Clinical validation of an AI-based pathology tool for scoring of metabolic dysfunction-associated steatohepatitis
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.
Authors
- Laryssa Manigat
- Vipul Baxi
- Chuhan Chung
- Anne Minnich (ORCID: https://orcid.org/0000-0001-5247-5276)
- Neil Anderson (ORCID: https://orcid.org/0000-0003-0233-1383)
- Shraddha S. Mehta
- Murray B. Resnick (ORCID: https://orcid.org/0000-0002-9392-3415)
- Scott D. Patterson (ORCID: https://orcid.org/0000-0002-9840-4964)
- Robert Egger (ORCID: https://orcid.org/0000-0003-0849-6904)
- Jonathan N. Glickman (ORCID: https://orcid.org/0000-0003-0910-2655)
- S. Adam Stanford-Moore (ORCID: https://orcid.org/0000-0002-0689-2607)
- Rohit Seth Loomba (ORCID: https://orcid.org/0000-0002-4845-9991)
- Quentin M. Anstee (ORCID: https://orcid.org/0000-0002-9518-0088)
- Cristin Taylor
- Marlena C. Vitali
- Katy Wack
- Arun Jayant Sanyal (ORCID: https://orcid.org/0000-0001-8682-5748)
- Vlad Ratziu (ORCID: https://orcid.org/0000-0002-6865-3791)
- Gobikrishnan Subramaniam (ORCID: https://orcid.org/0000-0001-5721-661X)
- Michael Montalto (ORCID: https://orcid.org/0000-0002-3991-2360)
- Stephen A. Harrison (ORCID: https://orcid.org/0000-0001-8285-2204)
- Hanna Pulaski (ORCID: https://orcid.org/0000-0001-8092-0066)
- Susan P. Madasu Christudoss
- Neel Patel (ORCID: https://orcid.org/0000-0002-7825-4380)
- Andrew H. Beck (ORCID: https://orcid.org/0000-0002-9978-134X)
- Robert P. Myers
- Anne‐Sophie Sejling
- Sara M. Hoffman
- Hypatia Hou
Institutions
- Program for Appropriate Technology in Health (US)
- Amgen (United States) (US)
- Harvard University (US)
- Inserm (FR)
- Virginia Commonwealth University (US)
- Novo Nordisk (Denmark) (DK)
- Brown University (US)
- Rhode Island Hospital (US)
- Critical Path Institute (US)
- AbbVie (United States) (US)
- University of California San Diego (US)
- Sorbonne Université (FR)
- Massachusetts General Hospital (US)
- Bristol-Myers Squibb (United States) (US)
- Bellevue Hospital Center (US)
- Pinnacle Clinical Research (US)
- Invicro (United States) (US)
- PathAI (United States) (US)
- Gilead Sciences (United States) (US)
- Fondation pour l’innovation en Cadiométabolisme et Nutrition (FR)
- Wheelock College (US)
- Newcastle University (GB)
Publication Details
- Journal
- Nature Medicine
- Published
- 2024-11-04
- DOI
- https://doi.org/10.1038/s41591-024-03301-2
- Citations
- 36
- Primary Topic
- Liver Disease Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 13.92
Funders
- Bristol-Myers Squibb
- Gilead Sciences
- Intercept Pharmaceuticals
- Novo Nordisk