'Lunit Insight CXR' Confirmed to Improve X-ray Interpretation Ability Through Joint Research with Harvard

[Asia Economy Reporter Chunhee Lee] Medical artificial intelligence (AI) company Lunit announced on the 13th that the use of its chest X-ray image analysis AI solution 'Lunit Insight CXR' by radiology specialists improved their diagnostic ability during image analysis. The results of this study were recently published in the international journal 'JAMA Network Open,' issued by the American Medical Association.

This study was conducted jointly by Lunit and Massachusetts General Hospital (MGH) of Harvard Medical School in the United States, with which Lunit established a research partnership in 2020. The research team applied Lunit Insight CXR to a total of 497 chest X-rays taken from April to November last year, which showed four major lung diseases?pneumonia, pulmonary nodules, pleural effusion, pneumothorax?and various other lung conditions, to measure the accuracy and efficiency of diagnosis.

As a result, the disease detection accuracy of Lunit Insight CXR for major lung diseases averaged 89%, significantly higher than the average diagnostic rate of 73% by radiology specialists. Additionally, the use of AI reduced the reading time by 10%.

Mannudeep K. Kalra, professor of radiology at MGH and lead researcher of the study, explained, "The significance of this study is that using AI for chest X-ray image interpretation improves the detection accuracy and reading efficiency for major lung diseases," adding, "It also enhances the diagnostic ability of radiologists with various levels of experience, including residents and specialists."

Seobum Seok, CEO of Lunit, said, "Lunit Insight CXR helps medical staff provide more accurate and efficient diagnoses to patients," and added, "Conducting joint research with medical staff from top-tier comprehensive hospitals in the United States is expected to be a great opportunity to further advance the technology and value of Lunit's AI products in the U.S. market."

This content was produced with the assistance of AI translation services.