AI and Medics' 'Joint' Role in Diagnostics
The implementation of artificial intelligence in the radiology field marks a groundbreaking advancement in healthcare diagnostics. The Royal College of Radiologists has signified the importance of improving diagnostics. Overlooked broken bones are the most common diagnostic error in A&E, where NICE recorded that broken bones were missed in 3-10% of cases. With A&E under immense pressure, and 5% of all emergency attendances being related to broken or fractured bones in 2018-2019, improving diagnostic methods for fractures and broken bones could have a positive effect on the A&E crisis.
​
Patients arriving at A&E with suspected broken bones undergo an X-ray scan. Then, if a radiographer or radiologist is available, they will interpret the images from the examination. However, with vacancy rates recorded at 12.5% for radiologists and 15% for radiographers, clinical experts are under extreme pressure and usually do not have time to interpret X-rays before diagnosis, meaning diagnoses may be based solely on interpretation by a less-specialised clinician, like a foundation year or resident doctor. This results in some missed fractures in diagnoses, leading to lower patient HRQoL (Health Related Quality of Life), where patients may experience prolonged pain, delayed recovery, worsened injury, or repeated admissions to the hospital, adversely affecting both patients and the healthcare team.
​
The number of patient referrals for diagnostic tests has risen by 25% over the last five years, meaning NHS diagnostic systems must evolve by utilising new technology to alleviate pressure on radiologists and radiographers, whilst simultaneously improving patient care and enhancing their quality of life. AI technology can be used to detect fractures, assisting the work of radiologists and radiographers. The NHS has been given guidance by NICE (National Institute of Health and Care Excellence) that the recommended AI tools are TechCare Alert, which can be used on patients of any age, Rayvolve, for adults only, and BoneView and RBfracture, for those older than two. These tools will eventually be integrated into all England urgent care units. The technology is not used alone but has been designed to complement a professional’s interpretation. This dual approach is expected to enhance accuracy of X-ray diagnoses without increasing the risk of incorrect diagnoses.
​
Another advantage of this AI technology is its cost-effectiveness. With each AI-assisted X-ray scan costing £1, it is a financially viable solution for the NHS, whilst also hopefully reducing costs from the NHS paying legal expenses and further treatment costs due to complications from missed fractures. This technology could also potentially reduce the need for follow-up appointments, reducing pressure on staff and allowing them to focus their attention on more life-threatening, critical cases.
​
The director of HealthTech at Nice, Mark Chapman stated “Using AI technology to help highly skilled professionals in urgent care centres to identify which of their patients has a fracture could potentially speed up diagnosis and reduce follow-up appointments needed because of a fracture missed during an initial assessment”. He claimed “These AI technologies are safe to use and could spot fractures which humans might miss, given the pressure and demands these professional groups work under”.
​
This exciting technology has been given the green light by NICE for the NHS to implement. After an independent review carried out by the radiology department, and consultation reviews, final guidance will be published on the NICE website.
References:
https://www.bbc.co.uk/news/articles/c2060gy9zy1o
https://www.nice.org.uk/guidance/indevelopment/gid-hte10044
https://www.nice.org.uk/news/articles/ai-technologies-recommended-for-use-in-detecting-fractures