Artificial intelligence that automatically diagnoses lung diseases could help ease winter pressures on hospitals, it has been claimed.
State-of-the-art technology was developed by researchers at the University of the West of Scotland.
It uses X-rays to compare scans against a database of images from thousands of patients with pneumonia, tuberculosis and Covid.
The technology then uses a process known as a deep convolutional neural network — an algorithm typically used to analyze visual images — to make a diagnosis in minutes.
During extensive testing, the technique was found to be approximately 98% accurate.
Tuberculosis and pneumonia, potentially serious infections that primarily affect the lungs, often require a combination of different diagnostic tests such as CT scans, blood tests, X-rays and ultrasounds.
They can get expensive with long waits for results.
The technology developed by UWS was originally developed to quickly detect Covid-19 on X-ray images.
It is now hoped that the technology can be used to help alleviate the winter strain on hard-pressed hospital departments through rapid and accurate disease detection.
The development of the technology was led by Professor Naeem Ramzan along with UWS PhD students Gabriel Okolo and Dr. Stamos Katsigiannis directed.
Professor Ramzan stated: “There is no doubt that hospital departments around the world are under pressure and the outbreak of Covid-19 has exacerbated this, putting additional strain on departments and staff who are under pressure.
“There is a real need for technology that can help alleviate some of these burdens and quickly and accurately detect a range of different diseases, freeing up valuable staff time.
“X-ray imaging is a relatively cheap and accessible diagnostic tool that is already helping to diagnose various diseases, including pneumonia, tuberculosis and Covid-19.
“Recent advances in AI have made automated diagnosis using chest X-rays a very real prospect in the medical setting.”
Researchers at the UWS are now investigating the technology’s suitability for detecting other diseases using X-ray images, such as cancer.
Professor Milan Radosavljevic, UWS Vice Director for Research, Innovation and Engagement, expressed his excitement about the potential of the technology.
“Hospitals around the world are under constant stress,” Radosavljevic said.
“This can be seen across the UK as our fantastic NHS continues to experience tremendous pressure, with the pressured medical staff bearing the brunt.
“I am excited about the potential of this innovative technology that could help streamline diagnostic processes and reduce the burden on staff.
“This is another example of focused, high-impact research at UWS as we strive to find solutions to global challenges.”