EUVIMEDEUVIMED entdecken
Open Access

The Impact of Temperature on Extracting Information From Clinical Trial Publications Using Large Language Models

Paul Windisch, Fabio Dennstädt, Carole Koechli, Christina Schröder, Daniel M Aebersold, Robert Förster, Daniel R Zwahlen

Cureus · 15.12.2024

DOI: 10.7759/cureus.75748 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cureus, erschienen am 15.12.2024. Verfasst von Paul Windisch und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Cantonal Hospital Winterthur, Winterthur, CHE. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The application of natural language processing (NLP) for extracting data from biomedical research has gained momentum with the advent of large language models (LLMs). However, the effect of different LLM parameters, such as temperature settings, on biomedical text mining remains underexplored and a consensus on what settings can be considered "safe" is missing. This study evaluates the impact of temperature settings on LLM performance for a named entity recognition and a classification task in clinical trial publications.

Methods

Two datasets were analyzed using GPT-4o and GPT-4o-mini models at nine different temperature settings (0.00-2.00). The models were used to extract the number of randomized participants and classify abstracts as randomized controlled trials (RCTs) and/or as oncology-related. Different performance metrics were calculated for each temperature setting and task.

Results

Both models provided correctly formatted predictions for more than 98.7% of abstracts across temperatures from 0.00 to 1.50. While the number of correctly formatted predictions started to decrease afterward with the most notable drop between temperatures 1.75 and 2.00, the other performance metrics remained largely stable.

Conclusion

Temperature settings at or below 1.50 yielded consistent performance across text-mining tasks, with performance declines at higher settings. These findings are aligned with research on different temperature settings for other tasks, suggesting stable performance within a controlled temperature range across various NLP applications.

Schlagwörter

Stichwörter der Autor:innen

large language modelsnatural language processingtemperaturetext miningtransformer

Autor:innen und Institutionen

  • Department of Radiation Oncology, Cantonal Hospital Winterthur, Winterthur, CHE.
  • Department of Radiation Oncology, Bern University Hospital, University of Bern, Bern, CHE.

Zitieren

APA

Windisch, P., Dennstädt, F., Koechli, C., Schröder, C., Aebersold, D. M., Förster, R., & Zwahlen, D. R. (2024). The Impact of Temperature on Extracting Information From Clinical Trial Publications Using Large Language Models. Cureus. https://doi.org/10.7759/cureus.75748

Vancouver

Windisch P, Dennstädt F, Koechli C, Schröder C, Aebersold DM, Förster R, et al. The Impact of Temperature on Extracting Information From Clinical Trial Publications Using Large Language Models. Cureus. 2024. doi:10.7759/cureus.75748

BibTeX
@article{Windisch2024,
  author = {Windisch, Paul and Dennstädt, Fabio and Koechli, Carole and Schröder, Christina and Aebersold, Daniel M and Förster, Robert and Zwahlen, Daniel R},
  title = {The Impact of Temperature on Extracting Information From Clinical Trial Publications Using Large Language Models},
  journal = {Cureus},
  year = {2024},
  doi = {10.7759/cureus.75748}
}
Kostenlos starten →