A Machine Learning Approach to Liver Histological Evaluation Predicts Clinically Significant Portal Hypertension in NASH Cirrhosis

Hepatology. 2021 Dec;74(6):3146-3160. doi: 10.1002/hep.32087.

Abstract

Background and aims: The hepatic venous pressure gradient (HVPG) is the standard for estimating portal pressure but requires expertise for interpretation. We hypothesized that HVPG could be extrapolated from liver histology using a machine learning (ML) algorithm.

Approach and results: Patients with NASH with compensated cirrhosis from a phase 2b trial were included. HVPG and biopsies from baseline and weeks 48 and 96 were reviewed centrally, and biopsies evaluated with a convolutional neural network (PathAI, Boston, MA). Using trichrome-stained biopsies in the training set (n = 130), an ML model was developed to recognize fibrosis patterns associated with HVPG, and the resultant ML HVPG score was validated in a held-out test set (n = 88). Associations between the ML HVPG score with measured HVPG and liver-related events, and performance of the ML HVPG score for clinically significant portal hypertension (CSPH) (HVPG ≥ 10 mm Hg), were determined. The ML-HVPG score was more strongly correlated with HVPG than hepatic collagen by morphometry (ρ = 0.47 vs. ρ = 0.28; P < 0.001). The ML HVPG score differentiated patients with normal (0-5 mm Hg) and elevated (5.5-9.5 mm Hg) HVPG and CSPH (median: 1.51 vs. 1.93 vs. 2.60; all P < 0.05). The areas under receiver operating characteristic curve (AUROCs) (95% CI) of the ML-HVPG score for CSPH were 0.85 (0.80, 0.90) and 0.76 (0.68, 0.85) in the training and test sets, respectively. Discrimination of the ML-HVPG score for CSPH improved with the addition of a ML parameter for nodularity, Enhanced Liver Fibrosis, platelets, aspartate aminotransferase (AST), and bilirubin (AUROC in test set: 0.85; 95% CI: 0.78, 0.92). Although baseline ML-HVPG score was not prognostic, changes were predictive of clinical events (HR: 2.13; 95% CI: 1.26, 3.59) and associated with hemodynamic response and fibrosis improvement.

Conclusions: An ML model based on trichrome-stained liver biopsy slides can predict CSPH in patients with NASH with cirrhosis.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Biopsy
  • Clinical Trials, Phase II as Topic
  • Diagnosis, Differential
  • Female
  • Humans
  • Hypertension, Portal / diagnosis*
  • Hypertension, Portal / etiology
  • Image Processing, Computer-Assisted / methods*
  • Liver / pathology*
  • Liver Cirrhosis / complications*
  • Liver Cirrhosis / pathology
  • Machine Learning
  • Male
  • Middle Aged
  • Non-alcoholic Fatty Liver Disease / complications*
  • Non-alcoholic Fatty Liver Disease / pathology
  • Portal Pressure
  • Prognosis
  • ROC Curve
  • Randomized Controlled Trials as Topic