ECGWavePuzzle as Morphology-Aware Auxiliary Supervision for Multitask Arrhythmia Classification

• Guilherme Silva UFOP
• Arthur Negrão UFOP
• Pedro Silva UFOP
• Eduardo Luz UFOP

DOI: https://doi.org/10.5753/sbcas.2026.21399

Abstract

Arrhythmia detection with deep learning often relies on heavy preprocessing and synthetic oversampling, obscuring whether models truly learn cardiac patterns. We propose a multitask self-supervised framework that jointly optimizes arrhythmia classification, RR-interval regression, and the ECGWavePuzzle pretext task. This design encourages the model to capture both temporal rhythm and intra-beat morphology directly from raw ECG signals. Evaluated on MIT-BIH, PTB-XL, and IEGM, the approach improves stability and predictive performance over single-task baselines without synthetic data generation. Our results suggest that physiologically grounded auxiliary objectives provide a more principled path to robust ECG representation learning.

References

ANSI/AAMI (2008). Testing and reporting performance results of cardiac rhythm and ST segment measurement algorithms. American National Standards Institute, Inc. (ANSI), Association for the Advancement of Medical Instrumentation (AAMI). ANSI/AAMI/ISO EC57, 1998-(R)2008.

Caruana, R. (1997). Multitask learning. Machine learning, 28(1):41–75.

Chen, M., Li, Y., Zhang, L., Zhang, X., Gao, J., Sun, Y., Shi, W., and Wei, S. (2024a). Multitask learning-based quality assessment and denoising of electrocardiogram signals. IEEE Transactions on Instrumentation and Measurement, 73:1–13.

Chen, Z., Yang, D., Cui, T., Li, D., Liu, H., Yang, Y., Zhang, S., Yang, S., and Ren, T.-L. (2024b). A novel imbalanced dataset mitigation method and ecg classification model based on combined 1d cbam-autoencoder and lightweight cnn model. Biomedical Signal Processing and Control, 87:105437.

Cohen, A. (2019). Biomedical Signal Processing: Volume 2: Compression and Automatic Recognition. CRC press.

De Chazal, P., O’Dwyer, M., and Reilly, R. B. (2004). Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE transactions on biomedical engineering, 51(7):1196–1206. Publisher: IEEE.

Fernández, A., Garcia, S., Herrera, F., and Chawla, N. V. (2018). Smote for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. Journal of artificial intelligence research, 61:863–905.

Geng, Q., Liu, H., Gao, T., Liu, R., Chen, C., Zhu, Q., and Shu, M. (2023). An ecg classification method based on multi-task learning and cot attention mechanism. In Healthcare, volume 11, page 1000. MDPI.

Hannun, A. Y., Rajpurkar, P., Haghpanahi, M., Tison, G. H., Bourn, C., Turakhia, M. P., and Ng, A. Y. (2019). Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature medicine, 25(1):65.

Jia, Z., Li, D., Liu, C., Liao, L., Xu, X., Ping, L., and Shi, Y. (2023). Tinyml design contest for life-threatening ventricular arrhythmia detection. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 43(1):127–140.

Lin, C.-H., Liu, Z.-Y., Chu, P.-H., Chen, J.-S., Wu, H.-H., Wen, M.-S., Kuo, C.-F., and Chang, T.-Y. (2025). A multitask deep learning model utilizing electrocardiograms for major cardiovascular adverse events prediction. npj Digital Medicine, 8(1):1.

Luz, E. J. d. S., Schwartz, W. R., Cámara-Chávez, G., and Menotti, D. (2016). Ecg-based heartbeat classification for arrhythmia detection: A survey. Computer methods and programs in biomedicine, 127:144–164.

Moody, G. B. and Mark, R. G. (2001). The impact of the MIT-BIH arrhythmia database. IEEE Engineering in Medicine and Biology Magazine, 20(3):45–50. Publisher: IEEE.

Shen, C., Chen, C., and Zhang, M. (2024). Vanet: A solution for ventricular arrhythmias detection of iegm on embedded devices. IEEE Embedded Systems Letters, 17(3):176–179.

Silva, G., Negrão, A., Moreira, G., Luz, E., and Silva, P. (2024a). An embedding multitask neural network for efficient arrhythmia detection. In Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 412–423. SBC.

Silva, G., Silva, P., Moreira, G., Freitas, V., Gertrudes, J., and Luz, E. (2025). A systematic review of ecg arrhythmia classification: Adherence to standards, fair evaluation, and embedded feasibility. arXiv preprint arXiv:2503.07276.

Silva, G., Silva, P., Moreira, G., and Luz, E. (2024b). Bridging the gap in ecg classification: Integrating self-supervised learning with human-in-the-loop amid medical equipment hardware constraints. In International Symposium on Applied Reconfigurable Computing, pages 63–74. Springer.

Singular Medical Technologies Inc. (2023). Iegm dataset. [link]. Accessed: 2023-05-01.

Strodthoff, N., Wagner, P., Schaeffter, T., and Samek, W. (2020). Deep learning for ecg analysis: Benchmarks and insights from ptb-xl. IEEE journal of biomedical and health informatics, 25(5):1519–1528.

Wagner, P., Strodthoff, N., Bousseljot, R.-D., Kreiseler, D., Lunze, F. I., Samek, W., and Schaeffter, T. (2020). Ptb-xl, a large publicly available electrocardiography dataset. Scientific data, 7(1):154.

WHO (2021). Cardiovascular diseases (cvds). [link].