This project implements an API for detecting Polycystic Ovary Syndrome (PCOS) using machine learning. The system is built with FastAPI for its high-performance asynchronous capabilities, providing a scalable and efficient deployment of the model.
Key Features:
Machine Learning Model: Trained on medical datasets to predict the likelihood of PCOS based on input features such as BMI, menstrual irregularity, and hormone levels. FastAPI Framework: Ensures fast request handling, automatic OpenAPI documentation, and easy integration with frontend applications. Endpoints: /predict: Accepts patient data in JSON format and returns a prediction on the likelihood of PCOS. /docs: Interactive API documentation with Swagger UI, allowing easy testing of endpoints. The deployment is designed to be lightweight, allowing integration into healthcare platforms or mobile applications for real-time PCOS risk assessment.