Multi-Task Deep Learning for Joint Heart Rate and Respiratory Rate Estimation from Photoplethysmography
Keywords:
photoplethysmography; heart rate; respiratory rate; multi-task deep learning; wearable sensing; physiological monitoring; signal processing; system designAbstract
Photoplethysmography has become a central modality for noninvasive physiological monitoring because it is inexpensive, easily integrated into wearable devices, and suitable for continuous data acquisition. Estimating heart rate and respiratory rate from a single photoplethysmography stream is attractive for clinical and consumer health applications but remains difficult under motion artifacts, variable tissue perfusion, skin pigmentation differences, sensor placement changes, and pathophysiological diversity. This paper presents a system-level analysis of multi-task deep learning architectures for joint estimation of heart rate and respiratory rate from photoplethysmography. Rather than focusing narrowly on a single algorithm, the discussion examines structural trade-offs among shared feature extractors, task-specific prediction heads, temporal modeling strategies, and signal preprocessing stages. The paper reviews the evolution from classical signal processing and feature engineering to end-to-end learning, emphasizing how shared representations can improve sample efficiency and reduce overfitting when task labels are noisy or incomplete. It further analyzes infrastructure requirements for training and deployment, including data provenance, annotation quality, model monitoring, interpretability, bias mitigation, and regulatory alignment. Key architectural tensions include latency versus accuracy, centralized versus on-device inference, personalization versus generalization, and fairness across heterogeneous populations. The deployment discussion addresses energy consumption, sensor fusion, edge computing, and continuous model updating. Policy implications are considered in relation to clinical validation, patient safety, privacy, and algorithmic accountability. The paper concludes that multi-task deep learning offers a promising unified framework for cardiorespiratory monitoring, but its translational success depends on careful system design, rigorous governance, and robust evaluation beyond aggregate performance metrics.
References
1. Allen, J. (2007). Photoplethysmography and its application in clinical physiological measurement. Physiological Measurement, 28(3), R1–R39. https://doi.org/10.1088/0967-3334/28/3/R01
2. Elgendi, M. (2012). On the analysis of fingertip photoplethysmogram signals. Current Cardiology Reviews, 8(1), 14–25. https://doi.org/10.2174/157340312801215782
3. Zhang, Z., Pi, Z., & Liu, B. (2015). TROIKA: A general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise. IEEE Transactions on Biomedical Engineering, 62(2), 522–531. https://doi.org/10.1109/TBME.2014.2359372
4. Temko, A. (2017). Accurate heart rate monitoring during physical exercises using PPG. IEEE Transactions on Biomedical Engineering, 64(9), 2017–2024. https://doi.org/10.1109/TBME.2017.2676243
5. Biswas, D., Simões-Capela, N., Van Hoof, C., & Van Helleputte, N. (2019). Heart rate estimation from wrist-worn PPG using a lightweight convolutional neural network. Sensors, 19(18), 3870. https://doi.org/10.3390/s19183870
6. Reiss, A., Indlekofer, I., Schmidt, P., & Van Laerhoven, K. (2019). Deep PPG: Large-scale heart rate estimation with convolutional neural networks. Sensors, 19(14), 3079. https://doi.org/10.3390/s19143079
7. Charlton, P. H., Birrenkott, D. A., Bonnici, T., Pimentel, M. A. F., Johnson, A. E. W., Alastruey, J., Tarassenko, L., Watkinson, P. J., Beale, R., & Clifton, D. A (2018). Breathing rate estimation from the electrocardiogram and photoplethysmogram: A review. IEEE Reviews in Biomedical Engineering, 11, 2–20. https://doi.org/10.1109/RBME.2017.2763681
8. Karlen, W., Raman, S., Ansermino, J. M., & Dumont, G. A. (2013). Multiparameter respiratory rate estimation from the photoplethysmogram. IEEE Transactions on Biomedical Engineering, 60(7), 1946–1953. https://doi.org/10.1109/TBME.2013.2246160
9. Hannun, A. Y., Rajpurkar, P., Haghpanahi, M., Tison, G. H., Bourn, C., Turakhia, M. P., & Ng, A. Y. (2019). Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature Medicine, 25(1), 65–69. https://doi.org/10.1038/s41591-018-0268-3
10. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). Association for Computing Machinery. https://doi.org/10.1145/2939672.2939785
11. Zheng, X., Dwyer, V. M., Barrett, L. A., Derakhshani, M., & Hu, S. (2022). Adaptive notch-filtration to effectively recover photoplethysmographic signals during physical activity. Biomedical Signal Processing and Control, 72, 103303.
12. Caruana, R. (1997). Multitask learning. Machine Learning, 28(1), 41–75. https://doi.org/10.1023/A:1007379606734
13. Ruder, S. (2017). An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098.
14. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems 30 (pp. 5998–6008).
15. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
16. Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019). Model cards for model reporting. In Proceedings of the Conference on Fairness, Accountability, and Transparency (pp. 220–229). https://doi.org/10.1145/3287560.3287596
17. Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., Daumé III, H., & Crawford, K. (2021). Datasheets for datasets. Communications of the ACM, 64(12), 86–92. https://doi.org/10.1145/3458723
18. Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., Ourselin, S., Sheller, M., Summers, R. M., Trask, A., Xu, D., Baust, M., & Cardoso, M. J. (2020). The future of digital health with federated learning. npj Digital Medicine, 3, 119. https://doi.org/10.1038/s41746-020-00323-1
19. Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., & Dean, J. (2019). A guide to deep learning in healthcare. Nature Medicine, 25(1), 24–29. https://doi.org/10.1038/s41591-018-0316-z
20. Wiens, J., Saria, S., Sendak, M., Ghassemi, M., Liu, V. X., Doshi-Velez, F., Jung, K., Heller, K., Kale, D., Saeed, M., Ossorio, P. N., Thadaney-Israni, S., & Goldenberg, A. (2019). Do no harm: A roadmap for responsible machine learning for health care. Nature Medicine, 25(9), 1337–1340. https://doi.org/10.1038/s41591-019-0548-6
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Clinical and Translational Medicine
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
