Detection of ventricular tachycardia risk by means of Wigner Distribution Interference Terms from the high resolution ECG

Reyna, Marco A.; Jané, R.

doi:10.1109/cic.1997.648127

Cited by 5 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We shall describe the results of using this method on a publicly available database [5] to detect artifacts in arterial blood pressure (ABP) signals by exploiting correlations with ECG signals. Numerous systems have been developed for automatically analyzing patient monitoring signals, and these have employed various methods ranging from traditional signal processing techniques such as frequency analysis, timefrequency analysis, and wavelet analysis [3], [7], [8], [9], [11] to techniques developed by Artificial Intelligence (AI) researchers such as neural networks (NN) [4], [6], [12], [15] and fuzzy logic [1], [10], [16]. The majority of these systems have focused on ECG signals and most of the systems have used a single-signal model, or when they do look at multi-channels, they are of the same type of signal -ECG signals from multiple leads.…”

Section: Introductionmentioning

confidence: 99%

Morphograms: exploiting correlation patterns to efficiently identify clinically significant events in intensive care units

AIi

Eshelman

The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

In this paper, we present a simple technique that utilizes the cross correlations between ECG signals and an arterial blood pressure (ABP) signal for the purpose of assessing signal quality and detecting artifacts in the ABP signal. The technique was tested using cases from a physician-annotated patient monitoring signal database from Beth Israel/Harvard-MIT University data bank. The results were encouraging: 45% of the manually annotated artifacts were correctly classified and 98% of the manually annotated true events were correctly classified.

show abstract

Section: Introductionmentioning

confidence: 99%

Morphograms: exploiting correlation patterns to efficiently identify clinically significant events in intensive care units

AIi

Eshelman

The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

show abstract

Ventricular tachycardia risk detection using wavelet decomposition of the signal averaged ECG

Rodriguez

Jané²,

Brooks³

Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163)

View full text Add to dashboard Cite

Identifying artifacts in arterial blood pressure using morphogram variability

Ali¹,

Eshelman²,

Saeed

Computers in Cardiology, 2004

View full text Add to dashboard Cite

In this article we present a simple technique that utilizes the cross correlations between ECG signals and haemodynamic signals for the purpose of assessing signal quality and detecting artifacts in the arterial blood pressure (ABP) signal. The technique was tested using cases from a physician-annotated patient monitoring signal database from Beth IsraeUHarvard-MIT University data bank. The results were encouraging: 90% of the manually annotated artifacts were correctly classified as artifacts and 99% of the manually annotated true events were correctly classified (out of a tQtd Of 683 manualiy annotated alarms). IntroductionAlarms . Tsien looked at a number of patient monitoring . signals, inchding blood pressure, carbon dioxide, oxygen and heart rate, exploring a number o f machine learning techniques for identifying artifacts and comparing single channef and multi-channel approaches. Zong, et at. developed a system for detecting artifacts in arterial brood pressure (ABP) signals by analyzing the relationship between the ABP signal and the ECG signaIs using a fuzzy logic approach to evaluate signal quality of the ABP waveform 191. Both of these studies found that the multi-signal approach was more effective than simply analyzing the targeted signal. Although much could be said about the strengths and weaknesses of these various methods, the algorithm complexity was quite significant.In the next section we shall describe a simple method that requires minimal computational power for exploiting the relationships among signals used in patient monitoring. In the third section we shall present experimental results that demonstrate the effectiveness of this method for detecting artifacts in ABP signals, and thereby reduce false blood pressure alarms. MethodsThe fundamental premise of this study is that relationships among certain patient monitoring signals can be used to assess a particular signal (e.g., whether it is an artifact) in light of the behavior of other signals. Here we will be relying on the correlation between ECG and ABP signals, using the ECG for examining the ABP's fidelity. The proposed method represents the interaction of the monitored signals as morphograms and specifies rules for interpreting changes to these morpograms. We use the term "morphogram" to describe the plotting of, one signal versus another for a given period of time --e.g., an ECG signal on the x-axis and the ABP on the yaxis,We investigated if the ABP and the various ECG signals are highly corretated by determining if a characteristic morphology or signature is present. The signature represents the correlated signals for a single heart beat. Since the time period used is greater than one heart beat, significant departures from this signature can be seen on the morphogram plots. These departures indicate either a physiologically caused event or an artifact. The underlying heuristic of the morphogram algorithm is that physiologically caused events are more likely to affect all signals, and thus there will be perturbations in a...

show abstract

Detection of ventricular tachycardia risk by means of Wigner Distribution Interference Terms from the high resolution ECG

Cited by 5 publications

References 11 publications

Morphograms: exploiting correlation patterns to efficiently identify clinically significant events in intensive care units

Morphograms: exploiting correlation patterns to efficiently identify clinically significant events in intensive care units

Ventricular tachycardia risk detection using wavelet decomposition of the signal averaged ECG

Identifying artifacts in arterial blood pressure using morphogram variability

Contact Info

Product

Resources

About