RESUMEN
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% 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.
RESUMEN
BACKGROUND: The use of dual antiplatelet therapy (DAPT) after coronary revascularization for left-main disease is still debated. The study aimed to characterize patients who received dual versus single antiplatelet therapy (SAPT) after coronary artery bypass grafting (CABG) for unprotected left-main disease and compare the outcomes of those patients. RESULTS: This multicenter retrospective cohort study included 551 patients who were grouped into 2 groups: patients who received SAPT (n = 150) and those who received DAPT (n = 401). There were no differences in age ( P = 0.451), gender ( P = 0.063), smoking ( P = 0.941), diabetes mellitus ( P = 0.773), history of myocardial infarction ( P = 0.709), chronic kidney disease ( P = 0.615), atrial fibrillation ( P = 0.306), or cerebrovascular accident ( P = 0.550) between patients who received SAPT versus DAPT. DAPTs were more commonly used in patients with acute coronary syndrome [87 (58%) vs. 273 (68.08%); P = 0.027], after off-pump CABG [12 (8%) vs. 73 (18.2%); P = 0.003] and in patients with radial artery grafts [1 (0.67%) vs. 32 (7.98%); P < 0.001]. While SAPTs were more commonly used in patients with low ejection fraction [55 (36.67%) vs. 61 (15.21%); P < 0.001] and in patients with postoperative acute kidney injury [27 (18%) vs. 37 (9.23%); P = 0.004]. The attributed treatment effect of DAPT for follow-up major adverse cerebrovascular and cardiac events was not significantly different from that of SAPT [ß, -2.08 (95% confidence interval (CI), -20.8-16.7); P = 0.828]. The attributed treatment effect of DAPT on follow-up all-cause mortality was not significantly different from that of SAPT [ß, 4.12 (CI, -11.1-19.32); P = 0.595]. There was no difference in bleeding between groups ( P = 0.666). CONCLUSIONS: DAPTs were more commonly used in patients with acute coronary syndrome, after off-pump CABG, and with radial artery grafts. SAPTs were more commonly used in patients with low ejection fraction and acute kidney injury. Patients on DAPT after CABG for left-main disease had comparable major adverse cerebrovascular and cardiac events and survival to patients on SAPT, with no difference in bleeding events.
Asunto(s)
Síndrome Coronario Agudo , Lesión Renal Aguda , Enfermedad de la Arteria Coronaria , Intervención Coronaria Percutánea , Humanos , Inhibidores de Agregación Plaquetaria/uso terapéutico , Síndrome Coronario Agudo/cirugía , Síndrome Coronario Agudo/inducido químicamente , Estudios Retrospectivos , Resultado del Tratamiento , Puente de Arteria Coronaria/efectos adversos , Hemorragia/inducido químicamente , Lesión Renal Aguda/inducido químicamenteRESUMEN
INTRODUCTION: The aim of this study was to evaluate the effects of baseline anemia and anemia following revascularization on outcomes in patients with unprotected left main coronary artery (ULMCA) disease. METHODS: This was a retrospective, multicenter, observational study conducted between January 2015 and December 2019. The data on patients with ULMCA who underwent revascularization through percutaneous coronary intervention (PCI) or coronary artery bypass graft (CABG) were stratified by the hemoglobin level at baseline into anemic and non-anemic groups to compare in-hospital events. The pre-discharge hemoglobin following revascularization was categorized into very low (<80 g/L for men and women), low (≥80 and ≤119 g/L for women and ≤129 g/L for men), and normal (≥130 g/L for men and ≥120 g/L for women) to assess impact on follow-up outcomes. RESULTS: A total of 2,138 patients were included, 796 (37.2%) of whom had anemia at baseline. A total of 319 developed anemia after revascularization and moved from being non-anemic at baseline to anemic at discharge. There was no difference in hospital major adverse cardiac and cerebrovascular event (MACCE) and mortality between CABG and PCI in anemic patients. At a median follow-up time of 20 months (interquartile range [IQR]: 27), patients with pre-discharge anemia who underwent PCI had a higher incidence of congestive heart failure (CHF) (p < 0.0001), and those who underwent CABG had significantly higher follow-up mortality (HR: 9.85 (95% CI: 2.53-38.43), p = 0.001). CONCLUSION: In this Gulf LM study, baseline anemia had no impact upon in-hospital MACCE and total mortality following revascularization (PCI or CABG). However, pre-discharge anemia is associated with worse outcomes after ULMCA disease revascularization, with significantly higher all-cause mortality in patients who had CABG, and a higher incidence of CHF in PCI patients, at a median follow-up time of 20 months (IQR: 27).