Machine Learning Approaches for the Prediction of Postoperative Major Complications in Patients Undergoing Surgery for Bowel Obstruction

Abstract

first_pagesettingsOrder Article Reprints Open AccessArticle Machine Learning Approaches for the Prediction of Postoperative Major Complications in Patients Undergoing Surgery for Bowel Obstruction by Alessandro D. Mazzotta 1,2ORCID,Elisa Burti 3,Francesco Andrea Causio 4,*ORCID,Alex Orlandi 5,Silvia Martinelli 4,Mattia Longaroni 6,Tiziana Pinciroli 7,Tarek Debs 8,Gianluca Costa 9ORCID,Michelangelo Miccini 10ORCID,Paolo Aurello 3 andNiccolò Petrucciani 3 1 Department of Surgery, Vannini General Hospital, Oncological and General Surgery, 00177 Rome, Italy 2 The BioRobotics Institute, Sant’Anna School of Advanced Studies, 56127 Pisa, Italy 3 Department of Medical and Surgical Sciences and Translational Medicine, Division of General and Hepatobiliary Surgery, St. Andrea Hospital, Sapienza University of Rome, 00185 Roma, Italy 4 Section of Hygiene, Department of Life Sciences and Public Health, Università Cattolica del Sacro Cuore, 00168 Rome, Italy 5 EIT Digital Master School, Polytech Nice Sophia, 06410 Biot, France 6 Department of Surgery, Santa Maria della Misericordia Hospital, University of Perugia, 06123 Perugia, Italy 7 MIT Professional Education, Massachusetts Institute of Technology, Cambridge, MA 02139, USA 8 Département de Chirurgie Digestive, Centre Hospitalier Universitaire de Nice, CHU Nice, 06000 Nice, France 9 Department of Life Science, Health, and Health Professions, Link Campus University, 00165 Rome, Italy 10 Department of Surgery, Sapienza University of Rome, 00185 Roma, Italy * Author to whom correspondence should be addressed. J. Pers. Med. 2024, 14(10), 1043; https://doi.org/10.3390/jpm14101043 Submission received: 27 July 2024 / Revised: 13 September 2024 / Accepted: 25 September 2024 / Published: 8 October 2024 (This article belongs to the Special Issue Artificial Intelligence Applied to Clinical Practice) Downloadkeyboard_arrow_down Browse Figures Review Reports Versions Notes

Abstract Background: Performing emergency surgery for bowel obstruction continues to place a significant strain on the healthcare system. Conventional assessment methods for outcomes in bowel obstruction cases often concentrate on isolated factors, and the evaluation of results for individuals with bowel obstruction remains poorly studied. This study aimed to examine the risk factors associated with major postoperative complications. Methods: We retrospectively analyzed 99 patients undergoing surgery from 2015 to 2022. We divided the patients into two groups: (1) benign-related obstruction (n = 68) and (2) cancer-related obstruction (n = 31). We used logistic regression, KNN, and XGBOOST. We calculated the receiver operating characteristic curve and accuracy of the model. Results: Colon obstructions were more frequent in the cancer group (p = 0.005). Operative time, intestinal resection, and stoma were significantly more frequent in the cancer group. Major complications were at 41% for the cancer group vs. 20% in the benign group (p = 0.03). Uni- and multivariate analysis showed that the significant risk factors for major complications were cancer-related obstruction and CRP. The best model was KNN, with an accuracy of 0.82. Conclusions: Colonic obstruction is associated with tumor-related blockage. Malignant cancer and an increase in C-reactive protein (CRP) are significant risk factors for patients who have undergone emergency surgery due to major complications. KNN could improve the process of counseling and the perioperative management of patients with intestinal obstruction in emergency settings.