DOCTOR AI: Interpretable Deep Learning Methods for modeling Electronic Health Records


June 11th

18:30 p.m. - 20:00 p.m.



Darkroom lecture hall,College of Design and Innovation,Tongji University281 Fuxin Road






Speaker:Jimeng Sun


 Abstract :

Deep neural networks provide great potential to create accurate predictive models for longitudinal electronic health records (EHRs). In this talk, we will present a series of case studies of deep learning for modeling EHR.

1) We illustrate how recurrent neural networks (RNN) can be used to model temporal relations among events in electronic health records (EHRs) to predict heart failures.

2) We introduce two interpretable models, CAML for predicting medical codes from clinical notes, and RETAIN for modeling longitudinal EHR data.

3) Finally, we present a collaboration with Vanderbilt, medical Generative Adversarial Network (medGAN), to generate realistic synthetic patient records.


 Biography :

Jimeng Sun is an Associate Professor of College of Computing at Georgia Tech. Prior to Georgia Tech, he was a researcher at IBM TJ Watson Research Center. His research focuses on health analytics and machine learning, especially in designing tensor factorizations, deep learning methods, and large-scale predictive modeling systems. He published over 120 papers and filed over 20 patents (5 granted). He has received SDM/IBM early career research award 2017, ICDM best research paper award in 2008, SDM best research paper award in 2007,and KDD Dissertation Runner-up Award in 2008.