Predicting cerebral infarction in patients with atrial fibrillation using machine learning: The Fushimi AF registry.

Abstract

The CHADS₂ and CHA₂DS₂-VASc scores are widely used to assess ischemic risk in the patients with atrial fibrillation (AF). However, the discrimination performance of these scores is limited. Using the data from a community-based prospective cohort study, we sought to construct a machine learning-based prediction model for cerebral infarction in patients with AF, and to compare its performance with the existing scores. All consecutive patients with AF treated at 81 study institutions from March 2011 to May 2017 were enrolled (n = 4396). The whole dataset was divided into a derivation cohort (n = 1005) and validation cohort (n = 752) after excluding the patients with valvular AF and anticoagulation therapy. Using the derivation cohort dataset, a machine learning model based on gradient boosting tree algorithm (ML) was built to predict cerebral infarction. In the validation cohort, the receiver operating characteristic area under the curve of the ML model was higher than those of the existing models according to the Hanley and McNeil method: ML, 0.72 (95%CI, 0.66-0.79); CHADS₂, 0.61 (95%CI, 0.53-0.69); CHA₂DS₂-VASc, 0.62 (95%CI, 0.54-0.70). As a conclusion, machine learning algorithm have the potential to perform better than the CHADS₂ and CHA₂DS₂-VASc scores for predicting cerebral infarction in patients with non-valvular AF.