Identifying high-risk patients having ERCP as a day surgery with an online prediction platform: Multicohort validation of a machine learning model

Abstract

Background and study aims

This study aimed to develop a clinical prediction model to assess the 24-hour post-ERCP complication risk in patients with common bile duct stones (CBDs), guiding clinical decision-making for ERCP as a day surgery.

Patients and methods

Retrospective data from The First Hospital of Lanzhou University (2010–2019) and prospective multicenter data on post-ERCP complications (2020–2023) were collected and registered on ClinicalTrials.gov (NCT04234126, NCT04242394). The ADASYN method was used for dataset balancing. Machine learning algorithms, including KNN, XGBoost, RF, SVM, and NB, were compared with traditional models. External validation was performed with retrospective data from other ERCP centers (2015–2017) and The First Hospital of Lanzhou University (2019–2020), with registration under NCT02510495. The optimal model was selected based on the ROC curve (AUC), and an online prediction tool was developed.

Results

A logistic regression (LR) model incorporating seven feature variables—mechanical lithotripsy, pancreatic duct cannulation, bile duct dilation, residual stones, white blood cell count, alanine aminotransferase (ALT) level, and pancreatic duct stent placement—was identified as the optimal model, The model yielded specificity, sensitivity, accuracy, and AUC values of 0.835, 0.655, 0.807, and 0.819 in the external validation set, with a second external validation set providing additional results of 0.799, 0.714, 0.784, and 0.805. Patients were stratified into high- and low-risk groups. An online calculator was developed (https://borujin.shinyapps.io/dynnomapp/).

Conclusions

The results indicate that the proposed LR model, utilizing the top seven risk factors, could serve as an effective tool for predicting occurrence of complications in day surgery.

Keywords

Pancreatobiliary (ERCP/PTCD) - Quality and logistical aspects - Performance and complications - GI surgery

Publikationsverlauf

Eingereicht: 27. Mai 2025

Angenommen nach Revision: 22. Oktober 2025

Accepted Manuscript online:
27. Oktober 2025

Artikel online veröffentlicht:
16. Dezember 2025

• References

• 1 Fujita N, Yasuda I, Endo I. et al. Evidence-based clinical practice guidelines for cholelithiasis 2021. J Gastroenterol 2023; 58: 801-833
• 2 Zhi ZWKZ. Chinese Research Hospitals Association, Committee of Enhanced Recovery After Surgery, China Ambulatory Surgery Alliance. Expert consensus on standardized processes of ambulatory biliary surgery (2018 edition) 2018; 56: 321-327
• 3 Wu CCH, Lim SJM, Khor CJL. Endoscopic retrograde cholangiopancreatography-related complications: risk stratification, prevention, and management. Clin Endosc 2023; 56: 433-445
• 4 Pal P, Ramchandani M. Management of ERCP complications. Best Pract Res Clin Gastroenterol 2024; 69: 101897
• 5 Dumonceau J-M, Kapral C, Aabakken L. et al. ERCP-related adverse events: European Society of Gastrointestinal Endoscopy (ESGE) Guideline. Endoscopy 2020; 52: 127-149
• 6 Cotton PB, Lehman G, Vennes J. et al. Endoscopic sphincterotomy complications and their management: an attempt at consensus. Gastrointest Endosc 1991; 37: 383-393
• 7 Yokoe M, Hata J, Takada T. et al. Tokyo Guidelines 2018: diagnostic criteria and severity grading of acute cholecystitis (with videos). J Hepatobiliary Pancreat Sci 2018; 25: 41-54
• 8 Cotton PB, Eisen GM, Aabakken L. et al. A lexicon for endoscopic adverse events: report of an ASGE workshop. Gastrointest Endosc 2010; 71: 446-454
• 9 Ikuta S, Fujikawa M, Nakajima T. et al. Machine learning approach to predict postpancreatectomy hemorrhage following pancreaticoduodenectomy: a retrospective study. Langenbecks Arch Surg 2024; 409: 29
• 10 Teji JS, Jain S, Gupta SK. et al. NeoAI 1.0: Machine learning-based paradigm for prediction of neonatal and infant risk of death. Comput Biol Med 2022; 147: 105639
• 11 Lin S, Zou Y, Hu J. et al. Development and assessment of machine learning models for predicting recurrence risk after endovascular treatment in patients with intracranial aneurysms. Neurosurg Rev 2022; 45: 1521-1531
• 12 Tse F, Yuan Y, Moayyedi P. et al. Guidewire-assisted cannulation of the common bile duct for the prevention of post-endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis. Cochrane Database Syst Rev 2012; 12: CD009662
• 13 Basile G, Vacante M, Corsaro A. et al. Treatment of acute pancreatitis. Minerva Surg 2025; 80: 236-257
• 14 Dumonceau J-M, Andriulli A, Elmunzer BJ. et al. Prophylaxis of post-ERCP pancreatitis: European Society of Gastrointestinal Endoscopy (ESGE) Guideline - updated June 2014. Endoscopy 2014; 46: 799-815
• 15 Pezzilli R, Romboli E, Campana D. et al. Mechanisms involved in the onset of post-ERCP pancreatitis. JOP 2002; 3: 162-168
• 16 Willems P, Hawes RH, Varadarajulu S. Mechanical lithotripsy for large common bile duct stones: Out of practice or just out of fashion?. Clin Gastroenterol Hepatol 2023; 21: 3197
• 17 French comment on article Digital cholangioscopy-guided laser versus mechanical lithotripsy for large bile duct stone removal after failed papillary large-balloon dilation: a randomized study. Endoscopy 2019; 51: 1106–1107.
• 18 Fujita K, Yazumi S, Matsumoto H. et al. Multicenter prospective cohort study of adverse events associated with biliary endoscopic retrograde cholangiopancreatography: Incidence of adverse events and preventive measures for post-endoscopic retrograde cholangiopancreatography pancreatitis. Digest Endosc 2022; 34: 1198-1204
• 19 García-Cano J, Viñuelas Chicano M, Del Moral Martínez M. et al. Pancreatic stent insertion after an unintentional guidewire cannulation of the pancreatic duct during ERCP. Rev Esp Enferm Dig 2018; 110: 416-420
• 20 Elfant AB, Bourke MJ, Alhalel R. et al. A prospective study of the safety of endoscopic therapy for choledocholithiasis in an outpatient population. Am J Gastroenterol 1996; 91: 1499-1502
• 21 Marçal MVL, Thuler FPBM, Ferrari AP. Endoscopic retrograde cholangiopancreatography can be performed safely in ambulatory centers. Arq Gastroenterol 2005; 42: 4-8
• 22 Katsinelos P, Kountouras J, Chatzimavroudis G. et al. Outpatient therapeutic endoscopic retrograde cholangiopancreatography is safe in patients aged 80 years and older. Endoscopy 2011; 43: 128-133