Accelerating Biopharmaceutical Development in the Decade of Health Information Technology: Applications of EHRs for outcomes research and clinical trials recruitment.

Electronic health records hold vast potential for streamlining patient recruitment for clinical trials and improving outcomes research.

Clinical terminology support for a national ambulatory practice outcomes research network.

The Medical Quality Improvement Consortium (MQIC) is a nationwide collaboration of 74 healthcare delivery systems, consisting of 3755 clinicians, who contribute de-identified clinical data from the same commercial electronic medical record (EMR) for quality reporting, outcomes research and clinical research in public health and practice benchmarking. Despite the existence of a common, centrally-managed, shared terminology for core concepts (medications, problem lists, observation names), a substantial "back-end" information management process is required to ensure terminology and data harmonization for creating multi-facility clinically-acceptable queries and comparable results. We describe the information architecture created to support terminology harmonization across this data-sharing consortium and discuss the implications for large scale data sharing envisioned by proponents for the national adoption of ambulatory EMR systems.

Application of information-theoretic data mining techniques in a national ambulatory practice outcomes research network.

The Medical Quality Improvement Consortium data warehouse contains de-identified data on more than 3.6 million patients including their problem lists, test results, procedures and medication lists. This study uses reconstructability analysis, an information-theoretic data mining technique, on the MQIC data warehouse to empirically identify risk factors for various complications of diabetes including myocardial infarction and microalbuminuria. The risk factors identified match those risk factors identified in the literature, demonstrating the utility of the MQIC data warehouse for outcomes research, and RA as a technique for mining clinical data warehouses.

Using NLP to extract concepts from chief complaints.

The NLM's MMTx natural language processing (NLP) engine was used to extract concepts from chief complaints entered into an ambulatory electronic medical record (EMR). Of the over 600,000 strings submitted to the process, approximately 25% were assigned at least one concept, with a rate of 2% for incorrect assignments.

The use of SNOMED CT simplifies querying of a clinical data warehouse.

The usefulness of digital clinical information is limited by difficulty in accessing that information. Information in electronic medical records (EMR) must be entered and stored at the appropriate level of granularity for individual patient care. However, benefits such as outcomes research and decision support require aggregation to clinical data -- "heart disease" as opposed to "S/P MI 1997" for example. The hierarchical relationships in an external reference terminology, such as SNOMED, can facilitate aggregation. This study examines whether by leveraging the knowledge built into SNOMED's hierarchical structure, one can simplify the query process without degrading the query results.