Automated recognition of corrupted arterial waveforms using neural network techniques

Pike, Tom; Mustard, Robert A.

doi:10.1016/0010-4825(92)90013-d

Cited by 15 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We validated pulmonary pressure beats by analyzing the fluctuations in eight characteristic features. Neural networks have been proposed to validate the shape of pressure signals [11,12]. Their disadvantages are that online learning is required and that their inference process is not as transparent.…”

Section: Discussionmentioning

confidence: 99%

Correction for respiration artifact in pulmonary blood pressure signals of ventilated patients

Hoeksel

Blom

Jansen

et al. 1996

J Clin Monitor Comput

View full text Add to dashboard Cite

ABSTRACT. Objective. To develop an algorithm that corrects pulmonary artery pressure signals of ventilated patients for the respiration artifact. The algorithm should test the validity of the pulmonary pressure signal and differentiate between the cyclic respiration artifact and true measurement artifacts. Methods. The shape of each pulmonary pressure beat is described by eight characteristic features, including mean pressure value and the systolic and diastolic timing and pressure values. The features are corrected for the respiration artifact by fitting them in a least-squares sense on the first and second harmonics of the ventilator frequency. The corrected features are used by a signal validation algorithm, which adds a validity flag to each pressure beat. The validation algorithm rejects pressure beats with sudden changes in their shape but adapts itself when the changes persist. Results. The performance of the correction and validation technique was evaluated using pulmonary artery pressure signals of 30 patients who were scheduled for open heart surgery. The algorithm correctly recognized as invalid data those pressure signals disturbed by coagulation, surgical manipulations, or flushes of the pressure line. The algorithm marked on average 77 + 11% of the pulmonary pressure beats as valid. Conclusions. The validation algorithm marked sufficient pressure beats as valid to update a trend display every 5 sec. The correction algorithm enabled the validation algorithm to differentiate between true measurement artifacts and the respiration artifact.

show abstract

Section: Discussionmentioning

confidence: 99%

Correction for respiration artifact in pulmonary blood pressure signals of ventilated patients

Hoeksel

Blom

Jansen

et al. 1996

J Clin Monitor Comput

View full text Add to dashboard Cite

show abstract

“…The variance, however, is increased. 2 4) The minimum of (10) in fact occurs at 3 = p p + p (11) and for = 3 we have…”

Section: Nonsymmetric Casesmentioning

confidence: 88%

The generalization error of the symmetric and scaled support vector machines

Feng

Williams

2001

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

It is generally believed that the support vector machine (SVM) optimizes the generalization error and outperforms other learning machines. We show analytically, by concrete examples in the one dimensional case, that the SVM does improve the mean and standard deviation of the generalization error by a constant factor, compared to the worst learning machine. Our approach is in terms of the extreme value theory and both the mean and variance of the generalization errors are calculated exactly for all the cases considered. We propose a new version of the SVM , called the scaled SVM, which can further reduce the mean of the generalization error of the SVM.

show abstract

“…Unfortunately, there is no way of telling how many nodes the network needs, or whether it has reached its optimal performance. However, neural network techniques have previously been shown to be able to handle the inaccuracy and inconsistency associated with patient histories and physical findings (Pike and Mustard, 1992;Edenbrandt et a[., 1992;Baxt, 1991;Gheorghiade and Anderson, 1988). Further, the networks appears to be able to deal with the complexities of disease states characterized by several totally differing clinical presentations (Dassen et al, 1990).…”

Section: Gt Anderson Er A1mentioning

confidence: 95%