Author information

• ¹PathAI, Boston, MA, USA.
• ²Gilead Sciences, Inc, Foster City, CA, USA.
• ³Lahey Hospital & Medical Center (emeritus), Burlington, MA, USA.
• ⁴University Gastroenterology, Portsmouth, RI, USA.
• ⁵Warren Alpert Medical School of Brown University, Providence, RI, USA.
• ⁶Translational & Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, UK.
• ⁷Department of Medicine and Therapeutics, The Chinese University of Hong Kong, Hong Kong.
• ⁸Division of Gastroenterology and Hepatology, Medical University of Vienna, Austria.
• ⁹Texas Liver Institute, UT Health San Antonio, Texas, United States.
• ¹⁰Pinnacle Clinical Research, San Antonio, TX, USA, Boston.
• ¹¹Saiseikai Suita Hospital, Suita City, Osaka, Japan.
• ¹²Hospital Universitario Virgen del Rocio, Sevilla, Spain.
• ¹³Department of Medicine, Inova Fairfax Medical Campus, Falls Church, VA, USA.
• ¹⁴Betty and Guy Beatty Center for Integrated Research, Inova Health System, Falls Church, VA, USA.
• ¹⁵NAFLD Research Center, University of California at San Diego, La Jolla, CA, USA.

Abstract

Background & aims: Manual histologic assessment is currently the accepted standard for diagnosing and monitoring disease progression in nonalcoholic steatohepatitis (NASH), but is limited by variability in interpretation and insensitivity to change. Thus, there is a critical need for improved tools to assess liver pathology in order to risk stratify NASH patients and monitor treatment response.

Approach & results: Here, we describe a machine learning (ML)-based approach to liver histology assessment, which accurately characterizes disease severity and heterogeneity, and sensitively quantifies treatment response in NASH. We utilize samples from three randomized controlled trials to build and then validate deep convolutional neural networks to measure key histologic features in NASH including steatosis, inflammation, hepatocellular ballooning, and fibrosis. The ML-based predictions showed strong correlations with expert pathologists and were prognostic of progression to cirrhosis and liver-related clinical events. We developed a new heterogeneity-sensitive metric of fibrosis response, the Deep Learning Treatment Assessment (DELTA) Liver Fibrosis score, which measured anti-fibrotic treatment effects that went undetected by manual pathological staging and was concordant with histologic disease progression.

Conclusions: Our ML method has shown reproducibility, sensitivity, and was prognostic for disease progression demonstrating the power of ML to advance our understanding of disease heterogeneity in NASH, risk stratify affected patients, and facilitate the development of novel therapies.