Now an AI tool to accurately locate hip fractures

Researchers used 3,659 hip X-rays to train and test the neural networks, and achieved an overall accuracy of 92%.

sharathkumar.nair

Published 2022-02-16T05:30:00.000+05:30Updated 2022-02-16T05:30:00.000+05:30

Key takeaways

Researchers developed neural networks to identify hip fractures with 19% higher accuracy than clinicians.
The tool aims to improve efficiency in hip fracture care, enhancing patient outcomes.
Hip fractures significantly impact the elderly, leading to increased morbidity and healthcare costs.
Accurate classification of fractures prior to surgery is essential for effective treatment.
The process could reduce the backlog of unreported radiographs in the UK.

5 min

FollowPreferred Source Google News WhatsApp Telegram

Researchers at the University of Bath have developed two convolutional neural networks to identify and classify hip fractures from X-rays with a 19% higher accuracy compared to clinicians.

The research team, fromc, as well as colleagues from the Royal United Hospitals Trust Bath, North Bristol NHS Trust, and Bristol Medical School, aims to help clinicians make hip fracture care more efficient to drive better patient outcomes.

Hip fractures are a major cause of morbidity and mortality in the elderly, incurring high costs to health and social care. Classifying a fracture prior to surgery is crucial to help surgeons select the right interventions to treat the fracture and restore mobility and improve patient outcomes

Researchers used 3,659 hip X-rays to train and test the neural networks, and achieved an overall accuracy of 92%.

"The process we've developed could help standardise that process, achieve greater accuracy, speed up diagnosis and alleviate the bottleneck of 300,000 radiographs that remain unreported in the UK for over 30 days," said Prof Richie Gill, lead author of the paper and co-director of the Center for Therapeutic Innovation.