An IoMT Based Prediction Model for Cardiac Monitoring Using Machine Learning Algorithms

Abstract

The complex health issues faced by the people are studied and different heart disease monitoring techniques are discussed to present complications. The observation of this monitoring is to enhance human fitness regardless of the situation. The Proposed Methodology is implemented on the benchmark University of California Irvine Dataset and various machine learning techniques are applied and the accuracy is calculated. The main objective of the research work is to improve the wellness of the people and to decrease the mortality rates. Internet of Medical Things (IoMT) is now a recent technology to monitor human health remotely without any human intervention. Further such implementation is developed into IOMT Based Cardiac Monitoring System which alerts the medical staff in case of any abnormality found. Data are collected through sensors to measure patient physical status and monitored and saved in the cloud which can be received by the medical specialists. With the help of a remote cardiac monitoring system, the patients have confidence to contact the doctors without visiting medical centres. The remote cardiac monitoring system is practiced in affluent countries but it is still not implemented in underdeveloped countries. The proposed cardiac Monitoring system plays a vital role in monitoring patients. In the proposed work the ML algorithms such as KNN, SVM, AD, DT, MLP, RF, NB, LR and XGBoost were done and the accuracy percentage of 87.5 was found from XGBoost. The Ultimate goal is to implement different machine learning methodologies for keeping track of the patient’s health.