FDA grants permission to market artificial intelligence algorithm to help providers detect wrist fractures
The FDA announced it has granted Imagen permission to market OsteoDetect, a type of computer-aided detection and diagnosis software that can detect wrist fractures in adult patients, according to a press release. The software is intended to be used by clinicians in primary care, emergency medicine, urgent care and specialty care, such as orthopedics.
The OsteoDetect software uses an artificial intelligence algorithm to analyze 2-D X-ray images for signs of distal radius fracture. The software identifies the location of the fracture on the image to assist the provider with detection and diagnosis. The OsteoDetect uses machine-learning techniques to highlight regions of distal radius fracture during review of X-ray images of adult wrists. The OsteoDetect is to serve as an adjunct tool and is not intended to replace a clinician’s review of the radiograph or clinical judgement.
“Artificial intelligence algorithms have tremendous potential to help health care providers diagnose and treat medical conditions,” Robert Ochs, PhD, acting deputy director for radiological health, Office of In Vitro Diagnostics and Radiological Health in the FDA’s Center for Devices and Radiological Health, said in the release. “This software can help providers detect wrist fractures more quickly and aid in the diagnosis of fractures.”
Imagen submitted a retrospective study of 1,000 radiograph images that evaluated the image analysis algorithm for detecting wrist fractures and the accuracy of fracture localization using the OsteoDetect against the performance of three board-certified orthopedic hand surgeons. The company also submitted a retrospective review of 24 providers who assessed 200 cases. According to the release, the studies demonstrated the software improved readers’ performance in the detection of wrist fractures.
The FDA reviewed the software through the de novo premarket review pathway and granted Imagen marketing authorization of the OsteoDetect.