Machine Learning Approach for Blood Pressure Risk Assessment and Prediction

Abstract

This project focuses on predicting blood pressure risk levels using machine learning techniques. The system processes a dataset containing systolic and diastolic blood pressure values and classifies them into different risk categories. Data preprocessing steps such as normalization, shuffling, and label encoding are applied to improve model performance. Two algorithms, Decision Tree and Logistic Regression, are implemented and evaluated based on accuracy, precision, recall, and F1- score. The Decision Tree model achieved significantly higher accuracy compared to Logistic Regression, making it more suitable for this prediction task. Visualizations such as graphs and confusion matrices are used to analyse performance and results clearly. The system also allows testing with new input values to predict risk levels effectively. Overall, this project demonstrates how machine learning can assist in early detection and monitoring of blood pressure-related health risks.