← Issue №20/ week of Nov 15, 2026/Endoscopy

Pre-puncture EUS-based prediction of technical failure during EUS-guided hepaticogastrostomy: development and internal validation of a three-factor model.

From GI Signals issue №20: what this paper found, what it changes, and where it sits against the current standard of care, reviewed by Simon Mathews, MD.

Endoscopy retrospective · n=453 · Nov 12, 2026 · GIE · IF 8.0

Pre-puncture EUS-based prediction of technical failure during EUS-guided hepaticogastrostomy: development and internal validation of a three-factor model.

New evidenceEUScomputer-aided detectionartificial intelligence
Clinical takeawayNo clinical action yet: this is a retrospective model requiring prospective multicenter validation before use in decision-making.
What it foundA three-factor model (bile duct diameter, needle-duct angle, hepatic parenchymal length) predicted first-attempt EUS-HGS failure with AUC 0.932, identifying high-risk patients with a 51.9% failure rate, intermediate-risk with 9.0%, and low-risk with 1.7%. The optimal cutoff probability was 0.130, yielding 86.8% sensitivity and 85.5% specificity.
ContextChallenges current practice by identifying pre-puncture anatomical predictors of EUS-HGS failure, which were previously assessed only post-puncture.
No standard claimed for this paper

Every paper is compared to the standard governing its question. This one is not: either no standard in the corpus matches it, or the comparison did not hold up on review and was withdrawn rather than published unverified. Both are logged.

Ogura T … Liao SC · Gastrointestinal Endoscopy · IF 8.0 · PubMed ↗Permalink
← Read the whole of issue №20 Every paper GI Signals surfaces gets a page like this one. All issues