Author information

¹PathAI, Inc., Boston, MA, USA.

²Pinnacle Clinical Research, San Antonio, TX, USA.

³AbbVie, Inc., Irvine, CA, USA.

⁴Virginia Commonwealth University, Richmond, VA, USA.

⁵Whoop Inc., Boston, MA, USA.

⁶Invicro, Needham, MA, USA.

⁷Harvard Medical School, Boston, MA, USA.

⁸Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.

⁹Department of Pathology and Laboratory Medicine, Rhode Island Hospital, Brown University, Providence, RI, USA.

¹⁰OrsoBio, Inc., Palo Alto, CA, USA.

¹¹Inipharm, Inc., Bellevue, WA, USA.

¹²Gilead Sciences, Inc., Foster City, CA, USA.

¹³Novo Nordisk, Bagsvaerd, Denmark.

¹⁴Bristol Myers Squibb, Princeton, NJ, USA.

¹⁵Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, UK.

¹⁶UCSD School of Medicine, San Diego, CA, USA.

¹⁷Sorbonne Université, ICAN Institute for Cardiometabolism and Nutrition, Assisstance Publique Hôpitaux de Paris, INSERM UMRS, Paris, France.

¹⁸Amgen, Thousand Oaks, CA, USA.

¹⁹PathAI, Inc., Boston, MA, USA. katy.wack@pathai.com.

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.