AI equals experts in diagnosing lung disease

A team of scientists in Japan have developed an artificial intelligence (AI) model that can identify idiopathic pulmonary fibrosis as accurately as medical experts.

The AI ​​model developed at Nagoya University makes its diagnosis based solely on information from non-invasive tests, including lung images and medical information gathered during daily medical care.

Idiopathic pulmonary fibrosis, a life-threatening condition that can scar a person’s lungs, is notoriously difficult to diagnose, especially in the early stages.

This AI model, developed in collaboration with RIKEN and Tosei General Hospital, was able to analyze hospital patient data and diagnose disease with a level of accuracy similar to that of a human specialist, which physicians often need to consult when dealing with lung diseases. fibrosis.

“Idiopathic pulmonary fibrosis has a very poor prognosis among lung diseases,” said Taiki Furukawa, assistant professor at Nagoya University Hospital. “It was difficult to diagnose, even for general practitioners in pulmonology.

“The diagnostic AI developed in this study would enable any hospital to obtain a diagnosis equivalent to that of a specialist. For idiopathic pulmonary fibrosis, the diagnostic AI developed is useful as a screening tool and can lead to personalized medicine by collaborating with medical specialists.”

The AI ​​suggested that the red area is idiopathic pulmonary fibrosis and the blue area is non-idiopathic pulmonary fibrosis./ Tosei General Hospital, Reiko Matsushita

Image credit: Tosei General Hospital, Reiko Matsushita

Currently, there are no therapies to cure idiopathic pulmonary fibrosis, although some drugs are able to delay disease progression if identified early. To do this, patients often have to be subjected to invasive diagnostic techniques, such as lung biopsies.

Unlike current diagnostic techniques, the AI ​​model can identify the disease without risking making it worse or increasing the patient’s risk of death.

“Practical application of diagnostic AI and collaborative diagnosis with specialists can lead to more accurate diagnosis and treatment,” Furukawa added. “We expect it to revolutionize medical care.”

The team’s findings were published in the journal Pulmonologywhere, the scientists stressed that AI should be seen as a supporting tool, rather than a substitute for medical specialists.

Sign up for the E&T News email to get great stories like this delivered to your inbox every day.