Key result
An artificial neural network classifier using ECG features achieved classification accuracies between VT and VF of 92% (power spectrum), 91% (correlation dimension), and 87% (surrogate time domain).
Why the study?
The differentiation between ventricular tachycardia and ventricular fibrillation by specialists in critical situations carries a risk of incorrect diagnosis, motivating investigation of ECG feature-based classification methods.
Does an artificial neural network using ECG features accurately classify ventricular tachycardia and ventricular fibrillation?
Does an artificial neural network using ECG features accurately classify ventricular tachycardia and ventricular fibrillation?
Answers are grounded in this paper and cite their sources.
Artificial neural networks using frequency and phase space ECG features can accurately distinguish between ventricular tachycardia and ventricular fibrillation.
Ventricular tachycardia (VT) is a fast heart rate that arises from improper electrical activity in the ventricular of the heart. VT may eventually lead to lethal ventricular fibrillation (VF) which is characterized by fast and irregular heart rhythm. Since difference between VT and VF is diagnosed by specialist in a critical and stressful situation, the possibility of wrong decision is not low. Here, various set of ECG features belonged to different domains are implemented to investigate the predictability and discriminability of VT and VF episodes. Informative features from different domains such as correlation dimension (phase space) and power spectrum (frequency domain) were elicited from electrocardiogram (ECG) signals to describe the amount of irregularity/variation through the attack. In addition raw signal samples were used to assess the classification task based on the time domain features. Applying correlation dimension, power spectrum and the raw samples of ECGs to artificial neural network (ANN) classifier provides 91%, 92% and 71% classification accuracy between VT and VF signals, respectively. However, to enrich the time domain features, surrogate data was generated and the results of time domain is increased up to 87% which represents that ANNs are able to learn the dynamic nature of chaotic signals.
No takes yet. Share an insight, caveat, or question.
Noruzi et al. (2017) studied Ventricular tachycardia and ventricular fibrillation. Artificial neural network (ANN) classifier using ECG features was evaluated on Classification accuracy between VT and VF signals. An artificial neural network classifier using ECG features achieved classification accuracies between VT and VF of 92% (power spectrum), 91% (correlation dimension), and 87% (surrogate time domain).
Synapse has enriched 10 related papers. Consider them for comparative context: