Derived Peak (DP) encoding achieved superior performance to unencoded inputs for ECG classification in the presence of shift (AUC 0.91 vs 0.62) and rescaling artefacts (AUC 0.91 vs 0.79).
Does Derived Peak (DP) encoding improve the robustness of deep learning models for ECG classification against common artefacts compared to unencoded inputs?
Derived Peak encoding is a simple, non-parametric method that significantly improves the robustness of deep learning-based ECG classification to common artefacts like baseline drift, shift, and rescaling.
Absolute Event Rate: 0.91% vs 0.62%
Common artefacts such as baseline drift, rescaling, and noise critically limit the performance of machine learning-based automated ECG analysis and interpretation. This study proposes Derived Peak (DP) encoding, a non-parametric method that generates signed spikes corresponding to zero crossings of the signal's first and second-order time derivatives. Notably, DP encoding is invariant to shift and scaling artefacts, and its implementation is further simplified by the absence of user-defined parameters. DP encoding was used to encode the 12-lead ECG data from the PTB-XL dataset (n=18,869 participants) and was fed to 1D-ResNet-18 models trained to identify myocardial infarction, conductive deficits and ST-segment abnormalities. Robustness to artefacts was assessed by corrupting ECG data with sinusoidal baseline drift, shift, rescaling and noise, before encoding. The addition of these artefacts resulted in a significant drop in accuracy for seven other methods from prior art, while DP encoding maintained a baseline AUC of 0.88 under drift, shift and rescaling. DP achieved superior performance to unencoded inputs in the presence of shift (AUC under 1 mV shift: 0.91 vs 0.62), and rescaling artefacts (AUC 0.91 vs 0.79). Thus, DP encoding is a simple method by which robustness to common ECG artefacts may be improved for automated ECG analysis and interpretation.
O’Shea et al. (Mon,) conducted a other in ECG classification (n=18,869). Derived Peak (DP) encoding vs. Unencoded inputs and prior art methods was evaluated on Model performance (AUC) under shift and rescaling artefacts. Derived Peak (DP) encoding achieved superior performance to unencoded inputs for ECG classification in the presence of shift (AUC 0.91 vs 0.62) and rescaling artefacts (AUC 0.91 vs 0.79).