Academic Activities

Image

TBSI Greater Bay Area Intellectual Forum Lecture 53丨Research Seminar【Nanshan i-Park】

  1. 报告主题:Seeking Sophisticated but Interpretable Machine Learning Models for Healthcare Applications
  2. 报告人:Professor Jimeng Sun
  3. 主持:Professor Lin Zhang
  4. 附件:Prof. Sun Jimeng Seeking Sophisticated but Interpretable Machine Learning Models for Healthcare Applications

Notice: This lecture is a research seminar for credit.

Time

————————————

September 26th, Wednesday, 2018  2:30-4:00 p.m.


Abstract

————————————

People often talk about trade-off between model accuracy and interpretability. However, in healthcare, we need both. In this talk, I will present two examples of sophisticated models that can be accurate yet interpretable.

1)    Intensive Care Unit (ICU) outcome prediction: Integration of high-density ICU monitoring data with the discrete clinical events (including diagnosis, medications, labs) is challenging but potentially rewarding since richness and granularity in such multimodal data increase the possibilities for accurate detection of complex problems and predicting outcomes (e.g., length of stay and mortality). We propose Recurrent Attentive and Intensive Model (RAIM) for jointly analyzing continuous monitoring data and discrete clinical events. RAIM introduces an efficient attention mechanism for continuous monitoring data (e.g., ECG), which is guided by discrete clinical events (e.g, medication usage).

2)    Heart Failure Phenotyping:  Understanding subtypes of heart failure patients is extremely hard but important. We propose an integer tensor factorization method SUSTain to model electronic health records. EHR data are commonly represented by integers (e.g., the values correspond to event counts or ordinal measures). The conventional approach is to treat integer data as real, and then apply real-valued factorizations. However, doing so fails to preserve important characteristics of the original data, thereby making it hard to interpret the results. In our preliminary study, 87% of the resulting phenotypes were clinically meaningful.

References:

1.RAIM: Recurrent Attentive and Intensive Modeling of Multimodal Continuous Patient Monitoring Data, KDD’18

2.SUSTain: Scalable Unsupervised Scoring for Tensors and its Application to Phenotyping, KDD’18



Speaker's Bio

————————————

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 data mining, especially in designing tensor factorizations, deep learning methods, and large-scale predictive modeling systems. Dr. Sun has been collaborating with many healthcare organizations.

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. Dr. Sun received B.S. and M.Phil. in Computer Science from Hong Kong University of Science and Technology in 2002 and 2003, PhD in Computer Science from Carnegie Mellon University in 2007 advised by Christos Faloutsos.



Registration

————————————

Professors and students of TBSI are welcome to attend. The lecture is also open to the public. For off-campus personnel, please scan the QR code and and fill in your information (name, company, contact number, ID number). The language of the lecture is English.