Key result
A deep learning method using a UNet network for real-time QRS complex detection in ultra-high-frequency ECG achieved an overall F1 score of 97.11% on the test set.
Why the study?
Real-time UHF-ECG analysis can optimize pacing locations during pacemaker implantation, but current real-time QRS detection methods require suppressed pacemaker stimuli.
Does a deep learning method (UNet network) accurately detect QRS complexes in real-time ultra-high-frequency ECG?
Does a deep learning method (UNet network) accurately detect QRS complexes in real-time ultra-high-frequency ECG?
A deep learning method using a UNet network achieved a 97.11% F1 score for real-time QRS complex detection in ultra-high-frequency ECG, potentially reducing measurement time during pacemaker implant procedures.
High accuracy supports real-time UHF-ECG QRS detection feasibility; leaves open prospective clinical validation before practice change.
Background: Analysis of ultra-high-frequency ECG (UHF-ECG, sampled at 5,000 Hz) informs about dyssynchrony of ventricles activation. This information can be evaluated in real-time, allowing optimization of a pacing location during pacemaker implantation. However, the current method for real-time QRS detection in UHF-ECG requires suppressed pacemaker stimuli. Aim: We present a deep learning method for real-time QRS complex detection in UHF-ECG. Method: A 3-second window from V1, V3, and V6 lead of UHF-ECG signal is standardized and processed with the UNet network. The output is an array of QRS probabilities, further transformed into resultant QRS annotation using QRS probability and distance criterion. Results: The model had been trained on 2,250 ECG recordings from the FNUSA-ICRC hospital (Brno, Czechia) and tested on 300 recordings from the FNKV hospital (Prague, Czechia). We received an overall F1 score of 97.11 % on the test set. Conclusion: Presented approach improves UHF-ECG analysis performance and, consequently, could reduce measurement time during implant procedures.
No takes yet. Share an insight, caveat, or question.
Koscova et al. (2021) studied Ventricular dyssynchrony during pacemaker implantation (n=2,550). Deep learning method (UNet network) for real-time QRS complex detection was evaluated on Overall F1 score on the test set. A deep learning method using a UNet network for real-time QRS complex detection in ultra-high-frequency ECG achieved an overall F1 score of 97.11% on the test set.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: