Research Data Platforms

We developed a data management framework to support both large and small data collection efforts. Core components include automated data pipelines, a data repository, and a data portal allowing data discovery through search and static and dynamic datasets, as well as computational workspaces. The framework’s cloud-based architecture takes advantage of serverless, fully managed, and augmented capabilities. It uses metadata, semantics, and machine learning (ML) capabilities to enrich data and enhance utility.

CDC VISION Virtual Network

Using medical, laboratory, pharmacy, and vaccination records for conducting research on flu vaccine effectiveness and COVID-19 outcomes, 趣赢平台 is:

• Developing a common protocol for harmonization across 4 large health care systems submitting millions of electronic health records (EHRs)
• Building a secure, cloud-based research data platform in AWS for expedient data ingestion
• Conducting automated data quality checks
• Providing a data portal with access to data and visualizations summarizing patient data
• Assembling analysis-ready datasets and supporting analysis for CDC

Early Psychosis Intervention Network (EPINET)

Our activities on EPINET include creating the research data platform for facilitating collaboration, sharing data elements, exchanging innovative practices, and providing analytic support and dissemination activities across hubs and clinics. We are also curating and harmonizing key assessment measures, clinical strategies, and data elements, as well as implementing a health informatics approach within and across regional hubs. Finally, we are facilitating practice-based research through developing a research dissemination infrastructure and disseminating resources to the broader scientific, provider, and patient community, including developing a public EPINET website.