Artificial intelligence could help diagnose lung diseases much quicker than current tests, university researchers have said.

Developed by the University of the West of Scotland, the technology was originally used to detect Covid-19 from X-ray images, which could help in easing winter pressures on hospitals.

Serious lung diseases, such as tuberculosis and pneumonia, often require a combination of tests like CT scans, blood tests, X-rays and ultrasounds to diagnose.

These tests can be time-consuming so researchers hope the AI will lead to quick and accurate detection of diseases.

South Wales Argus: Quick and accurate detection of lung diseases is what is being aimed forQuick and accurate detection of lung diseases is what is being aimed for (Image: PA)

The technology developed uses X-rays, and then compares the scans to a database of thousands of images from patients with pneumonia, tuberculosis and Covid.

It then uses a process known as a deep convolutional neural network, an algorithm typically used to analyse imagery, to make a diagnosis.

The university said the technique had proven to be around 98% accurate, and it is now seeing if it can be used to detect other problems, such as cancer.


READ MOREFlu and pneumonia mentioned more times than Covid-19 on death certificates


Professor Naeem Ramzan, a researcher at the University of the West of Scotland said there was a need for technology to "help ease" some of the hospital pressures and "free up valuable staff time".

He added: “X-ray imaging is a relatively cheap and accessible diagnostic tool that already assists in the diagnosis of various conditions, including pneumonia, tuberculosis and Covid-19.

“Recent advances in AI have made automated diagnosis using chest X-ray scans a very real prospect in medical settings.”