NIH opens COVID-19 big data hub to researchers
Connecting state and local government leaders
The National Institutes of Health launched a secure, cloud-based research hub that will apply machine learning to a massive clinical COVID-19 dataset to inform best practices for resource allocation, drug discovery and treatment options.
The National Institutes of Health launched a secure, cloud-based research hub that will apply machine learning to a massive clinical COVID-19 dataset to inform best practices for resource allocation, drug discovery and treatment options.
The data platform is part of NIH’s National COVID Cohort Collaborative, or N3C, and addresses the lack enough standardized clinical data for researchers to learn how to direct COVID-response efforts and treat patients. The rapid aggregation and harmonization of clinical, laboratory and diagnostic data from hospitals and health care plans will support big data analyses of the virus and help identify effective interventions.
Access to such a large data repository, said NIH, could unlock answers to questions that were previously unknowable because of disparate, scattered patient data. It could provide keener insight into predicting which patients may require dialysis, need ventilators or require different treatments.
N3C launched with 35 institutions contributing data on COVID-tested patients, including demographics, symptoms, medications, lab test results and outcomes, NIH said. The only identifying data on the platform will include the ZIP code of the health care group providing the information and the dates of service. Data access will be open to all approved users, regardless of whether they contribute. Data use will be governed by an oversight committee, NIH said, and approved users must analyze data within the platform; it cannot be removed or downloaded.
The National Center for Advancing Translational Sciences, which funds and oversees N3C, is using the Palantir Foundry Analytic Platform to identify connections and patterns more quickly than can be done through traditional methodologies, officials said. The data will reside Amazon Web Services GovCloud and is authorized by the Federal Risk and Authorization Management Program at the moderate impact level.
A version of this article was first posted to FCW, a sibling site to GCN.