Using machine learning to predict atrial fibrillation diagnosed after ischemic stroke.

Abstract Background Selecting best candidates for prolonged poststroke cardiac monitoring in acute ischemic stroke (AIS) patients is still challenging. We aimed to develop a machine learning (ML) model to select AIS patients at high risk of poststroke atrial fibrillation (AF) for prolonged cardiac monitoring and then to compare ML model with traditional risk scores and classic statistical logistic regression (classic-LR) model. Methods AIS patients from July 2012 to September 2020 across Nanjing First Hospital were collected. We performed the LASSO regression for selecting the critical features and built five ML models to assess the risk of poststroke AF. The SHAP and partial dependence plot (PDP) method were introduced to interpret the optimal model. We also compared ML model with CHADS2 score, CHA2DS2-VASc score, AS5F score, HAVOC score, and classic-LR model. Results A total of 3929 AIS patients were included. Among the five ML models, deep neural network (DNN) was the model with best performance. It also exhibited superior performance compared with CHADS2 score, CHA2DS2-VASc score, AS5F score, HAVOC score and classic-LR model. The results of SHAP and PDP method revealed age, cardioembolic stroke, large-artery atherosclerosis stroke, and NIHSS score at admission were the top four important features and revealed the DNN model had good interpretability and reliability. Conclusion The DNN model achieved best performance and improved prediction performance compared with traditional risk scores and classic-LR model. The DNN model can be applied to identify AIS patients at high risk of poststroke AF as best candidates for prolonged poststroke cardiac monitoring.