A Secure Remote Health Monitoring for Heart Disease Prediction using machine learning and deep learning techniques in XAI framework

Machine intelligence models are effective at classifying datasets for data analytics and predicting insights that can be used to make clinical decisions. The models would aid in disease prognosis and preliminary disease investigation, both of which are necessary for effective treatment. In today's world, there is a high demand for the interpretability and explainability of decision models. XAI is an extension of artificial intelligence that extends ai's capability by explaining why it has made that prediction and whether we can rely on it or not. The goal of this paper is to predict heart disease prediction using the RHMIoT model in the XAI framework. The patient clinical data are gathered using medical IoT sensors and stored in a secure cloud storage using a lightweight block encryption and decryption approach. The model is used to predict the accuracy of heart disease and its severity level. The accuracy levels of cardiac disease are calculated using Deep Learning and auto-encoder-based methods. We present a novel strategy for identifying key features using machine learning and deep learning techniques in a secured cloud environment to improve the accuracy of CVD. A lightweight block encryption and decryption technique is provided for a secure RHMIoT. The outcomes were determined using several performance matrices. The performance of auto-encoder Kernel SVM model provided the greatest accuracy of 87.00%. The suggested RHMIoT system identifies the presence of heart disease in a patient and helps to get quick medical attention in case of an emergency situation.