Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis
Hanna Pulaski, Stephen A. Harrison, Shraddha S. Mehta, Arun J. Sanyal, Marlena C. Vitali, Laryssa Manigat, Hypatia Hou, Susan P. Madasu Christudoss, Sara M. Hoffman, S. Adam Stanford-Moore, Robert Egger, Jonathan N. Glickman, Murray B. Resnick, Neel Patel, Cristin Taylor, Robert P. Myers, Chuhan Chung, Scott D. Patterson, Anne‐Sophie Sejling, Anne Minnich, Vipul Baxi, Gobikrishnan Subramaniam, Quentin M. Anstee, Rohit Loomba, Vlad Ratziu, Michael Montalto, Nick P. Anderson, Andrew H. Beck, Katy Wack
Abstract
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.