Mapping medications within large, multi-site databases is not routinely performed, and if it is completed, it might be incorrect. In this preliminary work, we have demonstrated the feasibility of using machine learning and noisy labels to map prescription-based medication information found in a large databases to a standard terminology (i.e., RxNorm concept unique identifiers).

Learning Objective: By the end of this session, the learner will be able to describe the role of noisy labels and machine learning to assign a standardized, unique identifier to database records.


Alvin Jeffery (Presenter)
U.S. Department of Veterans Affairs

Sharidan Parr, Vanderbilt University School of Medicine
Michael Matheny, U.S. Department of Veterans Affairs

Presentation Materials: