Leveraging machine learning to enhance postoperative risk assessment in coronary artery bypass grafting patients with unprotected left main disease: a retrospective cohort study

Abstract

Background: Risk stratification for patients undergoing coronary artery bypass surgery (CABG) for left main coronary artery (LMCA) disease is essential for informed decision-making. This study explored the potential of machine learning (ML) methods to identify key risk factors associated with mortality in this patient group.

Methods: This retrospective cohort study was conducted on 866 patients from the Gulf Left Main Registry who presented between 2015 and 2019. The study outcome was hospital all-cause mortality. Various machine learning models [logistic regression, random forest (RF), k-nearest neighbor, support vector machine, naïve Bayes, multilayer perception, boosting] were used to predict mortality, and their performance was measured using accuracy, precision, recall, F1 score, and area under the receiver operator characteristic curve (AUC).

Results: Nonsurvivors had significantly greater EuroSCORE II values (1.84 (10.08-3.67) vs. 4.75 (2.54-9.53) %, P <0.001 for survivors and nonsurvivors, respectively). The EuroSCORE II score significantly predicted hospital mortality (OR: 1.13 (95% CI: 1.09-1.18), P <0.001), with an AUC of 0.736. RF achieved the best ML performance (accuracy=98, precision=100, recall=97, and F1 score=98). Explainable artificial intelligence using SHAP demonstrated the most important features as follows: preoperative lactate level, emergency surgery, chronic kidney disease (CKD), NSTEMI, nonsmoking status, and sex. QLattice identified lactate and CKD as the most important factors for predicting hospital mortality this patient group.

Conclusion: This study demonstrates the potential of ML, particularly the Random Forest, to accurately predict hospital mortality in patients undergoing CABG for LMCA disease and its superiority over traditional methods. The key risk factors identified, including preoperative lactate levels, emergency surgery, chronic kidney disease, NSTEMI, nonsmoking status, and sex, provide valuable insights for risk stratification and informed decision-making in this high-risk patient population. Additionally, incorporating newly identified risk factors into future risk-scoring systems can further improve mortality prediction accuracy.

Figure 1

The study flow diagram showing the steps for building machine learning models. AI, artificial intelligence; ANN, artificial neural network; CABG, coronary artery bypass grafting; KNN, k-nearest neighbor; LMCA, left main coronary artery; SVM, support vector machine.

Figure 2

Receiver operating characteristic (ROC) curve of the association between EuroSCORE II and hospital mortality. The area under the curve (AUC) is 0.736.

Figure 3

Confusion matrix of the random forest model predicting in-hospital mortality after CABG for unprotected left main coronary artery disease.

Figure 4

(A) Feature importance ranking in the random forest model for predicting in-hospital mortality after CABG for left main coronary artery disease using SHAP (B) SHAP feature importance for predicting in-hospital mortality after CABG. Red indicates a greater SHAP value (greater influence on prediction), and the position on the X-axis represents the feature value (higher on the right). Positive SHAP values increase mortality prediction, while negative values increase survival prediction. AF, atrial fibrillation; CKD, chronic kidney disease; EF, ejection fraction; LM, left main; MI, myocardial infarction; MR, mitral regurgitation; NSTEMI, non-ST-elevation myocardial infarction; PAP, pulmonary artery pressure; Trop, troponin.

Figure 5

Quantum graph for factors predicting hospital mortality in CABG patients with left main coronary artery disease. CKD, chronic kidney disease.