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

Authors

Abstract

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. To differentiate demonstrated capabilities from extrapolated and conceptual applications, a three-tier readiness framework is proposed, summarized in a domain table and a clinical-pathway figure. We find that, although the field is still very early-stage, AI has strong potential to transform endohepatology into a single, machine-driven platform for diagnostic and therapeutic success, provided that standardized datasets, prospective validation, and clear regulatory and governance standards are in place. The most immediate value will be in applications with transferable evidence, with hemodynamic and risk-prediction applications following as device-level data accrue.

Tags

Topics