January 1, 2019IEEE AccessOpen Access

Inter-Patient CNN-LSTM for QRS Complex Detection in Noisy ECG Signals

View Full Paper

Ask AI

Bookmark

Why the study?

Generalization ability across patients is critical to automated ECG analysis for big data collected from noisy wearable ECG devices.

Population

ECG signals from the MIT-BIH and European ST-T noise stress test databases

Design

Algorithm development and validation study

Authors

BYBrosnan Yuen XDXiaodai Dong TLTao Lű

Discussion

Member takes

Overview

CNN-LSTM may improve QRS detection in noisy ECGs; leaves open prospective clinical validation before adoption.

Structured PICO

Population

ECG records from the MIT-BIH arrhythmia database and the European ST-T database, with simulated noise (12 dB and 0 dB SNR) to mimic wearable ECG devices.

Intervention

Convolutional neural network (CNN) with long short-term memory (LSTM) algorithm for QRS complex detection

Comparator

Pan and Tompkins, GQRS, Wavedet, Xiang et al.'s CNN, and Chandra et al.'s CNN algorithms

Outcome

QRS complex detection performance measured by sensitivity (recall), positive predictive value (precision), F1 score, and timing root mean square error (RMSE) of R peak positionssurrogate

A novel CNN-LSTM architecture demonstrates superior inter-patient QRS complex detection performance in noisy ECG signals compared to traditional and other machine learning algorithms.

Cite This Study

Yuen et al. (2019) studied this question.

synapsesocial.com/papers/6a76590c5beab9a4d381455f https://doi.org/10.1109/access.2019.2955738

View Full Paper

Ask AI

Bookmark

January 1, 2019IEEE AccessOpen Access

Inter-Patient CNN-LSTM for QRS Complex Detection in Noisy ECG Signals

View Full Paper

Ask AI

Bookmark

Why the study?

Generalization ability across patients is critical to automated ECG analysis for big data collected from noisy wearable ECG devices.

Population

ECG signals from the MIT-BIH and European ST-T noise stress test databases

Design

Algorithm development and validation study

Authors

BYBrosnan Yuen XDXiaodai Dong TLTao Lű

Discussion

Member takes

Overview

CNN-LSTM may improve QRS detection in noisy ECGs; leaves open prospective clinical validation before adoption.

Structured PICO

Population

ECG records from the MIT-BIH arrhythmia database and the European ST-T database, with simulated noise (12 dB and 0 dB SNR) to mimic wearable ECG devices.

Intervention

Convolutional neural network (CNN) with long short-term memory (LSTM) algorithm for QRS complex detection

Comparator

Pan and Tompkins, GQRS, Wavedet, Xiang et al.'s CNN, and Chandra et al.'s CNN algorithms

Outcome

QRS complex detection performance measured by sensitivity (recall), positive predictive value (precision), F1 score, and timing root mean square error (RMSE) of R peak positionssurrogate

A novel CNN-LSTM architecture demonstrates superior inter-patient QRS complex detection performance in noisy ECG signals compared to traditional and other machine learning algorithms.

Cite This Study

Yuen et al. (2019) studied this question.

synapsesocial.com/papers/6a76590c5beab9a4d381455f https://doi.org/10.1109/access.2019.2955738

View Full Paper

Ask AI

Bookmark