Leveraging Open-Source Large Language Models for Data Augmentation in Hospital Staff Surveys: Mixed Methods Study
JMIR Medical Education · 19.11.2024 · 10 · e51433-e51433
DOI: 10.2196/51433 ↗Kurz gefasst
Mixed-Methods-Studie in der Zeitschrift JMIR Medical Education, online erschienen am 19.11.2024. Verfasst von Carl Ehrett und 4 weiteren Autor:innen. Beteiligte Einrichtung: Watt Family Innovation Center, Clemson University, Clemson, SC, United States. Hauptthemen laut MEDLINE: COVID-19. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Generative large language models (LLMs) have the potential to revolutionize medical education by generating tailored learning materials, enhancing teaching efficiency, and improving learner engagement. However, the application of LLMs in health care settings, particularly for augmenting small datasets in text classification tasks, remains underexplored, particularly for cost- and privacy-conscious applications that do not permit the use of third-party services such as OpenAI’s ChatGPT.
Objective
This study aims to explore the use of open-source LLMs, such as Large Language Model Meta AI (LLaMA) and Alpaca models, for data augmentation in a specific text classification task related to hospital staff surveys.
Methods
The surveys were designed to elicit narratives of everyday adaptation by frontline radiology staff during the initial phase of the COVID-19 pandemic. A 2-step process of data augmentation and text classification was conducted. The study generated synthetic data similar to the survey reports using 4 generative LLMs for data augmentation. A different set of 3 classifier LLMs was then used to classify the augmented text for thematic categories. The study evaluated performance on the classification task.
Results
The overall best-performing combination of LLMs, temperature, classifier, and number of synthetic data cases is via augmentation with LLaMA 7B at temperature 0.7 with 100 augments, using Robustly Optimized BERT Pretraining Approach (RoBERTa) for the classification task, achieving an average area under the receiver operating characteristic (AUC) curve of 0.87 (SD 0.02; ie, 1 SD). The results demonstrate that open-source LLMs can enhance text classifiers’ performance for small datasets in health care contexts, providing promising pathways for improving medical education processes and patient care practices.
Conclusions
The study demonstrates the value of data augmentation with open-source LLMs, highlights the importance of privacy and ethical considerations when using LLMs, and suggests future directions for research in this field.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Watt Family Innovation Center, Clemson University, Clemson, SC, United States.
- Department of Industrial Engineering, Clemson University, Clemson, SC, United States.
- Department of Computer Science, Clemson University, Clemson, SC, United States.
ORCID-Profile: Carl Ehrett, Sudeep Hegde, Kwame Andre, Dixizi Liu, Timothy Wilson
Zitieren
APA
Ehrett, C., Hegde, S., Andre, K., Liu, D., & Wilson, T. (2024). Leveraging Open-Source Large Language Models for Data Augmentation in Hospital Staff Surveys: Mixed Methods Study. JMIR Medical Education, 10, e51433-e51433. https://doi.org/10.2196/51433
Vancouver
Ehrett C, Hegde S, Andre K, Liu D, Wilson T. Leveraging Open-Source Large Language Models for Data Augmentation in Hospital Staff Surveys: Mixed Methods Study. JMIR Medical Education. 2024;10:e51433-e51433. doi:10.2196/51433
BibTeX
@article{Ehrett2024,
author = {Ehrett, Carl and Hegde, Sudeep and Andre, Kwame and Liu, Dixizi and Wilson, Timothy},
title = {Leveraging Open-Source Large Language Models for Data Augmentation in Hospital Staff Surveys: Mixed Methods Study},
journal = {JMIR Medical Education},
year = {2024},
volume = {10},
pages = {e51433--e51433},
doi = {10.2196/51433}
}
EUVIMED