Key result
Feeding raw ECG signals into convolution neural network-based classifiers achieved the best classification performance for arrhythmia detection, but at the expense of high inference time.
Why the study?
With the emerging trend of deep learning methods capable of automatic feature extraction, it was unknown whether feeding raw ECG sequences directly into classifiers yields good performance or if handcrafted feature extraction/selection is necessary.
Does feeding raw ECG sequences directly into deep learning classifiers improve classification performance compared to handcrafted feature extraction in arrhythmia detection?
Does feeding raw ECG sequences directly into deep learning classifiers improve classification performance compared to handcrafted feature extraction in arrhythmia detection?
Convolutional neural networks using raw ECG signals provide the best classification performance for arrhythmia detection, albeit with higher inference times compared to traditional feature extraction methods.
Answers are grounded in this paper and cite their sources.
Favors raw ECG CNNs for arrhythmia classification research; leaves open clinical viability due to inference latency.
Automated Electrocardiogram (ECG)-based arrhythmia detection methods replace traditional, manual arrhythmia detection reducing the requirement for trained medical staff. Traditionally, ECG-based arrhythmia detection is performed via QRS complex detection followed by feature extraction, based on hand-crafted features, such as RR-intervals, Fast Fourier Transform-based features, wavelet analysis, higher order statistics and Hermite features. After the features are extracted, the ECG segments are classified into pre-defined categories. This study investigates the value of the feature extraction and selection methods for ECG-based arrhythmia detection. That is, with the emerging trend of deep learning methods which are capable of automatic feature extraction and selection, the research question addressed in this paper is if good classification performance can be obtained by feeding the raw ECG sequence directly into robust classifiers or handcrafted feature extraction/selection is necessary. Classification performance across a range of state-of-the-art classification methods indicates that feeding raw signals into the convolution neural network-based classifiers usually leads to the best performance but at the expense of high inference time.
No takes yet. Share an insight, caveat, or question.
Ye et al. (2021) studied Arrhythmia. Convolution neural network-based classifiers using raw ECG signals vs. Handcrafted feature extraction/selection methods was evaluated on Classification performance. Feeding raw ECG signals into convolution neural network-based classifiers achieved the best classification performance for arrhythmia detection, but at the expense of high inference time.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: