Evaluation of GPT-4's Chest X-Ray Impression Generation: A Reader Study on Performance and Perception

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.

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of medical Internet research 2023-12, Vol.25 (5), p.e50865-e50865
Hauptverfasser: Ziegelmayer, Sebastian, Marka, Alexander W, Lenhart, Nicolas, Nehls, Nadja, Reischl, Stefan, Harder, Felix, Sauter, Andreas, Makowski, Marcus, Graf, Markus, Gawlitza, Joshua
Format: Artikel
Sprache:eng
Schlagworte:
Artificial intelligence
Automation
Bilingualism
Datasets
Heuristic
Language
Machine learning
Medical imaging
Medical imaging equipment
Multimedia
Natural language
Preprints
Radiology
X-rays
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
ISSN:1438-8871
1439-4456
1438-8871
DOI:10.2196/50865