AI can analyse X-rays and diagnose medical issues just as accurately as doctors, according to a study.
Scientists from King’s College and the University of Warwick trained an AI using 2.8 million chest X-rays from over 1.5 million patients. The AI was told to look for a possible 37 health conditions.
It was found to be just as accurate or more accurate at identifying abnormalities than the doctor’s analysis at the time of the X-ray for 35 out of 37 conditions.
Researchers said the AI, called X-Raydar, could reduce doctors’ workload and delays in diagnosis and offer “the ultimate second opinion”.
Dr Giovanni Montana, Professor of Data Science at Warwick, and lead author, said: “This programme has been trained on millions of X-rays and is highly accurate. It eliminates the elements of human error, which is unavoidable, and bias. If a patient is referred for an X-ray with a heart problem, doctors will inevitably focus on the heart over the lungs.
“This is totally understandable but runs the risk of undetected problems in other areas. This AI eliminates that human bias – it’s the ultimate second opinion”.
The AI understood that some abnormalities for which it scanned were more serious than others, and could flag the most urgent to medics.
Senior radiologists cross examined 1,400 X-rays analysed by the AI to verify its accuracy.
They then compared the diagnoses made by the AI with those made by radiologists at the time.
A recent poll by the Royal College of Radiologists found that shortages of radiologists were leading to longer wait times, and delays in treatment, at 97 per cent of the UK’s cancer treatment centres.
Co-author Professor Vicky Goh, of King’s College London, said: “Current AI programmes available to us in the NHS only have a limited scope. Comprehensive AI programmes like this will be the future of medicine, with AI acting as a co-pilot for busy doctors.
“With the acute shortage of radiologists in the UK, programmes like this will facilitate interpretation and reduce delays for diagnosis and treatment”.
Ministers have already given funding to 64 NHS trusts for AI tools that can analyse X-rays and CT scans to speed up the diagnosis of lung cancer.
