How Do Multimodal Large Language Models Perform on Clinical Vignette Questions?

How did GPT-4 Vision, a model that can work with images and text as input, perform when answering clinical challenge questions from medical journals? Daniel Truhn, MD, MSc, of the University Hospital Aachen in Germany, joins JAMA Editor in Chief Kirsten Bibbins-Domingo, PhD, MD, MAS, to discuss this topic. Related Content: Comparative Analysis of Multimodal Large Language Model Performance on Clinical Vignette Questions