OsteoDetect is the first ever FDA-cleared software device for Radiological Computer Aided Diagnosis/Detection (CAD). It uses AI to help detect and localize distal radius fractures – the most commonly misdiagnosed musculoskeletal injury. In a clinical study, the average clinician experienced a relative reduction in misinterpretation rate of 47% when aided by the software.
In this work, we tested whether Imagen’s FDA cleared software for detecting fractures (FractureDetect) in musculoskeletal radiographs would improve clinicians’ accuracy at diagnosing fractures. Clinicians were more accurate at diagnosing fractures when assisted by the deep learning system (p < 0.01). Clinicians with limited training in musculoskeletal image interpretation had a 61% relative reduction in missed fractures for X-rays from Medicare-aged patients when assisted by the deep learning system. Reducing the number of missed fractures may allow for improved patient care and increased patient mobility.