Aidoc obtains FDA clearance for AI that uses CT scans to help diagnose COVID-19

Aidoc, which bills itself as an AI solutions provider for radiologists, today announced that the U.S. Food and Drug Administration has allowed the use of its algorithms for “adjunctive” detection of findings associated with COVID-19. The models aren’t meant to replace traditional COVID-19 diagnostic tests, like serological tests and nasopharyngeal swabs, but the agency’s allowance acknowledges they could be used to prioritize incidental (i.e., non-specific) CT findings tied with COVID-19 infections.

While the U.S. Centers for Disease Control and Prevention (CDC) recommends against the use of CT scans or X-rays for COVID-19 diagnosis, as does the American College of Radiology (ACR) and radiological organizations in Canada, New Zealand, and Australia, others assert systems from companies like Alibaba, RadLogics, Lunit, DarwinAI, Infervision, Qure.ai, and now Aidoc might play a role in triage by indicating further testing is required. Even the best AI systems sometimes can’t tell the difference between COVID-19 and common lung infections like bacterial or viral pneumonia, but recent studies show that as many as 10% of asymptomatic patients undergoing CT scans for other conditions were discovered to have COVID-19.

Aidoc — which has four FDA cleared solutions, meaning they’ve been proven “substantially equivalent” to other similar legally marketed products — says its COVID-19 tool helps to isolate anomalies in CT studies containing the lung or part of the lung. Concretely, that includes the chest, abdomen, and cervical spine.

“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. The outbreak of the COVID-19 pandemic may occur in waves and should these waves occur, it will become increasingly important to identify imaging findings suggestive of COVID-19 in a variety of clinical settings,” Dr. Paul Chang, professor of radiology at the University of Chicago, said in a statement. “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.”

Aidoc got its start in 2016, when veterans of the Israeli Defense Force put their heads together to create an AI platform targeting health care verticals. The startup’s diagnostics toolset, which doesn’t require dedicated hardware, runs continuously in an on-premises virtual machine and ingests scans from picture archiving and communication and radiological information systems. It deidentifies these and sends them onto Aidoc’s cloud, where algorithms identify and highlight abnormalities before returning the images to radiology workstations for reidentification.

Aidoc offers tests for intracranial hemorrhages and spinal fractures and several chest exams for pulmonary embolisms, pneumothorax, rib fractures, and lung nodules. (All excepting the chest tests, which are limited by U.S. and EU law to investigational use, have CE markings indicating that they conform with health, safety, and environmental protection standards for products sold within most of Europe.) Abdominal tests for free air, dissections, and aneurysms are currently in development.

Aidoc claims that its products can reduce report turnaround times by up to 60.1%, and says that they’ve so far analyzed over 1.2 million scans, detected over 360,000 signs of disease, and helped to prioritize more than 150,000 cases across over 300 inpatient and outpatient clinics, level 1 trauma centers, imaging centers, and teleradiology facilities.