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% confidence interval: 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.
METHODS: The Gulf-CS registry included 1,513 patients with AMI-CS diagnosed between January 2020 and December 2022.
RESULTS: The incidence of AMI-CS was 4.1% (1513/37379). The median age was 60 years. The most common presentation was ST-elevation MI (73.83%). In-hospital mortality was 45.5%. Majority of patients were in SCAI stage D and E (68.94%). Factors associated with hospital mortality were previous coronary artery bypass graft (OR:2.49; 95%CI: 1.321-4.693), cerebrovascular accident (OR:1.621, 95%CI: 1.032-2.547), chronic kidney disease (OR:1.572; 95%CI1.158-2.136), non-ST-elevation MI (OR:1.744; 95%CI: 1.058-2.873), cardiac arrest (OR:5.702; 95%CI: 3.640-8.933), SCAI stage D and E (OR:19.146; 95CI%: 9.902-37.017), prolonged QRS (OR:10.012; 95%CI: 1.006-1.019), right ventricular dysfunction (OR:1.679; 95%CI: 1.267-2.226) and ventricular septal rupture (OR:6.008; 95%CI: 2.256-15.998). Forty percent had invasive hemodynamic monitoring, 90.02% underwent revascularization, and 45.80% received mechanical circulatory support (41.31% had Intra-Aortic Balloon Pump and 14.21% had Extracorporeal Membrane Oxygenation/Impella devices). Survival at 12 months was 51.49% (95% CI: 46.44- 56.29%).
CONCLUSIONS: The study highlighted the significant burden of AMI-CS in this region, with high in-hospital mortality. The study identified several key risk factors associated with increased hospital mortality. Despite the utilization of invasive hemodynamic monitoring, revascularization, and mechanical circulatory support in a substantial proportion of patients, the 12-month survival rate remained relatively low.