Personalized Lifestyle Guidance for Women with PCOS: A Machine Learning Approach to Sustainable Health

Polycystic Ovary Syndrome (PCOS) is a common hormonal condition that affects many women of reproductive age. It often goes unnoticed because its symptoms can appear in many different ways, making early detection difficult. Early identification of the specific type of PCOS and tailored lifestyle interventions can reduce long-term health risks such as infertility, metabolic complications, and cardiovascular disease. This study introduces PCOS Management and Guidance, a web-based application designed to classify PCOS types using a Random Forest classifier trained on clinical and symptomatic data. The system incorporates optical character recognition (OCR) to process ultrasound images and supplements the prediction with personalized guidance on diet, exercise, and stress management. The model achieved a high level of accuracy, demonstrating that ML-based methods can be effectively applied in women’s health diagnostics. By combining type detection with lifestyle recommendations, PCOS Management and Guidance offers a practical tool to support early intervention and patient selfmanagement.