Ensembling convolutional and long short-term memory networks for electrocardiogram arrhythmia detection

Structured PICO

Does an ensemble of convolutional and long short-term memory networks improve the detection of cardiac arrhythmia from noisy ECG signals?

Population

Noisy ECG signals for cardiac arrhythmia detection

Intervention

Ensemble classifier using convolutional and long short-term memory (LSTM) networks

Outcome

Detection of cardiac arrhythmia

An ensemble CNN-LSTM model provides robust detection of cardiac arrhythmias from noisy ECG signals without requiring manual feature engineering.

Abstract

Without employing a time-consuming feature engineering step, the ensemble classifier trained with this architecture provided a robust solution to the problem of detecting cardiac arrhythmia from noisy ECG signals. In addition, interpretation of the classifier by inspection of its network parameters and predictions revealed what aspects of the ECG signal the classifier considered most discriminating.

Mark Helpful

Bookmark

Relay