science

AI detects COVID-19 on chest X-rays with accuracy, speed

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.

Related posts

Researchers find close relatives to COVID-19 pathogen in samples collected in 2010

xxx

Gut microbes involved in pathogenesis of autism: study

xxx

Aussie research on bioprinting mini kidney raises hope for lab-grown transplantation

xxx