Utilizing ANN in an Advanced Machine Learning Framework

Heart disease remains a significant global health concern, necessitating progressive predictive models for early verdict and intervention. In this study, a comprehensive Machine Learning approach is presented that integrates temporal segmentation, principal component analysis (PCA) for feature selection, and artificial neural networks (ANN) for heart disease prediction. The first phase involves temporal segmentation of heart-related datasets to capture dynamic patterns over time. PCA as a feature selection method reduce dimensionality and enhance the interpretability of the dataset. Finally, ANN, known for its ability to model complex relationships, is trained on the selected features to predict heart disease outcomes. The proposed approach is validated using Python Software with a heart disease dataset. Performance metrics, including accuracy, sensitivity, and specificity, demonstrate superior results in predicting Heart disease utilizing the proposed approach.