February 1, 2016

Decision Support System for Arrhythmia Beats Using Ecg Signals With Dct, DWT and Emd Methods: A Comparative Study

Q: What is the clinical evidence from this study?

Study design: Other. Population: Arrhythmia. Intervention: Independent Components (ICs) on Discrete Wavelet Transform (DWT) vs. Discrete Cosine Transform (DCT) and Empirical Mode Decomposition (EMD) methods. Primary outcome: Classification accuracy of five classes of arrhythmia beats.

Key Result

Automated diagnosis using Independent Components on Discrete Wavelet Transform and a k-NN classifier achieved 99.77% accuracy in classifying five types of arrhythmia beats.

Structured PICO

Which computational method (DCT, DWT, or EMD with PCs or ICs) provides the highest classification accuracy for automated diagnosis of arrhythmia beats from ECG signals?

Population

ECG signals for automated diagnosis of five classes of beats (Non-ectopic, Supraventricular ectopic, Ventricular ectopic, Fusion, and Unknown)

Intervention

Six different approaches: Principal Components (PCs) on DCT, Independent Components (ICs) on DCT, PCs on DWT, ICs on DWT, PCs on EMD, and ICs on EMD, using k-Nearest Neighbor (k-NN) classifier

Comparator

Comparison among the six different computational approaches

Outcome

Classification accuracysurrogate

The use of Independent Components on Discrete Wavelet Transform provides highly accurate automated classification of arrhythmia beats from ECG signals.

Abstract

Electrocardiogram (ECG) signal is a non-invasive method, used to diagnose the patients with cardiac abnormalities. The subjective evaluation of interval and amplitude of ECG by physician can be tedious, time consuming, and susceptible to observer bias. ECG signals are generated due to the excitation of many cardiac myocytes and hence resultant signals are non-linear in nature. These subtle changes can be well represented and discriminated in transform and non-linear domains. In this paper, performance of Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT) and Empirical Mode Decomposition (EMD) methods are compared for automated diagnosis of five classes namely Non-ectopic (N), Supraventricular ectopic (S), Ventricular ectopic (V), Fusion (F) and Unknown (U) beats. Six different approaches: (i) Principal Components (PCs) on DCT, (ii) Independent Components (ICs) on DCT, (iii) PCs on DWT, (iv) ICs on DWT, (v) PCs on EMD and (vi) ICs on EMD are employed in this work. Clinically significant features are selected using ANOVA test (Formula: see text) and fed to k-Nearest Neighbor (k-NN) classifier. We have obtained a classification accuracy of 99.77% using ICs on DWT method. Consistency of performance is evaluated using Cohen’s kappa statistic. Developed approach is robust, accurate and can be employed for mass diagnosis of cardiac healthcare.

Bookmark

Cite This Study

Desai et al. (Mon,) conducted a other in Arrhythmia. Independent Components (ICs) on Discrete Wavelet Transform (DWT) vs. Discrete Cosine Transform (DCT) and Empirical Mode Decomposition (EMD) methods was evaluated on Classification accuracy of five classes of arrhythmia beats. Automated diagnosis using Independent Components on Discrete Wavelet Transform and a k-NN classifier achieved 99.77% accuracy in classifying five types of arrhythmia beats.

synapsesocial.com/papers/6a06f2582edded7c7b841eba https://doi.org/https://doi.org/10.1142/s0219519416400121

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

Bookmark