Publication
Title
Imagistic findings using artificial intelligence in vaccinated versus unvaccinated SARS-CoV-2-positive patients receiving in-care treatment at a tertiary lung hospital
Author
Abstract
Background: In December 2019 the World Health Organization announced that the widespread severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection had become a global pandemic. The most affected organ by the novel virus is the lung, and imaging exploration of the thorax using computer tomography (CT) scanning and X-ray has had an important impact. Materials and Methods: We assessed the prevalence of lung lesions in vaccinated versus unvaccinated SARS-CoV-2 patients using an artificial intelligence (AI) platform provided by Medicai. The software analyzes the CT scans, performing the lung and lesion segmentation using a variant of the U-net convolutional network. Results: We conducted a cohort study at a tertiary lung hospital in which we included 186 patients: 107 (57.52%) male and 59 (42.47%) females, of which 157 (84.40%) were not vaccinated for SARS-CoV-2. Over five times more unvaccinated patients than vaccinated ones are admitted to the hospital and require imaging investigations. More than twice as many unvaccinated patients have more than 75% of the lungs affected. Patients in the age group 30-39 have had the most lung lesions at almost 69% of both lungs affected. Compared to vaccinated patients with comorbidities, unvaccinated patients with comorbidities had developed increased lung lesions by 5%. Conclusion: The study revealed a higher percentage of lung lesions among unvaccinated SARS-CoV-2-positive patients admitted to The National Institute of Pulmonology "Marius Nasta" in Bucharest, Romania, underlining the importance of vaccination and also the usefulness of artificial intelligence in CT interpretation.
Language
English
Source (journal)
Journal of Clinical Medicine
Publication
2023
ISSN
2077-0383
DOI
10.3390/JCM12227115
Volume/pages
12 :22 (2023) , p. 1-11
Article Reference
7115
ISI
001113578400001
Pubmed ID
38002725
Full text (Publisher's DOI)
Full text (open access)
UAntwerpen
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Web of Science
Record
Identifier
Creation 09.01.2024
Last edited 11.01.2024
To cite this reference