Generative Terminology Mapping of Source Medication Terms to RxNorm: Using LLMs as Clinical Expert Reviewer

At Atropos Health, we innovated an approach combining NLP models with Large Language Models (LLMs) to map medication text strings to RxNorm in Real World Data. This method achieved 99.2% accuracy in ingredient correctness on a billion-scale dataset, significantly reducing the NLP model’s error rate from 9% to 0.7%. Notably, this technique displayed a high agreement level (Cohen’s κ of 0.899) between its results and human experts, demonstrating its reliability and potential for broad application.

This approach led to a 98% reduction in mapping costs compared to manual processes, emphasizing its scalability and cost-effectiveness. This efficient method did not require model fine-tuning, training, extensive data exposure to the LLM, or the use of a clinically-focused LLM at all. The presentation will explore the technical challenges, cost analysis, and future prospects of this innovative approach.

About the speaker

Philip Ballentine

Sr Director, Data Engineering at Atropos Health

Phil Ballentine has been leading Data Engineering at Atropos Health since 2022, focusing on leveraging real-world data to fill evidence gaps in healthcare and life sciences. This role at the venture-backed startup capitalizes on Phil’s extensive experience in healthcare data integration and real-world evidence, previously honed at Health Catalyst and athenahealth. Phil holds an MSc in Health Informatics and Analytics from Tufts University School of Medicine.




Sessions: April 2nd – 3rd 2024
Trainings: April 15th – 19th 2024



Presented by