PMean: Mining the electronic health record, why and how

I’m submitting a talk to an upcoming research conference. I’m not sure if they’ll accept it, but wish me luck. Here’s the title and abstract.

Mining the Electronic Health Record, Why and How.

Stephen D. Simon
Department of Biomedical and Health Informatics, UMKC

Medical records are now stored electronically, allowing opportunities for research and quality improvement studies that did not exist before. In this talk, I will review the extraction of information into i2b2, a database that is scrubbed of personal identifiers, and will discuss the strengths and limitations of this data compared to other commonly used health care data sets. I will also show a simple example of creating a medical record phenotype and validating it against a tumor registry.