A Stress Test of Artificial Intelligence: Can Deep Learning Models Trained From Formal Echocardiography Accurately Interpret Point-of-Care Ultrasound?

Journal: Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine

PMID: 35560254

Abstract

OBJECTIVES: To test if a deep learning (DL) model trained on echocardiography images could accurately segment the left ventricle (LV) and predict ejection fraction on apical 4-chamber images acquired by point-of-care ultrasound (POCUS).

Authors

David Crockett

Department of Emergency Medicine, University of Utah, Salt Lake City, UT, USA.
Christopher Kelly

Google Health, London, UK.
James Brundage

School of Medicine, University of Utah, SLC, UT, USA.
Jamal Jones

Department of Emergency Medicine, University of Utah, Salt Lake City, UT, USA.
Patrick Ockerse

Department of Emergency Medicine, University of Utah, Salt Lake City, UT, USA.

Keywords

Artificial Intelligence Deep Learning Echocardiography Exercise Test Heart Failure Humans Point-of-Care Systems

External Resources

View on PubMed Access via DOI PubMed (35560254)

A Stress Test of Artificial Intelligence: Can Deep Learning Models Trained From Formal Echocardiography Accurately Interpret Point-of-Care Ultrasound?

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals