EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Automating Precision Oncology Literature Curation: A Decision Tree Approach Using Large Language Models

Frank P Lin, Minh Tran, Subotheni Thavaneswaran, John P Grady, Maya Kansara, Jeffrey Chan, Mandy L Ballinger, John Simes, David M Thomas

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti250839 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Frank P Lin und 8 weiteren Autor:innen. Beteiligte Einrichtung: Garvan Institute of Medical Research, Sydney, Australia. Hauptthemen laut MEDLINE: Precision Medicine, Decision Trees, Medical Oncology, Natural Language Processing. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The curation of precision oncology knowledge bases requires intensive screening of scientific literature. Large Language Models (LLMs) offer potential to assist with knowledge extraction and curation through automated abstract screening, though their utility in this context remains unexplored. We developed a decision tree-based pipeline utilising LLMs to automate literature screening for precision oncology knowledge bases. The system employs structured prompts to evaluate biomarker-therapeutic relationships across 8,012 abstracts from 25 oncology journals published in 2024. Performance was assessed against expert review using standard evaluation metrics; the pipeline achieved an overall accuracy of 92.9% (sensitivity [recall] 87.1%, specificity 93.7%) in shortlisting 1,328 candidate abstracts, of which 888 are considered relevant by experts, delivering a 5.26-fold enrichment in classification precision. Analysis of correctly identified abstracts revealed comprehensive coverage of key molecular targets, drug classes (immunotherapies and targeted therapies), and relevant cancer types. This pipeline automates literature triage for precision oncology knowledge bases for relevance, maintaining high specificity and potentially reducing manual screening burden whilst offering a scalable framework for sustainable knowledge base maintenance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Precision MedicineDecision TreesMedical OncologyNatural Language ProcessingData MiningData CurationNeoplasmsHumansKnowledge BasesLarge Language Models

Stichwörter der Autor:innen

Artificial intelligenceGenomicsLarge language modelsNatural language processingOncologyPrecision medicine

Autor:innen und Institutionen

  • Garvan Institute of Medical Research, Sydney, Australia.
  • NHMRC Clinical Trials Centre, University of Sydney, Australia.
  • Faculty of Medicine and Health, UNSW Sydney, Australia.
  • Kinghorn Cancer Centre, St Vincent's Hospital Sydney, Australia.
  • Centre for Molecular Oncology, UNSW Sydney, Australia.

Zitieren

APA

Lin, F. P., Tran, M., Thavaneswaran, S., Grady, J. P., Kansara, M., Chan, J., Ballinger, M. L., Simes, J., & Thomas, D. M. (2025). Automating Precision Oncology Literature Curation: A Decision Tree Approach Using Large Language Models. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250839

Vancouver

Lin FP, Tran M, Thavaneswaran S, Grady JP, Kansara M, Chan J, et al. Automating Precision Oncology Literature Curation: A Decision Tree Approach Using Large Language Models. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250839

BibTeX
@article{Lin2025,
  author = {Lin, Frank P and Tran, Minh and Thavaneswaran, Subotheni and Grady, John P and Kansara, Maya and Chan, Jeffrey and Ballinger, Mandy L and Simes, John and Thomas, David M},
  title = {Automating Precision Oncology Literature Curation: A Decision Tree Approach Using Large Language Models},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti250839}
}
Kostenlos starten →