Eight to 10% of patients undergoing CT scans for other conditions were discovered by radiologists to have Covid-19 despite having no associated respiratory symptoms, according to published studies from Brussels, Chicago and Brescia (Italy), as well as a report from Maimonides Medical Center in New York.
These “incidental” findings fortunately enabled isolation and treatment measures to begin sooner.
Now, the US Food and Drug Administration has allowed the use of AI algorithms from Israeli artificial intelligence company Aidoc as an adjunct to help radiologists detect Covid-19 during any CT study of lung or part of a lung.
The product detects and prioritizes incidental findings associated with Covid-19 and provides information for further patient evaluation.
“In our experience, it is not unusual for the radiologist to be the first to diagnose Covid-19 disease in patients especially when the disease is clinically unsuspected,” said Dr. Paul Chang, vice chairman of radiology informatics at University of Chicago Medicine.
“Aidoc’s ability to detect and triage patients with incidental findings associated with Covid-19 acts as another layer of protection as the disease may continue to circulate in the months to come.”
This product is the latest addition to Aidoc’s suite of AI radiology solutions already helping radiologists at more than 300 medical centers worldwide flag conditions found on CT scans, including intracranial hemorrhage, large-vessel occlusion, pulmonary embolism and cervical spine fractures.