N3C Education Tenant

The mission of the N3C Education Tenant is to provide educators and learners a space to develop and practice the skills needed to analyze real-world data (RWD, e.g., non-clinical trial data, such as data from medical records, insurance claims, patient surveys, or census or community datasets). The Education Tenant contains only synthetic datasets, no real patient data is in this Tenant. Synthetic datasets contain only data that were generated by looking at the distribution of features from real patient electronic health records but that contain no real patient data themselves. There are three total synthetic datasets contained in the Education Tenant. Each of these synthetic datasets has undergone thorough  testing to mitigate any concerns about privacy. The Education Tenant also provides a series of training tutorials, the Researcher’s Guide to the N3C - a virtual textbook of the concepts and skills needed to study RWD, and access to many of the shared resources available to the broader N3C community. 

Since the Education Tenant does not include any real patient data, only simulated data, there are no restrictions on recording or sharing screen views, making it a rich venue for training programs, courses and workshops. To ensure its educational value, this data contains common elements (e.g., conditions, devices, drugs, measurements, observations, procedures and visits) that have been preliminarily verified to be highly concordant with the original EHR data across a number of domains and applications. In summary, the following are the main synthetic datasets available to researchers in the Education Tenant.

Like all N3C tenants, resources such as code templates (prewritten sets of commonly used programming code) and concept sets (prewritten sets of commonly used medical codes) are sharable, allowing instructors and learners to develop material during training that can be shared and used in research projects. Users of the Education Tenant also have access to the training and support materials developed for the other N3C tenants. External Datasets such as publicly available data (e.g., U.S. Census and regional data) for use alongside EHR data is also available for use while in the Education Tenant. Users can request ingestion of additional external datasets. See The National Clinical Cohort Collaborative (N3C) page for details and currently available datasets.

Using the Education Tenant

If you want to access and use data within the Education Tenant, you must complete several steps. For details, see N3C Education.