The FDA’s decision was made based on a retrospective analysis of 1000 radiograph images that were used to evaluate the independent enactment of the OsteoDetect AI algorithm.
The US Food and Drug Administration (FDA) announced it has granted marketing permission for the Imagen OsteoDetect, a computer-aided software for diagnosis and detection of wrist fractures in adult patients.
The software utilizes an artificial intelligence (AI) algorithm to analyze 2-dimensional X-ray images for indications of distal radial fractures. It then marks the location of the fracture on the X-ray image to help the health care provider in both detection and diagnosis.
“Artificial intelligence algorithms have tremendous potential to help health care providers diagnose and treat medical conditions,” said Robert Ochs, PhD, the acting deputy director for radiological health in the Office of In Vitro Diagnostics and Radiological Health at the FDA’s Center for Devices and Radiological Health, in a statement. “This software can help providers detect wrist fractures more quickly and aid in the diagnosis of fractures.”
The FDA’s decision was made based on a retrospective analysis of 1000 radiograph images that were used to evaluate the independent enactment of the OsteoDetect AI algorithm as well as the accuracy of fracture localization in comparison with 3 board-certified orthopedic hand surgeons using standard clinical methods.
The results showed that the readers’ performance was improved when utilizing the software, with improvements shown in sensitivity, specificity, and positive and negative predictive values. Additionally, Imagen submitted a study of 24 providers who reviewed 200 patient cases, which revealed similar performance metrics.