Key result
Patient-specific LSTM and CNN ECG algorithm achieves ~85% sensitivity for SVEB detection.
Why the study?
Does an integrated LSTM and CNN algorithm improve ECG classification accuracy for arrhythmia recognition compared to prior works?
Does an integrated LSTM and CNN algorithm improve ECG classification accuracy for arrhythmia recognition compared to prior works?
An integrated LSTM and CNN algorithm improves the accuracy of automated ECG classification for arrhythmia monitoring without requiring manual feature extraction.
May aid automated arrhythmia monitoring; leaves open prospective clinical validation before practice adoption.
This paper presents an automated patient-specific ECG classification algorithm, which integrates long short-term memory (LSTM) and convolutional neural networks (CNN). While LSTM extracts the temporal features, such as the heart rate variance (HRV) and beat-to-beat correlation from sequential heartbeats, CNN captures detailed morphological characteristics of the current heartbeat. To further improve the classification performance, adaptive segmentation and re-sampling are applied to align the heartbeats of different patients with various heart rates. In addition, a novel clustering method is proposed to identify the most representative patterns from the common training data. Evaluated on the MIT-BIH arrhythmia database, our algorithm shows the superior accuracy for both ventricular ectopic beats (VEB) and supraventricular ectopic beats (SVEB) recognition. In particular, the sensitivity and positive predictive rate for SVEB increase by more than 8.2% and 8.8%, respectively, compared with the prior works. Since our patient-specific classification does not require manual feature extraction, it is potentially applicable to embedded devices for automatic and accurate arrhythmia monitoring.
No takes yet. Share an insight, caveat, or question.
Wu et al. (2020) studied Cardiovascular arrhythmia (n=43). Integrated LSTM and CNN algorithm vs. Prior ECG classification algorithms was evaluated on Sensitivity and positive predictive rate for supraventricular ectopic beats (SVEB) and ventricular ectopic beats (VEB). An integrated LSTM and CNN algorithm for patient-specific ECG classification achieved 85.0% sensitivity and 82.8% positive predictive rate for supraventricular ectopic beats.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: