Events Calendar

PhD Defense - Zhengping Che

Title: Deep Learning Models for Temporal Data in Health Care
Date, Time, and Location: Friday, August 31, 2018, at 2:30 PM in SAL 322

Ph.D. Candidate: Zhengping Che

Committee:
Professor Yan Liu (chair)
Professor Kevin Knight
Professor Shinyi Wu (outside member)

Abstract:
The national push for electronic health records has resulted in an exponential surge in volume, detail, and availability of digital health data which offers an unprecedented opportunity to solve many difficult and important problems in health care. Clinicians are collaborating with computer scientists by using this opportunity to improve the state of data-driven and personalized health care services. Meanwhile, recent success and development of deep learning is revolutionizing many domains and provides promising solutions to the problem of prediction and feature discovery on health care data, which have made us closest ever towards the ultimate goal of improving health quality, reducing cost, and most importantly saving lives. However, the recent rise of this research field with more available data and new applications has also introduced several challenges which have not been answered well. Our work focuses on providing deep learning-based solutions to three major challenges in this field from data heterogeneity, data availability, and the difficulty of applying deep learning in healthcare applications in practice. In this talk, we will first introduce a hierarchical deep generative model for multi-rate multivariate time series which can capture multi-scale temporal dependencies and complex underlying generation mechanism of temporal healthcare data. Then we will introduce a semi-supervised learning framework with modified generative adversarial networks to boost prediction performance with a limited amount of labeled data. Finally, we will describe our deep learning solutions to opioid usage and addiction study on a large-scale dataset and demonstrate how deep learning can be applied to important and urgent healthcare tasks in the real world.

Location: Henry Salvatori Computer Science Center (SAL) - 322

Audiences: Everyone Is Invited

Contact: Lizsl De Leon