COVID-19 Detection Through Smartphone-recorded Coughs Using Artificial Intelligence: An Analysis of Applicability for Pre-screening COVID-19 Patients in Vietnam

Abstract

The Covid-19 pandemic is one of the most serious global health epidemics in recent decades. Its consequences have affected hundreds of millions of people in countries around the world because of the high contagiousness and mortality rate of the virus. Since the fourth wave of Covid-19 infections broke out and spread to many cities and provinces in Vietnam, there were over 10,000 infected cases in the community within two months by the Delta coronavirus variants. Therefore, it is very necessary to have a faster and more effective method to prescreen and isolate infected patients as soon as possible. That is why the paper proposes a method using artificial intelligence techniques to detect covid-19 infected patients based on smartphone-recorded cough sounds. The learning models are built using the publicly available data as COUGHVID and Coswara. An analysis of the applicability of the learning models for prescreening Covid-19 patients in Vietnam is also mentioned in the paper.