Project Overview This project focuses on predicting pregnancy-related complications using machine learning techniques. By analyzing key maternal health indicators, the model aims to accurately assess risk levels and support early intervention strategies.

Dataset Information The dataset used was sourced from UC Irvine repository https://archive.ics.uci.edu/dataset/863/maternal+health+risk It contains 1,014 entries and 7 key features: Age Systolic Blood Pressure (SystolicBP) Diastolic Blood Pressure (DiastolicBP) Blood Sugar Level (BS) Body Temperature (BodyTemp) Heart Rate (HeartRate) Risk Level (Target variable: Low, Medium, High)

Project Aim To develop a machine learning model for accurate classification of maternal health risk levels.

Technologies Used Programming: Python Libraries: Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn Visualization: Pairplots, Pie charts, Feature Correlation Analysis Machine Learning Models: Support Vector Classifier, Random Forest, Decision Trees IDE: Google collab

Key Findings & Insights Feature Correlation: No strong correlations were observed between independent variables. Class Imbalance: The dataset is imbalanced, which reflects real-life maternal health scenarios. Model Optimization: Future improvements could include resampling techniques or synthetic data generation.

Future Enhancements

• Implement deep learning models for improved accuracy.
• Develop an interactive interface for real-time maternal risk assessment.
• Integrate domain-specific medical insights to enhance feature engineering.

Real-World Applications

• Early detection of complication supports maternal health professionals in service delivery.
• Integration into mobile or hospital-based diagnostic tools.
• Predictive analytics for personalized maternal care.

Contact For collaboration, improvement, inquiries or to connect:

• Submit a pull request or fork this repository
• https://www.linkedin.com/in/olubunmi-adenuga/