Résumé
In order to reduce the burden on healthcare systems and in particular to support an appropriate way to the Emergency Department (ED) access, home tele-monitoring patients was strongly recommended during the COVID-19 pandemic. Furthermore, paper from numerous groups has shown the potential of using data from wearable devices to characterize each individual's unique baseline, identify deviations from that baseline suggestive of a viral infection, and to aggregate that data to better inform population surveillance trends. However, no evidence about usage of Artificial Intelligence (AI) applicatives on digitally data collected from patients and doctors exists. With a growing global population of connected wearable users, this could potentially help to improve the earlier diagnosis and management of infectious individuals and improving timeliness and precision of tracking infectious disease outbreaks. During the study RICOVAI-19 (RICOVero ospedaliero con strumenti di Artificial Intelligence nei pazienti con COVid-19) performed in a Marche Region, Italy, we evaluated N129 subjects monitored at home in a six-months period between March 22, 2021 and October 22, 2021. During the monitoring, personal on demand health technologies were used to collect clinical and vital data in order to feed the database and the machine learning engine. The AI output resulted in a clinical stability index (CSI) which enables the system to deliver suggestions to the population and doctors about how intervene . Results showed the beneficial influence of CSI for predicting clinical classes of subjects and identifying who of them need to be admitted at ED. The same pattern of results was confirming the alert included in the decision support system in order to request further testing or clinical information in some cases. In conclusion, our study does support an high impact of AI tools on COVID outcomes to fight this pandemic by driving new approaches to public awareness.