Building an Intelligent Telemonitoring System for Heart Failure: The Use of the Internet of Things, Big Data, and Machine Learning

Abstract

Heart failure (HF) is a significant and chronic health disease. Nevertheless, despite the high mortality rate and associated costs, it can be managed. Emerging technologies such as artificial intelligence, big data, and internet of things offer advantages for the management of HF. Using the medical records of HF patients, five machine learning algorithms - deep learning (DL), generalized linear models (GLM), naïve base (NB), random forest (RF), and support vector machines(SVM) were used to build classifiers to predict HF. The results indicate that machine learning algorithms are effective tools for classifying the medical records of HF patients. GLM and SVM can potentially be utilized together to predict HF with high classification accuracy.