Northwestern University (NU) researchers have developed a new artificial intelligence (AI) platform, called DeepCOVID-XR, to detect COVID-19 by analyzing X-ray images of the lungs.
The machine-learning algorithm has outperformed a team of specialized thoracic radiologists by spotting COVID-19 in X-rays about 10 times faster and 1-6 percent more accurately.
To develop, train and test the new algorithm, the researchers used 17,002 chest X-ray images. Of those images, 5,445 came from COVID-19-positive patients from sites across the Northwestern Memorial Healthcare System.
The researchers then tested DeepCOVID-XR against five experienced cardiothoracic fellowship-trained radiologists on 300 random test images from Lake Forest Hospital. Each radiologist took approximately two-and-a-half to three-and-a-half hours to examine this set of images, whereas the AI system took about 18 minutes.
The radiologists' accuracy ranged from 76-81 percent. DeepCOVID-XR performed slightly better at 82-percent accuracy.
"Radiologists are expensive and not always available," said NU's Aggelos Katsaggelos, an AI expert and senior author of the study. "X-rays are inexpensive and already a common element of routine care. This could potentially save money and time -- especially because timing is so critical when working with COVID-19."
NU researchers have made the algorithm publicly available with hopes that others can continue to train it with new data. DeepCOVID-XR is still in the research phase, but could potentially be used in the clinical setting in the future.
The study was published Tuesday in the journal Radiology.
