International Research Journal of Education and Technology

Heart disease remains one of the leading causes of mortality worldwide, contributing to millions of deaths annually and imposing significant socio-economic burdens on healthcare systems. Early detection and risk prediction are critical to reducing mortality rates and enabling preventive interventions. With the rapid advancement of digital healthcare technologies, large-scale medical datasets are being generated through electronic health records (EHRs), diagnostic systems, and wearable monitoring devices. However, traditional statistical analysis methods are insufficient to extract actionable insights from such high-dimensional healthcare data. This research presents a Predictive Data Science Platform for Heart Disease Risk Analytics that integrates machine learning algorithms, feature engineering, statistical modeling, and interactive visualization into a unified system. The platform leverages clinical attributes such as age, resting blood pressure, cholesterol levels, fasting blood sugar, electrocardiographic results, maximum heart rate, chest pain type, and exercise-induced angina to predict the probability of cardiovascular disease. Supervised machine learning models including Logistic Regression, Decision Trees, Random Forest, and Support Vector Machines are trained and evaluated using real-world datasets. Data preprocessing techniques such as normalization, missing value handling, categorical encoding, and outlier detection are employed to enhance dataset quality. The platform provides risk scores and classification outputs, supporting healthcare professionals in preventive decision-making. Furthermore, it integrates interactive dashboards and visualization tools to enhance interpretability. The proposed system demonstrates how predictive data science can transform raw medical data into meaningful clinical insights, enabling proactive cardiac care and reducing long-term healthcare costs.