EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ERNIE-UIE: Advancing information extraction in Chinese medical knowledge graph

Bei Li, Changbiao Li, Jianwei Sun, Xu Zeng, Xiaofan Chen, Jing Zheng iD

PLOS One · 29.05.2025 · 20 (5) · e0325082

DOI: 10.1371/journal.pone.0325082 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 29.05.2025. Verfasst von Bei Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, School of Life Science, Central South University, Changsha, Hunan, China. Hauptthemen laut MEDLINE: Data Mining, Information Storage and Retrieval, Medical Informatics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shenzhen Health Development Research and Data Management Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The field of information extraction (IE) is currently exploring more versatile and efficient methods for minimization of reliance on extensive annotated datasets and integration of knowledge across tasks and domains.

Objective

We aim to evaluate and refine the application of the universal IE (UIE) technology in the field of Chinese medical expertise in terms of processing accuracy and efficiency.

Methods

Our model integrates ontology modeling, web scraping, UIE, fine-tuning strategies, and graph databases, thereby covering knowledge modeling, extraction, and storage techniques. The Enhanced Representation through Knowledge Integration-UIE (ERNIE-UIE) model is fine-tuned and optimized using a small amount of annotated data. A medical knowledge graph is then constructed, followed by validating the graph and conducting knowledge mining on the data stored within it.

Results

Incorporating the characteristics of whole-course management, we implemented a comprehensive medical knowledge graph–construction model and methodology. Entities and relationships were jointly extracted using the pretrained language model, resulting in 8,525 entity data points and 9,522 triple data points. The accuracy of the knowledge graph was verified using graph algorithms.

Conclusion

We optimized the construction process of a Chinese medical knowledge graph with minimal annotated data by utilizing a generative extraction paradigm, validating the graph’s efficacy and achieving commendable results. This approach addresses the challenge of insufficient annotated training corpora in low-resource knowledge graph construction, thereby contributing to cost savings in the development of knowledge graphs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Data MiningInformation Storage and RetrievalMedical InformaticsAlgorithmsChinaDatabases, Factual

Autor:innen und Institutionen

  • Department of Biomedical Informatics, School of Life Science, Central South University, Changsha, Hunan, China.
  • Shenzhen Health Development Research and Data Management Center, Shenzhen, Guangdong, China.

ORCID-Profile: Jing Zheng

Förderung

  • Shenzhen Health Development Research and Data Management Center

Zitieren

APA

Li, B., Li, C., Sun, J., Zeng, X., Chen, X., & Zheng, J. (2025). ERNIE-UIE: Advancing information extraction in Chinese medical knowledge graph. PLOS One, 20(5), e0325082. https://doi.org/10.1371/journal.pone.0325082

Vancouver

Li B, Li C, Sun J, Zeng X, Chen X, Zheng J. ERNIE-UIE: Advancing information extraction in Chinese medical knowledge graph. PLOS One. 2025;20(5):e0325082. doi:10.1371/journal.pone.0325082

BibTeX
@article{Li2025,
  author = {Li, Bei and Li, Changbiao and Sun, Jianwei and Zeng, Xu and Chen, Xiaofan and Zheng, Jing},
  title = {ERNIE-UIE: Advancing information extraction in Chinese medical knowledge graph},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {5},
  pages = {e0325082},
  doi = {10.1371/journal.pone.0325082}
}
Kostenlos starten →