Paper Contents
Abstract
Polycystic Ovary Disease (PCOD) is a common condition affecting many women worldwide, often leading to issues like infertility, weight gain, hormonal imbalances, and a higher risk of heart disease. Early detection is important to manage symptoms and prevent complications. This study collected data from 163 individuals, focusing on 13 key factors related to menstrual health and PCOD risk, such as irregular periods, acne, family history, and insulin resistance. Machine learning techniques, including Artificial Neural Networks (ANN), Random Forest and Naive Bayes were used to predict PCOD risk. The findings highlight major risk factors like menstrual irregularities, hormonal imbalances, and thyroid dysfunction. By developing a reliable system for identifying PCOD risk, this research helps raise awareness and supports healthcare professionals in providing early diagnosis, personalized treatment plans, and better lifestyle recommendations to manage the condition effectively. The models achieved the accuracy of ANN-79%, Random Forest-100% and Naive Bayes-76%.
Copyright
Copyright © 2025 KABISA P. This is an open access article distributed under the Creative Commons Attribution License.
