Polycystic Ovary Syndrome Detection Based on Optimized Machine Learning Techniques

Research interest in using machine learning algorithms to develop models for detecting Polycystic Ovary Syndrome (PCOS) has increased significantly in recent years. This surge is understandable, as the condition mostly affects reproductive-age women and is a major cause of infertility. Consequently, researchers employ machine learning techniques to address this ailment. However, issues of accuracy and optimal results are still major issues to contend with using this technology owing to the complexity of the medical dataset. Therefore, this study proposes to detect PCOS using Support Vector Machine, Random Forest, and AdaBoost with the aid of optimized techniques such as the Red Deer Algorithm (RDA) and Firefly Optimization Algorithm. The optimization techniques and three machine learning models were used to optimize the 45 features of the PCOS dataset that was obtained from the Kaggle repository. The RDA + SVM achieved an accuracy of 88%, the RDA + RF achieved an accuracy of 82%, the RDA + AdaBoost achieved an accuracy of 85%, the FF + SVM achieved an accuracy of 89%, and the PSO + RF achieved an accuracy of 89%.