TY - CONF A1 - Güldenring, Daniel A1 - Doggart, Peter A1 - Kennedy, Alan A1 - Bond, Raymond A1 - Finlay, Dewar T1 - Identifying Noisy ECG Signals in Large Datasets Using a Temporal Convolutional Neural Network Trained to Estimate Pseudo-SNR T2 - Computing in Cardiology 2023 N2 - Background: Electrocardiogram (ECG) signals are often contaminated by noise. Manual review of large ECG databases to identify noisy signals is time-consuming. Traditional signal quality assessment algorithms often do not generalize well or are computationally expensive. This study developed a Temporal Convolutional Neural Network (TCNN) to estimate the signal-to-noise ratio (SNR) of ECG signals. Method: We trained a TCNN on a proprietary database of 134,019 12-lead ECGs without any machine or human-added noise labels. Assuming that this data had high SNR, we randomly selected a single lead from each ECG and added random Gaussian noise. We then scaled the signals and added noise to give a negatively skewed normal distribution of true SNR values. We trained a TCNN to regress low- and high-frequency pseudo-SNR values from the raw noisy input signals. Results: On the testing dataset, the TCNN achieved a mean error of 0.31±1.80 dB and a Pearson correlation coefficient of 0.96 for low-frequency pseudo-SNR. Similarly, for high-frequency pseudo-SNR, the mean error was 0.29±1.63 dB and the Pearson correlation coefficient was 0.97. Conclusion: A Temporal Convolutional Neural Network can accurately estimate the SNR of unseen ECGs. KW - Künstliche Intelligenz KW - Elektrokardiogramm KW - Biomedizinische Signalverarbeitung KW - ECG Y1 - 2024 UR - https://opus4.kobv.de/opus4-hs-kempten/frontdoor/index/index/docId/2125 SN - 979-8-3503-8252-5 SN - 2325-887X VL - 2023 IS - 50 SP - 1 EP - 4 PB - IEEE CY - Piscataway ER -