This repository is aimed at developing a digital platform for improving maternal health outcomes in Nigeria
# MaternalWatch AI: Intelligent Early Warning System for Maternal Health Risk Detection in Nigeria
## Overview
MaternalWatch AI is a digital health platform leveraging artificial intelligence and machine learning to provide real-time maternal health risk assessment and early warning capabilities for pregnant women in Nigeria. This project demonstrates the end-to-end process of building a predictive model for maternal health risk using real-world data, including data cleaning, exploratory analysis, feature engineering, model training, evaluation, interpretation, and deployment.
---
## Table of Contents
- Problem Statement
- Dataset
- Project Structure
- Installation
- Project Walkthrough
- 1. Data Inspection & Cleaning
- 2. Exploratory Data Analysis (EDA)
- 3. Feature Engineering & Encoding
- 4. Data Balancing
- 5. Model Training & Evaluation
- 6. Model Comparison
- 7. Model Interpretation
- 8. Model Deployment
- 9. Streamlit Web Application
- Results & Insights
- References
---
## Problem Statement
Nigeria faces a severe maternal health crisis, with high maternal mortality rates due to inadequate healthcare infrastructure, limited access to skilled providers, and poor early detection of high-risk pregnancies. MaternalWatch AI aims to address these challenges by providing predictive analytics and real-time monitoring to enable timely interventions.
---
## Dataset
- **Source:** Kaggle - Maternal Health Risk Data Set
- **Features:**
- Age
- SystolicBP
- DiastolicBP
- BloodGlucose
- BodyTemp
- HeartRate
- RiskLevel (target: low, mid, high risk)
---
## Project Structure
- `MarternalWatchAI.qmd`: Main Quarto notebook containing all code, analysis, and documentation.
- `data/Maternal Health Risk Data Set.csv`: Dataset file.
- `extra_trees_model.pkl`: Saved trained model for deployment.
---
## Installation
1. **Clone the repository**
```
git clone
github.com /MaternalWatch-AI-Intelligent-Early-Warning-System-for-Maternal-Health-Risk-Detection-in-Nig …