Artificial intelligence in detecting paediatric fractures: where are we now?

Paediatric fractures make up a large part of the acute paediatric workload both in the emergency department and community-based care, such as urgent care and walk-in centres. Paediatric fractures can be very subtle, posing a diagnostic challenge for the untrained eye. Missed fractures can have a significant impact in children, including opportunities to raise safeguarding concerns in cases of suspected physical abuse, growth plate disturbances leading to long-term disability and chronic pain. Timely diagnosis of fractures is important as prompt management with surgery or immobilisation can improve long-term outcomes for children.

The shortage of radiologists in the UK, and in particular of paediatric radiologists, poses an enormous challenge for the NHS. The use of AI algorithms to aid with fracture detection presents an exciting opportunity for more efficient patient diagnosis and management. If proven to be useful, AI could be helpful in the hospital setting but also in community-based care, where access to paediatric radiologists is limited.

A recent review article published in 2023 outlined the evidence behind the commercially available AI tools on the market for fracture detection. Out of the 16 commercially available products currently available, only three are approved for use in the paediatric population, highlighting the need for research and product development in the field.

To access the full article as a pdf please sign up to our newsletter.

The content on this page is provided by the individuals concerned and does not represent the views or opinions of RAD Magazine.