A scalogram tensor decomposition based ECG quality assessment

• Published in: Journal of electrocardiology Vol. 81; pp. 169 - 175
• Main Authors: Sharma, Ashish, Sawant, Nidhi, Patidar, Shivnarayan
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.11.2023
• Subjects: 12‑lead ECG; Algorithms; Cardiovascular; ECG quality assessment system; Electrocardiography; Humans; Scalogram; Signal Processing, Computer-Assisted; Tucker tensor decomposition; 12‑lead ECG; Scalogram; ECG quality assessment system; Tucker tensor decomposition
• ISSN: 0022-0736; 1532-8430; 1532-8430
• DOI: 10.1016/j.jelectrocard.2023.09.002

ECG quality assessment is crucial for reducing false alarms and physician strain in automated diagnosis of cardiovascular diseases. Recent researches have focused on constructing an automatic noisy ECG record rejection mechanism. This work develops a noisy ECG record rejection system using scalogram and Tucker tensor decomposition. The system can reject ECG records, which cannot be analyzed or diagnosed. Scalogram of all 12‑lead ECG signals per subject are stacked to form a 3-way tensor. Tucker tensor decomposition is applied with empirical settings to obtain the core tensor. The core tensor is reshaped to form the latent features set. When tested using the PhysioNet challenge 2011 dataset in five-fold cross validation settings, the RusBoost ensemble classifier proved to be a very reliable option, producing an accuracy of 92.4% along with sensitivity of 87.1% and specificity of 93.5%. According to the experimental findings, combining the scalogram with Tucker tensor decomposition yields competitive performance and has the potential to be used in actual evaluation of ECG quality. •A three-way tensor is formed by computing scalograms of all the 12 channels of ECG and stacking them channel-wise.•The Tucker tensor decomposition is used to extract and compress the discriminative information from the three-way tensor.•The method avoids calculation of handcrafted features such as time, frequency, time-frequency domain, and nonlinear features.•The method performance is consistent even with a reduced scalogram image size.•Thus, the computation complexity associated with the tensor factorization is reduced.