The National Institutes of Health's Biomedical Translational Research Information System (BTRIS): design, contents, functionality and experience to date

Abstract

The US National Institutes of Health (NIH) has developed the Biomedical Translational Research Information System (BTRIS) to support researchers' access to translational and clinical data. BTRIS includes a data repository, a set of programs for loading data from NIH electronic health records and research data management systems, an ontology for coding the disparate data with a single terminology, and a set of user interface tools that provide access to identified data from individual research studies and data across all studies from which individually identifiable data have been removed. This paper reports on unique design elements of the system, progress to date and user experience after five years of development and operation.

Keywords: Clinical research; Ontology; Research data repository; Research data warehouse; Translational research.

Figure 1

Simplified entity-relation diagram showing table relationships in BTRIS. Table names are in bold, column names in regular font; column names marked with (*) indicate unique key for table; solid arrows show one-to-many relationships between table rows. Tables shown are for measureable observations and their corresponding events. “GUID” stands for :”globally unique identifier”, with Subject_GUID being the identifier for human subjects. Parent, Child and Sequence rows convey structure among entities and observations. The full specifications are available at http://people.dbmi.columbia.edu/~ciminoj/BTRIS-Data-Model.xhtml.

Figure 2

Representative example of a RED Concept. Attributes (properties, roles and associations) are shown in bold, qualifiers are shown in italic, and the values of attributes and qualifiers are shown in plain text. The concept corresponds to a particular NICHD research study from the CTDB system. Of particular note, it has two parents (“superconcepts”) and is related to several other RED concepts that correspond to specific encounter forms for the study. Parts of this concept description have been edited out for clarity.

Figure 3

Example of “prompt page” for capturing a user's specifications for a study-specific BTRIS identified data report; in this case, the report will retrieve laboratory test results. Selection of a study (“Protocol Number” at upper left) is required. All other parameters are optional; clicking on “Run Report” with no other parameter values would retrieve all results for all subjects on the selected study. In this case, the user has selected four subjects, a date range, and specified that the results should be within five days of the date that the subjects signed their respective consent forms (the dates they started the study). The user has also used the RED browser (not shown here but similar to Figure 8) to specify that results should be in the test classes “Glucose Intravascular Test” and “Glycosylated Hemoglobin (A1c Hgb) Intravascular Test”.

Figure 4

Results of running a BTRIS identified data report; in this case, the Radiology Report. The user has completed the appropriate prompt page (not shown, but similar to Figure 3) and selected a study and the RED class “Ultrasound”. The report is in spreadsheet form with one row per result. The 7^th column contains identifiers such as “US0903625” that are hyperlinks. Clicking on one of these links evokes a viewer application that retrieves the relevant images from the Radiology Departments picture archiving and communication system (PACS). This figure shows the result of clicking on one such link from an ultrasound report.

Figure 5

Display of BTRIS data using the Lifelines2 visualization tool from the University of Maryland's Human Computer Interface Laboratory.[28] Data consist of timing of administration of a study medication (blue triangles, labeled “MED0”) and occurrences of a particular adverse event (green triangles, labeled “Event”), with each horizontal row corresponding to a particular study subject; 12 subjects are shown in the top panel. The panel at the bottom shows the monthly counts for medications and events for all 126 subjects in the study. Together, they show that the event often appears to follow the administration of the medication and that increased events noted in 2011 (right side of both panels) correlate with increased use of the medication.

Figure 6

Data use agreement for retrieval of BTRIS data across all studies (with personal identifiers removed). The use must click on “Agree” prior to any use of the query tool (shown in Figure 7).

Figure 7

User interface for retrieval of BTRIS data across all studies (with personal identifiers removed). In this example, the user has constructed a query to find subjects that have had a diagnosis of chronic granulomatous disease (“Diagnosis1”) and tuberculosis (“Diagnosis2”) and have had liver function tests performed (“Labs3). The user has selected disease and test terms from the RED (see Figure 8). Execution of the query shows that there are 7,285 test results on four unique subjects. Clicking on the “Download Detailed Result” button initiates the data retrieval and notification processes, as described in the text.

Figure 8

Web-based tool for retrieving concepts from the RED. This screen shows the result of the search for tests and test classes with the word “Liver” (see the “Lab3” panel in Figure 7). In this example, the user has expanded the hierarchy under “Alkaline Phosphatase Intravascular Test” so show more specific test terms, including some from the CRIMSON and C3D systems. The mouse pointer is hovering over the intravascular test class term, causing the hover box to be displayed showing the RED Code for the concept (C111370) and the total number of results (3,727,698) in BTRIS for all tests in this class.