Machine Learning-Based Prediction of Short-Term Mortality After Coronary Artery Bypass Grafting: A Retrospective Cohort Study

Le résumé fourni par la source

Objectives: This study aimed to develop and validate a machine learning (ML) algorithm to predict 30-day mortality following isolated coronary artery bypass grafting (CABG) and to compare its performance against the widely used European System for Cardiac Operative Risk Evaluation II (EuroSCORE II) risk prediction model. Methods: In this retrospective study, we included consecutive adult patients who underwent isolated CABG between January 2009 and December 2022. Three predictive models were compared: (1) EuroSCORE II variables alone (baseline), (2) EuroSCORE II combined with additional preoperative variables (Model I), and (3) EuroSCORE II plus preoperative and postoperative variables available within five days after surgery (Model II). Logistic Regression (LR), Random Forest (RF), and Neural Network (NN) were employed and validated. Predictive accuracy was assessed using the area under the receiver operating characteristic curve (AUC) and specificity at 85% sensitivity. Results: Among the 3483 patients included, the mean age was 66.2 years (SD 10.3), with an overall 30-day mortality rate of 2.5%. The mean EuroSCORE II was 3.12 (SD 4.8). Integrating additional preoperative variables significantly improved specificity at 85% sensitivity for both random forest (from 42% to 51%; p < 0.001) and NN (from 28% to 43%; p < 0.001) but not for LR. Incorporating preoperative along with postoperative data (Model II) further improved specificity to approximately 70% across all ML methods (p < 0.001). The most influential postoperative predictors included kidney failure, pulmonary complications, and myocardial infarction. Conclusions: ML models incorporating preoperative and postoperative variables significantly outperform the traditional EuroSCORE II in predicting short-term mortality following isolated CABG.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.