Zero- and Few-shot Named Entity Recognition and Text Expansion in Medication Prescriptions using ChatGPT

TL;DR

This study demonstrates that ChatGPT 3.5 can effectively perform zero- and few-shot named entity recognition and text expansion on complex medication prescriptions, improving interpretability and safety in medical data processing.

Contribution

The paper introduces a novel application of ChatGPT for NER and text expansion in medication prescriptions, highlighting the benefits of few-shot prompting for accuracy and safety.

Findings

NER F1 score of 0.94 with best prompt

Text expansion F1 score of 0.87 with few-shot prompt

Few-shot prompts reduce hallucinations in sensitive data

Abstract

Introduction: Medication prescriptions are often in free text and include a mix of two languages, local brand names, and a wide range of idiosyncratic formats and abbreviations. Large language models (LLMs) have shown promising ability to generate text in response to input prompts. We use ChatGPT 3.5 to automatically structure and expand medication statements in discharge summaries and thus make them easier to interpret for people and machines. Methods: Named-entity Recognition (NER) and Text Expansion (EX) are used in a zero- and few-shot setting with different prompt strategies. 100 medication statements were manually annotated and curated. NER performance was measured by using strict and partial matching. For the task EX, two experts interpreted the results by assessing semantic equivalence between original and expanded statements. The model performance was measured by precision, recall, and F1 score. Results: For NER, the best-performing prompt reached an average F1 score of 0.94 in the test set. For EX, the few-shot prompt showed superior performance among other prompts, with an average F1 score of 0.87. Conclusion: Our study demonstrates good performance for NER and EX tasks in free-text medication statements using ChatGPT. Compared to a zero-shot baseline, a few-shot approach prevented the system from hallucinating, which would be unacceptable when processing safety-relevant medication data.