Is That the Right Dose? Investigating Generative Language Model Performance on Veterinary Prescription Text Analysis

Brian Hur, Lucy Lu Wang, Laura Hardefeldt, Meliha Yetisgen


Abstract
Optimizing antibiotic dosing recommendations is a vital aspect of antimicrobial stewardship (AMS) programs aimed at combating antimicrobial resistance (AMR), a significant public health concern, where inappropriate dosing contributes to the selection of AMR pathogens. A key challenge is the extraction of dosing information, which is embedded in free-text clinical records and necessitates numerical transformations. This paper assesses the utility of Large Language Models (LLMs) in extracting essential prescription attributes such as dose, duration, active ingredient, and indication. We evaluate methods to optimize LLMs on this task against a baseline BERT-based ensemble model. Our findings reveal that LLMs can achieve exceptional accuracy by combining probabilistic predictions with deterministic calculations, enforced through functional prompting, to ensure data types and execute necessary arithmetic. This research demonstrates new prospects for automating aspects of AMS when no training data is available.
Anthology ID:
2024.bionlp-1.30
Volume:
Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Dina Demner-Fushman, Sophia Ananiadou, Makoto Miwa, Kirk Roberts, Junichi Tsujii
Venues:
BioNLP | WS
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
390–397
Language:
URL:
https://aclanthology.org/2024.bionlp-1.30
DOI:
10.18653/v1/2024.bionlp-1.30
Bibkey:
Cite (ACL):
Brian Hur, Lucy Lu Wang, Laura Hardefeldt, and Meliha Yetisgen. 2024. Is That the Right Dose? Investigating Generative Language Model Performance on Veterinary Prescription Text Analysis. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 390–397, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Is That the Right Dose? Investigating Generative Language Model Performance on Veterinary Prescription Text Analysis (Hur et al., BioNLP-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.bionlp-1.30.pdf