Automated voice-based detection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) could facilitate the screening for COVID19. A dataset of cellular phone recordings from 88 subjects was recently collected. The dataset included vocal utterances, speech and coughs that were self-recorded by the subjects in either hospitals or isolation sites. All subjects underwent nasopharyngeal swabbing at the time of recording and were labelled as SARS-CoV-2 positives or negative controls. The present study harnessed deep machine learning and speech processing to detect the SARS-CoV-2 positives. A three-stage architecture was implemented. A self-supervised attention-based transformer generated embeddings from the audio inputs. Recurrent neural networks were used to produce specialized sub-models for the SARS-CoV-2 classification. An ensemble stacking fused the predictions of the sub-models. Pre-training, bootstrapping and regularization techniques were used to prevent overfitting. A recall of 78% and a probability of false alarm (PFA) of 41% were measured on a test set of 57 recording sessions. A leave-one-speaker-out cross validation on 292 recording sessions yielded a recall of 78% and a PFA of 30%. These preliminary results imply a feasibility for COVID19 screening using voice.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8769003 | PMC |
http://dx.doi.org/10.1109/OJEMB.2020.3026468 | DOI Listing |
J Clin Microbiol
March 2025
Institute of Virology, Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humbolt-Universität zu Berlin, Berlin, Germany.
The COVID-19 pandemic highlighted the importance of laboratory preparedness. Regular monitoring of diagnostic tools via external quality assessments (EQAs) is key to maintaining robust public health response service. We hereby conducted a third SARS-CoV-2 EQA assessing the diagnostic capabilities of European expert public health laboratories.
View Article and Find Full Text PDFFront Ophthalmol (Lausanne)
February 2025
Department of Ophthalmology, Medical University Graz, Graz, Austria.
Purpose: Our study aimed to investigate the prevalence and timing of ocular surface manifestations in hospitalized COVID-19 patients, providing insights into the occurrence of eye involvement before, during, or after the illness. This study contributes to understanding the extent of ocular involvement in COVID-19, which has been suggested to occur due to potential viral entry through the eyes.
Methods: 451 confirmed COVID-19 patients had a history of hospitalization in Styria, Austria.
Cureus
February 2025
Department of Independent Research, McNair Academic High School, Jersey City, USA.
Background and objective The actual community burden of SARS-CoV-2 is undervalued, as the estimates are just the symptomatic infections. The acute phase of the pandemic has waned, and the analytical comparison of infection spread through repeated sero-epidemiological studies is important in the formulation of effective public health strategies. This study investigated the level of seroprevalence of IgG antibodies for the SARS-CoV-2 virus in the Nagpur district, Maharashtra, India.
View Article and Find Full Text PDFFront Cardiovasc Med
February 2025
Department of Cardiology, The Second Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
Background: SARS-CoV-2 antibody positivity, whether due to natural infection or vaccination, is known to be associated with specific cardiac and vascular damage, yet its impact on cardiac structure and function in prospective cohorts remains incompletely understood.
Objective: We aimed to assess cardiac changes in the UK Biobank cohort among individuals with self-reported seropositive results for SARS-CoV-2 antibodies.
Methods: UK Biobank participants with self-reported serological results for SARS-CoV-2 antibodies, who underwent their first cardiac magnetic resonance (CMR) scan after 2019 were included.
Health Sci Rep
March 2025
Department of Dermatology, Rasool Akram Medical Complex Clinical Research Development Center (RCRDC), School of Medicine Iran University of Medical Sciences (IUMS) Tehran Iran.
Background And Aims: Vascular injuries characterized by petechiae, purpura, and ecchymosis have been reported as potential adverse effects following COVID-19 vaccination. This study aims to identify the characteristics of patients experiencing vascular injuries postvaccination and to outline key clinical considerations.
Methods: A systematic review was conducted in accordance with PRISMA guidelines.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!