Key result
Deep recurrent neural networks with Long Short Term Memory (LSTM) units showed promising results for detecting anomalies in ECG signals without requiring elaborate preprocessing.
Population
ECG time series data from the MIT-BIH Arrhythmia Database, including normal periods and periods during four…
Design
Other
Authors
Loading...
May aid unsupervised ECG anomaly detection; leaves open prospective clinical validation before practice integration.
Deep LSTM networks can effectively detect arrhythmias as anomalies in raw ECG signals without requiring extensive preprocessing or prior training on specific abnormal patterns.
Chauhan et al. (2015) studied Arrhythmia. Deep recurrent neural network with Long Short Term Memory (LSTM) units was evaluated on Anomaly detection in ECG signals. Deep recurrent neural networks with Long Short Term Memory (LSTM) units showed promising results for detecting anomalies in ECG signals without requiring elaborate preprocessing.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: