%0 Journal Article
%@ 1438-8871
%I JMIR Publications
%V 25
%N 
%P e50865
%T Evaluation of GPT-4’s Chest X-Ray Impression Generation: A Reader Study on Performance and Perception
%A Ziegelmayer,Sebastian
%A Marka,Alexander W
%A Lenhart,Nicolas
%A Nehls,Nadja
%A Reischl,Stefan
%A Harder,Felix
%A Sauter,Andreas
%A Makowski,Marcus
%A Graf,Markus
%A Gawlitza,Joshua
%+ Department of Diagnostic and Interventional Radiology, School of Medicine & Klinikum rechts der Isar, Technical University of Munich, Ismaninger Straße 22, Munich, 81675, Germany, 49 1759153694, ga89rog@mytum.de
%K generative model
%K GPT
%K medical imaging
%K artificial intelligence
%K imaging
%K radiology
%K radiological
%K radiography
%K diagnostic
%K chest
%K x-ray
%K x-rays
%K generative
%K multimodal
%K impression
%K impressions
%K image
%K images
%K AI
%D 2023
%7 22.12.2023
%9 Research Letter
%J J Med Internet Res
%G English
%X Exploring the generative capabilities of the multimodal GPT-4, our study uncovered significant differences between radiological assessments and automatic evaluation metrics for chest x-ray impression generation and revealed radiological bias.
%M 38133918
%R 10.2196/50865
%U https://www.jmir.org/2023/1/e50865
%U https://doi.org/10.2196/50865
%U http://www.ncbi.nlm.nih.gov/pubmed/38133918