Insights into Internet of Medical Things (IoMT): Data fusion, security issues and potential solutions

Abstract

The Internet of Medical Things (IoMT) has created a wide range of opportunities for knowledge exchange in numerous industries. The opportunities include patient empowerment, healthcare collaboration, medical education and training, remote monitoring and telemedicine, customized treatment plans, data sharing for innovation, continuous medical learning, supply chain management, public health initiatives, wearable health devices, and quality improvement initiatives. However, the adoption of IoMT faces numerous challenges regarding interoperability, data privacy, security, regulatory, and infrastructure costs. This paper aims to address the implications of data fusion in IoMT, as well as the associated security challenges and their potential solutions, which are lacking in the literature. Data collected from IoMT devices has a direct impact on the accuracy of predictions because of its quality, quantity, and relevance. With an accuracy of 99.53 % to 99.99 %, the Epilepsy seizure detector-based Naive Bayes (ESDNB) algorithm is found to be the most effective for detecting epileptic seizures in IoMT networks. However, the way data are stored must also undergo a major revolution, and all phases—collection, protection, and storage—need to be improved. The standardization of architecture and security measures may improve the detection of security threats and compromises. Methods to detect malware in cross platforms is also an avenue for future research that can effectively tackle the heterogeneity of the IoMT systems. Cryptography and blockchain technology have shown to be promising ways to increase the security of an IoMT-based system. The findings of this review will assist a wide variety of stakeholders in the healthcare ecosystem.