Citation :

Amit M. Sahu, Jayant P. Mehare, "DRW-CNN: A Dilated Residual Wavelet CNN for ECG-based Severe Heart Failure Screening," International Journal of Electrical and Electronics Engineering, vol. 13, no. 9, pp. 66-84, 2026. Crossref, https://doi.org/10.14445/23488379/IJEEE-V13I9P106

Abstract

Electrocardiogram (ECG)-based heart-failure screening requires clinically valid labels, record-independent evaluation, and uncertainty analysis at the level of independent records. This study evaluates a Dilated Residual Wavelet Convolutional Neural Network (DRW-CNN) for discrimination of clinically confirmed severe Congestive Heart Failure (CHF) from normal sinus rhythm. The primary cohort comprises all 15 available BIDMC CHF records and 18 MIT-BIH Normal Sinus Rhythm Database records. Records are partitioned before segmentation, yielding 528 training, 96 validation, and 168 held-out test segments from mutually exclusive records. The network applies level-4 Daubechies-4 wavelet denoising, z-score normalization, residual blocks with dilation factors 1, 2, and 4, global average pooling, and sigmoid classification. Class-weighted binary cross-entropy addresses imbalance without deleting independent records. At the prespecified threshold of 0.5, held-out predictions achieve 95.238% accuracy, 95.833% sensitivity, 94.792% specificity, 93.243% precision, 94.521% F1-score, MCC 0.903, ROC-AUC 0.988, and average precision 0.989. Record-cluster bootstrap intervals, calibration, threshold sensitivity, record-level aggregation, leave-one-record-out stability, and auxiliary non-HF domain-shift stress analyses are also reported. The study provides a leakage-resistant severe-CHF screening evaluation that separates disease-specific evidence from auxiliary abnormality testing and quantifies uncertainty at record level.

Keywords

Biomedical signal processing, Class-weighted learning, Domain shift, Patient-independent validation, Precision-recall analysis.

