Our Data Network
The MassCPR Federated Data Network
The COVID-19 pandemic underscored the critical role of high-quality, up-to-date data in guiding public policy, understanding disease dynamics, and developing effective interventions. Yet, accessing such data remains a major challenge. Despite holding clinical information on millions of patients, public health agencies and hospitals have historically stored their data in separate, siloed systems—limited by technical, privacy, and governance barriers.
The MassCPR Federated Data Network addresses these challenges by combining the aggregate results of analyses that are performed locally within each participating institution using electronic health record (EHR) data. By leveraging the collective informatics capabilities of the consortium, this network enables data discovery and sharing while maintaining institutional autonomy and patient privacy.
Wide Applications
This powerful platform will support a wide range of use cases:
- Surveillance and epidemiology during inter-pandemic periods
- Early insights into disease trends and at-risk populations at the onset of an outbreak
- Accelerated clinical trials through feasibility assessments, recruitment support, and identification of recruitment sites
- Support for translational research integrating biospecimens and patient data
Patient Privacy
As a federated network, each participating institution retains control over its data: individual patient records never leave the institution. Instead, analyses are run locally, and only aggregate counts and statistical summaries are shared. This protects patient privacy, reduces regulatory hurdles, and ensures access to the most current hospital data—critical for early outbreak detection.
The network is powered by widely used, open-source informatics tools developed at Mass General Brigham and Harvard Catalyst:
- i2b2 (Informatics for Integrating Biology & the Bedside) links diverse data types, such as diagnoses, medications, laboratory test results, vaccinations, and clinical notes, into a local queryable database.
- SHRINE (Shared Health Research Information Network) connects i2b2 systems across sites, harmonizing the data so the same analyses can be run consistently at each institution.
Actionable Information
The first major phase of the federated network connects EHRs from the broader Beth Israel Lahey Health, Mass General Brigham, and Dana-Farber Cancer Institute systems, enabling real-time research, surveillance, and clinical insights using data on more than 10 million patients.
By transforming fragmented, siloed data into coordinated, actionable information, the MassCPR Federated Data Network enhances preparedness, accelerates research, and strengthens the public health response to future infectious threats across the region and beyond.