EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Ensemble pretrained language models to extract biomedical knowledge from literature

Zhao Li, Qiang Wei, Liang-Chin Huang, Jianfu Li, Yan Hu iD, Yao-Shun Chuang, Jianping He, Avisha Das, Vipina Kuttichi Keloth, Yuntao Yang, Chiamaka S Diala, Kirk E Roberts iD und 4 weitere

Journal of the American Medical Informatics Association · 01.09.2024 · 31 (9) · 1904-1911

DOI: 10.1093/jamia/ocae061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 23.03.2024. Verfasst von Zhao Li und 15 weiteren Autor:innen. Beteiligte Einrichtung: McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX 77030, United States. Hauptthemen laut MEDLINE: Natural Language Processing. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIBIB NIH HHS, Cancer Prevention and Research Institute of Texas, NIA NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

The rapid expansion of biomedical literature necessitates automated techniques to discern relationships between biomedical concepts from extensive free text. Such techniques facilitate the development of detailed knowledge bases and highlight research deficiencies. The LitCoin Natural Language Processing (NLP) challenge, organized by the National Center for Advancing Translational Science, aims to evaluate such potential and provides a manually annotated corpus for methodology development and benchmarking. Materials and Methods For the named entity recognition (NER) task, we utilized ensemble learning to merge predictions from three domain-specific models, namely BioBERT, PubMedBERT, and BioM-ELECTRA, devised a rule-driven detection method for cell line and taxonomy names and annotated 70 more abstracts as additional corpus. We further finetuned the T0pp model, with 11 billion parameters, to boost the performance on relation extraction and leveraged entites’ location information (eg, title, background) to enhance novelty prediction performance in relation extraction (RE).

Results

Our pioneering NLP system designed for this challenge secured first place in Phase I—NER and second place in Phase II—relation extraction and novelty prediction, outpacing over 200 teams. We tested OpenAI ChatGPT 3.5 and ChatGPT 4 in a Zero-Shot setting using the same test set, revealing that our finetuned model considerably surpasses these broad-spectrum large language models. Discussion and Conclusion Our outcomes depict a robust NLP system excelling in NER and RE across various biomedical entities, emphasizing that task-specific models remain superior to generic large ones. Such insights are valuable for endeavors like knowledge graph development and hypothesis formulation in biomedical research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingData MiningMachine LearningHumans

Stichwörter der Autor:innen

ensemble learningknowledge baselarge language modelnamed entity recognitionrelation extraction

Autor:innen und Institutionen

  • McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX 77030, United States.
  • Section of Biomedical Informatics and Data Science, School of Medicine, Yale University, New Haven, CT 06510, United States.

ORCID-Profile: Yan Hu, Kirk E Roberts, Xiaoqian Jiang, W Jim Zheng, Hua Xu

Förderung

  • NIBIB NIH HHS
  • Cancer Prevention and Research Institute of Texas
  • NIA NIH HHS
  • NIMH NIH HHS
  • NLM NIH HHS
  • Department of Defense
  • NCATS NIH HHS
  • NIH HHS

Zitieren

APA

Li, Z., Wei, Q., Huang, L. C., Li, J., Hu, Y., Chuang, Y. S., He, J., Das, A., Keloth, V. K., Yang, Y., Diala, C. S., Roberts, K. E., Tao, C., Jiang, X., Zheng, W. J., & Xu, H. (2024). Ensemble pretrained language models to extract biomedical knowledge from literature. Journal of the American Medical Informatics Association, 31(9), 1904-1911. https://doi.org/10.1093/jamia/ocae061

Vancouver

Li Z, Wei Q, Huang LC, Li J, Hu Y, Chuang YS, et al. Ensemble pretrained language models to extract biomedical knowledge from literature. Journal of the American Medical Informatics Association. 2024;31(9):1904-1911. doi:10.1093/jamia/ocae061

BibTeX
@article{Li2024,
  author = {Li, Zhao and Wei, Qiang and Huang, Liang-Chin and Li, Jianfu and Hu, Yan and Chuang, Yao-Shun and He, Jianping and Das, Avisha and Keloth, Vipina Kuttichi and Yang, Yuntao and Diala, Chiamaka S and Roberts, Kirk E and Tao, Cui and Jiang, Xiaoqian and Zheng, W Jim and Xu, Hua},
  title = {Ensemble pretrained language models to extract biomedical knowledge from literature},
  journal = {Journal of the American Medical Informatics Association},
  year = {2024},
  volume = {31},
  number = {9},
  pages = {1904--1911},
  doi = {10.1093/jamia/ocae061}
}
Kostenlos starten →