Electronic medical records (EMR) represent a rich source of clinical data that can be utilized for research, quality assurance, and pay-for-performance, among others. However, it is important to recognize that, like any other data source, EMR data has its own pitfalls that need to be approached in a rigorous fashion. In particular, a large fraction of data in EMR is “locked” in narrative documents and can therefore be especially challenging to extract. This presentation will discuss issues users can expect to encounter when analyzing EMR data and how they can be approached. The presentation will specifically focus on using natural language processing to extract data from narrative electronic documents, using publicly available NLP platform Canary as an example. The discussion will be illustrated by specific instances of clinical research using EMR data, including narrative text.
Alexander Turchin, MD, MS is Director of Clinical Informatics at Baim Institute for Clinical Research, Director of Informatics Research at the Division of Endocrinology at Brigham and Women’s Hospital and Associate Professor of Medicine at Harvard Medical School. Dr. Turchin is a graduate of Johns Hopkins University School of Medicine and Massachusetts Institute of Technology (Medical Informatics). His research focuses on analysis of electronic medical record data; he uses advanced informatics technologies including natural language processing to study quality of care and outcomes in chronic endocrine diseases. Dr. Turchin is a Fellow of the American College of Medical Informatics and has published over 80 papers and book chapters; his research has been funded by AHRQ, NIH and private foundations.