Automatic Posology Structuration : What role for LLMs?

TL;DR

This paper investigates using Large Language Models to convert ambiguous French medication instructions into structured data, proposing a hybrid system that combines NERL and LLMs for improved accuracy and efficiency.

Contribution

It introduces a hybrid pipeline leveraging both NERL and fine-tuned LLMs, optimizing accuracy and computational efficiency for clinical posology structuration.

Findings

Hybrid pipeline achieves 91% accuracy

Prompting improves LLM performance but fine-tuning is more accurate

Combining NERL and LLMs reduces computational costs

Abstract

Automatically structuring posology instructions is essential for improving medication safety and enabling clinical decision support. In French prescriptions, these instructions are often ambiguous, irregular, or colloquial, limiting the effectiveness of classic ML pipelines. We explore the use of Large Language Models (LLMs) to convert free-text posologies into structured formats, comparing prompt-based methods and fine-tuning against a "pre-LLM" system based on Named Entity Recognition and Linking (NERL). Our results show that while prompting improves performance, only fine-tuned LLMs match the accuracy of the baseline. Through error analysis, we observe complementary strengths: NERL offers structural precision, while LLMs better handle semantic nuances. Based on this, we propose a hybrid pipeline that routes low-confidence cases from NERL (<0.8) to the LLM, selecting outputs based on confidence scores. This strategy achieves 91% structuration accuracy while minimizing latency and compute. Our results show that this hybrid approach improves structuration accuracy while limiting computational cost, offering a scalable solution for real-world clinical use.