Key result
Rlign algorithm boosts shallow models to 93.4% AUC, outperforming CNNs on limited unaligned ECG data.
Why the study?
Deep learning models for ECG analysis require large annotated datasets and have limited explainability, prompting interest in shallow learning methods.
The Rlign algorithm restructures ECG signals to enable shallow machine learning models to achieve CNN-level performance with better explainability and lower data requirements.
May aid interpretable ECG classification with scarce data; leaves open clinical utility and prospective validation.
Aims: Electrocardiogram (ECG) recordings are fundamental for diagnosing cardiac conditions. Recent advances in automatic ECG analysis have been dominated by deep learning, particularly convolutional neural networks (CNNs). CNNs excel in processing high-dimensional signal data, where their ability to automatically extract complex features has enabled significant progress. However, while CNNs are powerful for biomedical signal analysis, their application to ECG data also carries disadvantages, such as the requirement for large annotated datasets and limited explainability. To address these challenges, we aim to reintroduce shallow learning methods, such as linear classifiers, by leveraging the cyclic nature of ECG signals. Methods and results: We developed an adaptive transformation that restructures ECG signals into a fully structured format suitable for shallow learning algorithms. This method aligns R-peaks across all signals in a dataset and resamples the inter-QRS segments to match a predefined reference heart rate. The approach was systematically evaluated across tasks including classification, clustering, and explainability. Our transformation substantially improved the performance of shallow learning techniques. Compared with CNN approaches, shallow models trained on transformed ECGs achieved superior accuracy and interpretability in data-limited scenarios. Conclusion: We demonstrate that shallow machine learning methods, when combined with our alignment-based transformation, can reach CNN level performance in ECG analysis, especially under conditions of limited training data. This approach offers clear advantages in classification, clustering, and explainability and provides an accessible alternative to deep learning. To facilitate adoption and further research, we release a publicly available framework for ECG signal alignment at https://github.com/imi-ms/rlign.
No takes yet. Share an insight, caveat, or question.
Plagwitz et al. (2026) studied Electrocardiogram abnormalities (n=18,869). Rlign algorithm (heart-rate-corrected R-peak alignment) vs. Unaligned raw ECG data and Uni-G median beats was evaluated on Macro-averaged area under the curve (AUC) for classification performance. The Rlign algorithm for heart-rate-corrected R-peak alignment enabled shallow learning models like SVM to achieve a macro AUC of 93.4% in binary classification, outperforming CNNs on unaligned data when training data is limited.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: