{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Elbeji A"],"funding":["André Losch Foundation","Luxembourg National Research Fund","Luxembourg Institute of Health"],"pagination":["e062463"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9684280"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["12(11)"],"pubmed_abstract":["<h4>Objective</h4>To develop a vocal biomarker for fatigue monitoring in people with COVID-19.<h4>Design</h4>Prospective cohort study.<h4>Setting</h4>Predi-COVID data between May 2020 and May 2021.<h4>Participants</h4>A total of 1772 voice recordings were 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 2 weeks following SARS-CoV-2 infection.<h4>Primary and secondary outcome measures</h4>Four machine learning algorithms (logistic regression, k-nearest neighbours, support vector machine and soft voting classifier) were used to train and derive the fatigue vocal biomarker. The models were evaluated based on the following metrics: area under the curve (A"],"journal":["BMJ open"],"pubmed_title":["Vocal biomarker predicts fatigue in people with COVID-19: results from the prospective Predi-COVID cohort study."],"pmcid":["PMC9684280"],"funding_grant_id":["N/A","14716273"],"pubmed_authors":["Despotovic V","Nazarov PV","Elbeji A","Higa E","Fischer A","Zhang L","Aguayo G","Fagherazzi G"],"additional_accession":[]},"is_claimable":false,"name":"Vocal biomarker predicts fatigue in people with COVID-19: results from the prospective Predi-COVID cohort study.","description":"<h4>Objective</h4>To develop a vocal biomarker for fatigue monitoring in people with COVID-19.<h4>Design</h4>Prospective cohort study.<h4>Setting</h4>Predi-COVID data between May 2020 and May 2021.<h4>Participants</h4>A total of 1772 voice recordings were 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 2 weeks following SARS-CoV-2 infection.<h4>Primary and secondary outcome measures</h4>Four machine learning algorithms (logistic regression, k-nearest neighbours, support vector machine and soft voting classifier) were used to train and derive the fatigue vocal biomarker. The models were evaluated based on the following metrics: area under the curve (A","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Nov","modification":"2026-05-27T19:11:11.878Z","creation":"2025-02-19T03:23:28.901Z"},"accession":"S-EPMC9684280","cross_references":{"pubmed":["36414294"],"doi":["10.1136/bmjopen-2022-062463"]}}