Investigating the role of machine learning techniques in internet of things during the COVID-19 pandemic: A systematic review

Abstract

Background: Research has shown that the use the Internet of Things (IoT) and artificial intelligence (AI) can enhance the effectiveness of telemedicine. Therefore, the objective of this study is to systematically investigate the utilization of machine learning (ML)-based IoT during the COVID-19 pandemic. Methods: A comprehensive search of PubMed, Scopus and IEEE was conducted from January 2020 to February 2023 according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Results: Out of the 1576 studies identified, 57 were included in the analysis. The use of IoT was 30 % for detection and 22 % for monitoring. Parameters considered included vital signs, diagnostic images, physical symptoms, tests, air quality, and medical history. A review of the sensors revealed that body temperature sensors were of interest in 65 % of the studies. The random forest algorithm was found to be the most common ML model, used in 14 % of the studies. Performance measures were reported in over 90 % of the studies to evaluate the models. Conclusion: This study provides valuable insights into the integration of IoT and ML to address challenges related to COVID-19. This systematic review can serve as a roadmap for advancing research at the intersection of healthcare, IoT, and ML.

Keywords

• IoT
• Internet of things
• Artificial intelligence
• Machine learning
• Data mining
• COVID-19