<![CDATA[Early detection of chronic diseases is a critical step in effective prevention and treatment. Decision Support Systems (DSS) based on classification algorithms have become an increasingly important tool in helping medical personnel accurately and efficiently identify chronic disease risks. This study aims to analyze the performance of various classification algorithms in SPK for early detection of chronic diseases, focusing on accuracy, precision, recall, and F1-score as evaluation metrics. The research method involves the collection of health datasets that include clinical and demographic variables of patients. Classification algorithms evaluated include Decision Tree, Random Forest, Support Vector Machine (SVM), K - Nearest Neighbors (KNN), and Neural Network. The Dataset was divided into training data and test data, with a proportion of 80:20, and cross-validation was carried out to ensure the reliability of the results. Algorithm performance evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The results showed that Random Forest achieved the highest accuracy of 92.5%, followed by Neural Network with 90.8% accuracy. Decision Tree and KNN showed quite good performance with accuracy of 88.3% and 86.7%, respectively, while SVM had the lowest accuracy of 84.2%. In terms of precision and recall, Random Forest also excelled with values of 91.8% and 92.0%, respectively, showing its good ability to identify positive cases and reduce false positives.]]>
