Postpartum Hemorrhage Prediction

The PPH Early Risk Prediction System is an AI-powered maternal health web application built using Streamlit that helps predict the risk of Postpartum Hemorrhage (PPH), which is one of the leading causes of maternal mortality worldwide. The platform uses a pre-trained machine learning model loaded via Joblib, along with SHAP for explainability, to analyze clinical inputs such as age, BMI, and gestational age, and classify patients into Low, Moderate, or High risk categories. It supports two types of users — patients and doctors — each with their own dashboard and features. Patients can check their risk, book appointments, view checkup schedules, and interact with an AI health assistant chatbot for guidance. Doctors can monitor all registered patients, filter and focus on high-risk cases, manage appointment requests by confirming or cancelling them, and provide notes to patients. The application stores all data locally using SQLite and presents it through interactive charts built with Matplotlib and Plotly. It also supports PDF report generation using fpdf2, allowing clinical summaries to be downloaded. The UI is styled with custom CSS using Google Fonts for a clean, professional look, and the platform includes multilingual support to cater to diverse user bases. Overall, this system serves as a clinical decision support tool designed to assist healthcare providers in the early identification and management of high-risk pregnancies, ultimately aiming to reduce maternal deaths caused by postpartum hemorrhage.