Revolutionizing Cardiac Prediction based on Fog-Cloud-IoT Integrated Heart Disease Model

Abstract

In a time when technology is having a profound effect on medical applications, the rapid remote diagnosis of any cardiac disease has proven to be a formidable obstacle. These days, computers can swiftly process a large volume of patient medical records. Recent developments in the IoT and medical applications, such as the IoMT, have opened the possibility of data diffusion among numerous locations pertaining to patients. This study presents the IHDPM, an integrated model for the prediction of cardiac disease that takes into account dimensionality declining through PCA (principal component analysis), feature collection over sequential feature selection (SFS), and classifications through the random forest (RF) classifier. The proposed model outperforms over different unadventurous classification methods, including LR (logistic regression), NB (naive Bayes), SVM (support vector machine), KNN (K-nearest neighbors), DT (decision trees), and RF, according to experiments conducted using the CHDD (Cleveland Heart Disease Dataset) as of the UCI-ML source and the Python programming linguistic. Medical professionals may find the proposed model useful for making accurate diagnoses of cardiac patients. While DL approaches may produce more accurate prediction results, it would be supplementary operative to reduce the extents count before cluster generation to improve the results.