Retrospective Study
Copyright ©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastrointest Oncol. Apr 15, 2025; 17(4): 100089
Published online Apr 15, 2025. doi: 10.4251/wjgo.v17.i4.100089
Machine learning for modeling and identifying risk factors of pancreatic fistula
Mikhail B Potievskiy, Leonid O Petrov, Sergei A Ivanov, Pavel V Sokolov, Vladimir S Trifanov, Nikolai A Grishin, Ruslan I Moshurov, Peter V Shegai, Andrei D Kaprin
Mikhail B Potievskiy, Center for Clinical Trials, Center for Innovative Radiological and Regenerative Technologies, FSBI “National Medical Research Radiological Center” of the Ministry of Health of the Russian Federation, Obninsk 249036, Kaluzhskaya Oblast, Russia
Leonid O Petrov, Department of Radiation and Surgical Treatment of Abdominal Diseases, A. Tsyb Medical Radiological Center, FSBI “National Medical Research Radiological Center” of the Ministry of Health of the Russian Federation, Obninsk 249036, Kaluzhskaya Oblast, Russia
Sergei A Ivanov, Andrei D Kaprin, Department of Administration, FSBI “National Medical Research Radiological Center” of the Ministry of Health of the Russian Federation, Obninsk 249036, Kaluzhskaya Oblast, Russia
Pavel V Sokolov, Department of Operation Unit, FSBI “National Medical Research Radiological Center” of the Ministry of Health of the Russian Federation, Obninsk 249036, Kaluzhskaya Oblast, Russia
Vladimir S Trifanov, Nikolai A Grishin, Ruslan I Moshurov, Department of Abdominal Oncology, P. Herzen Moscow Oncological Institute, FSBI “National Medical Research Radiological Center” of the Ministry of Health of the Russian Federation, Obninsk 249036, Kaluzhskaya Oblast, Russia
Peter V Shegai, Center for Innovative Radiological and Regenerative Technologies, FSBI “National Medical Research Radiological Center” of the Ministry of Health of the Russian Federation, Obninsk 249036, Kaluzhskaya Oblast, Russia
Andrei D Kaprin, Department of Urology and Operative Nephrology with Course of Oncology, Medical Faculty, Medical Institute, Peoples’ Friendship University of Russia, Moscow 117198, Moskva, Russia
Author contributions: Potievskiy MB, Petrov LO, Sokolov PV, Grishin NA, and Moshurov RI designed the study and collected the data; Trifanov VS, Ivanov SA, Shegai PV, and Kaprin AD contributed to study design and revised the manuscript; Potievskiy MB developed the machine learning tools and wrote the manuscript draft.
Institutional review board statement: The aforementioned project has been reviewed and approved by the Review Board, based on the Declaration of Helsinki, the manuscript was reviewed by members of the Review Board and recommended for publication in a peer-reviewed journal.
Informed consent statement: This is a retrospective study. The FSBI NMRRC Research Ethics Committee has confirmed that no ethical approval is required.
Conflict-of-interest statement: The authors declare that they have no conflict of interest.
Data sharing statement: The raw data supporting the conclusions of this article will be made available by the authors on request. The code is publicly available at GitHub: https://github.com/MikhailPot/POPF.
Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Mikhail B Potievskiy, MD, MSc, Research Scientist, Center for Clinical Trials, Center for Innovative Radiological and Regenerative Technologies, FSBI “National Medical Research Radiological Center” of the Ministry of Health of the Russian Federation, Koroleva 4, Obninsk 249036, Kaluzhskaya Oblast, Russia. potievskiymikhail@gmail.com
Received: August 7, 2024
Revised: December 5, 2024
Accepted: February 5, 2025
Published online: April 15, 2025
Processing time: 230 Days and 4.7 Hours
Abstract
BACKGROUND

Pancreatic fistula is the most common complication of pancreatic surgeries that causes more serious conditions, including bleeding due to visceral vessel erosion and peritonitis.

AIM

To develop a machine learning (ML) model for postoperative pancreatic fistula and identify significant risk factors of the complication.

METHODS

A single-center retrospective clinical study was conducted which included 150 patients, who underwent pancreatoduodenectomy. Logistic regression, random forest, and CatBoost were employed for modeling the biochemical leak (symptomless fistula) and fistula grade B/C (clinically significant complication). The performance was estimated by receiver operating characteristic (ROC) area under the curve (AUC) after 5-fold cross-validation (20% testing and 80% training data). The risk factors were evaluated with the most accurate algorithm, based on the parameter “Importance” (Im), and Kendall correlation, P < 0.05.

RESULTS

The CatBoost algorithm was the most accurate with an AUC of 74%-86%. The study provided results of ML-based modeling and algorithm selection for pancreatic fistula prediction and risk factor evaluation. From 14 parameters we selected the main pre- and intraoperative prognostic factors of all the fistulas: Tumor vascular invasion (Im = 24.8%), age (Im = 18.6%), and body mass index (Im = 16.4%), AUC = 74%. The ML model showed that biochemical leak, blood and drain amylase level (Im = 21.6% and 16.4%), and blood leukocytes (Im = 11.2%) were crucial predictors for subsequent fistula B/C, AUC = 86%. Surgical techniques, morphology, and pancreatic duct diameter less than 3 mm were insignificant (Im < 5% and no correlations detected). The results were confirmed by correlation analysis.

CONCLUSION

This study highlights the key predictors of postoperative pancreatic fistula and establishes a robust ML-based model for individualized risk prediction. These findings contribute to the advancement of personalized perioperative care and may guide targeted preventive strategies.

Keywords: Pancreatoduodenectomy; Postoperative pancreatic fistula; Risk factors; Machine learning; Precision oncology

Core Tip: The study provides a machine-learning approach with a focus on medical data evaluation, based on algorithm selection. The best algorithm was CatBoost. Young age and large tumor size were associated with fistula B/C and biochemical leak development. Blood and drain amylase level increases and biochemical leak were the major risk factors of subsequent fistula B/C development.