Advanced Non-linear Modeling and Explainable Artificial Intelligence Techniques for Predicting 30-Day Complications in Bariatric Surgery: A Single-Center Study

Purpose Metabolic bariatric surgery (MBS) became integral to managing severe obesity. Understanding surgical risks associated with MBS is crucial. Different scores, such as the Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program (MBSAQIP), aid in patient selection and outcome prediction. This study aims to evaluate machine learning (ML) models performance in predicting 30-day post-operative complications and compare them with the MBSAQIP risk score. Materials and Methods We retrospectively evaluated 424 consecutive patients (2006–2020) who underwent MBS, analyzing 30-day surgical complications according to Clavien-Dindo Classification. ML models, including logistic regression, support vector machine, random forest, k-nearest neighbors, multi-layer perceptron, and extreme gradient boosting, were analyzed and compared to MBSAQIP risk score. Performance was measured by area under receiver operating characteristic curve (AUROC) analysis. Results Random forest showed the highest AUROC in the training (AUROC = 0.94) and the validation set (AUROC = 0.88). ML algorithms, particularly random forest, outperformed MBSAQIP in predicting negative 30-day outcomes in both the training and validation sets (AUROC = 0.64, DeLong’s Test p < 0.001). The five features that were more relevant for the prediction of the random forest model were serum alkaline phosphatase, platelet count, triglycerides, glycated hemoglobin, and albumin. Conclusion We developed several ML model that identifies patients at risk for 30-day complications after MBS. Among these, random forest is the most performing one and outperforms the already established MBSAQIP score. This model could increase the identification of high-risk patients before MBS.