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

2025-02-05

AI Summary

This study addresses the low efficiency and poor cross-lingual adaptability of drug information extraction from clinical notes. We propose a lightweight end-to-end Transformer architecture for medication entity recognition and relation extraction in both French and English. Our key innovations include a medical relation–aware efficient attention mechanism and a parameter-sharing cross-lingual encoder, jointly optimizing accuracy and computational efficiency. Experiments demonstrate state-of-the-art performance: relation extraction F1 scores of 0.82 (French) and 0.96 (English), and end-to-end joint extraction F1 scores of 0.69 and 0.82, respectively. Compared to baseline models, our approach achieves a 10× speedup in inference and reduces GPU memory consumption by 90%. The method thus delivers high accuracy, minimal resource requirements, and strong cross-lingual transferability—providing an efficient, scalable solution for multilingual clinical natural language processing.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

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

Problem

• Extracting medication information efficiently
• Evaluating NLP method in two languages
• Reducing computational cost in clinical text processing

Innovation

• Transformer-based architecture for NLP
• Efficient medication information extraction
• Low computational cost solution