Developed a Machine Learning-based PCOS detection system using medical and lifestyle data. Performed data preprocessing, feature analysis, and classification modeling to predict PCOS risk. Implemented ML algorithms using Python, Pandas, and Scikit-learn for early healthcare prediction and analysis.

HerHealth AI– PCOS Detection uses machine learning to predict the likelihood of Polycystic Ovary Syndrome based on medical data. Built with Python and Streamlit, it provides a user-friendly interface for early detection and proactive healthcare support.

The PCOS detection system was created using Random Forest and customized CNN. Users first answer questions to assess symptoms, with a Random Forest classifier determining a likelihood of PCOS. If needed, users upload ultrasound images for CNN analysis, confirming PCOS or not.

The objective of the project was to develop a model using machine learning Algorithms to detect and classify the presence of PCOS/PCOD in women using python.

The project provides python code for detection system detects if a patient is infected with PCOS based on the ultrasound image of an ovary, helps count number of follicles as well as reveals geometric parameters about the follicles by effectively using a novel segmentation technique called "salt segmentation"

A data analysis project on PCOS using Python and Power BI. It highlights key indicators like BMI, AMH, LH/FSH ratio, and lifestyle habits. Through EDA and visual insights, the project supports early detection and deeper understanding of PCOS.