References

1. Muhammad Shahzeb Khan et al., “Global Epidemiology of Heart Failure,” Nature Reviews Cardiology, vol. 21, no. 10, pp. 717-734, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Gianluigi Savarese, and Lars H. Lund, “Global Public Health Burden of Heart Failure,” Cardiac Failure Review, vol. 3, no. 1, pp. 7-11, 2017.
   [CrossRef] [Google Scholar] [Publisher Link]
3. PhysioNet, BIDMC Congestive Heart Failure Database, PhysioNet, 2000.
   [CrossRef] [Publisher Link]
4. Ary L. Goldberger et al., “PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals,” Circulation, vol. 101, no. 23, pp. e215-e220, 2000.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Matthias Unterhuber et al., “Deep Learning Detects Heart Failure with Preserved Ejection Fraction using a Baseline Electrocardiogram,” European Heart Journal-Digital Health, vol. 2, no. 4, pp. 699-703, 2021.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Zheng Gao et al., “Electrocardiograph Analysis for Risk Assessment of Heart Failure with Preserved Ejection Fraction: A Deep Learning Model,” ESC Heart Failure, vol. 12, no. 1, pp. 631-639, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Patrik Bachtiger et al., “Point-of-Care Screening for Heart Failure with Reduced Ejection Fraction using Artificial Intelligence During ECG-Enabled Stethoscope Examination in London, UK: A Prospective, Observational, Multicentre Study,” The Lancet Digital Health, vol. 4, no. 2, pp. E117-E125, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Lovedeep S. Dhingra et al., “Heart Failure Risk Stratification using Artificial Intelligence Applied to Electrocardiogram Images: A Multinational Study,” European Heart Journal, vol. 46, no. 11, pp. 1044-1053, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Lovedeep S. Dhingra et al., “Artificial Intelligence-Enabled Prediction of Heart Failure Risk from Single-Lead Electrocardiograms,” JAMA Cardiology, vol. 10, no. 6, pp. 574-584, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Awni Y. Hannun et al., “Cardiologist-Level Arrhythmia Detection and Classification in Ambulatory Electrocardiograms using a Deep Neural Network,” Nature Medicine, vol. 25, no. 1, pp. 65-69, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Antônio H. Ribeiro et al., “Automatic Diagnosis of the 12-Lead ECG using a Deep Neural Network,” Nature Communications, vol. 11, no. 1, pp. 1-9, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Marek Malik et al., “Heart Rate Variability: Standards of Measurement, Physiological Interpretation, and Clinical use,” European Heart Journal, vol. 17, no. 3, pp. 354-381, 1996.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Suzhao Bi et al., “Accurate Arrhythmia Classification with Multi-Branch, Multi-Head Attention Temporal Convolutional Networks,” Sensors, vol. 24, no. 24, pp. 1-21, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Huawei Jiang et al., “ECG-Mamba: Cardiac Abnormality Classification with Non-Uniform-Mix Augmentation on 12-Lead ECGs,” IEEE Journal of Translational Engineering in Health and Medicine, vol. 13, pp. 461-470, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Yupeng Qiang et al., “ECGMamba: Towards ECG Classification with State Space Models,” 2024 IEEE International Conference on Bioinformatics and Biomedicine, Lisbon, Portugal, pp. 6498-6505, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Alexey Dosovitskiy et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” arXiv preprint arXiv, pp. 1-22, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Albert Gu, and Tri Dao, “Mamba: Linear-Time Sequence Modeling with Selective State Spaces,” arXiv preprint arXiv, pp. 1-36, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Ashish Vaswani et al., “Attention is All you Need,” Advances in Neural Information Processing Systems, vol. 30, 2017.
    [Google Scholar] [Publisher Link]
19. Shaojie Bai, J. Zico Kolter, and Vladlen Koltun, “An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling,” arXiv preprint arXiv, pp. 1-14, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Kaiming He et al., “Deep Residual Learning for Image Recognition,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
    [Google Scholar] [Publisher Link]
21. Paul S. Addison, “Wavelet Transforms and the ECG: A Review,” Physiological Measurement, vol. 26, no. 5, pp. R155-R199, 2005.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Stéphane G. Mallat, “A Theory for Multiresolution Signal Decomposition: The Wavelet Representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 7, pp. 674-693, 1989.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Changfang Chen et al., “Wavelet-Domain Group-Sparse Denoising Method for ECG Signals,” Biomedical Signal Processing and Control, vol. 83, pp. 1-10, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Takaya Saito, and Marc Rehmsmeier, “The Precision-Recall Plot is More Informative than the ROC Plot when Evaluating Binary Classifiers on Imbalanced Datasets,” PLoS One, vol. 10, no. 3, pp. 1-21, 2015.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Tom Fawcett, “An Introduction to ROC Analysis,” Pattern Recognition Letters, vol. 27, no. 8, pp. 861-874, 2006.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Diederik P. Kingma, and Jimmy Ba, “Adam: A Method for Stochastic Optimization,” arXiv preprint arXiv, pp. 1-15, 2015.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Matthew B.A. McDermott et al., “Reproducibility in Machine Learning for Health Research: Still a Ways to Go,” Science Translational Medicine, vol. 13, no. 586, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
28. Kuba Weimann, and Tim O.F. Conrad, “Transfer Learning for ECG Classification,” Scientific Reports, vol. 11, no. 1, pp. 1-12, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
29. Arthur Gretton et al., “A Kernel Two-Sample Test,” Journal of Machine Learning Research, vol. 13, no. 25, pp. 723-773, 2012.
    [Google Scholar] [Publisher Link]
30. George B. Moody, W.E. Muldrow, and G. Mark Roger, “A Noise Stress Test for Arrhythmia Detectors,” Computers in Cardiology, vol. 11, no. 3, pp. 381-384, 1984.
    [Google Scholar]
31. Patrick Wagner et al., “PTB-XL, A Large Publicly Available Electrocardiography Dataset,” Scientific Data, vol. 7, no. 1, pp. 1-15, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
32. Jianwei Zheng et al., “A 12-Lead Electrocardiogram Database for Arrhythmia Research Covering More than 10,000 Patients,” Scientific Data, vol. 7, no. 1, pp. 1-8, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
33. George B. Moody, and Roger G. Mark, “The impact of the MIT-BIH Arrhythmia Database,” IEEE Engineering in Medicine and Biology Magazine, vol. 20, no. 3, pp. 45-50, 2001.
    [CrossRef] [Google Scholar] [Publisher Link]
34. D.G. Altman, and J.M. Bland, “Diagnostic Tests 1: Sensitivity and Specificity,” British Medical Journal, vol. 308, no. 6943, 1994.
    [CrossRef] [Google Scholar] [Publisher Link]
35. Glenn W. Brier, “Verification of Forecasts Expressed in Terms of Probability,” Monthly Weather Review, vol. 78, no. 1, pp. 1-3, 1950.
    [CrossRef] [Google Scholar] [Publisher Link]
36. Ibrahim Karabayir et al., “ECG-based Artificial Intelligence for Classifying Left Ventricular Dysfunction and Heart Failure with Preserved Ejection Fraction,” Journal of the American Heart Association, vol. 15, no. 15, pp. 1-11, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
37. Enhan Liu et al., “A Teacher-Student Deep Learning Framework for Enhanced Clinical Screening of Heart Failure from 12-Lead Electrocardiograms,” Physiological Measurement, vol. 47, no. 5, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
38. Akshay S. Desai et al., “Predicting Heart Failure from 12-Lead ECGs using AI: A HeartShare/AMP-HF Pooled Cohort Analysis,” Journal of the American College of Cardiology, vol. 87, no. 8, pp. 990-1005, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
39. Lovedeep S Dhingra et al., “Artificial Intelligence-enhanced Electrocardiography for Heart Failure Screening and Risk Stratification,” Current Heart Failure Reports, vol. 23, no. 1, pp. 1-16, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]