Predicting the risk of gastroparesis in critically ill patients after CME using an interpretable machine learning algorithm - a 10-year multicenter retrospective study.

Background: Gastroparesis following complete mesocolic excision (CME) can precipitate a cascade of severe complications, which may significantly hinder postoperative recovery and diminish the patient's quality of life. In the present study, four advanced machine learning algorithms-Extreme Gradient Boosting (XGBoost), Random Forest (RF), Support Vector Machine (SVM), and Methods: We gathered 34 feature variables from a cohort of 1,097 colon cancer patients, including 87 individuals who developed gastroparesis post-surgery, across multiple hospitals, and applied a range of machine learning algorithms to construct the predictive model. To assess the model's generalization performance, we employed 10-fold cross-validation, while the receiver operating characteristic (ROC) curve was utilized to evaluate its discriminative capacity. Additionally, calibration curves, decision curve analysis (DCA), and external validation were integrated to provide a comprehensive evaluation of the model's clinical applicability and utility. Results: Among the four predictive models, the XGBoost algorithm demonstrated superior performance. As indicated by the ROC curve, XGBoost achieved an area under the curve (AUC) of 0.939 in the training set and 0.876 in the validation set, reflecting exceptional predictive accuracy. Notably, in the Conclusion: The onset of postoperative gastroparesis in colon cancer patients remains an elusive challenge to entirely prevent. However, the prediction model developed in this study offers valuable assistance to clinicians in identifying key high-risk factors for gastroparesis, thereby enhancing the quality of life and survival outcomes for these patients.