PCOS Detection using XGBoost
Problem Solved: Early and accurate detection of Polycystic Ovary Syndrome (PCOS) in young females (13–25 years old), enabling timely diagnosis, better treatment, and personalized care.
Description: A healthcare-focused ML model built using XGBoost that uses hormonal and physical parameters to predict PCOS. Provides direct recommendations based on predicted outcomes.
Inputs
- Hormone levels (FSH, LH, AMH)
- Cycle duration, weight, BMI, acne, facial hair, etc.
- Glucose, insulin, thyroid indicators
Outputs
- PCOS Detected / Not Detected (Binary)
- Probability Score (0–1)
- Health-based recommendations
Features
- Streamlit interface with intuitive UI
- Live data visualizations and probability meter
- XGBoost model optimized with GridSearchCV
- Real-time insights and interpretability
Tech Stack
Python, Pandas, Scikit-learn, Streamlit, XGBoost, Seaborn