Construction and Validation of Synthetic Electronic Medical Records

Authors

  • Linda Moniz Johns Hopkins Univ. Applied Physics Laboratory
  • Anna L. Buczak Johns Hopkins Univ. Applied Physics Laboratory
  • Lang Hung Johns Hopkins Univ. Applied Physics Laboratory
  • Steven Babin Johns Hopkins Univ. Applied Physics Laboratory
  • Michael Dorko Johns Hopkins Univ. Applied Physics Laboratory and Carnegie Mellon University
  • Joseph Lombardo Johns Hopkins Univ. Applied Physics Laboratory

DOI:

https://doi.org/10.5210/ojphi.v1i1.2720

Abstract

There is a current and pressing need for a test bed of electronic medical records (EMRs) to insure consistent development, validation and verification of public health related algorithms that operate on EMRs. However, access to full EMRs is limited and not generally available to the academic algorithm developers who support the public health community. This paper describes a set of algorithms that produce synthetic EMRs using real EMRs as a model. The algorithms were used to generate a pilot set of over 3000 synthetic EMRs that are currently available on CDC’s Public Health grid. The properties of the synthetic EMRs were validated, both in the entire aggregate data set and for individual (synthetic) patients. We describe how the algorithms can be extended to produce records beyond the initial pilot data set.

Downloads

Published

2009-12-10

How to Cite

Moniz, L., Buczak, A. L., Hung, L., Babin, S., Dorko, M., & Lombardo, J. (2009). Construction and Validation of Synthetic Electronic Medical Records. Online Journal of Public Health Informatics, 1(1). https://doi.org/10.5210/ojphi.v1i1.2720

Issue

Section

Original Articles