Key result
A random forest classifier using variational mode decomposition and bispectral features of ECG signals differentiated dilated from ischemic cardiomyopathy with 98.21% accuracy, 98.22% sensitivity, and 98.19% specificity.
Why the study?
ICM clinically resembles DCM, which typically requires invasive coronary angiography to definitively diagnose, and prior ECG modal decomposition studies lacked interpretability and optimal classification performance.
Does a machine learning classification algorithm based on variational mode decomposition and high order spectra analysis of ECG signals accurately distinguish between dilated cardiomyopathy and ischemic cardiomyopathy?
Observational (n=75)
No
Does a machine learning classification algorithm based on variational mode decomposition and high order spectra analysis of ECG signals accurately distinguish between dilated cardiomyopathy and ischemic cardiomyopathy?
A machine learning framework using variational mode decomposition and bispectrum analysis of ECG signals can highly accurately differentiate between ischemic and dilated cardiomyopathy, potentially reducing the need for invasive coronary angiography.
May enable noninvasive ICM versus DCM distinction via ECG modes; leaves open prospective validation against angiography.
The clinical manifestations of ischemic cardiomyopathy (ICM) bear resemblance to dilated cardiomyopathy (DCM). The definitive diagnosis of DCM necessitates the identification of invasive, costly, and contraindicated coronary angiography. Many diagnostic studies of cardiovascular disease have tried modal decomposition based on electrocardiogram (ECG) signals. However, these studies ignored the connection between modes and other fields, thus limiting the interpretability of modes to ECG signals and the classification performance of models. This study proposes a classification algorithm based on variational mode decomposition (VMD) and high order spectra, which decomposes the preprocessed ECG signal and extracts its first five modes obtained through VMD. After that, these modes are estimated for their corresponding bispectrums, and the feature vector is composed of fifteen features including bispectral, frequency, and nonlinear features based on this. Finally, a dataset containing 75 subjects (38 DCM, 37 ICM) is classified and compared using random forest (RF), decision tree, support vector machine, and K-nearest neighbor. The results show that, in comparison to previous approaches, the technique proposed provides a better categorization for DCM and ICM of ECG signals, which delivers 98.21% classification accuracy, 98.22% sensitivity, and 98.19% specificity. And mode 3 always has the best performance among single mode. The proposed computerized framework significantly improves automatic diagnostic performance, which can help relieve the working pressure on doctors, possible economic burden and health threaten.
No takes yet. Share an insight, caveat, or question.
Han et al. (2023) conducted an observational in Dilated cardiomyopathy and ischemic cardiomyopathy (n=75). Variational mode decomposition and bispectrum analysis of ECG signals (Random Forest classifier) vs. Coronary angiography (gold standard) was evaluated on Classification accuracy for differentiating dilated cardiomyopathy and ischemic cardiomyopathy. A random forest classifier using variational mode decomposition and bispectral features of ECG signals differentiated dilated from ischemic cardiomyopathy with 98.21% accuracy, 98.22% sensitivity, and 98.19% specificity.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: