NHS in England has given the green light for AI scans to help detect bone fractures

Millions of patients in England with suspected broken bones could have their X-rays checked with a £1 artificial intelligence scan to help NHS doctors prevent missing fractures.

Overlooked bone fractures are among the most common mistakes made in emergency rooms and urgent care centers, with as many as 10% of fracture cases going unnoticed by medical professionals or diagnosed late.

Missing a fracture during an initial assessment can lead to further injury or damage to the patient, worsening the patient’s condition and making it more difficult for hospitals to treat quickly.

The NHS has now been given the green light by the National Institute for Health and Care Excellence (Nice) to use AI as a way to improve fracture detection when examining X-rays.

Clinical evidence suggests that using AI can improve detection in scans, compared to a medical professional reviewing it themselves, “without increasing the risk of incorrect diagnoses,” Nice said.

The use of AI could reduce the number of fractures missed at initial presentation, prevent further harm or injury to people in the time between initial assessment and a decision on further treatment, and “could reduce variation in care across the country help reduce,” it added.

This move could also reduce the need for follow-up checks and appointments during the NHS staffing crisis.

Mark Chapman, director of HealthTech in Nice, said: “Thousands of images are interpreted across the NHS every day by expert radiologists and radiographers, but there is a high vacancy rate within these departments across the country and more support is needed to manage them. to manage. their workload.

“These AI technologies are safe to use and can identify breaches that people may miss given the pressures and demands under which these professional groups work.”

In addition to a trained healthcare professional assessing the X-rays, the NHS can use four AI platforms under draft guidance published by Nice.

The recommended options are TechCare Alert, which can be used on patients of any age; Rayvolve, adults only; and BoneView and RBfracture, for adults and children aged two years and over.

Chapman said: “Using AI technology to help highly qualified professionals in urgent care centers identify which of their patients has a fracture could potentially speed diagnosis and reduce the number of follow-up appointments needed due to a missed fracture during an initial assessment .”

Patients with suspected fractures are usually assessed by a nurse or doctor, who may have an x-ray taken by a radiographer.

Nice recommends that these X-rays be reviewed by a radiologist, radiographer, or other trained professional, who should provide a detailed report before a patient is discharged. Nevertheless, Nice said this was not always possible in practice, with delays in reporting lasting days or weeks.

During modelling, the cost for each AI scan was estimated at £1. The NHS has been advised to ensure costs remain close to that estimate.

Charlotte Beardmore of the Society of Radiographers supported the plans, but said that while AI could improve accuracy, it could not replace the expertise of radiographers and radiologists.

A consultation on the draft recommendations will run until November 5.