An example of analysis using deep learning: The AI suggests that the red area...
An example of analysis using deep learning: The AI suggests that the red area is idiopathic pulmonary fibrosis and blue area is non-idiopathic pulmonary fibrosis

Image credit: Tosei General Hospital, Reiko Matsushita

News • Machine learning analysis of idiopathic pulmonary fibrosis

IDF diagnosis: AI on par with medical specialists

A Nagoya University research group has developed an AI algorithm that accurately and quickly diagnoses the lung disease idiopathic pulmonary fibrosis (IDF). The algorithm makes its diagnosis based only on information from non-invasive examinations, including lung images and medical information collected during daily medical care.

Doctors have waited a long time for an early means of diagnosing idiopathic pulmonary fibrosis, a potentially fatal disease that can scar a person’s lungs. Except for drugs that can delay the disease’s progression, established therapies do not exist. Since doctors face many difficulties diagnosing the disease, they often have to request a specialist diagnosis. In addition, many of the diagnostic techniques, such as lung biopsy, are highly invasive. These investigative measures may exacerbate the disease, increasing a patient's risk of dying. 

Taiki Furukawa, Assistant Professor of the Nagoya University Hospital, in collaboration with RIKEN and Tosei General Hospital, has developed a new technology to diagnose IDF. Using artificial intelligence (AI), the group analyzed medical data from patients in Tosei General Hospital’s interstitial pneumonia treatment facility, collected during normal care. They found that their AI diagnosed IDF with a similar level of accuracy as a human specialist. They published their results in the journal Respirology.

For idiopathic pulmonary fibrosis, the developed diagnostic AI is useful as a screening tool, and may lead to personalized medicine by collaborating with medical specialists

Taiki Furukawa

Despite finding that their AI performed just as well as experts, the team stress that they do not see it as replacing medical professionals. Instead, they hope that specialists will use AI in medical treatment to ensure that they do not miss opportunities for early treatment. Its use would also avoid invasive procedures, such as lung biopsies, which could save lives. “Idiopathic pulmonary fibrosis has a very poor prognosis among lung diseases,” Furukawa says. “It has been difficult to diagnose even for general respiratory physicians. The diagnostic AI developed in this study would allow any hospital to get a diagnosis equivalent to that of a specialist. For idiopathic pulmonary fibrosis, the developed diagnostic AI is useful as a screening tool, and may lead to personalized medicine by collaborating with medical specialists.” 

Furukawa is excited about the possibilities: “The practical application of diagnostic AI and collaborative diagnosis with specialists may lead to a more accurate diagnosis and treatment. We expect it to revolutionize medical care.” 


Source: Nagoya University

30.07.2022

Related articles

Photo

News • Interpretable machine learning system

AI to detect colorectal cancer from pathology slides

Researchers work on the first prototype that applies AI to colorectal diagnosis. The prototype achieved a diagnostic acuity of 93.44% and a sensitivity of 99.7% in the detection of high-risk lesions.

Photo

News • Chest X-ray evaluation

Human readers still outperform AI in lung disease identification

Reports of AI gaining the upper hand in diagnostic imaging interpretation are piling up, but there are still areas where the eye of a trained human radiologist remains superior.

Photo

News • Improving heart attack diagnosis

Using AI to reduce pressure on emergency departments

An algorithm developed using artificial intelligence could soon be used by doctors to diagnose heart attacks with better speed and accuracy than ever before, according to new research.

Related products

Subscribe to Newsletter