Speaker: Yuzhe Yang UCLA
Time: 2025-02-21 15:00-2025-02-21 16:00
Venue: Seminar Room 2, 19th Floor, Tower C, TusPark

Abstract:

Today's clinical systems frequently exhibit delayed diagnoses, sporadic patient visits, and unequal access to care. Can we identify chronic diseases earlier, potentially before they manifest clinically? Furthermore, can we bring comprehensive medical assessments into patient's own homes to ensure accessible care for all? In this talk, I will present machine learning approaches to bridge the persistent gaps in healthcare discovery, delivery, and equity. I will first introduce an AI-powered digital biomarker that detects Parkinson's disease multiple years before clinical diagnosis, using just nocturnal breathing signals. I will then introduce self-supervised learning methods for contactless measurements of human vital signs from daily mobile devices. Finally, I will discuss how we build large-scale wearable foundation models that interact with millions of hours of multimodal sensor data and its scaling laws.

Short Bio:

Yuzhe Yang is an Assistant Professor of Computational Medicine and Computer Science at UCLA (start 2025) and a visiting research scientist at Google Health. He completed his Ph.D. in Computer Science at MIT, advised by Dina Katabi. Before MIT, he received my B.S. with honors from Peking University. Yuzhe develops machine learning methods to solve important problems in healthcare and medicine (Please see his research lab for details). His work has been recognized by Ten Notable Advances in 2022 by Nature Medicine, Takeda PhD Fellowship, Baidu PhD Fellowship, MathWorks PhD Fellowship, Rising Stars in AI (Yunfan Award), Rising Stars in Data Science, and Forbes 30 Under 30 in Healthcare & Science.