Comparative Analysis of Machine Learning Algorithms in Diagnosis of Polycystic Ovarian Syndrome

In a study from September 2020, researchers compared various machine learning algorithms, including Support Vector Machine, CART, Naive Bayes Classification, Random Forest, and Logistic Regression, for diagnosing Polycystic Ovarian Syndrome (PCOS) in women of reproductive age. The algorithms were evaluated using clinical data such as body mass index, hormone levels, hair loss, acne, skin darkening, hirsutism, menstrual cycle length, endometrial thickness, and blood pressure levels. The performance of these algorithms was assessed based on accuracy, precision, recall, F-statistics, and Kappa Coefficient. The study concluded that the Random Forest algorithm had the highest accuracy at 96% for diagnosing PCOS.