OSIC Opens Large Database to Aid Research Into PF, Other ILDs
A large and multi-ethnic database, reported to be the first of its kind for rare lung diseases, is now compiling real-world clinical and imaging data on people with pulmonary fibrosis (PF) and other interstitial lung diseases (ILDs) from centers across the globe.
Launched by the Open Source Imaging Consortium (OSIC), a global nonprofit, the OSIC Data Repository harbors the largest collection of quality-controlled scans with accompanying clinical data to aid scientists investigating the causes of ILDs and working to design better treatments.
OSIC is led by David Barber, PhD, a professor of machine learning (artificial intelligence) at University College London; the pulmonologist Kevin Brown, MD, with the National Jewish Health in Denver, Colorado; and the thoracic radiologist Simon Walsh, MD, with the National Heart and Lung Institute, Imperial College London.
“The future of medical research depends heavily on our ability to collate significant amounts of data, and make that data available for detailed and open scientific investigation. It’s a proud moment that OSIC is at the forefront of this movement,” Barber said in a press release.
“Data is the essence of scientific progress and the OSIC Data Repository already contains preliminary data rich enough to better understand the causes of disease, leading to better treatment and patient outcomes,” he added.
The OSIC Data Repository currently holds close to 1,500 quality-controlled scans with accompanying clinical data, all stripped of information that might identify a patient. An additional 5,000 scans are undergoing a quality control analysis.
By April 2022, the repository aims to hold 15,000 anonymized scans collected from governmental agencies, patient advocacy groups, and via direct patient outreach, OSIC stated.
Combining clinical data with large-scale imaging analysis will help in developing applications that, powered by artificial intelligence, can quickly analyze lung characteristics and disease biomarkers, and improve diagnosis and patients’ care at lower cost.
“In recent years, we have seen rapid developments in advanced medical imaging analysis, but a major obstacle to harnessing this technology used to study pulmonary fibrosis is the lack of large diverse imaging repositories needed for computer training,” Walsh said.
“OSIC addresses this unmet need by providing researchers with the data needed to develop [artificial intelligence]-based applications for improving patient care and facilitating precision medicine,” Walsh added. “Being able to reliably predict how pulmonary fibrosis will progress in an individual patient would allow doctors to initiate appropriate treatment at the earliest opportunity and slow disease progression.
“It remains one of the most urgent challenges for effective management for patients with fibrotic lung disease,” he said.
For almost three years, OSIC’s members across the world, including radiologists, clinicians, computational scientists, and industry competitors, have collaborated to build the OSIC Data Repository. They continue to work together in the development of digital imaging biomarkers that could help to diagnose patients and predict their responses to treatment.
“We’ve seen efforts like this in common diseases, but nothing truly like it for rare diseases,” Brown said. “As the OSIC database grows and we continuously learn from it, a real and substantial improvement in our ability to diagnose early, to predict outcomes, and to measure responses to therapy will be the result.”
The content of the database, as well as any OSIC-created algorithms, will be made available to OSIC members, which include academia, industry, and patient advocacy groups. The database has a central institutional review board (IRB) and multiple institution IRB approvals, and will be managed in a way to ensure it complies with all current privacy laws, regulations, consents, and related restrictions.
In this regard, the database has been vetted by two global privacy firms, which will ensure it follows general data protection regulation and the Health Insurance Portability and Accountability Act’s Privacy Rule, a U.S. law prohibiting health care providers, businesses, and other individuals working with them from disclosing a person’s health information without their consent.
Supporting partners of OSIC include charity organizations, patient support groups, pharmaceutical companies, academic centers, and hospitals. More information about OSIC’s current member institutions, and how to become a member, can be found here.