlena C., Subramaniam, G. Mani, Taylor, Cristin E., Loomba, Rohit, Ratziu, Vlad, Anstee, Quentin M., Myers, Robert P., Minnich, Anne, Mehta, Shraddha S., Harrison, Stephen A., Anderson, Nick P., Wack, Katy E., Patterson, Scott D.

2025

Overview

Metabolic dysfunction-associated steatohepatitis (MASH) is a major cause of liver-related morbidity and mortality, yet treatment options are limited. Manual scoring of liver biopsies, currently the gold standard for clinical trial enrollment and endpoint assessment, suffers from high reader variability. This study represents the most comprehensive multisite analytical and clinical validation of an artificial intelligence (AI)-based pathology system, AI-based measurement of metabolic dysfunction-associated steatohepatitis (AIM-MASH), to assist pathologists in MASH trial histology scoring. AIM-MASH demonstrated high repeatability and reproducibility compared to manual scoring. AIM-MASH-assisted reads by expert MASH pathologists were superior to unassisted reads in accurately assessing inflammation, ballooning, MAS ≥ 4 with ≥1 in each score category and MASH resolution, while maintaining non-inferiority in steatosis and fibrosis assessment. These findings suggest that AIM-MASH could mitigate reader variability, providing a more reliable assessment of therapeutics in MASH clinical trials. In a prospective, regulatory-grade study of assistance to pathologists in MASH histology scoring, AIM-MASH-assisted reads by expert MASH pathologists were superior to unassisted reads and decreased inter-reader variability.

• Publisher: Nature Publishing Group US,Nature Publishing Group
• Subject: 631/114/1305 / 631/154/53/2421 / 692/308/153 / 692/53/2421 / 692/699/1503/1607/2751 / Adult / Artificial Intelligence / Biomedical and Life Sciences / Biomedicine / Biopsy / Cancer Research / Clinical trials / Fatty Liver - diagnosis / Fatty Liver - metabolism / Fatty Liver - pathology / Female / Fibrosis / Histology / Humans / Infectious Diseases / Liver / Liver - pathology / Liver diseases / Male / Metabolic Diseases / Metabolism / Middle Aged / Molecular Medicine / Morbidity / Neurosciences / Non-alcoholic Fatty Liver Disease - pathology / Pathology / Reproducibility / Reproducibility of Results / Steatosis