medicine with healthcare technology
Illuminating the power of strategic thinking and technology in the fight against rare disease
Idiopathic pulmonary fibrosis (IPF) has no known cause or cure—and it’s very difficult to diagnose.
A first-of-its-kind open source medical imaging and data repository platform is highlighting new possibilities to help improve the speed and accuracy of diagnosis and help patients, providers and researchers better manage the disease.
OSIC’s commitment to highlighting rare disease, Microsoft’s secure and flexible technology and PwC’s dedication to solving important problems and building trust in society are together driving vital advancements in medicine that can change patient lives for the better.
A platform for sharing anonymized global imaging and clinical data that can impact diagnosis and decision-making, with the fundamental goal of better patient outcomes.
Within months of launch, this groundbreaking effort is already promising to enable more timely, accurate diagnoses for IPF patients. In time, OSIC hopes to use AI technology to shine a spotlight on other rare diseases and help further democratize medicine, giving patients around the world the same diagnostic tools available to those in major research centers.
For patients navigating interstitial lung diseases (ILDs), seeing the big picture means the ability to make more informed decisions.
One key to diagnosing IPF and other ILDs lies in identifying a specific pattern on a chest scan via high-resolution computed tomography (HRCT).
But identifying patterns on a scan can be challenging. Rare diseases make for rare data, and medical providers are often left with only limited snapshots based on highly variable, siloed information. Creating a more complete picture of what patients face and decreasing the time to diagnosis are two of the more impactful ways to improve outcomes for those with IPF.
Current clinical challenges of IPF
OSIC is a 501(c)(3) not-for-profit cooperative effort that brings together members from academia, industry and patient advocacy groups. This groundbreaking coalition has turned sometimes-competitors into willing collaborators, leveraging their collective knowledge to help accelerate the fight against IPF, fibrosing ILDs and other respiratory diseases including emphysematous conditions.
By coalescing critical research, experience and clinical data into one central repository, OSIC looks to enable more accurate imaging-based prognosis, diagnosis and prediction of response to therapy. Doctors and researchers can now be connected with the resources and experience they need for improved patient care.
Clinicians and researchers provide their institution’s high-quality, anonymized HRCT scans with accompanying clinical data to a large database. They can then access this same database to find data from other participants, which they can then use to build predictive models and change lives.
The consortium provides members with access to the data-rich repository, which houses a plethora of multi-ethnic and multi-center, real-world clinical and imaging data. The database is managed in compliance with applicable privacy laws, regulations, consents and related restrictions.
Patients receive more targeted treatment decisions, ultimately leading to earlier diagnosis, enhanced prognosis and improved management of disease.
Hear the discussion between OSIC, Microsoft and PwC as they collaborated to improve the speed and accuracy of diagnosing a rare disease through digital and cloud technologies. Learn how data and analytics, AI and cloud are reshaping the future of healthcare—and what it means for your organization.
Using Microsoft Azure, PwC collaboratively constructed a data repository to house all of OSIC’s anonymized images and clinical data. The platform looks to incorporate a crowdsourced algorithm that detects IPF progression.
PwC helped design the platform and, together with OSIC-member expertise, led the intake and management process for diagnostic imaging data and performed both manual and automated data quality checks. In the future, these checks can help enable a highly secure AI, machine learning and sightless diagnostic environment to accelerate rare disease treatment.
Hear directly from Microsoft, OSIC and PwC on new possibilities in healthcare.
Anonymized data is encrypted, transferred and stored in a secure, digital vault that’s monitored continuously to prevent public access.
The platform performs automated, multi-stage quality control and anonymization of metadata before ingesting images and data sets.
3. Data access
Members can leverage scans and rich data sets collaboratively for imaging-based diagnosis, prognosis and prediction of response to therapy.
4. AI and machine learning
Thousands of scans look to supplement provider observations with principled AI and machine learning to determine whether an HRCT scan shows early signs of IPF.
5. Detection, treatment and time
Providers aspire to deliver faster, more accurate diagnoses and predictions to give patients more time under treatment.
A data-powered solution is not successful until people can understand and use it. The OSIC Data Repository is designed to dramatically increase the volume and usability of vital information to fuel faster decisions and predict better treatment outcomes.
More diverse data
The medical community was relying on limited information, such as scans from a center’s own region or missing data from referral sites, to illustrate how the disease might progress. And because IPF is a rare disease, no single center had enough patients to supply the data needed for real progress. The OSIC Data Repository’s large database could help healthcare professionals build algorithms to find answers and change lives.
The OSIC Data Repository pulls together a plethora of global, multi-ethnic clinical and imaging data that can help cut down the time to diagnosis.
OSIC clinicians and research members in any location would have access to and benefit from the same technology and information as those affiliated with major research centers. Any OSIC-created algorithms will be made open source for the benefit of patients everywhere.
The platform is designed to explain the patterns detected by its AI so providers could then apply their own insights and learn alongside the AI.
patients with follow-up data
anticipated scans by end of 2022
National Heart and Lung Institute, Imperial College London, OSIC Radiology Lead, "Why the OSIC Data Repository Matters"
The OSIC model looks to yield far-reaching benefits for IPF and beyond
The impressive early feedback has OSIC thinking big. Its model represents a beacon of hope for those fighting pulmonary fibrosis and other rare lung diseases.
Successful outcomes through OSIC could result in open source digital biomarkers that support reliable and accurate diagnosis and prediction of outcome in patients with IPF and other progressive fibrosing respiratory disorders.
New uses for old imaging
HRCTs aren’t available everywhere, but the OSIC platform could make better use of more widely available X-ray technology by associating patient X-rays with their CT-based diagnosis. In time, the platform could expand to different modalities, including X-rays.
Applications for other rare diseases
The OSIC platform is very flexible, and its AI can push the limits of medical diagnoses and prediction of outcome. As the OSIC database expands and adds more contributors, it’s likely to help shine a light on other rare diseases, providing much-needed research and attention.
1. "Time to diagnosis of idiopathic pulmonary fibrosis in the IPF-PRO Registry," US National Library of Medicine, BMJ Open Respiratory Research, July 5, 2020.
2. Emily Malcolm, "12 Facts About Pulmonary Fibrosis Prognosis and Life Expectancy," Pulmonary Fibrosis News, August 16, 2019.
3. Open Source Imaging Consortium
4. "September is Pulmonary Fibrosis Month," American Association for Respiratory Care, August 27, 2021.
5. "September is Pulmonary Fibrosis Month," American Association for Respiratory Care, August 27, 2021.
6. "Barriers to timely diagnosis of interstitial lung disease in the real world: the INTENSITY study," US National Library of Medicine, BMC Pulmonary Medicine, January 17, 2018.