Prediction of the development of acute kidney injury following cardiac surgery by machine learning.

BACKGROUND: Cardiac surgery-associated acute kidney injury (CSA-AKI) is a major complication that results in increased morbidity and mortality after cardiac surgery. Most established prediction models are limited to the analysis of nonlinear relationships and fail to fully consider intraoperative variables, which represent the acute response to surgery. Therefore, this study utilized an artificial intelligence-based machine learning approach thorough perioperative data-driven learning to predict CSA-AKI. METHODS: A total of 671 patients undergoing cardiac surgery from August 2016 to August 2018 were enrolled. AKI following cardiac surgery was defined according to criteria from Kidney Disease: Improving Global Outcomes (KDIGO). The variables used for analysis included demographic characteristics, clinical condition, preoperative biochemistry data, preoperative medication, and intraoperative variables such as time-series hemodynamic changes. The machine learning methods used included logistic regression, support vector machine (SVM), random forest (RF), extreme gradient boosting (XGboost), and ensemble (RF + XGboost). The performance of these models was evaluated using the area under the receiver operating characteristic curve (AUC). We also utilized SHapley Additive exPlanation (SHAP) values to explain the prediction model. RESULTS: Development of CSA-AKI was noted in 163 patients (24.3%) during the first postoperative week. Regarding the efficacy of the single model that most accurately predicted the outcome, RF exhibited the greatest AUC (0.839, 95% confidence interval [CI] 0.772-0.898), whereas the AUC (0.843, 95% CI 0.778-0.899) of ensemble model (RF + XGboost) was even greater than that of the RF model alone. The top 3 most influential features in the RF importance matrix plot were intraoperative urine output, units of packed red blood cells (pRBCs) transfused during surgery, and preoperative hemoglobin level. The SHAP summary plot was used to illustrate the positive or negative effects of the top 20 features attributed to the RF. We also used the SHAP dependence plot to explain how a single feature affects the output of the RF prediction model. CONCLUSIONS: In this study, machine learning methods were successfully established to predict CSA-AKI, which determines risks following cardiac surgery, enabling the optimization of postoperative treatment strategies to minimize the postoperative complications following cardiac surgeries.

Percutaneous Coronary Intervention With a Drug-Eluting Stent Versus Coronary Artery Bypass Grafting in Patients Receiving Dialysis: A National Study From Taiwan.

Rationale & Objective: We aimed to study the comparative effectiveness of percutaneous coronary intervention with drug-eluting stent and coronary artery bypass grafting in patients receiving dialysis. Study Design: This was a retrospective observational cohort study. Setting & Participants: This population-based study identified patients receiving dialysis hospitalized for coronary revascularization between January 1, 2009 and December 31, 2015, in the Taiwan National Health Insurance Research Database. Exposures: Patients received percutaneous coronary intervention with drug-eluting stent versus coronary artery bypass grafting. Outcomes: The study outcomes were all-cause mortality, in-hospital mortality, and repeat revascularization. Analytical Approach: Propensity scores were used to match patients. Cox proportional hazards models and logistic regression models were constructed to examine associations between revascularization strategies and mortality. Interval Cox models were fitted to estimate time-varying hazards during different periods. Results: A total of 1,840 propensity score-matched patients receiving dialysis were analyzed. Coronary artery bypass grafting was associated with higher in-hospital mortality (coronary artery bypass grafting vs percutaneous coronary intervention with drug-eluting stent; crude mortality rate 12.5% vs 3.3%; adjusted OR, 5.22; 95% CI, 3.42-7.97; P < 0.001) and longer hospitalization duration (median [IQR], 20 [14-30] days vs 3 [2-8] days; P < 0.001). After discharge, repeat revascularization, acute coronary syndrome, and repeat hospitalization all occurred more frequently in the percutaneous coronary intervention with drug-eluting stent group. Importantly, with a median follow-up of 2.8 years, coronary artery bypass grafting was significantly associated with a higher risk of all-cause overall mortality (adjusted HR, 1.19; 95% CI, 1.05-1.35; P = 0.006) in the multivariable Cox proportional hazard model. Sensitivity and subgroup analyses yielded consistent results. Limitations: This was an observational study with mainly Asian ethnicity. Conclusions: Percutaneous coronary intervention with drug-eluting stent may be associated with better survival than coronary artery bypass grafting in patients receiving dialysis. Future studies are warranted to confirm this finding.

Although coronary artery bypass grafting offers better long-term survival in the general population than percutaneous coronary intervention with drug-eluting stent, patients receiving dialysis may be too frail to tolerate the increased perioperative mortality risk of coronary artery bypass grafting. In this retrospective study in a national cohort of patients receiving dialysis from Taiwan, percutaneous coronary intervention with drug-eluting stent is associated with lower in-hospital mortality and better long-term survival when compared with coronary artery bypass grafting. Subsequent acute coronary syndrome, repeat revascularization, and rehospitalization were noted more frequently in the percutaneous coronary intervention with drug-eluting stent group. These findings may suggest percutaneous coronary intervention with drug-eluting stent as a safe revascularization strategy for patients receiving dialysis.