• Home
  • Introduction
  • Faculty Directory
  • Seminar
  • Contact Us
  • Peking University
  • Belt & Road Institute
  • 中文
  • Seminar

    speaker Bin Zhang, Eller College of Management, University of Arizona time Thursday, June 28th, 10:00--11:30
    place Room 217, Guanghua Building 2

    Management Science and Information Systems' Seminar2018-04

    Topic:Hospital Readmission Prediction UsingTrajectory-Based Deep Learning Approach

    Speaker:Bin Zhang, Eller College of Management, University of Arizona

    Time:Thursday, June 28th, 10:00--11:30

    Place:Room 217, Guanghua Building 2


    Hospital readmission refers to the situation where a patient is re-hospitalized with the same primary diagnosis within a specific time interval after discharge. Hospital readmission causes $26 billion of preventable expenses to the U.S. health systems annually and often indicates suboptimal patient care. To alleviate those severe financial and health consequences, it is crucial to proactively predict patients’ readmission risk. Such prediction is challenging because the evolution of medical events (illness trajectory) is dynamic and complex. The state-of-the-art studies apply statistical models which assume homogeneity among all patients and use static predictors in a period, failing to consider patients’ heterogeneous illness trajectories. Our approach – TADEL (Trajectory-bAsed DEep Learning) – is motivated to tackle the problems with the existing approaches by capturing various illness trajectories and accounting for patient heterogeneity. We evaluated TADEL on a five-year national Medicare claims dataset including 3.6 million patients per year over all hospitals in the United States, reaching an F1 score of 0.867 and an AUC of 0.884. Our approach significantly outperforms all the state-of-the-art methods. Our findings suggest that health status factors and insurance coverage are important predictors for readmission. This study contributes to IS literature and analytical methodology by formulating the trajectory-based readmission prediction problem and developing a novel deep-learning-based readmission risk prediction framework. From a health IT perspective, this research delivers implementable methods to assess patients’readmission risk and take early interventions to avoid potential negative consequences.


    Bin Zhang is an assistant professor in the Department of Management Information Systems, University of Arizona, and a visiting research fellow at Carnegie Mellon University. He is also an affiliated member of Artificial Intelligence Lab, University of Arizona. Bin received his Ph.D. degree in Information Systems Management from Carnegie Mellon University, and a Master's degree in Machine Learning, from the School of Computer Science at CMU. His primary research interests are large social network analysis and machine learning. Bin's research projects have been funded by federal and national agencies such as NSF and NSFC. His work has appeared in premier journals such as Information Systems Research. Bin also serves as review panelist of NSF and associate editor of Electronic Commerce Research. Before joining academia, Dr. Zhang worked in the Internet industry at companies like Yahoo! and has designed architectures of online ERP systems in the software industry.

    Your participation is warmly welcomed!

    © 2019 Guanghua School of Management Peking University