Performance Comparison of Neural Network-Based Models in the Classification of Polycystic Ovary Syndrome Disease

In this study, it was aimed to compare the performances of above mentioned ANN, MLP and deep learning methods determine polycystic ovary syndrome (PCOS) risk factors predict PCOS diagnosis. data set “Polycystic syndrome” used for diagnosis prediction. The performance models evaluated with accuracy, sensitivity, specificity, positive/negative predictive values. Factors associated were estimated from model that has best performance. Accuracy, positive value negative obtained method 87.25%, 79.66%, 90.93%, 81.03%, 90.19%. Neural Network 87.80%, 79.10%, 92.03%, 82.84%, 90.05%. Deep Learning 89.09%, 81.92%, 92.58%, 84.30%, 91.33%. According findings classification result according metrics artificial neural networks, in study belongs method. As a result, successfully classified light clinical tried be revealed by giving PCOS.