Key result
An attention-based hierarchical LSTM network using stationary wavelet transform decomposition achieved an overall accuracy of 98.55% for binary classification of heart valve diseases.
Why the study?
Does an attention-based hierarchical LSTM network using SWT decomposition accurately detect heart valve diseases from phonocardiogram signals?
Does an attention-based hierarchical LSTM network using SWT decomposition accurately detect heart valve diseases from phonocardiogram signals?
An attention-based hierarchical LSTM network using stationary wavelet transform decomposition of phonocardiogram signals achieves high accuracy in detecting heart valve diseases.
Requires prospective validation before screening use; leaves open real-world utility of wavelet-LSTM models.
This article presents a phonocardiogram (PCG) based heart valve diseases (HVDs) detection for primary healthcare units. In this work, we propose a stationary wavelet transform (SWT) decomposition, followed by an attention-based hierarchical LSTM (HLSTM) network for each subband to detect HVDs. Initially, the PCG signal is preprocessed and segmented into PCG segments. Then, each PCG segment is decomposed using SWT. We employ subband-specific HLSTM networks to utilize the temporal and relative temporal information present in each subband of the PCG segment for detecting HVDs. Then, the outputs of each subband-specific HLSTM are fed to their respective intra-subband attention layer for weighted aggregation to obtain the subband-specific representation. Further, the inter-subband attention layer aggregates these subband-specific representation vectors to improve the detection of HVDs. The proposed method is tested and validated using two open-access databases. The Physionet challenge 2016 database shows an overall sensitivity of 97.96 %, overall specificity of 99.02 %, and overall accuracy (OA) of 98.55 %, using the proposed method for binary classification. Similarly, the heart sound murmur database shows impressive classwise performance measures and an OA of 99.47 %, using the proposed method for multiclass HVD classification. The proposed method’s impressive performance and generalization can help to detect HVD anomalies during preliminary check-ups in healthcare units.
No takes yet. Share an insight, caveat, or question.
Das et al. (2023) studied Heart valve diseases. Stationary wavelet transform (SWT) decomposition and attention-based hierarchical LSTM (HLSTM) network was evaluated on Overall accuracy for binary classification of heart valve diseases. An attention-based hierarchical LSTM network using stationary wavelet transform decomposition achieved an overall accuracy of 98.55% for binary classification of heart valve diseases.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: