This research presents a robust hybrid methodology for heart disease prediction, amalgamating logistic regression, feature engineering, random forest algorithms, and generative artificial intelligence. Logistic regression elucidates intricate relationships between dependent and independent variables, while feature engineering meticulously refines raw data to augment model performance. The incorporation of the random forest algorithm, leveraging decision trees, establishes an ensemble for precise predictions. The integration of generative AI employs machine learning techniques to synthesize supplementary data, fortifying the model’s resilience. The proposed comprehensive framework has the potential to significantly advance the prediction of heart disease, with implications for improving patient care. This framework integrates seamless API connectivity, facilitating real-time result presentation on a web interface. By emphasizing precision and accessibility, the framework aligns with the broader objective of driving meaningful progress in the forecasting of cardiovascular health outcomes.