IEEE Access (Jan 2024)

CoViS: A Contactless Health Monitoring System for the Nursing Home

  • Sergio Ivan Lopes,
  • Fabio Silva,
  • Pedro Pinho,
  • Paulo Marques,
  • Carlos Abreu,
  • Joao Milheiro,
  • Bruno Braga,
  • Gabriel Queiros,
  • Rita Almeida,
  • Nuno Borges Carvalho

DOI
https://doi.org/10.1109/ACCESS.2024.3355060
Journal volume & issue
Vol. 12
pp. 20802 – 20821

Abstract

Read online

In a pandemic, the availability of health indicators among at-risk populations, such as the elderly, is crucial due to the disease’s rapid transmission and the need to act quickly to contain its evolution. Traditional clinical methods for monitoring vital signs typically involve contact-based sensors that must be precisely attached by a skilled healthcare professional. However, these methods are less practical for repeatable measurements and are unsuitable for long-term monitoring. On the other hand, contactless vital signs monitoring, employing radar-based techniques or IR-thermal imaging, eliminates the need for physical electrodes and proves beneficial for remote health monitoring. This not only reduces physical contact between subjects and healthcare professionals, ensuring social distancing, especially in nursing homes, but also shields the elderly population from external factors that may increase the likelihood of infection. This article presents three key contributions: (i) vital signs characterization in the elderly population; (ii) a state-of-the-art review of the most prominent techniques and methods for Contactless Health Monitoring (CHM); (iii) the design, specification, and evaluation of a low-cost proof-of-concept CHM system for nursing homes, incorporating an IoT Edge Device. This facilitates real-time monitoring of vital signs (cardio-respiratory rates and elevated body temperature) using a multimodal approach based on Doppler radar and IR thermal imaging sensors, generating health indicators without any form of contact or invasiveness. Direct comparisons with reference instruments have revealed an error rate below 10%, in 74%, 52%, and 96% of cases for Heart Rate, Respiratory Rate, and Body Temperature measurements, respectively.

Keywords