Abstract
Impressive growth in the number of wearable health monitoring devices has affected global health industry as they provide rapid and intricate details related to physical examinations, such as discomfort, heart rate, and blood glucose level, which enable doctors to efficiently diagnose sensitive heart troubles. The Internet of Medical Things (IoMT) is a phenomenon wherein computer networks and medical equipment are connected through the Internet to provide real-time interaction between physicians and patients. In this article, we present a comprehensive view of the IoMT and its related Machine Learning (ML)-based developed frameworks designed, or being utilized, in the last decade, i.e., from 2010 to 2019. The presented techniques are designed for monitoring limbs, controlling rural healthcare, identifying e-health applications, monitoring health through mobile apps, classifying heart sounds, detecting stress in drivers, monitoring cardiac diseases, making the decision to predict heart attacks, recognizing human activities, and classifying breast cancer. The aim is to provide a clear picture of the existing IoMT environment so that the analysis may pave the way for the diagnosis of critical disorders such as cancer, heart attack, and blood pressure among others. In the end, we also provide some unresolved challenges that are confronted in the deployment of the secure IoMT-based healthcare systems.