EUVIMEDEUVIMED entdecken
Mixed-Methods-StudieOpen Access

Leveraging Open-Source Large Language Models for Data Augmentation in Hospital Staff Surveys: Mixed Methods Study

Carl Ehrett iD, Sudeep Hegde iD, Kwame Andre iD, Dixizi Liu iD, Timothy Wilson iD

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

COVID-19HumansSurveys and QuestionnairesPersonnel, Hospital

Stichwörter der Autor:innen

AIartificial intelligencedata augmentationdata privacydata securityethicslarge language modelsmedical educationmedical staffnatural language processing

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}
}
Kostenlos starten →