Artificial Intelligence in Endohepatology: Toward an Intelligent One-Stop Shop for Liver-Directed Endoscopy

In brief

Endohepatology (the implementation of contemporary advanced endoscopy in hepatology) has reached a point where endoscopic ultrasound (EUS)-guided liver biopsy, portal pressure gradient measurement, parenchymal elastography, and variceal screening and therapy can be integrated into a single procedural session of liver-directed endoscopy. Concurrently, artificial intelligence (AI) has revolutionized luminal endoscopy and is advancing rapidly across hepatology imaging, digital pathology, and outcome prediction, yet its translation into the liver-targeted endoscopic workflow has never been synthesized into a coherent domain.

This narrative review maps this evolving convergence of AI and endohepatology across four functional pillars: intelligent hemodynamic assessment, virtual histology, precision tissue acquisition, and integrated risk stratification with therapeutic and decision support. As direct EUS-specific AI evidence in the liver remains limited, the review serves as a forward-looking roadmap for a work in progress that combines adjacent proof-of-concept from AI-assisted EUS in nonhepatic indications, transabdominal AI elastography, and AI histopathology to present possible near-term integration.