Subscribe free

HPB & Spleen ·

Machine learning distinguishes MD-IPMN from chronic pancreatitis

A new model helps surgeons accurately differentiate main-duct intraductal papillary mucinous neoplasms from chronic pancreatitis when imaging results are unclear.

  • Among 123 patients, intraductal nodules were found in 20% of MD-IPMN cases vs 2.4% in chronic pancreatitis (p=0.003).
  • Ductal stones were present in 77.1% of chronic pancreatitis cases compared to just 2.5% in MD-IPMN (p<0.001).

The model shows high accuracy (AUC of 0.946; F1-score of 0.879) and remains reliable even in stone-negative scenarios.

  • A web-based tool is available to aid clinical decision-making and standardize evaluations.

Journal Article by Li J, Prabhakaran SD (…) Akshintala VS et 13 al. in Gastrointest Endosc

Copyright © 2026. Published by Elsevier Inc.

read the whole article in Gastrointest Endosc

open it in PubMed

Summaries are written to help you decide what to read. They do not replace the full paper.

Free · 5 minutes a day

Get every new paper in HPB & Spleen.

Plus the Daily Selection: the five most relevant papers of the day, each cut to its key points.

Specialty newsletters: every new paper in your field, as a list of titles linked to the source. Daily Selection: the five that matter, cut to their key points.

FreeNo spamOne-click unsubscribe

More in HPB & Spleen

The latest stitches

All papers in HPB & Spleen →