khalidak07/Pregnancy-Risk-Prediction-

This project aims to address the challenge of high-risk pregnancies in developing nations, particularly Nigeria. It focuses on women from lower and middle-income backgrounds who often lack access to proper healthcare and awareness about potential pregnancy complications. # Pregnancy-Risk-Prediction- ## Overview This project aims to address the challenge of high-risk pregnancies in developing nations, particularly Nigeria. It focuses on women from lower and middle-income backgrounds who often lack access to proper healthcare and awareness about potential pregnancy complications. ## Objective The main goal is to develop a machine learning classification model to predict the risk level of pregnancy complications. The model classifies patients into low, medium, or high-risk categories based on various health factors during pregnancy. ## Features Utilizes an AdaBoost machine learning model for predictions for easy user interaction Predicts pregnancy risk levels based on key health indicators ## Dataset The model is trained on an open-source dataset from Kaggle, which includes the following features: Age Body Temperature Heart Rate Systolic Blood Pressure Diastolic Blood Pressure BMI Blood Glucose (HbA1c) Blood Glucose (Fasting) Dataset source: Pregnancy Risk Factor Data on Kaggle Technologies Used Python Pandas for data manipulation Scikit-learn for machine learning Streamlit for web application deployment Recommendations This project introduces an innovative approach to analyze and predict the severity of risk factors in maternal and fetal health. By leveraging Data Science and Machine Learning, it offers a data-driven perspective on pregnancy risk assessment. However, it's important to emphasize that while this tool provides valuable insights, it should complement rather than replace expert clinical judgment, which remains crucial for individual patient care. The model's predictive capabilities demonstrate the potential of ML in supporting healthcare decisions. Nevertheless, there's room for further enhancement. Future research could focus on expanding the dataset to encompass a broader range of demographic and clinical variables. Additionally, exploring advanced techniques such as deep learning-based neural networks could unco …