<![CDATA[Stroke is a disease caused by a sudden disruption of blood flow to the brain and is one of the leading causes of death in Indonesia. The high mortality rate and delays in early detection make stroke a serious health problem that requires technology-based solutions. Therefore, an approach is needed to support the rapid and accurate classification of stroke disease. This study aims to develop and evaluate a stroke disease classification model using the Support Vector Machine (SVM) algorithm. The dataset used in this study was obtained from the Kaggle platform and consists of 5,110 records with 11 attributes representing stroke risk factors. The research stages include data collection, preprocessing, which consists of data type conversion, feature selection, data cleaning, normalization, and data transformation. To address class imbalance in the dataset, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. Furthermore, the data were partitioned using the 10-Fold Cross Validation method before performing the classification process using the SVM algorithm. Model performance evaluation was conducted using a Confusion Matrix with accuracy, precision, and recall parameters. The experimental results show that the SVM model achieved an average accuracy of 0.79, precision of 0.72, and recall of 0.93. Based on these results, it can be concluded that the Support Vector Machine algorithm demonstrates good performance in classifying stroke disease and has the potential to be used as an effective support system for early stroke detection.]]>
