<![CDATA[Diabetes remains a significant global health challenge, with the number of cases increasing annually. Early detection is essential to prevent severe complications and reduce the burden on healthcare systems. However, traditional diagnostic methods often demand considerable time and resources. This study investigates the performance of two machine learning algorithms—K-Nearest Neighbors (K-NN) and Support Vector Machine (SVM)—in classifying diabetes using the Healthcare-Diabetes dataset. The models were evaluated based on accuracy, precision, recall, and F1-score. Experimental results indicate that the K-NN algorithm outperforms SVM, achieving an accuracy of 92.20% and an F1-score of 0.93. In comparison, the SVM algorithm attained an accuracy of 88.39% and an F1-score of 0.89. These findings suggest that the K-NN algorithm is more effective for diabetes classification in this dataset context.]]>
Copyrights © 2025
