The FDA approved an artificial intelligence algorithm designed to help physicians detect wrist fractures May 24.
The computer-aided detection and diagnosis software, dubbed OsteoDetect and developed by Imagen, analyzes X-ray images of adult wrists. The software applies an AI algorithm to detect signs of distal radius fracture, a common type of wrist injury, and highlights these locations to aid a physician in their diagnosis.
The FDA has not OK'd the software for use without a physician or to replace a provider's review of a radiograph. However, the agency noted a provider may use the software as an adjunct tool in various clinical settings, including primary care, emergency medicine, urgent care and orthopedics.
The FDA reviewed the algorithm under its De Novo premarket review pathway, which targets new low- to moderate-risk medical devices.
"Artificial intelligence algorithms have tremendous potential to help healthcare providers diagnose and treat medical conditions," Robert Ochs, PhD, acting deputy director for radiological health in the FDA's Office of In Vitro Diagnostics and Radiological Health, said in a May 24 statement. "This software can help providers detect wrist fractures more quickly and aid in the diagnosis of fractures."
In a series of tweets in April, FDA Commissioner Scott Gottlieb, MD, wrote the agency is working toward a new regulatory approach to promote the use of AI algorithms that diagnose and treat diseases.
"[The] FDA is taking steps to promote innovation and support the use of artificial intelligence based medical devices," he wrote. "We're working with providers and consumers to address technology & safety questions re: continuous learning AI."