Why the study?
Subcutaneous and extravascular ICDs are prone to oversensing, and predictive T- or P-wave to R-wave amplitude ratios vary over a 24-hour period. Yet S-ICD screening uses only a single 10-second ECG segment, and the EV-ICD lacks a formal screening protocol.
Does a 1D convolutional neural network architecture (AmpRatioNet-SE) operating directly on 24-hour ambulatory ECG signals improve the prediction accuracy of T:R and P:R amplitude ratios for S-ICD and EV-ICD screening compared to 2D Phase Space Reconstruction CNNs and classical peak labelling algorithms?
Observational (n=89)
No
Does a 1D convolutional neural network architecture (AmpRatioNet-SE) operating directly on 24-hour ambulatory ECG signals improve the prediction accuracy of T:R and P:R amplitude ratios for S-ICD and EV-ICD screening compared to 2D Phase Space Reconstruction CNNs and classical peak labelling algorithms?
Direct 1D convolutional neural network modeling of 24-hour ambulatory ECGs via AmpRatioNet-SE substantially improves T:R and P:R wave amplitude ratio predictions over 2D image-based deep learning and classical algorithms, enabling extended 24-hour oversensing risk screening for both S-ICD and EV-ICD candidates.
Answers are grounded in this paper and cite their sources.
Hypothesis-generating for 24-hour oversensing screening in S-ICD/EV-ICD candidates; prospective validation required before clinical adoption.
This paper studies two non-transvenous implantable cardioverter-defibrillators (ICDs), namely the Subcutaneous ICD (S-ICD) and the Extravascular ICD (EV-ICD). Both avoid the complications of transvenous leads but are prone to oversensing, which can trigger inappropriate shocks associated with increased mortality. Oversensing risk is predicted by the ratio of T- or P-wave amplitude to R-wave amplitude (T:R, P:R), and these ratios vary over a 24-hour period. Yet S-ICD screening uses a single 10-second electrocardiogram (ECG) segment, and the EV-ICD has no formal screening protocol whatsoever. We present a 24-hour ambulatory screening framework for both devices which includes the first T:R analysis in an EV-ICD cohort and the first full evaluation of P:R prediction. We introduce AmpRatioNet, a family of 1D convolutional neural network architectures operating directly on the ECG signal, and benchmark it against the best existing approach - based on 2D phase space reconstruction images. Evaluation uses 4,605 clinician-annotated 10-second segments from 89 patients, with patient-level 10-fold cross-validation and bootstrap confidence intervals. AmpRatioNet-SE demonstrates superior performance on every metric in each setting with no device- or ratio-specific redesign. An explainability analysis against interpretable classical peak labelling algorithms shows that AmpRatioNet-SE's increase in error on oversensing-prone segments is up to 14 times smaller than theirs. Segment-level predictions are aggregated into a 24-hour timeline, extending S-ICD screening beyond 10 seconds and offering a plausible EV-ICD screening pathway pending device-level validation.
No takes yet. Share an insight, caveat, or question.
Morawski et al. (2026) conducted an observational in Non-transvenous implantable cardioverter-defibrillator (S-ICD and EV-ICD) oversensing screening (n=89). AmpRatioNet-SE (1D convolutional neural network) vs. 2D phase space reconstruction (PSR) CNN and classical peak labelling (CPL) algorithms was evaluated on Root Mean Squared Error (RMSE) in T:R and P:R ECG amplitude ratio prediction (37-57% reduction in RMSE vs 2D PSR CNN; up to 14-fold smaller oversensing error increase vs CPL).
Synapse has enriched 10 related papers. Consider them for comparative context: