About this item:

593 Views | 691 Downloads

Author Notes:

Address for correspondence: Li-wei Lehman, lilehman@mit.edu, Shamim Nemati, shamim.nemati@emory.edu.

Subjects:

Research Funding:

This work was supported by the National Institutes of Health (NIH) grant R01-EB001659 and R01GM104987 from the National Institute of Biomedical Imaging and Bioengineering (NIBIB), the James S. McDonnell Foundation Postdoctoral grant.

Keywords:

  • Science & Technology
  • Technology
  • Computer Science, Interdisciplinary Applications
  • Engineering, Multidisciplinary
  • Engineering, Biomedical
  • Computer Science
  • Engineering

Patient Prognosis from Vital Sign Time Series: Combining Convolutional Neural Networks with a Dynamical Systems Approach

Tools:

Proceedings Title:

Computing in Cardiology

Conference Name:

Computing in Cardiology Conference (CinC), 2015

Publisher:

Volume/Issue:

Volume 42

Publication Date:

Type of Work:

Conference | Post-print: After Peer Review

Abstract:

In this work, we propose a stacked switching vector-autoregressive (SVAR)-CNN architecture to model the changing dynamics in physiological time series for patient prognosis. The SVAR-layer extracts dynamical features (or modes) from the time-series, which are then fed into the CNN-layer to extract higher-level features representative of transition patterns among the dynamical modes. We evaluate our approach using 8-hours of minute-by-minute mean arterial blood pressure (BP) from over 450 patients in the MIMIC-II database. We modeled the time-series using a third-order SVAR process with 20 modes, resulting in first-level dynamical features of size 20×480 per patient. A fully connected CNN is then used to learn hierarchical features from these inputs, and to predict hospital mortality. The combined CNN/SVAR approach using BP time-series achieved a median and interquartile-range AUC of 0.74 [0.69, 0.75], significantly outperforming CNN-alone (0.54 [0.46, 0.59]), and SVAR-alone with logistic regression (0.69 [0.65, 0.72]). Our results indicate that including an SVAR layer improves the ability of CNNs to classify nonlinear and nonstationary time-series.

Copyright information:

© 2015, IEEE

Export to EndNote