The summaries are free for public
use. The Chronic Liver Disease
Foundation will continue to add and
archive summaries of articles deemed
relevant to CLDF by the Board of
Trustees and its Advisors.
Abstract Details
A Machine Learning Approach to Liver Histological Evaluation Predicts Clinically Significant Portal Hypertension in NASH Cirrhosis
Hepatology. 2021 Aug 1. doi: 10.1002/hep.32087. Online ahead of print.
Jaime Bosch12, Chuhan Chung3, Oscar M Carrasco-Zevallos4, Stephen A Harrison5, Manal F Abdelmalek6, Mitchell L Shiffman7, Don C Rockey8, Zahil Shanis4, Dinkar Juyal4, Harsha Pokkalla4, Quang Huy Le4, Murray Resnick4, Michael Montalto4, Andrew H Beck4, Ilan Wapinski4, Ling Han3, Catherine Jia3, Zachary Goodman9, Nezam Afdhal10, Robert P Myers3, Arun J Sanyal11
Author information
1Department of Biomedical Research, University of Bern, Switzerland.
2University of Barcelona-IDIBAPS, Spain.
3Gilead Sciences, Inc, Foster City.
4PathAI, Inc, Boston.
5Pinnacle Clinical Research, San Antonio.
6Duke University, Durham.
7Bon Secours Liver Institute of Richmond.
8Medical University of South Carolina, Charleston.
9Inova Fairfax Hospital, Falls Church.
10Beth Israel Deaconess Medical Center, Harvard Medical School, Boston.
11Virginia Commonwealth University, Richmond.
Abstract
Background: 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.
Methods: NASH patients 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.
Results: 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 mmHg) and elevated HVPG (5.5-9.5 mmHg), and CSPH (median: 1.51 vs 1.93 vs 2.60; all p<0.05). The AUROCs (95%CI) of the ML HVPG score for CSPH were 0.85 (0.80,0.90) and 0.76 (0.68,85) in the training and test sets, respectively. Discrimination of the ML HVPG score for CSPH improved with addition of a ML parameter for nodularity, ELF, platelets, AST, and bilirubin (AUROC in test set: 0.85;95%CI 0.78,0.92). While 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: A ML-model based on trichrome-stained liver biopsy slides can predict CSPH in NASH patients with cirrhosis.