EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access

Performance Evaluation and Implications of Large Language Models in Radiology Board Exams: Prospective Comparative Analysis

Boxiong Wei iD

JMIR Medical Education · 2025

DOI: 10.2196/64284 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift JMIR Medical Education, 2025. Verfasst von Boxiong Wei. Beteiligte Einrichtung: Department of Ultrasound, Peking University First Hospital, 8 Xishiku Rd, Xicheng District, Beijing, 100034, China, 86 13132150190, 86 314521. Hauptthemen laut MEDLINE: Radiology, Educational Measurement, Artificial Intelligence. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Artificial intelligence advancements have enabled large language models to significantly impact radiology education and diagnostic accuracy.

Objective

This study evaluates the performance of mainstream large language models, including GPT-4, Claude, Bard, Tongyi Qianwen, and Gemini Pro, in radiology board exams.

Methods

A comparative analysis of 150 multiple-choice questions from radiology board exams without images was conducted. Models were assessed on their accuracy for text-based questions and were categorized by cognitive levels and medical specialties using χ 2 tests and ANOVA.

Results

GPT-4 achieved the highest accuracy (83.3%, 125/150), significantly outperforming all other models. Specifically, Claude achieved an accuracy of 62% (93/150; P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadiologyEducational MeasurementArtificial IntelligenceHumansProspective StudiesClinical CompetenceLarge Language Models

Stichwörter der Autor:innen

AIGPT-4LLMartificial intelligencediagnosticslarge language modelsmedical educationmedical trainingradiologyradiology examsultrasound

Autor:innen und Institutionen

  • Department of Ultrasound, Peking University First Hospital, 8 Xishiku Rd, Xicheng District, Beijing, 100034, China, 86 13132150190, 86 314521.

ORCID-Profile: Boxiong Wei

Zitieren

APA

Wei, B. (2025). Performance Evaluation and Implications of Large Language Models in Radiology Board Exams: Prospective Comparative Analysis. JMIR Medical Education. https://doi.org/10.2196/64284

Vancouver

Wei B. Performance Evaluation and Implications of Large Language Models in Radiology Board Exams: Prospective Comparative Analysis. JMIR Medical Education. 2025. doi:10.2196/64284

BibTeX
@article{Wei2025,
  author = {Wei, Boxiong},
  title = {Performance Evaluation and Implications of Large Language Models in Radiology Board Exams: Prospective Comparative Analysis},
  journal = {JMIR Medical Education},
  year = {2025},
  doi = {10.2196/64284}
}
Kostenlos starten →