Learning outcome-discriminative dynamics in multivariate physiological cohort time series

Shamim Nemati, Li Wei H. Lehman, Ryan P. Adams

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Model identification for physiological systems is complicated by changes between operating regimes and measurement artifacts. We present a solution to these problems by assuming that a cohort of physiological time series is generated by switching among a finite collection of physiologically-constrained dynamical models and artifactual segments. We model the resulting time series using the switching linear dynamical systems (SLDS) framework, and present a novel learning algorithm for the class of SLDS, with the objective of identifying time series dynamics that are predictive of physiological regimes or outcomes of interest. We present exploratory results based on a simulation study and a physiological classification example of decoding postural changes from heart rate and blood pressure. We demonstrate a significant improvement in classification over methods based on feature learning via expectation maximization. The proposed learning algorithm is general, and can be extended to other applications involving state-space formulations.

Original languageEnglish (US)
Title of host publication2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
Pages7104-7107
Number of pages4
DOIs
StatePublished - 2013
Externally publishedYes
Event2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013 - Osaka, Japan
Duration: Jul 3 2013Jul 7 2013

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Other

Other2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2013
Country/TerritoryJapan
CityOsaka
Period7/3/137/7/13

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Health Informatics
  • Computer Vision and Pattern Recognition
  • Biomedical Engineering

Fingerprint

Dive into the research topics of 'Learning outcome-discriminative dynamics in multivariate physiological cohort time series'. Together they form a unique fingerprint.

Cite this