Evaluating GPT-4 with Vision on Detection of Radiological Findings on Chest Radiographs
Yiliang Zhou, Hanley Ong, Patrick Kennedy, Carol Wu, Jacob Kazam, Keith Hentel, Adam Flanders, George Shih, Yifan Peng
arXiv:2403.15528v31 citationsh-index: 7
Originality Synthesis-oriented
AI Analysis
This addresses the problem of AI reliability in medical imaging for clinicians and patients, showing incremental testing of an existing model.
The study evaluated GPT-4V's ability to detect radiological findings on 100 chest radiographs and found it is not ready for real-world diagnostic use.
The study examines the application of GPT-4V, a multi-modal large language model equipped with visual recognition, in detecting radiological findings from a set of 100 chest radiographs and suggests that GPT-4V is currently not ready for real-world diagnostic usage in interpreting chest radiographs.