Evaluation of GPT-4's Chest X-Ray Impression Generation: A Reader Study on Performance and Perception
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.
Saved in:
Main Authors: | Sebastian Ziegelmayer (Author), Alexander W Marka (Author), Nicolas Lenhart (Author), Nadja Nehls (Author), Stefan Reischl (Author), Felix Harder (Author), Andreas Sauter (Author), Marcus Makowski (Author), Markus Graf (Author), Joshua Gawlitza (Author) |
---|---|
Format: | Book |
Published: |
JMIR Publications,
2023-12-01T00:00:00Z.
|
Subjects: | |
Online Access: | Connect to this object online. |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
OSCE: Learning chest X-ray
by: Kundan Mittal, et al.
Published: (2019) -
Chest X-ray-confirmed pneumonia in children in Fiji
by: H.C. Magree, et al.
Published: (2005) -
Chest X-ray Findings in Community-acquired Pneumonia
by: Marwan Majeed Ibrahim
Published: (2024) -
The story of a "horrible looking chest X-ray"
by: Raghavendra Bhat
Published: (2020) -
Comparing the Results of Chest X-ray with Chest Ultrasound in Neonates Admitted in Neonatal Intensive Care Unit
by: Elham Zarei, et al.
Published: (2018)