Readmission Prediction for Patients with Heterogeneous Hazard: A Trajectory-Based Deep Learning Approach

41 Pages Posted: 24 Mar 2018

See all articles by Jiaheng Xie

Jiaheng Xie

University of Arizona - Department of Management Information Systems

Bin Zhang

University of Arizona - Eller College of Management

Jian Ma

University of Colorado, Colorado Springs - Department of Information Systems

Daniel Dajun Zeng

University of Arizona - Department of Management Information Systems

Jenny Lo Ciganic

University of Arizona

Date Written: March 20, 2018

Abstract

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 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.

Keywords: Hospital readmission, predictive analytics, deep learning, design science, trajectory theory

Suggested Citation

Xie, Jiaheng and Zhang, Bin and Ma, Jian and Zeng, Daniel Dajun and Lo Ciganic, Jenny, Readmission Prediction for Patients with Heterogeneous Hazard: A Trajectory-Based Deep Learning Approach (March 20, 2018). Available at SSRN: https://ssrn.com/abstract=3144798 or http://dx.doi.org/10.2139/ssrn.3144798

Jiaheng Xie (Contact Author)

University of Arizona - Department of Management Information Systems ( email )

AZ
United States

Bin Zhang

University of Arizona - Eller College of Management ( email )

1130 E. Helen St
RM430Z
Tucson, AZ 85721
United States
(520) 626-9239 (Phone)

Jian Ma

University of Colorado, Colorado Springs - Department of Information Systems

CO
United States

Daniel Dajun Zeng

University of Arizona - Department of Management Information Systems ( email )

AZ
United States

Jenny Lo Ciganic

University of Arizona ( email )

Department of History
Tucson, AZ 85721
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
145
rank
190,785
Abstract Views
504
PlumX Metrics