Register Now: Image-Based Risk: The Next Frontier in Breast Cancer Screening
News|Articles|May 21, 2026

X-Ray AI Software Gets Expanded FDA Clearance for Detecting Joint Effusions and Dislocations

Author(s)Jeff Hall

Recently published multinational research revealed that AZtrauma had a 95.6 percent AUC for detecting dislocations and a 97.5 percent AUC for detecting joint effusions.

The Food and Drug Administration (FDA) has granted an expanded 510(k) clearance for the X-ray AI software AZtrauma, which can now be employed for the detection of dislocations and joint effusions in adults and pediatric patients > 2 years of age.1

Previously cleared by the FDA for fracture detection, AZtrauma was recently evaluated in a multinational study involving 100 facilities and 258,373 X-rays.2

Overall, the researchers found that AZtrauma had a 98.3 percent AUC with sensitivity and specificity rates of 97.4 percent and 96.4 percent respectively. Specifically, for joint effusions, AZtrauma offered a 97.5 percent AUC, a 96.1 percent sensitivity rate and a 98.8 percent specificity rate. For dislocations, the study authors noted that AI software provided a 95.6 percent AUC along with 93.4 percent sensitivity and 96.7 percent specificity.2

"AZmed's investment allows us to consistently and immediately identify and triage fractures, joint effusions and dislocations across adult and pediatric populations before the radiologist ever opens the study. Our AI is fully optimized to support and prepare the radiologist for the study at hand, aligning perfectly with our mission to integrate image analysis solutions into our all-in-one SaaS platform,” noted Alejandro Bugnone, MD, a musculoskeletal radiologist and chief executive officer of Radin Health.

References

  1. Radin Health. Radin Health and AZmed elevate radiology workflow with AZtrauma’s expanded FDA-cleared AI capabilities. Available at: https://www.prnewswire.com/news-releases/radin-health-and-azmed-elevate-radiology-workflow-with-aztraumas-expanded-fda-cleared-ai-capabilities-302779315.html . Published May 21, 2026. Accessed May 21, 2026.
  2. Cohen E, Quertani MS, Beaumel P, et al. Performance of a complete AI radiographic suite across 258,373 X-rays from 26 countries: a worldwide evaluation. Radiography. 2026:32(4): 103361.

Related to this article

Key Sessions of Interest for Radiologists at the Upcoming HLTH USA Conference
How will generative AI software be evaluated by the FDA in the future? What’s next for point-of-care ultrasound? What steps have been successful in facilitating adoption of AI applications across enterprise systems? Leaders in radiology and health care will be discussing these topics and more at the upcoming HLTH USA conference.
Current Perspectives on Integrating AI into Radiology
In a recent interview with Diagnostic Imaging, Joseph Cavallo, MD, MBA, offered insights on post-deployment monitoring with AI, the potential for improved workflow efficiency and the ongoing challenge of balancing essential clinical skills and AI literacy in the training of radiology residents and fellows.