Comparison of the effects of semaglutide on liver histology in patients with non-alcoholic steatohepatitis cirrhosis between machine learning model assessment and pathologist evaluation
- Liver biopsies evaluated by hepatopathologists are a key method for assessing treatment response in trials of non-alcoholic steatohepatitis (NASH).1,2
- Artificial intelligence has also shown promise in liver biopsy assessment.2
- Identification and assessment of NASH components can be subject to inter- and intra-observer variability, especially for hepatocyte ballooning.3
- This post hoc analysis aimed to assess the effect of semaglutide vs placebo on histological components of NASH as assessed by a pathologist and PathAI’s machine learning (ML) models.
- The analysis used data from a randomized, double-blind, placebo-controlled phase 2 trial investigating once-weekly subcutaneous semaglutide 2.4 mg in patients with NASH and compensated cirrhosis.
- NAFLD Research Center, University of California San Diego, La Jolla, CA, USA;
- Novo Nordisk A/S, Søborg, Denmark;
- PathAI, Inc., Boston, MA, USA;
Loomba et al.