Originally posted on IU IT News.
Regenstrief Institute and Indiana University are partnering to provide a data commons to support research related to the pandemic. This platform will provide secure and efficient access to critical COVID-19 data without the usual barriers of health data privacy regulations.
The project is called the COVID-19 Research Data Commons, or CoRDaCo.
Through CoRDaCo, Regenstrief and IU’s University Information Technology Services’ (UITS) Scalable Compute Archive (RT-SCA) uses curated datasets of COVID-19 patient data to generate synthetic medical data. Synthetic data reflects the characteristics of real patient data, but does not include real patient information. Because it is statistically similar, it can be used in the same way as real data, but without compromising privacy. This allows for quicker access to the information.
The original data comes from the Indiana Network of Patient Care (INPC), which is managed by the Indiana Health Information Exchange. Regenstrief provides access to the data for research purposes. The INPC is one of the largest health information exchanges in the nation and contains records from health systems across the state.
CoRDaCo uses MDClone software to scrub sensitive patient information and augments it with information such as age, mobility, and other social determinants of health. The datasets similarly provide abstracted, synthetic data from COVID19 mitigation testing, as well as government vital records, to create complete datasets for research.
“The capabilities of CoRDaCO’s upgraded technologies will not only provide more security, but also will facilitate faster and easier availability to valuable COVID-19 data necessary for IU researchers who are evaluating vast amounts of information and seeking solutions,” said Umberto Tachinardi, M.D., MSc, Regenstrief chief information officer. “The paired experience of Regenstrief and UITS Research Technologies will provide benefit to these COVID research efforts.”
“I am excited to expand the already strong collaboration between Regenstrief and UITS. The CoRDaCo project contains the essential data public health experts need to address the COVID-19 pandemic, without the researchers having to worry about exposing sensitive patient information and handling HIPAA regulations” said Robert Henschel, director of Research Software and Solutions in University Information Technology Services. HIPAA is the Health Insurance Portability and Accountability Act, a federal law that protects sensitive patient health information from being disclosed without the patient’s consent or knowledge.
An earlier collaboration between Regenstrief and the RT-SCA team evaluated the MDClone research application, which serves as the framework for CoRDaCo’s datasets. The infrastructure behind CoRDaCo was originally made possible by the Indiana University Grand Challenge Precision Health Initiative.
“Regenstrief Data Services (RDS) is excited to partner with RT-SCA, combing their experience running highly scalable and secure systems with our medical informatics expertise, to make CoRDaCo readily accessible to IU researchers”, said Tony French, RDS director of technical services. “Arvind Gopu’s exceptional technical leadership, Ray Perigo’s system administration skills and Anurag Shankar’s assistance with security alignment exemplifies the strong support Regenstrief receives from UITS.”
“We are pleased to support research efforts to contain and understand this global pandemic, starting at a local scale with potential for national significance,” said Arvind Gopu, manager at the RT-SCA. “Our experience supporting research using critical data in secure environments via an ongoing partnership with the IU Center for Advanced Cybersecurity Research (CACR) helps make CoRDaCo possible.”
The Data Access Committee (DAC), consisting of researchers, administrators and privacy experts, governs CoRDaCo’s policies and procedures to access and use the data. RDS, led by Dr. Tachinardi, will administer CoRDaCo operations and data quality functions.
