Abstract:
|
Electronic health record (EHR) data present an incredibly appealing opportunity for public health and medical research. Relative to data from dedicated designs, EHR data often contains rich information on a broad range of patients over long timeframes and in real-world settings. Furthermore, it is typically relatively cheap to obtain. Nevertheless, the use of EHR data for research purposes is subject to many challenges, including (i) accurate extraction of text-based information, (ii) missing data, (iii) measurement error and misclassification, and (iv) the control of confounding. While these issues arise in other contexts, the complexity and high-dimensional nature of EHR data poses additional challenges for statisticians. The purpose of this roundtable is to provide a forum for statisticians and analysts to discuss these issues in general and in their own contexts, as well as discuss recent methodologic developments in the area.
|
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.