Research Uses

Many tools exist for working with clinical data, but what makes i2b2 and tranSMART different is a flexible ontology-driven architecture and community developed plugins and interfaces, which enable a variety of configurations to support the needs of scientists, clinical investigators and data scientists across academic, government and industrial labs.

Patient Recruitment Use Case

One of the most common uses of the Foundation’s platforms is in the exploration and identification of a patient cohort for a particular study.  The ability to easily look across a wide range of patient information for particular symptoms, medical history, genomic profile, etc. and review and analyze the resulting sets of patients make our platforms useful for clinicians and research teams.

For example, large hospitals and medical centers load data on millions of patients into i2b2 to evaluate clinical trial feasibility and to accelerate patient recruitment. Through a web-based query tool, investigators can define complex inclusion and exclusion criteria, apply temporal and value-based constraints, and access patients’ notes and biobank data.

The Use Case Working Group is compiling sets of examples that will be linked to this site in the near future.

Translational Studies Use Case

Translational studies use the PIC-SURE software to integrate clinical and genomic data from multiple sources. Clinicians and data scientists explore and analyze the data with tranSMART and tools from 3rd party companies such as the hyve. Users can also query the PIC-SURE APIs programmatically through software such as jupyter and connect to hail for large scale genomic research.

One of the new components is the PIC-SURE interface that provides integration as well as allows users to query the data programmatically through software such as Jupyter and to connect to other data repositories such as Hail for large scale genomic research.

Federated Networks Use Case

Institutions that map their local coding systems to a common ontology can use the SHRINE software to build federated data networks, which protect patient privacy by keeping the data within each hospital’s local i2b2 database. The largest SHRINE networks contain data on more than 100 million patients, enabling large population-wide studies.

It is important to note that these different architectures can be combined, so that an institution can use the same i2b2 core database for more than one use case. This flexibility is what makes i2b2 tranSMART unique and is a main reason why the platform has been adopted by more than 200 institutions worldwide.

Training & Tutorial Program

The i2b2 tranSMART Foundation and members are working to create a training & tutorial program to assist the scientific community to use, maintain and build upon the tranSMART Platform to answer clinical genomic questions.  Registration links will be added shortly.

We are growing a set of collateral materials in the form of documents, training manuals and video tutorials that can be viewed or downloaded from this site.  In addition, a regular program of training offerings is being created as well as the opportunity to request special or customized training for your organization or project.

The i2b2 tranSMART Foundation and members have created a training & tutorial program to assist the scientific community to use, maintain and build upon the tranSMART Platform to answer clinical genomic questions.  Registration links will be added shortly.

Link to Training Classes and Video Tutorials