Machine learning models to predict the recurrence of common bile duct stones after ERCP
Xu Han, Mujie Ye, Ye Tian, Qin Long, Qiyun Tang, Hong Zhu · 2026
Read Machine learning models to predict the recurrence of common bile duct stones after ERCP by Xu Han, Mujie Ye, Ye Tian, Qin Long, Qiyun Tang, Hong Zhu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13479889.txt.
Description
Xu Han and colleagues present a 2026 study building machine learning models to predict whether bile duct stones return after endoscopic removal. Recurrence is common enough that follow-up planning matters, and a risk estimate could target surveillance. Records from 1,130 patients were split seventy-thirty into training and test sets.
Automated feature selection and logistic regression narrowed the predictors to eight risk factors. Three model families were tuned by random search with ten-fold cross-validation: random forest, gradient boosting, and logistic regression. Accuracy measures and decision curve analysis compared their clinical usefulness. The winning model was then opened up with Shapley explanations, which show how much each factor pushes an individual prediction up or down.
Catalog record
| CREATOR | Xu Han, Mujie Ye, Ye Tian, Qin Long, Qiyun Tang, Hong Zhu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45530 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |