Intelligent Heart Disease Prediction System Using DBSCAN and Fuzzy Logic with Automated Patient Report Generation

Abstract

Heart disease continues to be a major cause of mortality worldwide, highlighting the urgent need for effective early detection and preventive healthcare systems. This research paper proposes a new system called the Intelligent Heart Disease Prediction System that combines the use of modern technology such as DBSCAN Clustering and Fuzzy Logic Classification. This system is designed to provide high-quality, reliable risk assessments based on multiple factors like age, cholesterol levels, dietary habits, physical activity level, and medical history in order to determine a person's likelihood of developing heart disease. A secure web-based interface is used to collect patient data, which is accessible and offers privacy of data. The collected information is stored in an SQLite database and undergoes preprocessing, including handling missing values and normalisation, to enhance prediction accuracy. DBSCAN clustering has been applied to identify latent patterns and to cluster groups of patients with similar profiles, without the use of a pre-defined label. Fuzzy logic is then used to categorise patients into different risk levels by effectively managing uncertainty and imprecision within the medical data. The system produces automated PDF reports featuring in-depth risk analysis, symptom evaluation and tailored recommendations. Interactive dashboards provide a visual representation of patient trends and historical data. Overall, the proposed system supports efficient, remote heart disease prediction, facilitating early diagnosis, reducing healthcare costs, and improving patient outcomes.