DESIGN AND IMPLEMENTATION OF MEDICAL PREDICTION SYSTEM FOR CARDIOVASCULAR DISEASES

ABSTRACT Cardiovascular diseases (CVDs) remain one of the leading causes of global mortality, accounting for millions of deaths each year. Early detection and preventive monitoring are essential to reduce the risk of severe cardiovascular complications, yet access to diagnostic tools in many developing regions remains limited. This research presents the Design and Implementation of a Question-Based Medical Prediction System for Cardiovascular Disease, developed to provide a low-cost, accessible, and intelligent means of assessing heart disease risk through user interaction. The system employs a question-based simulation approach that mimics clinical reasoning by collecting user responses to structured health-related questions covering age, blood pressure, cholesterol, smoking habits, diabetes history, and physical activity. These responses are processed using a hybrid predictive model combining rule-based logic and lightweight machine learning techniques to estimate individual cardiovascular risk levels. The system was implemented using Python and Streamlit, ensuring an interactive, web-based interface that delivers instant feedback and personalized recommendations. Testing and evaluation of the model yielded satisfactory performance, with an overall accuracy of approximately 86%, indicating that the system effectively distinguishes between low and high-risk cases. The results demonstrate the system’s potential as a practical tool for early cardiovascular screening, health education, and community awareness.