Risk factors and prediction model for acute ischemic stroke after off-pump coronary artery bypass grafting based on Bayesian network

Abstract

Background: This study aimed to identify the risk factors of acute ischemic stroke (AIS) occurring during hospitalization in patients following off-pump coronary artery bypass grafting (OPCABG) and utilize Bayesian network (BN) methods to establish predictive models for this disease.

Methods: Data were collected from the electronic health records of adult patients who underwent OPCABG at Beijing Anzhen Hospital from January 2018 to December 2022. Patients were allocated to the training and test sets in an 8:2 ratio according to the principle of randomness. Subsequently, a BN model was established using the training dataset and validated against the testing dataset. The BN model was developed using a tabu search algorithm. Finally, receiver operating characteristic (ROC) and calibration curves were plotted to assess the extent of disparity in predictive performance between the BN and logistic models.

Results: A total of 10,184 patients (mean (SD) age, 62.45 (8.7) years; 2524 (24.7%) females) were enrolled, including 151 (1.5%) with AIS and 10,033 (98.5%) without AIS. Female sex, history of ischemic stroke, severe carotid artery stenosis, high glycated albumin (GA) levels, high D-dimer levels, high erythrocyte distribution width (RDW), and high blood urea nitrogen (BUN) levels were strongly associated with AIS. Type 2 diabetes mellitus (T2DM) was indirectly linked to AIS through GA and BUN. The BN models exhibited superior performance to logistic regression in both the training and testing sets, achieving accuracies of 72.64% and 71.48%, area under the curve (AUC) of 0.899 (95% confidence interval (CI), 0.876-0.921) and 0.852 (95% CI, 0.769-0.935), sensitivities of 91.87% and 89.29%, and specificities of 72.35% and 71.24% (using the optimal cut-off), respectively.

Conclusion: Female gender, IS history, carotid stenosis (> 70%), RDW-CV, GA, D-dimer, BUN, and T2DM are potential predictors of IS in our Chinese cohort. The BN model demonstrated greater efficiency than the logistic regression model. Hence, employing BN models could be conducive to the early diagnosis and prevention of AIS after OPCABG.

Keywords: Bayesian network; Coronary artery bypass grafting; Prediction model; Risk factor; Stroke; Type 2 diabetes mellitus.

Fig. 1

Flowchart describing the screening of patients underwent CABG. CABG, coronary artery bypass grafting

Fig. 2

Variable selection by using the LASSO regression. A coefficient profile plot was produced against the log(lambda) sequence (A). Thirteen variables with nonzero coefficients were selected by optimal lambda. The optimal parameter (lambda) in the LASSO model was verified by plotting the binomial deviance curve against log(lambda), with dotted vertical lines indicating the minimum criteria and one standard error from the minimum(B). LASSO regression, least absolute shrinkage and selection operator regression

Fig. 3

BN for prediction of occurrence of AIS in patients underwent isolated OPCABG. BN, Bayesian network; OPCABG, off-pump coronary artery bypass grafting; AIS, acute ischemic stroke; IS, ischemic stroke; T2DM, type 2 diabetes mellitus; RDW-CV, red cell distribution width coefficient of variation; BUN, blood urea nitrogen; FBG, fasting blood glucose; GA, glycated albumin; TP, total protein; FDP, fibrin degradation products; PF, plasma fibrinogen

Fig. 4

ROC curves of BN model and LR model for prediction of in patients undergoing isolated OPCABG. The AUCs of the BN model for prediction of AIS was 0.899 (95% CI, 0.876–0.921) and 0.852 (95% CI, 0.769–0.935), as well as 0.876 (95% CI, 0.846–0.907) and 0.847 (95% CI, 0.799–0.895) of the LR model in training and test sets, respectively. ROC, Receiver operating characteristic; BN, Bayesian network; LR, logistic regression; OPCABG, off-pump coronary artery bypass grafting; AUCs areas under the curve; AIS, acute ischemic stroke

Fig. 5

Calibration of the predictive models. The calibration plots demonstrated that the predictive risk of AIS was in good agreement with the actually observed results, in either BN model of (A) train and (B) test sets, or in LR model of (C) train and (D) test sets. AIS, acute ischemic stroke; BN, Bayesian network; LR logistic regression