AUTHOR=Jeon Eun-Tae , Jung Seung Jin , Yeo Tae Young , Seo Woo-Keun , Jung Jin-Man 

TITLE=Predicting short-term outcomes in atrial-fibrillation-related stroke using machine learning

JOURNAL=Frontiers in Neurology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2023.1243700

DOI=10.3389/fneur.2023.1243700

ISSN=1664-2295

ABSTRACT=Background: Prognostic prediction and the identification of prognostic factors are critical during the early period of atrial-fibrillation (AF)-related strokes, as AF is associated with poor outcomes in stroke patients.Methods: Two independent datasets, namely the Korean Atrial Fibrillation Evaluation Registry in Ischemic Stroke Patients (K-ATTENTION) and the Korea University Stroke Registry (KUSR), were used for internal and external validation, respectively. These datasets include common variables such as demographic, laboratory, and imaging findings during early hospitalization. Outcomes were unfavorable functional status with modified Rankin scores of 3 or greater and mortality at three months. We developed two machine learning models, namely a tree-based model and a multi-layer perceptron (MLP), along with a baseline logistic regression model. The area under the receiver operating characteristic curve (AUROC) was used as the outcome metric. The Shapley additive explanation (SHAP) method was used to evaluate the contributions of variables.Results: Machine learning models outperformed logistic regression in predicting both outcomes. For three-month unfavorable outcomes, MLP exhibited significantly higher AUROC values of 0.890 and 0.859 in internal and external validations, respectively, than those of logistic regression. For three-month mortality, both machine learning models exhibited significantly higher AUROC values than the logistic regression for internal validation, but not external validation. The most significant predictor of both outcomes was the initial National Institute of Health and Stroke Scale.The explainable machine learning model can reliably predict short-term outcomes and identify high-risk patients with AF-related strokes.