Key result
A multiscale convolutional neural network using lower-order range subband signals achieved average accuracies of 99.34% to 99.95% for localizing various categories of myocardial infarction.
Why the study?
Localization of MI based on multi-lead ECG morphology is the initial diagnostic task, prompting the development of automated localization methods.
A multiscale convolutional neural network using Fourier-Bessel series expansion based empirical wavelet transform achieves >99% accuracy in localizing various categories of myocardial infarction from multi-lead ECG signals.
No takes yet. Share an insight, caveat, or question.
May aid automated MI localization from multi-lead ECG; leaves open prospective clinical validation before practice use.
Tripathy et al. (2019) studied Myocardial infarction. Multiscale convolutional neural network with Fourier-Bessel series expansion based empirical wavelet transform vs. Existing MI localization approaches was evaluated on Automated localization and classification of MI categories. A multiscale convolutional neural network using lower-order range subband signals achieved average accuracies of 99.34% to 99.95% for localizing various categories of myocardial infarction.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: