Real-Time Mental Health Analytics Using IoMT and Social Media Datasets: Research and Challenges

Abstract

Feelings of physical and mental well-being are fundamental to the overall health of an individual. Mental health is one of the most neglected areas of public health and is a critical part of overall wellness, early detection and providing the right healthcare facilities is essential. Diagnosis and treatment for mental health issues should therefore be the focus for global health. A real-time health system acquires, accrue, analyze and transform clinical and operational intelligence into actionable information through digital technology. Internet of Medical Things (IoMT) devices like monitoring tools, wearables, and other sensors capture the patient's data, and the use of smart algorithms for IoMT data analytics provide healthcare providers with valuable insights that may help in faster diagnosis and in providing more targeted treatment plans for mental well-being. Similarly, mental health can be determined using social media data where psycholinguistic features can be extracted and analyzed from social big data like posts, comments, videos, etc., that exhibit their disposition and sentiments to determine behavioral patterns for early detection of mental health issues. This work presents an overview of the research conducted in the domain of real-time mental health analytics on two key datasets, i.e., IoMT and social media datasets. The study demonstrates the research community's keenness within the domain and eventually helps to establish the primary challenges in real-time mental health analytics.