Log in or Register for enhanced features | Forgotten Password?
White Papers | Suppliers | Events | Report Store | Companies | Dining Club | Videos
Patient Care
Patient Monitoring
Return to: MDBR Home | Patient Care | Patient Monitoring

FDA authorises Imagen’s AI-based wrist fracture detection device

MDBR Staff Writer Published 25 May 2018

Imagen has secured authorization from the US Food and Drug Administration (FDA) to market its artificial intelligence (AI)-based OsteoDetect device for detecting wrist fractures in adults.

Designed as a computer-aided detection and diagnosis software, OsteoDetect employs an AI algorithm to examine two-dimensional X-ray images for signs of distal radius fracture.

The software highlights the fracture location on the image during the review of posterior-anterior as well as medial-lateral images using machine learning techniques.

The aim is to support providers during detection and diagnosis of the injury in primary care, emergency medicine, urgent and specialty care settings, among others.

OsteoDetect is meant to be used as an adjunct tool but not intended to replace a clinician’s radiograph review or their clinical judgment.

FDA Center for Devices and Radiological Health acting deputy director for radiological health in the office of in vitro diagnostics and radiological health Robert Ochs said: “Artificial intelligence algorithms have tremendous potential to help health care providers diagnose and treat medical conditions.

“This software can help providers detect wrist fractures more quickly and aid in the diagnosis of fractures.”

The regulatory agency’s decision comes after review of findings from a retrospective study conducted using 1,000 radiograph images to evaluate the independent performance of the AI algorithm in identifying wrist fractures.

In addition, the study compared OsteoDetect’s accuracy for the fracture localisation with that of three certified orthopaedic hand surgeons.

The company also submitted data from another retrospective study that involved 200 patient cases reviewed by 24 providers.

Results from both these studies revealed better performance of readers for detecting wrist fractures while using the new software, as compared to their unaided performance.

An increase in sensitivity, specificity, positive and negative predictive values was also observed with the OsteoDetect device.

The software was reviewed through the De Novo premarket regulatory pathway, a pathway for new type of low to moderate risk devices.