Leveraging Large Language Models for Cancer Variant Classification: A Comparative Study of GPT-4o, LLaMA 3, and Qwen 2.5
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti251185 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Kuan-Hsun Lin und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Management, Taipei Veterans General Hospital, Taipei, 11267, Taiwan, R.O.C. Hauptthemen laut MEDLINE: Neoplasms, Genetic Variation, Natural Language Processing, Programming Languages. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Background: Interpreting genomic variants from cancer sequencing data is a critical yet complex task in precision oncology. With advances in large language models (LLMs), there is increasing interest in leveraging their capacity for variant classification. This study benchmarks three state-of-the-art LLMs — GPT-4o, LLaMA 3, and Qwen 2.5 — on curated cancer variant databases to assess their utility in clinical genomic interpretation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Information Management, Taipei Veterans General Hospital, Taipei, 11267, Taiwan, R.O.C.
- Department of Information Management, National Taipei University of Nursing and Health Sciences, Taipei, 11219, Taiwan, R.O.C.
- Department of Pathology and Laboratory Medicine, Taipei Veterans General Hospital, Taipei, 11267, Taiwan, R.O.C.
- School of Medicine, National Yang Ming Chiao Tung University, 112304, Taipei, Taiwan, R.O.C.
Zitieren
APA
Lin, K. H., Chen, P. C., Kuo, C. T., Chu, Y. C., & Yeh, Y. C. (2025). Leveraging Large Language Models for Cancer Variant Classification: A Comparative Study of GPT-4o, LLaMA 3, and Qwen 2.5. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti251185
Vancouver
Lin KH, Chen PC, Kuo CT, Chu YC, Yeh YC. Leveraging Large Language Models for Cancer Variant Classification: A Comparative Study of GPT-4o, LLaMA 3, and Qwen 2.5. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti251185
BibTeX
@article{Lin2025,
author = {Lin, Kuan-Hsun and Chen, Paul Chih-Hsueh and Kuo, Chen-Tsung and Chu, Yuan-Chia and Yeh, Yi-Chen},
title = {Leveraging Large Language Models for Cancer Variant Classification: A Comparative Study of GPT-4o, LLaMA 3, and Qwen 2.5},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti251185}
}
EUVIMED