Classification of Biliary Strictures Using Real-Time Cholangioscopy Artificial Intelligence: The SMART-AI Trial

Neil B Marya; Patrick D Powers; Matthew Marcello; Prashanth Rau; Navine Nasser-Ghodsi; Christopher Marshall; Jaroslav Zivny; Jad P AbiMansour; Vinay Chandrasekhara

doi:10.1016/j.cgh.2026.03.033

Classification of Biliary Strictures Using Real-Time Cholangioscopy Artificial Intelligence: The SMART-AI Trial

Clin Gastroenterol Hepatol. 2026 Apr 9:S1542-3565(26)00245-4. doi: 10.1016/j.cgh.2026.03.033. Online ahead of print.

Authors

Neil B Marya¹, Patrick D Powers², Matthew Marcello³, Prashanth Rau³, Navine Nasser-Ghodsi³, Christopher Marshall³, Jaroslav Zivny³, Jad P AbiMansour⁴, Vinay Chandrasekhara⁴

Affiliations

¹ Division of Gastroenterology, UMass Chan Medical School, Worcester, Massachusetts; Program in Digital Medicine, UMass Chan Medical School, Worcester, Massachusetts. Electronic address: neil.marya@gmail.com.
² Division of Gastroenterology, UMass Chan Medical School, Worcester, Massachusetts; Program in Digital Medicine, UMass Chan Medical School, Worcester, Massachusetts.
³ Division of Gastroenterology, UMass Chan Medical School, Worcester, Massachusetts.
⁴ Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester Minnesota.

PMID: 41966465
DOI: 10.1016/j.cgh.2026.03.033

Abstract

Background & aims: Sampling techniques have poor accuracy for classifying biliary strictures as benign or malignant. Previously, a cholangioscopy artificial intelligence (AI) outperformed sampling techniques based solely on analysis of previously recorded cholangioscopy footage. The aim of this single-center, prospective trial was to compare the performance of a real-time cholangioscopy AI to both sampling techniques and human observers for the task of biliary stricture classification.

Methods: A cholangioscopy AI computer connected directly to a cholangioscope console. The computer analyzed the cholangioscopy video stream during procedures for suspected biliary strictures. The primary outcome of the study was comparison of the performance of cholangioscopy AI to sampling techniques-brush cytology and transpapillary forceps biopsy-for biliary stricture classification. Secondary outcomes included comparison of the AI classification performance to that of 14 human observers (separated into junior-level and experienced-level cohorts) who reviewed the cholangioscopy footage.

Results: A total of 41 patients were enrolled in the trial and had biliary strictures analyzed by cholangioscopy AI. For the classification of strictures, the AI had greater classification accuracy than standard sampling techniques (87.8% vs 67.4%; P = .043). Additionally, the cholangioscopy AI was significantly more accurate for biliary stricture classification than both junior-level (87.8% vs 61.5%; P = .001) and experienced endoscopists (87.8% vs 63.1%; P = .011).

Conclusions: This trial demonstrates that sampling techniques and human assessment of biliary strictures are flawed and there may be a benefit to the use of a cholangioscopy AI system to aid in biliary stricture classification.

Clinicaltrials: gov, Number: NCT05779436.

Keywords: Artificial Intelligence; Biliary Tract Malignancy; Cholangiocarcinoma; Cholangioscopy; ERCP.

Associated data

ClinicalTrials.gov/NCT05779436