How Do Multimodal Large Language Models Perform on Clinical

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

Listen now

Description

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

More Episodes

See all »

Cardiac Amyloidosis and the V142I Transthyretin Variant

What is the natural history and cardiovascular burden of the V142I transthyretin variant among US Black individuals who carry this variant? Senthil Selvaraj, MD, MS, MA, from Duke University, and Scott D. Solomon, MD, from Brigham and Women’s Hospital, discuss this and more with JAMA Executive...

Published 05/12/24

JAMA Author Interviews

Published 05/12/24

Racial and Ethnic Disparities in All-Cause and Cause-Specific Mortality Among US Youth

Between 2019 and 2021, pediatric mortality rates had the largest increases in at least half a century. Steven H. Woolf, MD, MPH, of Virginia Commonwealth University Center on Society and Health, joins JAMA Associate Editor Tracy A. Lieu, MD, MPH, to discuss how racial and ethnic disparities and...

Published 05/04/24