qure_logo.svg

Published 13 Jan 2022

Using artificial intelligence to risk stratify COVID19 patients based on chest X-ray findings

Author: Diego A Hipolito Canario1, Eric Fromke1, Matthew A. Patetta1, Mohamed T. Eltilib1, Juan P. Reyes-Gonzalez2, Georgina Cornelio Rodriguez2, Valeria A. Fusco Cornejo3, Seymour Dunckner3 and Jessica K. Stewart4. 1

SHARE

https://cms.qure.ai

Back

Background
Deep learning-based radiological image analysis could facilitate use of chest x-rays as a triaging tool for COVID-19 diagnosis in resource-limited settings. This study sought to determine whether a modified commercially available deep learning algorithm (M-qXR) could risk stratify patients with suspected COVID-19 infections. 
Methods
A dual track clinical validation study was designed to assess the clinical accuracy of M-qXR. The algorithm evaluated all Chest-X-rays (CXRs) performed during the study period for abnormal findings and assigned a COVID-19 risk score. Four independent radiologists served as radiological ground truth. The M-qXR algorithm output was compared against radiological ground truth and summary statistics for prediction accuracy were calculated. In addition, patients who underwent both PCR testing and CXR for suspected COVID-19 infection were included in a co-occurrence matrix to assess the sensitivity and specificity of the M-qXR algorithm. 
Results
625 CXRs were included in the clinical validation study. 98% of total interpretations made by M-qXR agreed with ground truth (p = 0.25). M-qXR correctly identified the presence or absence of pulmonary opacities in 94% of CXR interpretations. M-qXR’s sensitivity, specificity, PPV, and NPV for detecting pulmonary opacities were 94%, 95%, 99%, and 88% respectively. M-qXR correctly identified the presence or absence of pulmonary consolidation in 88% of CXR interpretations (p = 0.48). M-qXR’s sensitivity, specificity, PPV, and NPV for detecting pulmonary consolidation were 91%, 84%, 89%, and 86% respectively. Furthermore, 113 PCR-confirmed COVID-19 cases were used to create a co-occurrence matrix between M-qXR’s COVID-19 risk score and COVID-19 PCR test results. The PPV and NPV of a medium to high COVID-19 risk score assigned by M-qXR yielding a positive COVID-19 PCR test result was estimated to be 89.7% and 80.4% respectively. 
Conclusion
M-qXR was found to have comparable accuracy to radiological ground truth in detecting radiographic abnormalities on CXR suggestive of COVID-19. 

Authors

Diego A Hipolito Canario1, Eric Fromke1, Matthew A. Patetta1, Mohamed T. Eltilib1, Juan P. Reyes-Gonzalez2, Georgina Cornelio Rodriguez2, Valeria A. Fusco Cornejo3, Seymour Dunckner3 and Jessica K. Stewart4. 1

Citation

1. UNC School of Medicine 2. University of North Carolina at Chapel Hill 3. Bondurant Hall 4. CB 9535 5. Chapel Hill 6. NC 7. 27599-3280 8. United States Department of Radiology 9. Angeles del Pedregal Hospital 10. Camino de Sta 11. Teresa 1055-S 12. Héroes de Padierna 13. La Magdalena Contreras 14. 10700 15. Ciudad de México 16. Mexico Mindscale 17. 800 W El Camino Real Suite 180 Mountain View 18. CA 19. 94040 20. United States Division of Interventional Radiology 21. Department of Radiology 22. David Geffen School of Medicine 23. University of California at Los Angeles. 757 Westwood Plaza 24. Suite 2125 25. Los Angeles 26. CA 27. 90095 28. United States

Share this publication