Interpretable machine learning to predict postoperative adverse outcomes in cardiac surgery

Background Cardiac surgery is associated with significant mortality and complication risks. This study aims to develop an interpretable machine learning (ML) model to predict adverse outcomes (AOs) after cardiac surgery with high accuracy, and to uncover the underlying relationships between relevant important characteristics and predicted outcomes, providing robust support for improving patient prognosis. Methods Patients who underwent cardiopulmonary bypass (CPB) cardiac surgery between January 2013 and December 2022 at a tertiary hospital were included. Perioperative data were collected, and a predictive model was constructed using the light gradient boosting machine (LightGBM) algorithm. This model was compared with the European system for cardiac operative Risk evaluation (EuroSCORE). Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC) on a validation dataset. Additionally, counterfactual explanations (CE), an explainable artificial intelligence technique, were employed to enhance the model's applicability and credibility in real-world clinical settings. Results A total of 3,270 patients who underwent cardiac surgery under CPB were included in this study, of which 203 experienced AOs postoperatively. The LightGBM model built on perioperative data demonstrated good predictive performance (AUROC = 0.807), outperforming the traditional EuroSCORE assessment system (AUROC = 0.722). The application of the CE method to the ML model indicated that characteristics such as initial B-type natriuretic peptide (BNP) levels upon intensive care unit (ICU) admission, aortic cross-clamp time, CPB duration, initial urea levels upon ICU admission, and operation duration were key predictors of postoperative AOs. Conclusion The ML model shows potential in improving risk assessment for AOs after cardiac surgery in patients. The application of CE provides the model with more detailed and practical interpretability, enhancing the credibility of its predictions and promoting transparency and personalization in the clinical decision-making process.