Background: Contactless symptom tracking is essential for the diagnosis of COVID-19 cases that need hospitalization. Indications from sensors and user descriptions have to be combined in order to make the right decisions.
Methods: The proposed multipurpose platform Coronario combines sensory information from different sources for a valid diagnosis following a dynamically adaptable protocol. The information exchanged can also be exploited for the advancement of research on COVID-19. The platform consists of mobile and desktop applications, sensor infrastructure, and cloud services. It may be used by patients in pre- and post-hospitalization stages, vulnerable populations, medical practitioners, and researchers.
Results: The supported audio processing is used to demonstrate how the Coronario platform can assist research on the nature of COVID-19. Cough sounds are classified as a case study, with 90% accuracy.
Discussion/conclusions: The dynamic adaptation to new medical protocols is one of the main advantages of the developed platform, making it particularly useful for several target groups of patients that require different screening methods. A medical protocol determines the structure of the questionnaires, the medical sensor sampling strategy and, the alert rules.
Keywords: COVID-19 symptom tracking; Cloud; Cough/respiratory sound classification; Dynamic medical protocol; Mobile app.
Copyright © 2020 by S. Karger AG, Basel.