A First-of-its-Kind, Global Data Repository for Interstitial Lung Diseases
OSIC was created to look at lung diseases differently. To drive collaboration between unlikely partners and to find the best and brightest from around the globe. It was created to use artificial intelligence and other technological advances to build, and learn from, the largest and most diverse image and clinical database for fibrotic lung diseases.
The OSIC Data Repository is now live, and it was built with the expertise and help of global radiologists, pulmonologists, machine learners, and imaging experts from industry and academia. It is a data-rich repository of anonymized HRCT scans and clinical information regarding interstitial lung diseases (ILDs), and houses a plethora of real world clinical and imaging data that is both multi-ethnic and multi-center.
It is our belief that this database could be the start of finding digital imaging biomarkers that could potentially speed up diagnosis, and aid in better understanding of individual prognosis and response to therapy.
Building the OSIC repository has been a collaboration in its truest sense, with people from different disciplines, organizations, and countries all coming together on behalf of patients everywhere. This ability to collect and organize anonymized imaging and clinical data from across the world is the future of clinical science. We’ve seen efforts like this in common diseases, but nothing truly like it for rare diseases. 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."
Dr. Kevin Brown,
National Jewish Health,
OSIC Pulmonology Lead
Current Repository Overview
The repository currently houses close to 1,500 anonymized and quality-controlled scans with accompanying data, and has an additional 5,000 in the quality control queue. It is on track to reach its goal of 15,000 anonymized scans, available to OSIC members, by first quarter 2022.
OSIC is committed to protecting the privacy and integrity of patient data
The OSIC Data Repository was built with images and clinical data from a variety of sources, and every scan has been anonymized with a personal and automated quality control check. The database has been vetted by two global GDPR/HIPAA privacy firms, has Central IRB and multiple institution IRB approvals, and is managed in compliance with all applicable privacy laws, regulations, consents and related restrictions.
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. OSIC addresses this unmet need by providing researchers with the data needed to develop AI-based applications for improving patient care and facilitating precision medicine. 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.”
Dr. Simon Walsh,
National Heart and Lung Institute,
Imperial College London,
OSIC Radiology Lead
The data-rich, heterogeneous OSIC repository can help change lives
What specific ILD does my patient have? How will my patient respond to a particular therapy? What course of treatment should I recommend for the best possible outcome?
These are just a sampling of the many questions healthcare professionals are faced with when treating ILD patients. Machine learning technology can help shed light on treatment decisions by developing universal and accessible algorithms to analyze patients’ digital data – ultimately leading to earlier diagnosis, enhanced prognosis, and improved management of disease.
The problem? No single center will ever have enough patients to supply the data required for progress. The OSIC Data Repository is positioned to change this. Its large, heterogeneous database can help healthcare professionals build algorithms that will find answers and change lives. Its open science model is the best approach, and key to personalized treatment and drug development.
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. Data is the essence of scientific progress and the OSIC repository already contains preliminary data rich enough to better understand the causes of disease, leading to better treatment and patient outcomes."
Dr. David Barber,
University College London,
OSIC Computational Science Lead