ANALYTICAL STUDY OF THE CARDIOVASCULAR HEALTH KEY INDICATORS TOWARDS PROACTIVE FORECASTING OF HEART DISEASE USING DATA MINING METHODS

Abstract Across the world, cardiovascular diseases (CVDs) remain a leading contributor to death rates, necessitating timely identification and intervention strategies. This study presents an analytical approach to understand key health indicators, risk factors, and symptoms associated with cardiovascular health, with the goal of enhancing the early identification of heart disease risks using data mining approaches. By leveraging clinical datasets, the research identifies and evaluates significant key risk factors such as age, lifestyle attributes, cholesterol profile, lipid profile, arterial blood pressure, Coronary Artery Calcium (CAC) score and BMI (body mass index), and. Various data mining algorithms including Naïve Bayes classifier, Decision Tree (J48 Algorithm) and Support Vector Machine (SVM) are applied for developing predictive models aimed at improving diagnostic accuracy. The effectiveness of these algorithms is evaluated using common metrics including recall, precision and accuracy. The research underscores the significance of preprocessing and feature selection to enhance model reliability. Findings suggest that data-driven approaches can provide robust, cost-effective tools for medical practitioners to detect potential heart conditions proactively. Keywords: Heart Disease Prediction, Data Mining, Cardiovascular Disease, Key/Risk Indicators, Machine Learning, Predictive Modeling, Coronary Artery Calcium (CAC) score, Clinical Data Analysis.