Hip fractures mainly occur in elderly people and patients with major trauma, and complications of hip injuries have been associated with high mortality rates. Ping An's AI software was developed to reduce the rate of missed diagnoses and improve the comprehensiveness of detection.
In the retrospective study, a research team analyzed pelvic x-rays of 1,888 emergency room patients to evaluate the model's performance in obtaining fracture results and locations. It achieved an overall accuracy of 92.4%. Compared with general clinical diagnoses, the model substantially improves detection accuracy, according to the authors.
Ping An says the software can detect all fracture types captured on the x-rays, including hip fractures, pelvic fractures, femoral fractures, hip dislocation, and artificial joint peripheral fractures.
Copyright © 2021 AuntMinnie.com