Skip to main content

Watch: Putting AI to Work for Lung Disease Patients

Unleashing artificial intelligence on thousands of lung scans could lead to breakthroughs for people who have pulmonary fibrosis.


An open-source repository of lung scans could revolutionize medical care for people who have unexplained scarring of the lungs, organizers explain in a new video produced by Wired Magazine and pwc.

Global biotech leader CSL Behring is a founding member of the nonprofit Open Source Imaging Consortium (OSIC), a first-of-its-kind database for interstitial lung diseases (ILD) that brings together scientists, industry, academia and philanthropy. The repository was expected to amass 15,000 scans by early this year. Previous research relied on cohorts of several hundred at most. The open-source database also includes accompanying clinical data that has been anonymized to protect patient privacy.

The hope is that the power of artificial intelligence will reveal patterns now hidden in the combination of that clinical data and thousands of high-resolution computed tomography (HRCT) lung scans. These lung diseases, with symptoms such as shortness of breath, are hard to diagnose. About half of patients are misdiagnosed once and a third are misdiagnosed twice, according to researchers.

“We don’t want their lives to be shortened by this disease,” said Dr. Kevin Brown of National Jewish Health in Denver, Colorado, who is the OSIC pulmonology lead.

Watch the video above and learn more about the initiative at A Bold Approach to Rare Disease.