<![CDATA[Currently, stroke is the second cause of death globally. According to data from the World Health Organization (WHO), 7.9% of deaths in Indonesia are caused by stroke. Based on these data, analysis of the factors influencing the case growth rate is very useful. This paper analyzes various factors in electronic health records for effective stroke prediction with different machine-learning algorithms including Decision Tree and Neural Networks. This research uses a dataset consisting of 12 features, namely ID, gender, age, history of hypertension, history of heart disease, marital status, type of work, type of residence, average glucose level, BMI (Body Mass Index) number, and status. smoking, and prediction of stroke. These features were analyzed using the Neural Network and Decision Tree methods so that selected features were produced for further analysis using the Neural Network method. The feature selection results consist of 5 features: age, history of hypertension, marital status, average glucose level, and BMI (Body Mass Index) number. The highest accuracy results were obtained using the Neural Network method with a feature selection of 88.75, the second highest was obtained with the neural network method of 87.1875, and the lowest accuracy was obtained with the Decision Tree method which had an accuracy result of 81.25. Based on these accuracy results, it can be obtained that the most optimal results are shown by the Neural Network method with feature selection.]]>
