FDA Approves AI Algorithm That Helps Detect Wrist Fractures
The Food and Drug Administration (FDA) has granted marketing clearance for Imagen's OsteoDetect, an artificial intelligence algorithm designed as an adjunct tool to help detect and diagnose wrist fractures in adults.
OsteoDetect is a computer-aided detection and diagnostic software that uses an algorithm to analyze 2-D wrist radiographs for signs of distal radius fracture. Through machine learning techniques, the software identifies fracture regions as it scans the posterior-anterior and medial-lateral X-ray images of adult wrists.
A retrospective study compared the accuracy of fracture localization with OsteoDetect vs 3 board certified hand orthopedic hand surgeons for 1000 radiograph images; another retrospective study included 24 providers reviewing 200 patient cases. Both studies showed that the readers' ability to detect wrist fractures was improved by using the software as evident by greater sensitivity, specificity, and positive and negative predictive values, compared with unaided standard clinical practice.
"This software can help providers detect wrist fractures more quickly and aid in the diagnosis of fractures," stated 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.
OsteoDetect is not intended to replace a clinician's review of the radiograph or clinical judgment.
For more information visit FDA.gov.