Key result
Lightweight hybrid CNN-LSTM model achieves ~98% accuracy classifying cardiac arrhythmias from ECGs.
Why the study?
Early detection of cardiac arrhythmias is critical, motivating automated and computerized ECG signal classification methods.
Population
ECG signals from the MIT-BIH arrhythmia database and long-term AF database
Comparison
Light deep learning CNN-LSTM model vs other state-of-the-art methods
Authors
Loading...
May enhance early arrhythmia detection via automated ECG analysis; hypothesis-generating and requires prospective clinical validation.
A lightweight hybrid CNN-LSTM model achieved 98.24% accuracy in detecting 8 different cardiac arrhythmias from ECG signals, suggesting potential for implementation in Holter monitors.
Alamatsaz et al. (2022) studied Cardiac arrhythmias (n=131). Lightweight hybrid CNN-LSTM model was evaluated on Mean diagnostic accuracy. A lightweight hybrid CNN-LSTM model achieved a mean diagnostic accuracy of 98.24% in classifying 8 different cardiac arrhythmias and normal sinus rhythm from ECG recordings.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: