Multi-Beat Averaging Reveals U Waves Are Ubiquitous and Standing Tall at Elevated Heart Rates Following Exercise

Delineation of 12-Lead ECG Representative Beats Using Convolutional Encoder-Decoders with Residual and Recurrent Connections

The aim of this study is to address the challenge of 12-lead ECG delineation by different encoder-decoder architectures of deep neural networks (DNNs). This study compares four concepts for encoder-decoders based on a fully convolutional architecture (CED-Net) and its modifications with a recurrent layer (CED-LSTM-Net), residual connections between symmetrical encoder and decoder feature maps (CED-U-Net), and sequential residual blocks (CED-Res-Net). All DNNs transform 12-lead representative beats to three diagnostic ECG intervals (P-wave, QRS-complex, QT-interval) used for the global delineation of the representative beat (P-onset, P-offset, QRS-onset, QRS-offset, T-offset). All DNNs were trained and optimized using the large PhysioNet ECG database (PTB-XL) under identical conditions, applying an advanced approach for machine-based supervised learning with a reference algorithm for ECG delineation (ETM, Schiller AG, Baar, Switzerland). The test results indicate that all DNN architectures are equally capable of reproducing the reference delineation algorithm's measurements in the diagnostic PTB database with an average P-wave detection accuracy (96.6%) and time and duration errors: mean values (-2.6 to 2.4 ms) and standard deviations (2.9 to 11.4 ms). The validation according to the standard-based evaluation practices of diagnostic electrocardiographs with the CSE database outlines a CED-Net model, which measures P-duration (2.6 ± 11.0 ms), PQ-interval (0.9 ± 5.8 ms), QRS-duration (-2.4 ± 5.4 ms), and QT-interval (-0.7 ± 10.3 ms), which meet all standard tolerances. Noise tests with high-frequency, low-frequency, and power-line frequency noise (50/60 Hz) confirm that CED-Net, CED-Res-Net, and CED-LSTM-Net are robust to all types of noise, mostly presenting a mean duration error < 2.5 ms when compared to measurements without noise. Reduced noise immunity is observed for the U-net architecture. Comparative analysis with other published studies scores this research within the lower range of time errors, highlighting its competitive performance.

Enhancing electrocardiographic analysis by combining a high-resolution 12-lead ECG with novel software tools

INTRODUCTION

Signal-averaged electrocardiography is a non-invasive, computerized technique that amplifies, filters, and averages cardiac electrical signals reducing contaminating noise to obtain a high-resolution record. The most widely used signal averaging (SA) method involves a bipolar X, Y, and Z orthogonal lead system. Information is limited regarding its application in the standard resting 12-lead ECG. A novel system combining a high-resolution 12-lead ECG (HR-ECG) registered by SA with advanced analysis tools is presented.

HISTORY

Original programming of a commercially available signal-averaged HR-ECG device was modified, introducing more exhaustive electrocardiographic assessment instruments.

DESCRIPTION

Using SA techniques and placing surface electrodes in the standard 12-lead ECG positions, a HR-ECG is acquired within a bandwidth of 0.25 to 262 Hz at a rate of 1000 samples per second. It is advisable to average at least 200 cycles, taking three to five minutes to record. The package includes different optional high-frequency filters, manual calipers, zoom/superimposing/amplification functions.

CLINICAL ROLE

The main strength lies in obtaining a low noise HR-ECG with zooming capabilities without definition loss. Other potential advantages are the greater ease in performing high precision analysis and comparing different ECG leads simultaneously.

CURRENT PROBLEMS

The primary limitation is the inability to document intermittent or dynamic electrocardiographic disorders because of averaging similar electrical cardiac cycles.

FUTURE DEVELOPMENTS

Adding artificial intelligence and further refinements in the averaging process could lead to software upgrades.

CONCLUSION

Integrating HR-ECG, obtained through SA techniques, with novel advanced analysis tools can enhance the ability to detect electrocardiographic disorders of permanent expression expeditiously.