Researchers from Northwestern University and Northwestern Memorial Hospital developed a new AI system, DeepCOVID-XR, which can detect COVID-19 by analyzing X-ray images of the lungs. It serves as an early warning system, letting people know they need to isolate if they're found to have COVID-19. Results are available in seconds, well before regular tests. In a test against experienced radiologists, DeepCOVID-XR took about 18 minutes to examine 300 random test images while each radiologist took approximately 2.5-3.5 hours.
This research paper "DeepCOVID-XR: An Artificial Intelligence Algorithm to Detect COVID-19 on Chest Radiographs Trained and Tested on a Large US Clinical Dataset" is published in the Journal of Radiology.
DeepCOVID-XR, an artificial intelligence algorithm for detecting COVID-19 on chest radiographs, demonstrated performance similar to the consensus of experienced thoracic radiologists.
- DeepCOVID-XR classified 2,214 test images (1,194 COVID-19 positive) with an accuracy of 83% and AUC of 0.90 compared with the reference standard of RT-PCR.
- On 300 random test images (134 COVID-19 positive), DeepCOVID-XR’s accuracy was 82% (AUC 0.88) compared to 5 individual thoracic radiologists (accuracy 76%-81%) and the consensus of all 5 radiologists (accuracy 81%, AUC 0.85).
- Using the consensus interpretation of the radiologists as the reference standard, DeepCOVID-XR’s AUC was 0.95.