<![CDATA[Polycystic Ovary Syndrome (PCOS) is a hormonal disorder in women of reproductive age that poses challenges in diagnosis and early detection. This study aims to compare the performance of the K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Logistic Regression algorithms in classifying PCOS under consistent testing conditions. This study employs a quantitative approach and machine learning methods using secondary data from the PCOS Diagnosis dataset. The study population and sample consisted of 1,000 patient medical records, all of which were used, with 800 for training and 200 for testing. Altair AI Studio was used as the research tool, while analysis was conducted using confusion matrices, accuracy, precision, recall, and F1-score. The results show that KNN achieved an accuracy of 96.00%, precision of 90.91%, recall of 90.91%, and an F1-score of 90.91%, while SVM and Logistic Regression produced lower performance. In conclusion, KNN provided the most consistent classification performance on the research dataset and has the potential to be used as a supporting approach for PCOS classification based on clinical data.]]>
Copyrights © 2026
