ARAN - Access to Research at NUI Galway

Probabilistic Detection of Short Events, with Application to Critical Care Monitoring

ARAN - Access to Research at NUI Galway

Show simple item record

dc.contributor.author Manley, Geoffrey en
dc.contributor.author Cohen, Mitchell en
dc.contributor.author Staudenmayer, Kristan en
dc.contributor.author Morabito, Diane en
dc.contributor.author Madden, Michael G. en
dc.contributor.author Russell, Stuart en
dc.contributor.author Aleks, Norm en
dc.date.accessioned 2009-06-02T11:36:11Z en
dc.date.available 2009-06-02T11:36:11Z en
dc.date.issued 2008 en
dc.identifier.citation "Probabilistic Detection of Short Events, with Application to Critical Care Monitoring", Norm Aleks and Stuart Russell (UC Berkeley), Michael G. Madden (NUI, Galway), Diane Morabito, Geoffrey Manley, Kristan Staudenmayer, and Mitchell Cohen (UC San Francisco). Proceedings of NIPS 2008: 22nd Annual Conference on Neural Information Processing Systems, Vancouver, Canada, December 2008. en
dc.identifier.uri http://hdl.handle.net/10379/206 en
dc.description.abstract We describe an application of probabilistic modeling and inference technology to the problem of analyzing sensor data in the setting of an intensive care unit (ICU). In particular, we consider the arterial-line blood pressure sensor, which is subject to frequent data artifacts that cause false alarms in the ICU and make the raw data almost useless for automated decision making. The problem is complicated by the fact that the sensor data are averaged over fixed intervals whereas the events causing data artifacts may occur at any time and often have durations significantly shorter than the data collection interval. We show that careful modeling of the sensor, combined with a general technique for detecting sub-interval events and estimating their duration, enables detection of artifacts and accurate estimation of the underlying blood pressure values. Our model¿s performance identifying artifacts is superior to two other classifiers¿ and about as good as a physician¿s. en
dc.format application/pdf en
dc.language.iso en en
dc.subject Probabilistic modelling en
dc.subject Inference technology en
dc.subject Blood pressure monitoring en
dc.subject Intensice care units (ICU) en
dc.subject Sensor data en
dc.subject.lcsh Blood pressure -- Measurement en
dc.subject.lcsh Intensive care units en
dc.subject.lcsh Multisensor data fusion en
dc.title Probabilistic Detection of Short Events, with Application to Critical Care Monitoring en
dc.type Conference Paper en

Files in this item

This item appears in the following Collection(s)

Show simple item record