The pandemic of Coronavirus Disease 2019 (COVID-19) is causing enormous loss of life globally. Prompt case identification is critical. The reference method is the real-time reverse transcription PCR (RT-PCR) assay, whose limitations may curb its prompt large-scale application. COVID-19 manifests with chest computed tomography (CT) abnormalities, some even before the onset of symptoms. We tested the hypothesis that the application of deep learning (DL) to 3D CT images could help identify COVID-19 infections. Using data from 920 COVID-19 and 1,073 non-COVID-19 pneumonia patients, we developed a modified DenseNet-264 model, COVIDNet, to classify CT images to either class. When tested on an independent set of 233 COVID-19 and 289 non-COVID-19 pneumonia patients, COVIDNet achieved an accuracy rate of 94.3% and an area under the curve of 0.98. As of March 23, 2020, the COVIDNet system had been used 11,966 times with a sensitivity of 91.12% and a specificity of 88.50% in six hospitals with PCR confirmation. Application of DL to CT images may improve both efficiency and capacity of case detection and long-term surveillance.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7892869 | PMC |
| http://dx.doi.org/10.1038/s41598-021-83424-5 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Comparison of clinical characteristics and outcomes in candidaemia patients with and without COVID-19: a multicentre retrospective study.
BMC Infect Dis
December 2024
Department of Infectious Disease, Department of Internal Medicine, Chonnam National University Medical School, 42, Jebong Ro, Donggu, Gwangju, 61469, South Korea.
Background: Invasive fungal infections have been reported as complications with significant mortality and morbidity in patients hospitalized with COVID-19. This study aimed to evaluate the clinical characteristics and outcomes of candidaemia patients with COVID-19 and to investigate the association between COVID-19 and mortality in candidaemia patients.
Methods: This retrospective study included candidaemia patients aged 18 years or older admitted to four university-affiliated tertiary hospitals in South Korea between January 1, 2020, and December 31, 2022.
Performance of A-DROP, NEWS2, and REMS in predicting in-hospital mortality and mechanical ventilation in pneumonia patients in the emergency department: a retrospective cohort study.
Int J Emerg Med
December 2024
Department of Emergency Medicine, Faculty of Medicine, Siriraj Hospital, Mahidol University, 2 Wanglang Road, Bangkoknoi, Bangkok, 10700, Thailand.
Background: Pneumonia is a potentially life-threatening respiratory tract infection. Many Early Warning Scores (EWS) were developed to detect patients with high risk for adverse clinical outcomes, but few have explored the utility of these EWS for pneumonia patients in the Emergency Department (ED) setting. We aimed to compare the prognostic utility of A-DROP, NEWS2, and REMS in predicting in-hospital mortality and the requirement for mechanical ventilation among ED patients with pneumonia.
View Article and Find Full Text PDFDaily activities change is linked to acute angle closure occurrence in COVID-19 co-infected patients.
BMC Ophthalmol
December 2024
National Clinical Research Center for Ocular Diseases, Eye Hospital, Wenzhou Medical University, Wenzhou, 3250027, China.
Objectives: To analyze the influence of daily activity-related factors associated with COVID-19 infection on the occurrence of acute angle closure (AAC).
Methods: A multicenter hospital-based study was conducted at 23 ophthalmic centers in 17 provincial-level regions across China to recruit patients with confirmed AAC during the post-lockdown time of COVID-19 (P-TOC) from Dec 7, 2022, to Jan 17, 2023, and three lockdown time of COVID-19 (TOC) periods, which included the TOC-2022 (Sep 7, 2022 - Dec 6, 2022), TOC-2021(Sep 7, 2021 - Jan 6, 2022) and TOC-2020 (Sep 7, 2020 - Jan 6, 2021). Patient information, including demographic, a questionnaire on daily activity changes during the AAC period, COVID-19 history, and eye examination results, was collected.
Molecular pathogen profiling of COVID-19 coinfections.
BMC Infect Dis
December 2024
Department of Laboratory Medicine, The First Affiliated Hospital of Ningbo University, Ningbo, Zhejiang, China.
Objective: This study aims to investigate the prevalence, pathogen spectrum, clinical characteristics, and prognosis-related factors of other respiratory pathogens in COVID-19-infected patients, and to explore the application of molecular detection methods in the epidemiological investigation of multiple pathogen infections.
Methods: Respiratory samples and clinical data from 384 patients with outpatient and inpatient respiratory infections were collected and analyzed. Multiplex PCR and capillary electrophoresis were conducted to detect the distribution characteristics of 26 pathogen species, comprising 13 viruses, 13 bacteria.
Cognition, function, and mood post-COVID-19: Comparative analysis using the health and retirement study.
PLoS One
December 2024
School of Nursing, University of Washington, Seattle, Washington, United States of America.
Millions of Americans endure post-COVID conditions (PCC), yet research often lacks pre-illness measurements, relying primarily on follow-up assessments for analysis. The study aims to examine the prevalence of PCC, including cognitive impairment, functional limitation, and depressive symptoms, along with relevant risk factors, while controlling for individuals' pre-illness status measured in 2018. A cross-sectional retrospective study utilized the 2018 and 2020 Health and Retirement Study surveys.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!