This paper is only available as a PDF. To read, Please Download here.
Objective
To investigate the performance of a commercially available artificial intelligence (AI) algorithm for detection of pulmonary embolism (PE) on contrast-enhanced CTs in patients hospitalized for COVID-19.
Patients & Methods
Retrospective analysis was performed of all contrast-enhanced chest CTs on patients admitted for COVID-19 between March 2020 and December 2021. Based on the original radiology reports, all PE-positive exams were included (n=527). Using a reversed flow single gate diagnostic accuracy case-control model, a randomly selected cohort of PE-negative exams (n=977) was included. Pulmonary parenchymal disease severity was assessed for all included studies using a semi-quantitative system, the Total Severity Score (TSS). All included CTs were sent for interpretation by the commercially available AI algorithm, Aidoc. Discrepancies between AI and original radiology reports were resolved by three blinded radiologists, who rendered a final determination of indeterminate, positive, or negative.
Results
A total of 78 studies were found to be discrepant, of which 13 (16.6%) were deemed indeterminate by readers and excluded. The sensitivity and specificity of AI was 93.2%; (95% confidence interval [CI] 90.6-95.2%), and 99.6%; (95% CI 98.9-99.9%), respectively. AI's accuracy for all TSS groups (mild, moderate, severe) was high (98.4%, 96.7%, and 97.2%, respectively). AI was more accurate in PE detection on CTPAs vs CECTs (P < .001), with optimal HU of 362 (P=.048).
Conclusion
The AI algorithm demonstrated high sensitivity, specificity, and accuracy for PE on contrast enhanced CTs in COVID-19 patients regardless of parenchymal disease. Accuracy was significantly affected by the mean attenuation of the pulmonary vasculature. How this affects the legitimacy of the binary outcomes reported by AI is not yet known.
Abbreviations:
AI (artificial intelligence), CECT (contrast-enhanced computed tomography), COVID-19 (Coronavirus disease 2019), CTPA (computed tomography pulmonary angiogram), FN (false negative), FP (false positive), HU (Hounsfield unit), PE (pulmonary embolism), SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2), TN (true negative), TP (true positive)Article info
Publication history
Accepted:
March 3,
2023
Received:
January 6,
2023
Publication stage
In Press Accepted ManuscriptFootnotes
All authors declare no conflict of interest
Key Results
Sensitivity and specificity of the artificial intelligence algorithm for the detection of pulmonary embolism in hospitalized COVID-19 patients was 93.2% and 99.6%, respectively.
The degree of parenchymal disease characterized by the total severity scoring system did not affect the accuracy of AI (P=.375).
The accuracy of artificial intelligence was affected by the mean attenuation in the pulmonary vasculature and was significantly higher in the CTPA group compared to the contrast-enhanced CT (P<.001) with an optimal cutoff value for AI at 362 HU (P=.048).
Identification
Copyright
© 2023 THE AUTHORS. Published by Elsevier Inc on behalf of Mayo Foundation for Medical Education and Research.
User license
Creative Commons Attribution – NonCommercial – NoDerivs (CC BY-NC-ND 4.0) | How you can reuse 
Elsevier's open access license policy
Creative Commons Attribution – NonCommercial – NoDerivs (CC BY-NC-ND 4.0)
Permitted
For non-commercial purposes:
- Read, print & download
- Redistribute or republish the final article
- Text & data mine
- Translate the article (private use only, not for distribution)
- Reuse portions or extracts from the article in other works
Not Permitted
- Sell or re-use for commercial purposes
- Distribute translations or adaptations of the article
Elsevier's open access license policy
