As coronavirus continues to spread throughout the U.S. and the world and overburden hospitals and medical personnel, it is more critical than ever to develop tools to aid in swift and accurate triage and isolation of COVID-19 patients. A study published Nov/ 24 in Radiology reports that DeepCOVID-XR, an artificial intelligence (AI) algorithm trained to detect COVID-19 on chest X-rays, performs at the level of a consensus of experienced chest radiologists.
DeepCOVID-XR is an ensemble of convolutional neural networks to detect COVID-19 on frontal chest X-rays using real-time polymerase chain reaction (RT-PCR) as a reference standard. The algorithm was trained and validated on a large dataset of 14,788 images (4,253 COVID-19 positive) from sites across the Northwestern Memorial Healthcare System from February 2020 to April 2020, then tested on 2,214 images (1,192 COVID-19 positive) from a single institution.
A total of 5,853 patients (58±19 years, 3,101 women) were evaluated across datasets. On the entire test set, DeepCOVID-XR’s accuracy was 83%. On 300 random test images (134 COVID-19 positive), DeepCOVID-XR’s accuracy was 82%, compared to a consensus of 5 radiologists (81%).
“We feel that this algorithm has the potential to benefit healthcare systems in mitigating unnecessary exposure to the virus by serving as an automated tool to rapidly flag patients with suspicious chest imaging for isolation and further testing,” the authors wrote.
Accompanying editorial: “The Potential of Artificial Intelligence to Analyze Chest Radiographs for Signs of COVID-19 Pneumonia”Back To Top
AI-Based DeepCOVID-XR Performs Similar to Consensus of Experienced Thoracic Radiologists. Appl Radiol.