ML4H: Pierre Elias: Developing, Validating & Deploying an AI Model to Exceed My Clinical Expertise

Описание: In this video, Pierre Elias (Columbia) presents 'Developing, Validating, and Deploying an AI Model that Exceeds My Clinical Expertise'.

Presentation Date: 03/06/24

Abstract: In this talk we will discuss why and how deep learning approaches have the potential to greatly impact cardiac imaging. We will then explore use cases developed here at Columbia that have led to two of the world’s first prospective clinical trials of deep learning in cardiology. We will dive into some of the limitations of the technologies, open questions in the field, and future directions for AI in medicine.

Bio: Pierre Elias is an Assistant Professor in the Division of Cardiology and the Department of Biomedical Informatics at Columbia University Irving Medical Center, where he practices as a general cardiologist. He is also the Medical Director for Artificial Intelligence at NewYork-Presbyterian. His research lab develops machine learning technologies for medical imaging to improve the detection and management of cardiovascular disease. Dr. Elias received his medical degree at Duke University School of Medicine in North Carolina. He completed his residency in Internal Medicine and fellowship in Cardiovascular Disease at NewYork-Presbyterian/Columbia University Irving Medical Center through the Clinician-Scientist Pathway. He completed his postdoc under Dr. Adler Perotte in the Department of Biomedical Informatics. He has been named a STAT News Wunderkind highlighting 20 of the most innovative junior researchers in the country and has received the Emerging Generation Award from the American Society of Clinical Investigation. He was previously a data scientist at Lumiata, helping develop Google’s Knowledge Graph for Health.

For more information, visit: https://www.broadinstitute.org/ml4h

Copyright Broad Institute, 2025. All rights reserved.