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

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.