Key result
The proposed GSMD and SLT-based technique using GoogleNet achieved an overall accuracy of 99.2% for classifying healthy heart, atrial fibrillation, and ventricular fibrillation.
Why the study?
Timely and precise detection of cardiac arrhythmias like AF and VF is essential to reduce mortality rates and prevent complications such as strokes.
Population
ECG records from MIT-BIH databases and Mendeley-II dataset
Comparison
GSMD and SLT framework with deep neural models vs healthy heart, AF, and VF classification
Design
Algorithm development and validation study
Authors
Loading...
GSMD framework may aid arrhythmia detection; leaves open prospective clinical validation before adoption.
A novel framework using group sparse mode decomposition and superlet transform with deep learning models achieved high accuracy (>98%) in classifying cardiac arrhythmias from ECG signals.
Singhal et al. (2024) studied Cardiac arrhythmia. GSMD and SLT-based technique with deep neural networks was evaluated on Classification accuracy. The proposed GSMD and SLT-based technique using GoogleNet achieved an overall accuracy of 99.2% for classifying healthy heart, atrial fibrillation, and ventricular fibrillation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: