The NHS in England commissioned AI screening to help diagnose bone fractures

Millions of patients in England with suspected broken bones could be X-rayed with a £1 smart scanner to help NHS doctors prevent further fractures.

Overlooked fractures are among the most common mistakes in A&E units and intensive care units, with 10% of fracture cases either never seen by medical professionals or diagnosed too late.

Missing a fracture in the initial examination can cause further injury or harm to the patient, worsening their condition and making it 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 in X-rays.

Clinical evidence shows that the use of AI can lead to better diagnoses, compared to medical professionals who diagnose themselves, “without increasing the risk of wrong diagnosis,” said Nice.

The use of AI can reduce the number of fractures that are missed at the initial presentation, prevent further injuries or injure people in the period between the first examination and the decision of more treatment, and “it can help reduce the difference in care throughout the country”, it added.

The move could also reduce the need for follow-up checks and appointments among NHS staff.

Mark Chapman, director of HealthTech in Nice, said: “Every day across the NHS, thousands of images are interpreted by radiologists and radiographers, but there is a high demand in these departments across the country and more support is needed to manage their work.

“These AI technologies are safe to use and can see cracks that people might miss due to pressure and require these teams of experts to work.”

In addition to an expert medical technician reviewing X-rays, the NHS could use four AI platforms led by Nice.

Recommended by TechCare Alert, which can be used for patients of any age; Rayvolve, for adults only; and BoneView and RBfracture, for adults and children ages 2 and up.

Chapman said: “Using AI technology to help highly skilled professionals in urgent care to identify which patients have a fracture can speed up diagnosis and reduce the number of follow-up examinations required for fractures that occur during initial assessment.”

Patients with suspected fractures are usually evaluated by a nurse or physician, who may request an X-ray to be performed by a radiographer.

Nice recommends that these X-rays should be reviewed by a radiologist, radiographer or other trained specialist, who should provide a detailed report before the patient is discharged. However, Nice said this is not always possible, with delays of days or weeks.

At the time of the promotion, the cost of each AI scan was estimated at £1. The NHS has been advised to ensure that funding remains close to that figure.

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

The consultation on the planning proposal will take place until 5 November.