ABSTRACT
Objective To develop a vocal biomarker for fatigue monitoring in people with COVID-19. Design Prospective cohort study. Setting Predi-COVID data between May 2020 and May 2021. Participants A total of 1772 voice recordings was used to train an AI-based algorithm to predict fatigue, stratified by gender and smartphone s operating system (Android/iOS). The recordings were collected from 296 participants tracked for two weeks following SARS-CoV-2 infection. primary and secondary outcome measures Four machine learning algorithms (Logistic regression, k-nearest neighbors, support vector machine, and soft voting classifier) were used to train and derive the fatigue vocal biomarker. A t-test was used to evaluate the distribution of the vocal biomarker between the two classes (Fatigue and No fatigue). Results The final study population included 56% of women and had a mean (SD) age of 40 (13) years. Women were more likely to report fatigue (P
Subject(s)
COVID-19 , FatigueABSTRACT
BACKGROUND: After the World Health Organization declared the outbreak of coronavirus disease to be a public health emergency of international concern on January 30, 2020, the first SARS-CoV-2 infection was detected in Luxembourg on February 29, 2020. Representative population-based data, including asymptomatic individuals for assessing the viral spread and immune response were, however, lacking worldwide. METHODS: Using a panel-based method, we implemented a representative sample of the Luxembourgish population based on age, gender and residency for testing for SARS-CoV-2 infection and antibody status in order to define prevalence irrespective of clinical symptoms. Participants were contacted via email to fill an online questionnaire before biosampling at local laboratories. All participants provided information related to clinical symptoms, epidemiology, socioeconomic and psychological assessments and underwent biosampling, rRT-PCR testing and serology for SARS-CoV-2. RESULTS: We included a total of 1862 individuals in our representative sample of the general Luxembourgish population. Of these, 5 individuals had a current positive result for infection with SARS-CoV-2 based on rRT-PCR. Four of these individuals were oligosymptomatic and one was asymptomatic. Overall we found a positive IgG antibody status in 35 individuals (1.97%), of which 11 reported to be tested positive by rRT-PCR for SARS-CoV-2 previously and showed in addition their IgG positive status also a positive status for IgA. Our data indicate a prevalence of 0.3% for active SARS-CoV-2 infection and an infection rate of 2.15% in the Luxembourgish population between 18 and 79 years of age. CONCLUSIONS: Luxembourgish residents show a low rate of acute infections after 7 weeks of confinement and present with an antibody profile indicative of a more recent immune response to SARS-CoV-2. All infected individuals were oligo- or asymptomatic. Bi-weekly follow-up visits over the next 2 months will inform about the viral spread by a- and oligosymptomatic carriers and the individual changes in the immune profile.