ASHA: Machine Learning-Based Polycystic Ovary Syndrome (PCOS) Detection and Prediction System
Jayati Dixit, Anshuman Rai, Pulak Tandon, Dhiraj Pandey · 2025
About 17.5% of adults worldwide are infertile, which emphasizes the urgent need for cutting-edge reproductive healthcare solutions. Based on statistics from June 2023. According to the World Health Organization (WHO), 8-13% of females on earth who are in their reproductive age have PCOS, and about 70% of cases go undiagnosed. With the integration of PCOS detection, IVF success rate prediction, and a period tracking system, this work offers a comprehensive women's health application. In addition, a large percentage of women suffer from menstruation abnormalities, such as dysmenorrhea (38.1%) and irregular frequency (80.7%). This approach improves early illness detection and fertility planning by using data analysis and machine learning. The techniques used are Random Forest, K-Nearest Neighbor, Logistic Regression, Naive Bayes, Decision Tree and SVM; which provides us better accuracy than previous works.