Evaluating the Stroke Risk of Patients using Machine Learning: A New Perspective from Sichuan and Chongqing

Abstract

Stroke is the leading cause of death and disability among people in China, and it leads to heavy burdens for patients, their families and society. An accurate prediction of the risk of stroke has important implications for early intervention and treatment. In light of recent advances in machine learning, the application of this technique in stroke prediction has achieved plentiful promising results. To detect the relationship between potential factors and the risk of stroke and examine which machine learning method significantly can enhance the prediction accuracy of stroke. We employed six machine learning methods including logistic regression, naive Bayes, decision tree, random forest, K-nearest neighbor and support vector machine, to model and predict the risk of stroke. Participants were 233 patients from Sichuan and Chongqing. Four indicators (accuracy, precision, recall and F1 metric) were examined to evaluate the predictive performance of the different models. The empirical results indicate that random forest yields the best accuracy, recall and F1 in predicting the risk of stroke, with an accuracy of .7548, precision of .7805, recall of .7619 and F1 of .7711. Additionally, the findings show that age, cerebral infarction, PM 8 (an anti-atrial fibrillation drug), and drinking are independent risk factors for stroke. Further studies should adopt a broader assortment of machine learning methods to analyze the risk of stroke, by which better accuracy can be expected. In particular, RF can successfully enhance the forecasting accuracy for stroke.