Put AI to Work
April 15-18, 2019
New York, NY
Please log in

How deep learning can improve medical outcomes now

Eric Oermann (Mount Sinai Health System), Katie Link (Allen Institute for Brain Science)
1:50pm2:30pm Thursday, April 18, 2019
AI Business Summit, Case Studies
Location: Sutton North/Center
Secondary topics:  AI case studies, Computer Vision, Health and Medicine
Average rating: *****
(5.00, 1 rating)

Who is this presentation for?

  • Program managers, academics, clinical informatics professionals

Level

Intermediate

Prerequisite knowledge

  • Basic knowledge of machine learning (bias-variance trade-off, statistical distributions, etc.)

What you'll learn

  • Learn how to identify feasible clinical problems and avoid common pitfalls in developing production-ready solutions

Description

There’s significant interest in applying deep learning-based solutions to problems in medicine and healthcare. Eric Oermann and Katie Link identify actionable medical problems, recast them as tractable deep learning problems, and discuss techniques to solve them. Particularly, they focus on computer vision techniques and their application to problems in radiological computer-assisted diagnosis and clinical decision support in the intensive care unit. Along the way, Eric and Katie explore the unique nature of medical data and how it is sampled (nonrandomly) as well as techniques for accelerating the training and generalization of models in a medical work environment.

Photo of Eric Oermann

Eric Oermann

Mount Sinai Health System

Eric Karl Oermann is an instructor of neurological surgery in the Mount Sinai Health System and the director of AISINAI, Mount Sinai’s artificial intelligence research group. Prior to attending medical school, Eric spent six months with the President’s Council on Bioethics studying human dignity under the mentorship of physician-philosopher Edmund Pellegrino. He has won numerous awards for his scholarship, including fellowships from the American Brain Tumor Association and Doris Duke Charitable Research Foundation, where he was first exposed to neural networks and deep learning. He has published over 50 manuscripts spanning basic research on machine learning, tumor genetics, and the philosophy of medicine. As a PGY-2, he was selected as one of Forbes’s “30 under 30” for his work in applying machine learning to develop prognostic models for cancer patients. He’s interested in weakly supervised learning, reinforcement learning with imperfect information and in building artificial neural networks that more accurately model biological neural networks. As an actively practicing neurosurgeon, he is also interested in the application of deep learning to solve a wide range of problems in the medical sciences and improving clinical care. He holds an MD and studied mathematics at Georgetown University with a focus on differential geometry; he completed a postdoctoral fellowship at Google (Google Health/Verily Life Sciences).

Photo of Katie Link

Katie Link

Allen Institute for Brain Science

Katie Link is a data analyst at the Allen Institute for Brain Science, where she is working on building deep learning tools to solve practical problems in neuroscience research. A member of the Mount Sinai Health System AI Consortium (AISINAI), she is passionate about applying her skills in machine learning to solving problems in healthcare, and her research has focused on developing a novel semisupervised learning approach for accelerating the training of deep convolutional neural networks. She is a graduate of Johns Hopkins University (Phi Beta Kappa) with degrees in neuroscience and computer science and a FlexMed member of the Icahn School of Medicine’s class of 2023.