Augmenting Large Language Models With National Comprehensive Cancer Network Guidelines for Improved and Standardized Adjuvant Therapy Recommendations in Postoperative Breast Cancer Cases
JCO Clinical Cancer Informatics · 2025-11 · (9)
DOI: 10.1200/cci-24-00243 ↗Kurz gefasst
Leitlinie in der Zeitschrift JCO Clinical Cancer Informatics, 2025-11. Verfasst von Serene Si Ning Goh und 12 weiteren Autor:innen. Beteiligte Einrichtung: National University of Singapore and National University Health System, Saw Swee Hock School of Public Health, Singapore, Singapore. Hauptthemen laut MEDLINE: Breast Neoplasms, Practice Guidelines as Topic, Artificial Intelligence. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
PURPOSE Multidisciplinary breast tumor boards (MTBs) are essential for optimizing breast cancer treatment but face challenges related to logistics, variability in expertise, and lack of standardization. Large language models may support clinical decision making. This study evaluates the accuracy of adjuvant therapy recommendations generated by an artificial intelligence (AI)–driven tool, TheSerenityBot (TSB), in comparison with Claude-2 and GPT-4, using expert MTB consensus as the reference. METHODS Postoperative breast cancer cases reviewed at the National University Hospital, Singapore, between June and November 2023 were retrospectively analyzed. Eligible patients were women with invasive or preinvasive breast cancer who underwent surgery. Metastatic cases were excluded. TSB, a Claude-2–based model augmented with 2023 National Comprehensive Cancer Network guidelines, generated adjuvant therapy recommendations across seven treatment modalities. Outputs from TSB, Claude-2, and GPT-4 were evaluated for concordance with MTB recommendations. Model performance was assessed using generalized estimating equations. RESULTS Fifty patients were included (mean age, 59.8 years); 75.5% had hormone receptor–positive tumors, and 60.0% underwent breast-conserving surgery. TSB demonstrated the highest overall accuracy (0.89), followed by Claude-2 (0.86) and GPT-4 (0.78). GPT-4 showed significantly lower accuracy in genetic testing recommendations (odds ratio [OR], 0.05 [95% CI, 0.015 to 0.149]; P < .001), whereas Claude-2 was less accurate in radiotherapy recommendations (OR, 0.41 [95% CI, 0.17 to 0.98]; P = .040). CONCLUSION A guideline-augmented AI tool such as TSB shows promise in supporting adjuvant therapy decisions in breast cancer. To improve clinical relevance, future iterations will incorporate individualized patient factors, broader guideline frameworks, and electronic health record integration. Prospective trials are ongoing to assess the real-world impact.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- National University of Singapore and National University Health System, Saw Swee Hock School of Public Health, Singapore, Singapore.
- Department of Surgery, National University Hospital and National University Health System, Singapore, Singapore.
- Division of Surgical Oncology, National University Cancer Institute, Singapore, Singapore.
- Department of Biomedical Informatics, Academic Informatics Office, National University Health System, Singapore, Singapore.
- Department of Hematology-Oncology, National University Cancer Institute, Singapore, Singapore.
- Department of Radiation Oncology, National University Cancer Institute, Singapore, Singapore.
ORCID-Profile: Serene Si Ning Goh, Ragunathan Mariappan, Jiali Yao, Fook Ming Hew, Samuel Guan Wei Ow, Wee Yao Koh, Nesaretnam Barr Kumarakulasingh, Kee Yuan Ngiam
Zitieren
APA
Goh, S. S. N., Mariappan, R., Soo Woon Tan, G., Yao, J., Hew, F. M., Yeo, Y., Guan Wei Ow, S., Koh, W. Y., Kumarakulasingh, N. B., Tan, T. H., Tai, B. C., Hartman, M., & Ngiam, K. Y. (2025). Augmenting Large Language Models With National Comprehensive Cancer Network Guidelines for Improved and Standardized Adjuvant Therapy Recommendations in Postoperative Breast Cancer Cases. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-24-00243
Vancouver
Goh SSN, Mariappan R, Soo Woon Tan G, Yao J, Hew FM, Yeo Y, et al. Augmenting Large Language Models With National Comprehensive Cancer Network Guidelines for Improved and Standardized Adjuvant Therapy Recommendations in Postoperative Breast Cancer Cases. JCO Clinical Cancer Informatics. 2025. doi:10.1200/cci-24-00243
BibTeX
@article{Goh2025,
author = {Goh, Serene Si Ning and Mariappan, Ragunathan and Soo Woon Tan, Grace and Yao, Jiali and Hew, Fook Ming and Yeo, Yenshing and Guan Wei Ow, Samuel and Koh, Wee Yao and Kumarakulasingh, Nesaretnam Barr and Tan, Teng Hwee and Tai, Bee Choo and Hartman, Mikael and Ngiam, Kee Yuan},
title = {Augmenting Large Language Models With National Comprehensive Cancer Network Guidelines for Improved and Standardized Adjuvant Therapy Recommendations in Postoperative Breast Cancer Cases},
journal = {JCO Clinical Cancer Informatics},
year = {2025},
number = {9},
doi = {10.1200/cci-24-00243}
}
EUVIMED