Contextualized Medication Information Extraction Using Transformer-based Deep Learning Architectures

TL;DR

This paper presents a transformer-based NLP system that effectively extracts medication information and contextual changes from clinical texts, leveraging large language models to outperform smaller models in a challenging clinical NLP task.

Contribution

The study introduces the use of a large pretrained transformer model, GatorTron, for medication information extraction and contextual classification, demonstrating superior performance over existing models.

Findings

GatorTron achieved the highest F1-score of 0.9828 for medication extraction.

GatorTron outperformed other models in event and context classification.

Large language models provide significant advantages in clinical NLP tasks.

Abstract

Objective: To develop a natural language processing (NLP) system to extract medications and contextual information that help understand drug changes. This project is part of the 2022 n2c2 challenge. Materials and methods: We developed NLP systems for medication mention extraction, event classification (indicating medication changes discussed or not), and context classification to classify medication changes context into 5 orthogonal dimensions related to drug changes. We explored 6 state-of-the-art pretrained transformer models for the three subtasks, including GatorTron, a large language model pretrained using >90 billion words of text (including >80 billion words from >290 million clinical notes identified at the University of Florida Health). We evaluated our NLP systems using annotated data and evaluation scripts provided by the 2022 n2c2 organizers. Results:Our GatorTron models achieved the best F1-scores of 0.9828 for medication extraction (ranked 3rd), 0.9379 for event classification (ranked 2nd), and the best micro-average accuracy of 0.9126 for context classification. GatorTron outperformed existing transformer models pretrained using smaller general English text and clinical text corpora, indicating the advantage of large language models. Conclusion: This study demonstrated the advantage of using large transformer models for contextual medication information extraction from clinical narratives.