Research Direction Toward IoT-Based Machine Learning-Driven Health Monitoring Systems: A Survey

Abstract

Nowadays, the rapid growth of technology has emerged, and the outbreak of diseases has become a crucial issue. The healthcare industries and professionals face many challenges in controlling diseases and taking preventive measures in the IoT environment. With busy schedules, it is impossible to maintain a healthy lifestyle. The above-mentioned challenges are eliminated by using the smart health monitoring system. The fatality management and preventive health care in patients are attained by the utilization of machine learning and deep learning techniques that have achieved multiple targets related to health diseases of the patients concerning the analysis of the health data. The Internet of Things (IoT) has shown high potential for providing medical services in remote locations with the involvement of different medical devices and sensors. These approaches allow moving from the visionary approach and provide quick spotting of trends and recommendations as early as possible. In addition, these approaches have improved patient safety, accessibility of healthcare services, operational efficiency, and decreased the cost requirements in the healthcare industry. Therefore, this research work has collected some of the research works on IoT machine-driven health monitoring systems and explored the possibilities in designing the health monitoring systems. This work discusses the datasets used for health monitoring systems, performance measures for evaluating the system, the type of diseases considered for health monitoring systems, and algorithms employed for predicting and detecting the diseases. Finally, this review explores the research challenges and future research directions in the field of health monitoring systems.