Analytical and Clinical Validation of AIM-NASH: A Digital Pathology Tool for Artificial Intelligence-based Measurement of Nonalcoholic Steatohepatitis Histology

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 multi-site analytical and clinical validation of an AI-based pathology system, Artificial Intelligence-based Measurement of Nonalcoholic Steatohepatitis (AIM-NASH), to assist pathologists in MASH trial histology scoring. AIM-NASH demonstrated high repeatability and reproducibility compared to manual scoring. AIM-NASH-assisted reads by expert MASH pathologists were superior to unassisted reads in accurately assessing inflammation, ballooning, NAS >= 4 with >=1 in each score category, and MASH resolution, while maintaining non-inferiority in steatosis and fibrosis assessment. These findings suggest AIM-NASH could mitigate reader variability, providing a more reliable assessment of therapeutics in MASH clinical trials.