The Diagnostic Utility of Artificial Intelligence-Guided Computed Tomography-Based Severity Scores for Predicting Short-Term Clinical Outcomes in Adults with COVID-19 Pneumonia.

Publication date: Nov 10, 2023

Chest computed tomography (CT) imaging with the use of an artificial intelligence (AI) analysis program has been helpful for the rapid evaluation of large numbers of patients during the COVID-19 pandemic. We have previously demonstrated that adults with COVID-19 infection with high-risk obstructive sleep apnea (OSA) have poorer clinical outcomes than COVID-19 patients with low-risk OSA. In the current secondary analysis, we evaluated the association of AI-guided CT-based severity scores (SSs) with short-term outcomes in the same cohort. In total, 221 patients (mean age of 52. 6 +/- 15. 6 years, 59% men) with eligible chest CT images from March to May 2020 were included. The AI program scanned the CT images in 3D, and the algorithm measured volumes of lobes and lungs as well as high-opacity areas, including ground glass and consolidation. An SS was defined as the ratio of the volume of high-opacity areas to that of the total lung volume. The primary outcome was the need for supplemental oxygen and hospitalization over 28 days. A receiver operating characteristic (ROC) curve analysis of the association between an SS and the need for supplemental oxygen revealed a cut-off score of 2. 65 on the CT images, with a sensitivity of 81% and a specificity of 56%. In a multivariate logistic regression model, an SS > 2. 65 predicted the need for supplemental oxygen, with an odds ratio (OR) of 3. 98 (95% confidence interval (CI) 1. 80-8. 79; p < 0. 001), and hospitalization, with an OR of 2. 40 (95% CI 1. 23-4. 71; p = 0. 011), adjusted for age, sex, body mass index, diabetes, hypertension, and coronary artery disease. We conclude that AI-guided CT-based SSs can be used for predicting the need for supplemental oxygen and hospitalization in patients with COVID-19 pneumonia.

Open Access PDF

Concepts Keywords
Covid artificial intelligence
Hospitalization chest CT
Intelligence clinical outcomes
Pneumonia COVID-19
Tomography supplemental oxygen


Type Source Name
disease MESH COVID-19
disease MESH Pneumonia
disease MESH infection
disease MESH obstructive sleep apnea
disease IDO algorithm
disease VO volume
drug DRUGBANK Oxygen
drug DRUGBANK Saquinavir
disease MESH hypertension
disease MESH coronary artery disease
disease MESH Allergy
disease VO USA
disease VO organization
drug DRUGBANK Coenzyme M
disease VO time
drug DRUGBANK Aspartame
disease IDO process
disease VO effective
disease VO population
disease VO protocol
disease MESH malignancies
disease MESH tuberculosis
pathway KEGG Tuberculosis
disease MESH scars
disease MESH atelectasis
disease IDO history
pathway KEGG Coronavirus disease
disease VO dose

Original Article

(Visited 1 times, 1 visits today)