A machine learning approach for automating review of a RxNorm medication mapping pipeline output
Matthias Hüser1, John Doole1, Vinicius Pinho1
1TriNetX LLC, 100 Cambridgepark Dr #501, 02140 Cambridge, MA, United States.
Objective:
Medication mapping to standardized terminologies is an important prerequisite for performing analytics on a federated EHR network. TriNetX LLC operates the largest such network in the world.
Methods:
Here we report on a novel pipeline, called RxEmbed, for the mapping and binding of local medication descriptions to RxNorm ingredient codes, using LLMs, and automated mapping review using machine learning.
Results:
Performance of RxEmbed was assessed in a public data set from France as well as 6 Healthcare Organizations from the TriNetX federated EHR network across the United States and Brazil. On the public data set, RxEmbed outperformed two recently reported LLM-based baselines in terms of recall, and precision of generated mappings. In TriNetX network data, RxEmbed obtained RxNorm mapping recalls of 84%-93%, at a precision of 99.5%-100%.
Conclusion:
We built and evaluated a LLM-based medication mapping pipeline, that binds local medication descriptions from EHR systems to RxNorm ingredient codes. The high precision of the pipeline output implies very limited need for human review of the generated mappings.
