Can AI improve turnaround times for fracture detection?

Tuesday, November 28 | 9:50 a.m.-10:00 a.m. | T3-SSER01-3 | Room E451A

A tool that prioritizes x-ray exams when it detects fractures yields “tremendous reductions” in report turnaround times, according to a study to be presented in this session.

The study included 50,682 patients who underwent x-ray exams before (23,088 cases) and after (27,594 cases) use of an AI workflow algorithm designed to prioritize x-ray examinations if it detects fractures. PACS data were used to determine turnaround times (time from examination completion to report availability), with times for reports positive for fracture compared between periods.

Mean report turnaround time for fracture-positive exams during the post-AI period were significantly shorter compared with the pre-AI period (8.5 hours vs. 47.5 hours; mean difference, 39 hours), according to the findings.

“By assisting radiologists in providing rapid diagnoses, an AI tool could potentially enable earlier interventions for fractures, leading to better patient outcomes and more efficient use of healthcare resources,” noted Sean Raj, MD, of UT Southwestern Medical Center, who will present the findings.

Check out this scientific session on AI in emergency radiology for all of the details.