AI-based histologic scoring enables automated and reproducible assessment of enrollment criteria and endpoints in NASH clinical trials

• DOI: 10.1101/2023.04.20.23288534
• Publication Date: 2023-04-25T18:01:58Z
• Authors: Janani S. Iyer; Harsha Pokkalla; Charles Biddle-Snead; Oscar Carrasco-Ze...; Mary Lin; Zahil Shanis; Quang Le; Dinkar Juyal; Maryam Pouryahya; Aryan Pedawi; Sara Hoffman; Hunter Elliott; Kenneth Leidal; Robert P. Myers; Chuhan Chung; Andrew N. Billin; Timothy R. Watkins; Murray Resnick; Katy Wack; Jon Glickman; Alastair D. Burt; Rohit Loomba; Arun J. Sanyal; Michael C. Montalto; Andrew H. Beck; Amaro Taylor-Weiner; Ilan Wapinski
• Keywords: Article; 3. Good health

ABSTRACTClinical trials in nonalcoholic steatohepatitis (NASH) require histologic scoring for assessment of inclusion criteria and endpoints. However, guidelines for scoring key features have led to variability in interpretation, impacting clinical trial outcomes. We developed an artificial intelligence (AI)-based measurement (AIM) tool for scoring NASH histology (AIM-NASH). AIM-NASH predictions for NASH Clinical Research Network (CRN) grades of necroinflammation and stages of fibrosis aligned with expert consensus scores and were reproducible. Continuous scores produced by AIM-NASH for key histological features of NASH correlated with mean pathologist scores and with noninvasive biomarkers and strongly predicted patient outcomes. In a retrospective analysis of the ATLAS trial, previously unmet pathological endpoints were met when scored by the AIM-NASH algorithm alone. Overall, these results suggest that AIM-NASH may assist pathologists in histologic review of NASH clinical trials, reducing inter-rater variability on trial outcomes and offering a more sensitive and reproducible measure of patient therapeutic response.