Early Detection and Accurate Prediction of Heart Disease: The Role of Stacked GRU-TCN Model

cardiovascular diseases represent a significant global health challenge, with the incidence of cardiac conditions rising steadily due to lifestyle factors such as poor diet and lack of exercise. Detecting and monitoring cardiovascular disease within large datasets is critical for effective public health management. This study presents a systematic approach for the efficient detection of cardiovascular disease, encompassing data preprocessing, feature selection, and model training. Sequential processing is essential for each stage of the methodology. Data preprocessing involves outlier removal and data standardization to ensure data quality and consistency. Feature selection techniques are employed to identify the most influential variables for model training. Careful consideration is given to feature selection during the training of a Stacked GRU-TCN model to optimize model performance. Comparative analysis demonstrates the superior performance of the proposed approach over TCN and GRU algorithms, achieving an impressive accuracy rate of 96.70%. These findings underscore the potential of advanced modeling techniques in enhancing cardiovascular disease detection and management.