JAMA Author Interviews podcast

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

0:00
9:11
15 Sekunden vorwärts
15 Sekunden vorwärts

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:

Weitere Episoden von „JAMA Author Interviews“