A research group at Nagoya University has developed an AI algorithm that accurately and quickly diagnoses idiopathic pulmonary fibrosis, a lung disease. The algorithm makes its diagnosis based only on information from non-invasive tests, including lung images and medical information collected during daily medical care.
Doctors have long hoped for an early method to diagnose idiopathic pulmonary fibrosis, a potentially fatal disease that can scar a person’s lungs. Except for drugs that can slow the progression of the disease, there are no established therapies.
Because doctors have a lot of difficulty diagnosing the disease, they often have to ask for a specialized diagnosis. In addition, many of the diagnostic techniques, such as lung biopsy, are highly invasive. These investigative measures can make the disease worse, increasing the patient’s risk of dying.
Taiki Furukawa, assistant professor at Nagoya University Hospital, in collaboration with RIKEN and Tosei General Hospital, has developed a new technology for diagnosing idiopathic pulmonary fibrosis.
Using artificial intelligence (AI), the group analyzed medical data from patients at Tosei General Hospital’s interstitial pneumonia treatment facility, collected during normal care. They found that their AI diagnosed idiopathic pulmonary fibrosis with a level of accuracy similar to that of a human specialist. They published their results in the journal Respirology.
Despite finding that their AI performed just as well as experts, the team stresses that it does not see it as a replacement for medical professionals. Instead, they expect specialists to use AI in medical treatment to ensure they don’t miss opportunities for early treatment. Its use would also avoid potentially life-saving invasive procedures, such as lung biopsies.
Idiopathic pulmonary fibrosis has a very poor prognosis among lung diseases. It has been difficult to diagnose even for general respiratory doctors. The diagnostic AI developed in this study would allow any hospital to obtain 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.”
Taiki Furukawa, Assistant Professor, Nagoya University
Furukawa is excited about the possibilities: “Practical application of diagnostic AI and collaborative diagnosis with specialists can lead to more accurate diagnosis and treatment. We hope it will revolutionize medical care.
Source:
Journal reference:
Furukawa, T., et al. (2022) An intelligible machine learning tool to differentially diagnose idiopathic pulmonary fibrosis from other chronic interstitial lung diseases. Respirology doi.org/10.1111/resp.14310