Recent Events, Polycystic Ovarian Disease (PCOD) is very important in the realm of women's lives. PCOD is mostly caused by a hormonal imbalance and inherited predisposition. Each month, the two ovaries alternately release mature, ready-to-fertilize eggs in a typical menstrual cycle. For the prepossessing, the PCOD dataset is downloaded from the Kaggle repository as a.csv file type. In order to input into the prediction, pre-processing involves removing unnecessary data and filling in missing values. Currently, the analysis utilizes three deep learning algorithms for disease prediction: Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), and Deep Neural Networks (DNN) .The forecast takes into consideration the patient's age, height, weight, and particular characteristics like FSH, LH, endometrium thickness, II beta and I beta HCG, as well as whether or not the patient is pregnant. Pre-processed datasets are classified and algorithm accuracy is assessed using Deep Learning Models like DNN, RNN, and CNN. The performance of each algorithm is assessed by comparing classification metrics such as precision, recall, and f-measure values. Among them, DNN outperforms the others. Other categorization techniques were then employed to find enormous amounts of data.

Polycystic Ovarian Syndrome DNN RNN CNN