EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Leveraging Large Language Models for Synthetic Data Generation to Enhance Adverse Drug Event Detection in Tweets

Anthony Yazdani, Hossein Rouhizadeh, Alban Bornet, Douglas Teodoro

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti250465 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Anthony Yazdani und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Geneva, Switzerland. Hauptthemen laut MEDLINE: Natural Language Processing, Social Media, Drug-Related Side Effects and Adverse Reactions, Adverse Drug Reaction Reporting Systems. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Adverse drug event (ADE) detection in social media texts poses significant challenges due to the informal nature of the text and the limited availability of annotations. The scarcity of ADE named entity recognition (NER) datasets for social media hinders the development of robust ADE detection models for this type of corpus. In this paper, we leveraged the generative capabilities of large language models (LLMs) to create synthetic data, addressing this dataset gap. Specifically, we generated 17,000 tweets with ADE annotations and pre-trained NER models on this synthetic data. Our evaluations on an out-of-sample collection of 915 manually annotated tweets revealed that these models outperform state-of-the-art lexico-based and massively pre-trained open NER models. We also show that fine-tuning our synthetically pre-trained models on human-annotated data surpasses the current state-of-the-art in ADE detection on tweets. These findings suggest that synthetic data generated by LLMs can enhance ADE detection performance, offering a promising avenue to explore in response to the scarcity of annotated ADE datasets. The synthetic dataset is available at https://huggingface.co/datasets/anthonyyazdaniml/synthetic-ner-ade-tweets-v1.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingSocial MediaDrug-Related Side Effects and Adverse ReactionsAdverse Drug Reaction Reporting SystemsData MiningHumansLarge Language Models

Stichwörter der Autor:innen

Adverse Drug EventsLarge Language ModelsMetaMapNamed Entity RecognitionSocial MediaSynthetic Data GenerationTweetsZero-Shot Learning

Autor:innen und Institutionen

  • Department of Radiology and Medical Informatics, Faculty of Medicine, University of Geneva, Geneva, Switzerland.

Zitieren

APA

Yazdani, A., Rouhizadeh, H., Bornet, A., & Teodoro, D. (2025). Leveraging Large Language Models for Synthetic Data Generation to Enhance Adverse Drug Event Detection in Tweets. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250465

Vancouver

Yazdani A, Rouhizadeh H, Bornet A, Teodoro D. Leveraging Large Language Models for Synthetic Data Generation to Enhance Adverse Drug Event Detection in Tweets. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250465

BibTeX
@article{Yazdani2025,
  author = {Yazdani, Anthony and Rouhizadeh, Hossein and Bornet, Alban and Teodoro, Douglas},
  title = {Leveraging Large Language Models for Synthetic Data Generation to Enhance Adverse Drug Event Detection in Tweets},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti250465}
}
Kostenlos starten →