Taking advantage of continuity of care documents to populate a research repository

Abstract

Objective: Clinical data warehouses have accelerated clinical research, but even with available open source tools, there is a high barrier to entry due to the complexity of normalizing and importing data. The Office of the National Coordinator for Health Information Technology's Meaningful Use Incentive Program now requires that electronic health record systems produce standardized consolidated clinical document architecture (C-CDA) documents. Here, we leverage this data source to create a low volume standards based import pipeline for the Informatics for Integrating Biology and the Bedside (i2b2) clinical research platform. We validate this approach by creating a small repository at Partners Healthcare automatically from C-CDA documents.

Materials and methods: We designed an i2b2 extension to import C-CDAs into i2b2. It is extensible to other sites with variances in C-CDA format without requiring custom code. We also designed new ontology structures for querying the imported data.

Results: We implemented our methodology at Partners Healthcare, where we developed an adapter to retrieve C-CDAs from Enterprise Services. Our current implementation supports demographics, encounters, problems, and medications. We imported approximately 17 000 clinical observations on 145 patients into i2b2 in about 24 min. We were able to perform i2b2 cohort finding queries and view patient information through SMART apps on the imported data.

Discussion: This low volume import approach can serve small practices with local access to C-CDAs and will allow patient registries to import patient supplied C-CDAs. These components will soon be available open source on the i2b2 wiki.

Conclusions: Our approach will lower barriers to entry in implementing i2b2 where informatics expertise or data access are limited.

Keywords: Database Management Systems; Information Storage and Retrieval; Meaningful Use; Medical Informatics; Systems Integration.

Figure 1:

Anticipated uses for consolidated clinical document architecture (C-CDA) based Informatics for Integrating Biology and the Bedside (i2b2) import. Left: Small practices with low volume and certified electronic health records (EHRs) can use the C-CDA documents they already produce to populate an i2b2 data repository. Right: Patients will be able to export their C-CDA from healthcare systems through Blue Button+, which they can donate to disease registries for research. Bottom: i2b2 can then be used to study both cohorts and individual patients, through the i2b2 query tool and SMART apps, respectively (see figure 4).

Figure 2:

Technical design of the SETL (service based extract, transform, and load) cell import process. Left: The data flow among components in the architecture. (1) A request with a list of medical record numbers (MRNs) is sent to the SETL cell, which then (2) calls an external command to retrieve consolidated clinical document architecture (C-CDA) documents. For this study, this goes to our continuity of care document (CCD) factory connector at Partners Healthcare (Boston, Massachusetts, USA). (3) Retrieved documents are converted into Informatics for Integrating Biology and the Bedside (i2b2) patient data objects (PDOs) and (4) are sent to the data repository cell for storage, where MRNs are replaced by a unique pseudoidentifier. Finally (5, 6) a report on import errors and statistics is generated and returned to the user. ETL, extract, transform, and load. Right: The SETL cell embeds the Open Health Tools Model Driven Message Interoperability (MDMI) engine, which converts between healthcare data formats.

Figure 3:

Total time to import patient data, as number of imported observations increase. The time is split into color coded components. Continuity of care document (CCD) is Partners’ CCD factory time to generate a consolidated clinical document architecture (C-CDA). CCD-Notes is time to add encounter notes to the C-CDA from Partners’ outpatient notes service. Model Driven Message Interoperability (MDMI) is the time taken to convert the C-CDA into patient data object (PDO) by Open Health Tools-MDMI. SETL (service based extract, transform, and load) is all other processing of the PDO before sending to the clinical research chart (CRC) loader. CRC is the time taken by the CRC's loader service to import the PDO into the data repository.

Figure 4:

Imported data can be studied in aggregate or by patient. (Top) The Informatics for Integrating Biology and the Bedside (i2b2) query tool shows that six imported patients are using simvastatin 40 mg. (Bottom) The i2b2-SMART note viewer app shows the list of patient notes containing the word ‘sad’ for a test patient.