Large Language Model Superiority in Guideline-Based Neurointerventional Multiple-Choice Questions: Performance Analysis of Radiologists vs LLMs Across Experience Levels
The European Research Journal · 01.11.2026 · 1263-1269
DOI: 10.18621/eurj.1236 ↗Kurz gefasst
Leitlinie in der Zeitschrift The European Research Journal, online erschienen am 01.11.2026. Verfasst von Turay Cesur und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Objective
To assess large language models’ (LLMs) mastery of contemporary consensus documents in guideline-based neurointerventional decision-making domains and to compare their performance with radiologists of different experience levels.
Methods
In this cross-sectional study, 100 single-best-answer, 5-option MCQs were derived from 3 CIRSE guideline sources. A nonparticipating general radiologist authored the items (33 carotid stenting, 33 thrombectomy, 34 acute stroke EVT). One neurointerventional radiologist, 2 general radiologists, and 1 assistant radiologist answered independently, blinded to the key. The same set was posed in January 2026 to Claude 4.5 Opus, ChatGPT 5.2 Instant, and Gemini 3 Pro using default settings and a standardized prompt. Accuracy was compared with McNemar test and Bonferroni correction (P ≤ .002).
Results
The highest accuracy was observed with Claude 4.5 Opus (mean [SD], .99 [.10]); ChatGPT 5.2 Instant (.96 [.19]) and Gemini 3 Pro (.95 [.21]) showed comparable performance. Among human participants, the neurointerventional radiologist achieved the highest accuracy (.85 [.35]), while general radiologists scored .67 to .70 and the assistant radiologist achieved .57. Each of the 3 LLMs significantly outperformed all human groups. Moreover, Claude 4.5 Opus also demonstrated significantly higher performance than the neurointerventional radiologist (P = .001).
Conclusions
LLMs have reached a competitive level with neurointerventional radiologists in recalling and interpreting neurointerventional guideline knowledge. In particular, Claude 4.5 Opus demonstrated strong performance and appears to be a promising candidate for real-time decision support applications. Multimodal validation and verification studies using real clinical scenario–based designs are warranted.
Zitieren
APA
Cesur, T., Köseer, B. O., Güneş, Y. C., Çamur, E., & Karataş, G. (2026). Large Language Model Superiority in Guideline-Based Neurointerventional Multiple-Choice Questions: Performance Analysis of Radiologists vs LLMs Across Experience Levels. The European Research Journal, 1263-1269. https://doi.org/10.18621/eurj.1236
Vancouver
Cesur T, Köseer BO, Güneş YC, Çamur E, Karataş G. Large Language Model Superiority in Guideline-Based Neurointerventional Multiple-Choice Questions: Performance Analysis of Radiologists vs LLMs Across Experience Levels. The European Research Journal. 2026:1263-1269. doi:10.18621/eurj.1236
BibTeX
@article{Cesur2026,
author = {Cesur, Turay and Köseer, Burcu Orug and Güneş, Yasin Celal and Çamur, Eren and Karataş, Gökhan},
title = {Large Language Model Superiority in Guideline-Based Neurointerventional Multiple-Choice Questions: Performance Analysis of Radiologists vs LLMs Across Experience Levels},
journal = {The European Research Journal},
year = {2026},
pages = {1263--1269},
doi = {10.18621/eurj.1236}
}
EUVIMED