Study: AI can analyze X-rays as accurately as doctors

A new AI software has been found to be as effective as doctors are for analyzing X-rays and diagnosing medical issues, a new study led by the University of Warwick and King's College London has shown.

The software, called X-Raydar, was trained on 2.8 million historical chest X-rays from more than 1.5 million patients. It demonstrated comparable, if not better, results when put against the analysis of doctors at the time of the original x-ray for 35 out of 37 (94%) conditions.

To verify their findings, the research team took a sample of around 1,400 X-rays analyzed by the AI and tasked a group of senior radiologists to cross-examine them.

The software scans X-rays as soon as they are taken and flags any abnormalities with an associated percentage. It can also understand the seriousness of different conditions, alerting doctors when needed.

"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," explained Dr Giovanni Montana, a data science professor at Warwick University. "This AI eliminates that human bias - it's the ultimate second opinion."

The researchers open-sourced the AI software for non-commercial uses to accelerate research in this subject area.

The study's co-author, Professor Vicky Goh, is the immediate past chair of the Academic Committee at the Royal College of Radiologists.

"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," she said. "With the acute shortage of radiologists in the UK, programmes like this will facilitate interpretation and reduce delays for diagnosis and treatment."

The researchers also highlighted how the AI could improve efficiency for radiologists by identifying the X-rays that showed no abnormalities, ultimately allowing staff to focus on more critical demands.

A recent Royal College of Radiologists report found that shortages in the sector were causing longer waiting times and, thus, delays in treatment at 97% of the UK's cancer treatment centers.

The project was funded by a Wellcome Trust Innovator Award.