Abstract
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.
Author supplied keywords
Cite
CITATION STYLE
APA
Ziegelmayer, S., Marka, A. W., Lenhart, N., Nehls, N., Reischl, S., Harder, F., … Gawlitza, J. (2023). Evaluation of GPT-4’s Chest X-Ray Impression Generation: A Reader Study on Performance and Perception. Journal of Medical Internet Research, 25(1). https://doi.org/10.2196/50865
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
Already have an account? Sign in
Sign up for free