Efficient extraction of medication information from clinical notes: an evaluation in two languages

TL;DR

This paper presents a transformer-based NLP method for extracting medication info from clinical notes, demonstrating high accuracy and low computational cost across French and English texts, suitable for resource-limited hospital settings.

Contribution

The study introduces a novel transformer architecture for medication extraction that is efficient, portable across languages, and maintains competitive accuracy with reduced computational requirements.

Findings

Achieves state-of-the-art relation extraction performance in French and English.

Reduces computational cost by 10 compared to existing transformer methods.

Provides effective end-to-end medication information extraction in clinical texts.

Abstract

Objective: To evaluate the accuracy, computational cost and portability of a new Natural Language Processing (NLP) method for extracting medication information from clinical narratives. Materials and Methods: We propose an original transformer-based architecture for the extraction of entities and their relations pertaining to patients' medication regimen. First, we used this approach to train and evaluate a model on French clinical notes, using a newly annotated corpus from H\^opitaux Universitaires de Strasbourg. Second, the portability of the approach was assessed by conducting an evaluation on clinical documents in English from the 2018 n2c2 shared task. Information extraction accuracy and computational cost were assessed by comparison with an available method using transformers. Results: The proposed architecture achieves on the task of relation extraction itself performance that are competitive with the state-of-the-art on both French and English (F-measures 0.82 and 0.96 vs 0.81 and 0.95), but reduce the computational cost by 10. End-to-end (Named Entity recognition and Relation Extraction) F1 performance is 0.69 and 0.82 for French and English corpus. Discussion: While an existing system developed for English notes was deployed in a French hospital setting with reasonable effort, we found that an alternative architecture offered end-to-end drug information extraction with comparable extraction performance and lower computational impact for both French and English clinical text processing, respectively. Conclusion: The proposed architecture can be used to extract medication information from clinical text with high performance and low computational cost and consequently suits with usually limited hospital IT resources