European guideline informed RAG-based GPT-4 decision support tool in tumor board meetings for breast cancer treatment
European Journal of Surgical Oncology · 2025-11 · 51 (11) · 110384
DOI: 10.1016/j.ejso.2025.110384 ↗Kurz gefasst
Leitlinie in der Zeitschrift European Journal of Surgical Oncology, 2025-11. Verfasst von Nuran Abdullayev und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology and Neuroradiology, GFO Clinics Troisdorf, Academic Hospital of the Friedrich-Wilhelms-University Bonn, 53840, Troisdorf, Ger…. Hauptthemen laut MEDLINE: Breast Neoplasms, Practice Guidelines as Topic, Decision Support Techniques, Clinical Decision-Making. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Breast cancer is the most common cancer among women worldwide. Treatment decision-making in multidisciplinary tumor boards is complex, involving integration of clinical guidelines, patient data, and preferences. We retrospectively evaluated MammaBoardGPT, an few-shot in-context learning and Retrieval Augmented Generation (RAG) enhanced GPT-4 model with European guidelines and five Tumor Board labeled cases, against standard GPT-4 in 25 breast cancer cases discussed at a German hospital. After recursive prompting, MammaBoardGPT achieved complete agreement with tumor board decisions in 84 % of cases, partial agreement in 16 % and no disagreements; standard GPT-4 showed 76 % complete agreement, 20 % partial agreement, and 4 % complete disagreements. A significant difference was observed in MammaBoardGPT's (Stuart-Maxwell P = 0.0048) but not for GPT-4 agreement with tumor board decisions before versus after recursive prompting (Stuart-Maxwell P = 0.135), neither for MammaBoardGPT and GPT-4 in their tumor board decision agreement post-recursive prompting (Stuart-Maxwell P = 0.37). These findings support MammaBoardGPT's potential for tumor board decision support, warranting prospective validation and real-time assessment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Radiology and Neuroradiology, GFO Clinics Troisdorf, Academic Hospital of the Friedrich-Wilhelms-University Bonn, 53840, Troisdorf, Germany; Institute for Biomedical Engineering, Azerbaijan Technical Unive…
- Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, 50937, Cologne, Germany.
- Department of Radiology and Neuroradiology, GFO Clinics Troisdorf, Academic Hospital of the Friedrich-Wilhelms-University Bonn, 53840, Troisdorf, Germany.
- Department of Anesthesiology, Palliative Care, Intensive Care, and Pain Medicine, Paracelsus Klinik Golzheim, 40474, Düsseldorf, Germany.
- Faculty of Medicine, University of Cologne, 50391, Cologne, Germany.
- Institute for Biomedical Engineering, Azerbaijan Technical University, AZ1073, Baku, Azerbaijan.
Zitieren
APA
Abdullayev, N., Kottlors, J., Habibov, H., Yilmaz, F., Zimmer, C., Hokamp, N. G., Lennartz, S., Valiyev, V., Abbasli, C., Goertz, L., Borggrefe, J., Maintz, D., Ersahin, K., & Sanduleanu, S. (2025). European guideline informed RAG-based GPT-4 decision support tool in tumor board meetings for breast cancer treatment. European Journal of Surgical Oncology, 51(11), 110384. https://doi.org/10.1016/j.ejso.2025.110384
Vancouver
Abdullayev N, Kottlors J, Habibov H, Yilmaz F, Zimmer C, Hokamp NG, et al. European guideline informed RAG-based GPT-4 decision support tool in tumor board meetings for breast cancer treatment. European Journal of Surgical Oncology. 2025;51(11):110384. doi:10.1016/j.ejso.2025.110384
BibTeX
@article{Abdullayev2025,
author = {Abdullayev, Nuran and Kottlors, Jonathan and Habibov, Hikmat and Yilmaz, Fahrettin and Zimmer, Chantal and Hokamp, Nils Große and Lennartz, Simon and Valiyev, Vilayat and Abbasli, Cavid and Goertz, Lukas and Borggrefe, Jan and Maintz, David and Ersahin, Koray and Sanduleanu, Sebastian},
title = {European guideline informed RAG-based GPT-4 decision support tool in tumor board meetings for breast cancer treatment},
journal = {European Journal of Surgical Oncology},
year = {2025},
volume = {51},
number = {11},
pages = {110384},
doi = {10.1016/j.ejso.2025.110384}
}
EUVIMED