Gaussian Process Modeling of EEG for the Detection of Neonatal Seizures

Faul, Stephen; Gregorcic, Gregor; Boylan, Geraldine B.; Marnane, William P.; Lightbody, Gordon; Connolly, Seán

doi:10.1109/tbme.2007.895745

Cited by 54 publications

(37 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model based seizure detectors have been applied in the past with limited success (see [11], [27]). The idea of using model based features to simplify the detection problem such as whitening the data with a nonlinear (or linear approximation) filter, however, appeal.…”

Section: Discussionmentioning

confidence: 99%

“…Recently, the detection of newborn EEG seizure has been automated to assist the neurophysiologist when diagnosing long recordings of EEG, [1], [9], [11], [12], [19], [27]. Current techniques, although constantly improving, lack the necessary accuracy that is required for clinical implementation.…”

Section: Secondsmentioning

confidence: 99%

“…The parameters to be estimated for the model comparison include (1), (2) and (9) where m = 1 and k 1 = 0 to lessen the computation burden on the model identification algorithm. Parameter m was set to be constant as it primarily affects the gain 11 of the system and the linear component of g(x(t)) was set to zero as we were primarily interested in the effect of the nonlinear aspects of the model. Preliminary analysis showed negligible improvement was achieved from incorporating k 1 .…”

Section: A Newborn Eeg Seizure Modelmentioning

confidence: 99%

See 2 more Smart Citations

A Nonlinear Model of Newborn EEG with Nonstationary Inputs

et al. 2010

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Secondsmentioning

confidence: 99%

Section: A Newborn Eeg Seizure Modelmentioning

confidence: 99%

See 1 more Smart Citation

A Nonlinear Model of Newborn EEG with Nonstationary Inputs

et al. 2010

View full text Add to dashboard Cite

show abstract

“…Various interesting applications (e.g. [3], [4] in medicine and bioengineering fields) have exploited different properties of Gaussian pro-cess models. In the field of geostatistics Gaussian Process regression models are used for probabilistic analysis of data and are more commonly known under name Kriging.…”

Section: Introductionmentioning

confidence: 99%

Using Gaussian Process Models for Near-Infrared Spectroscopy Data Interpolation

Leamy

2010

Mechatronic Systems and Control

View full text Add to dashboard Cite

Gaussian Process (GP) model interpolation is used extensively in geostatistics. We investigated the effectiveness of using GP model interpolation to generate maps of cortical activity as measured by Near Infrared Spectroscopy (NIRS). GP model interpolation also produces a variability map, which indicates the reliability of the interpolated data. For NIRS, cortical hemodynamic activity is spatially sampled. When generating cortical activity maps, the data must be interpolated. Popular NIRS imaging software HomER uses Photon Migration Imaging (PMI) and Diffuse Optical Imaging (DOI) techniques based on models of light behaviour to generate activity maps. Very few non-parametric methods of NIRS imaging exist and none of them indicate the reliability of the interpolated data. Our GP model interpolation algorithm and HomER produced activity maps based on data generated from typical functional NIRS responses. Image results in HomER were taken as the bench mark as the images produced are commonly considered to be representative of the true underlying hemodynamic spatial response. The output from the GP approach was then compared to these on a qualitative basis. The GP model interpolation appears to produce less structured image maps of hemodynamic activity compared to those produced by HomER, however a broadly similar spatial response is compelling evidence of the utility of GP models for such applications. The additional generation of a variability map which is produced by the GP method may have some utility for functional NIRS as such information is not explicitly available from standard approaches. GP model interpolation can produce spatial activity maps from coarsely sampled NIRS data sets without any knowledge of the system being modelled. While the images produced do not appear to have the same feature resolution as photonic model-based methods the technique is worthy of further investigation due to its relative simplicity and, most intriguingly, its generation of ancillary information in the form of the variability map. This additional data may have some utility in NIRS optode design or perhaps it may have application as additional input for response classification purposes. This GP technique may also be of use where model information is inadequate for DOI techniques.

show abstract

“…Giraldo and colleagues [31] classified respiratory patterns of patients on weaning trials into those that will succeed or fail to sustain spontaneous breathing. Gaussian processes (GP) have been applied to the problem of neonatal seizure detection from electroencephalograph (EEG) signals, where they are shown to outperform other modeling methods currently in clinical use for EEG analysis [32].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Clinical Conditions after Coronary Bypass Surgery using Dynamic Data Analysis

Loon

Güiza

Meyfroidt³

et al. 2009

J Med Syst

View full text Add to dashboard Cite

This work studies the impact of using dynamic information as features in a machine learning algorithm for the prediction task of classifying critically ill patients in two classes according to the time they need to reach a stable state after coronary bypass surgery: less or more than 9 h. On the basis of five physiological variables (heart rate, systolic arterial blood pressure, systolic pulmonary pressure, blood temperature and oxygen saturation), different dynamic features were extracted, namely the means and standard deviations at different moments in time, coefficients of multivariate autoregressive models and cepstral coefficients. These sets of features served subsequently as inputs for a Gaussian process and the prediction results were compared with the case where only admission data was used for the classification. The dynamic features, especially the cepstral coefficients (aROC: 0.749, Brier score: 0.206), resulted in higher performances when compared to static admission data (aROC: 0.547, Brier score: 0.247). The differences in performance are shown to be significant. In all cases, the Gaussian process classifier outperformed to logistic regression.

show abstract

Gaussian Process Modeling of EEG for the Detection of Neonatal Seizures

Cited by 54 publications

References 22 publications

A Nonlinear Model of Newborn EEG with Nonstationary Inputs

A Nonlinear Model of Newborn EEG with Nonstationary Inputs

Using Gaussian Process Models for Near-Infrared Spectroscopy Data Interpolation

Prediction of Clinical Conditions after Coronary Bypass Surgery using Dynamic Data Analysis

Contact Info

Product

Resources

About