The Potential of Large Language Models in Gynecologic Oncology Telephone Triage
Diagnostics · 06.11.2026 · 16 (21) · 3668
DOI: 10.3390/diagnostics16213668 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 06.11.2026. Verfasst von Iason Psilopatis und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gynecology and Obstetrics, University Hospital Basel, University of Basel, 4031 Basel, Switzerland. Die Arbeit nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Nurse-led telephone triage, frequently guided by the United Kingdom Oncology Nursing Society (UKONS) tool, is a cornerstone of supportive oncology care, yet the appropriateness of triage decisions varies across settings. Large Language Models (LLMs) show promise in medical communication but remain unvalidated for autonomous clinical decision-making, particularly in gynecologic oncology, where remote and telephone-based care pose distinct challenges. Methods and Materials: Twenty fictitious case vignettes representing common treatment-related toxicities in gynecologic oncology were developed. Three board-certified gynecologic consultants independently assigned UKONS Red–Amber–Green (RAG) triage categories, reaching unanimous consensus that served as the reference standard. Vignettes were submitted verbatim, as single-turn queries with no follow-up prompting, to three publicly available LLMs (OpenEvidence, ChatGPT, Google Gemini). LLM responses were mapped to RAG categories and compared descriptively against the reference standard, stratified by treatment type and platform.
Results
All three LLMs achieved 100% concordance with the reference standard for all Red cases across both treatment groups, with no high-acuity case downgraded to self-care. Discrepancies clustered at lower-acuity boundaries. In the chemotherapy-alone group, errors were limited to omission of an explicit 24-h follow-up window for 1 Amber-rated complaints. In the combined group, all LLMs over-triaged intermediate-risk complaints toward immediate or same-day evaluation; low-risk complaints showed more variable over-triage.
Conclusions
LLMs identified unambiguous emergent gynecologic oncology symptoms, preserving the UKONS safety floor, but showed relatively reduced precision and a conservative over-triage bias at lower-acuity margins, especially in the combined-therapy collective. These findings support a supervised, adjunctive role for LLMs, rather than autonomous deployment, pending prospective validation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Gynecology and Obstetrics, University Hospital Basel, University of Basel, 4031 Basel, Switzerland.
- Department of Gynecology and Obstetrics, Universitätsklinikum Erlangen, Comprehensive Cancer Center Erlangen-EMN (CCC ER-EMN), Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91054 Erlangen, Germany.
- Dipartimento di Scienze per la salute della Donna e del Bambino e di Sanità Pubblica, UOC Ginecologia Oncologica, Fondazione Policlinico Universitario A. Gemelli, IRCCS, Largo Agostino Gemelli 8, 00168 Rome, Italy.
- Department of Biomedicine, University Hospital and University of Basel, 4031 Basel, Switzerland.
ORCID-Profile: Iason Psilopatis
Zitieren
APA
Psilopatis, I., Emons, J., Pavone, M., & Zwimpfer, T. A. (2026). The Potential of Large Language Models in Gynecologic Oncology Telephone Triage. Diagnostics, 16(21), 3668. https://doi.org/10.3390/diagnostics16213668
Vancouver
Psilopatis I, Emons J, Pavone M, Zwimpfer TA. The Potential of Large Language Models in Gynecologic Oncology Telephone Triage. Diagnostics. 2026;16(21):3668. doi:10.3390/diagnostics16213668
BibTeX
@article{Psilopatis2026,
author = {Psilopatis, Iason and Emons, Julius and Pavone, Matteo and Zwimpfer, Tibor A},
title = {The Potential of Large Language Models in Gynecologic Oncology Telephone Triage},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {21},
pages = {3668},
doi = {10.3390/diagnostics16213668}
}
EUVIMED