Factorial switching Kalman filters for condition monitoring in neonatal intensive care

Christopher K. I. Williams; John Quinn; Neil McIntosh

Factorial switching Kalman filters for condition monitoring in neonatal intensive care

Christopher K. I. Williams, John Quinn, Neil McIntosh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

The observed physiological dynamics of an infant receiving intensive care are affected by many possible factors, including interventions to the baby, the operation of the monitoring equipment and the state of health. The Factorial Switching Kalman Filter can be used to infer the presence of such factors from a sequence of observations, and to estimate the true values where these observations have been corrupted. We apply this model to clinical time series data and show it to be effective in identifying a number of artifactual and physiological patterns.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 18
Publisher	MIT Press
Pages	1513-1520
Number of pages	8
Publication status	Published - 2006

Access to Document

2784-factorial-switching-kalman-filters-for-condition-monitoring-in-neonatal-intensive-careFinal published version, 147 KB

http://papers.nips.cc/paper/2784-factorial-switching-kalman-filters-for-condition-monitoring-in-neonatal-intensive-care.pdf

PASCAL: Pattern analysis, statistical modelling and computational learning
Williams, C.
EU government bodies
1/12/03 → 30/09/08
Project: Research

Cite this

@inproceedings{59d2bfb79d04452ead948cd60a460077,

title = "Factorial switching Kalman filters for condition monitoring in neonatal intensive care",

abstract = "The observed physiological dynamics of an infant receiving intensive care are affected by many possible factors, including interventions to the baby, the operation of the monitoring equipment and the state of health. The Factorial Switching Kalman Filter can be used to infer the presence of such factors from a sequence of observations, and to estimate the true values where these observations have been corrupted. We apply this model to clinical time series data and show it to be effective in identifying a number of artifactual and physiological patterns.",

author = "Williams, {Christopher K. I.} and John Quinn and Neil McIntosh",

year = "2006",

language = "English",

pages = "1513--1520",

booktitle = "Advances in Neural Information Processing Systems 18",

publisher = "MIT Press",

}

TY - GEN

T1 - Factorial switching Kalman filters for condition monitoring in neonatal intensive care

AU - Williams, Christopher K. I.

AU - Quinn, John

AU - McIntosh, Neil

PY - 2006

Y1 - 2006

N2 - The observed physiological dynamics of an infant receiving intensive care are affected by many possible factors, including interventions to the baby, the operation of the monitoring equipment and the state of health. The Factorial Switching Kalman Filter can be used to infer the presence of such factors from a sequence of observations, and to estimate the true values where these observations have been corrupted. We apply this model to clinical time series data and show it to be effective in identifying a number of artifactual and physiological patterns.

AB - The observed physiological dynamics of an infant receiving intensive care are affected by many possible factors, including interventions to the baby, the operation of the monitoring equipment and the state of health. The Factorial Switching Kalman Filter can be used to infer the presence of such factors from a sequence of observations, and to estimate the true values where these observations have been corrupted. We apply this model to clinical time series data and show it to be effective in identifying a number of artifactual and physiological patterns.

M3 - Conference contribution

SP - 1513

EP - 1520

BT - Advances in Neural Information Processing Systems 18

PB - MIT Press

ER -

Factorial switching Kalman filters for condition monitoring in neonatal intensive care

Abstract / Description of output

Access to Document

Fingerprint

Projects

PASCAL: Pattern analysis, statistical modelling and computational learning

Cite this