Copyright
©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
Machine learning model-based prediction of postpancreatectomy acute pancreatitis following pancreaticoduodenectomy: A retrospective cohort study
Ji-Ming Ma, Peng-Fei Wang, Liu-Qing Yang, Jun-Kai Wang, Jian-Ping Song, Yu-Mei Li, Yan Wen, Bing-Jun Tang, Xue-Dong Wang
Ji-Ming Ma, Peng-Fei Wang, Yan Wen, Bing-Jun Tang, Xue-Dong Wang, Hepatopancreatobiliary Center, Beijing Tsinghua Changgung Hospital, Beijing 102218, China
Liu-Qing Yang, Department of Information Administration, Beijing Tsinghua Changgung Hospital, Beijing 102218, China
Jun-Kai Wang, Department of Radiology, Beijing Tsinghua Changgung Hospital, Beijing 102218, China
Jian-Ping Song, Organ Transplantation, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan 250012, Shandong Province, China
Yu-Mei Li, Department of Otorhinolaryngology, Xiangyang No. 1 People’s Hospital, Xiangyang 441000, Hubei Province, China
Co-first authors: Ji-Ming Ma and Peng-Fei Wang.
Co-corresponding authors: Bing-Jun Tang and Xue-Dong Wang.
Author contributions: Ma JM and Wang PF designed the study, collected the data, and wrote the first draft of the manuscript, they contributed equally to this manuscript as co-first authors; Yang LQ and Li YM offered statistical analysis and model analysis; Wang JK assisted in reading computed tomography scans; Song JP revised the article, and designed the study; Wen Y offered language support and writing assistance; Tang BJ and Wang XD revised the article, and the performed the research, and they contributed equally to this manuscript as co-corresponding authors.
Supported by the National Natural Science Foundation of China, No. 81930119.
Institutional review board statement: This retrospective cohort study was reviewed and approved by the Research Department and the Ethics Committee of Beijing Tsinghua Changgung Hospital, affiliated with Tsinghua University, No. 24017-7-01.
Informed consent statement: The need for patient consent was waived due to the retrospective nature of the study.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
STROBE statement: The authors have read the STROBE Statement-checklist of items, and the manuscript was prepared and revised according to the STROBE Statement-checklist of items.
Data sharing statement: The data that support the findings of this study are available from the author, Ji-Ming Ma, upon reasonable request.
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: Xue-Dong Wang, MD, Hepatopancreatobiliary Center, Beijing Tsinghua Changgung Hospital, No. 168 Litang Road, Changping District, Beijing 102218, China.
wxda01026@btch.edu.cn
Received: October 7, 2024
Revised: November 7, 2024
Accepted: January 3, 2025
Published online: February 28, 2025
Processing time: 107 Days and 11 Hours
BACKGROUND
The International Study Group of Pancreatic Surgery has established the definition and grading system for postpancreatectomy acute pancreatitis (PPAP). There are no established machine learning models for predicting PPAP following pancreaticoduodenectomy (PD).
AIM
To explore the predictive model of PPAP, and test its predictive efficacy to guide the clinical work.
METHODS
Clinical data from consecutive patients who underwent PD between 2016 and 2024 were retrospectively collected. An analysis of PPAP risk factors was performed, various machine learning algorithms [logistic regression, random forest, gradient boosting decision tree, extreme gradient boosting, light gradient boosting machine, and category boosting (CatBoost)] were utilized to develop predictive models. Recursive feature elimination was employed to select several variables to achieve the optimal machine algorithm.
RESULTS
The study included 381 patients, of whom 88 (23.09%) developed PPAP. PPAP patients exhibited a significantly higher incidence of postoperative pancreatic fistula (55.68% vs 14.68%, P < 0.001), grade C postoperative pancreatic fistula (9.09% vs 1.37%, P = 0.001). The CatBoost algorithm outperformed other algorithms with a mean area under the receiver operating characteristic curve of 0.859 [95% confidence interval (CI): 0.814-0.905] in the training cohort and 0.822 (95%CI: 0.717-0.927) in the testing cohort. According to shapley additive explanations analysis, pancreatic texture, main pancreatic duct diameter, body mass index, estimated blood loss, and surgery time were the most important variables based on recursive feature elimination. The CatBoost algorithm based on selected variables demonstrated superior performance, with an area under the receiver operating characteristic curve of 0.837 (95%CI: 0.788-0.886) in the training cohort and 0.812 (95%CI: 0.697-0.927) in the testing cohort.
CONCLUSION
We developed the first machine learning-based predictive model for PPAP following PD. This predictive model can assist surgeons in anticipating and managing this complication proactively.
Core Tip: We demonstrate a novel machine learning algorithm for predicting postpancreatectomy acute pancreatitis, achieving excellent performance. The model’s coherent interpretation provides clinical utility in the management and treatment of patients following pancreaticoduodenectomy. This study explains the serious harm caused by such complications and establishes a possible effective preventive measure, providing assistance for clinical work.
