Application of the K-Nearest Neighbor Algorithm for Polycystic Ovarian Syndrome (PCOS) Classification: A Diagnostic Tool

Abstract

Polycystic Ovarian Syndrome (PCOS) is a common hormonal disorder affecting women of reproductive age. Early detection and accurate classification of PCOS are crucial for timely intervention and management. This study proposes the use of the K-Nearest Neighbor (KNN) algorithm for classifying PCOS based on patient symptoms and characteristics. The KNN algorithm was applied to a dataset of 72 patients, and its performance was evaluated using various training and testing ratios and different values of K. The results showed that the KNN algorithm achieved the highest accuracy of 100% with a training ratio of 90:10 and K= 11. The proposed approach demonstrates the potential of machine learning techniques for accurate PCOS classification and highlights the importance of early detection for improving patient outcomes. However, the limited dataset size and potential overfitting issues should be addressed in future research.