IOT based Heart Disease Prediction using Machine Learning

Abstract

The proliferation of IoT devices offers a transformative solution to the pervasive issue of health monitoring, particularly in light of its potential to avert serious health complications stemming from inadequate surveillance. In the contemporary landscape, the healthcare sector is witnessing a proliferation of IoT-enabled devices facilitating remote patient monitoring and healthcare professionals' vigilance over their patients. This burgeoning trend, augmented by the burgeoning ecosystem of healthcare technology start-ups,
heralds a paradigm shift in the healthcare industry, with IoT technology at its vanguard, poised to revolutionize healthcare delivery and patient outcomes. The objective of the study is to develop a robust artificial neural network (ANN)-based model for efficient heart disease prediction, employing Internet of Things (IoT) technology. The primary aim is to accurately classify patients into two categories: those diagnosed with heart disease (1) and those not diagnosed with heart disease (0), utilizing a binary outcome
framework. To achieve this, we propose an IoT-integrated healthcare system tailored for heart disease prediction using artificial neural network. This approach is contrasted against conventional machine learning algorithms including Support Vector Machines (SVM), Logistic Regression (LR), Decision Trees (DT), and k-Nearest Neighbors (KNN).