Multi-Label Health State Retrieval from Wearable Biosignals Through Statistical-Prior Guided Representation Learning and Deep Hash Encoding
Keywords:
wearable biosignals, multi-label retrieval, representation learning, deep hashing, statistical priors, fairness, health informaticsAbstract
The proliferation of wearable devices capable of continuously capturing photoplethysmography, electrocardiography, and other biosignals has created an urgent need for systems that can retrieve comprehensive health states from exponentially growing data streams. This paper presents a system-level investigation of multi-label health state retrieval that couples statistical-prior guided representation learning with deep hash encoding to achieve efficient and clinically meaningful search across large-scale biosignal repositories. The architecture is designed around a dual objective: first, a foundation modeling backbone integrates physiological and distributional priors to learn robust, generalizable signal representations that remain invariant to sensor noise, inter-individual variability, and temporal dynamics; second, a deep hashing module maps these representations into compact binary codes that support sublinear retrieval while preserving fine-grained semantic relationships, including comorbidity patterns and simultaneous physiological conditions. We discuss the structural trade-offs inherent in balancing code length, retrieval recall, and energy consumption, and analyze infrastructure choices spanning on-device inference, edge-cloud coordination, and federated learning for privacy-preserving model updates. Considerable attention is devoted to fairness, bias amplification across demographic and skin-tone groups, and the governance implications of deploying retrieval-driven decision support in regulated healthcare ecosystems. Through cross-domain comparisons with image and text retrieval, we highlight unique challenges such as physiological concept drift, multi-label granularity, and the interpretability of hash-based similarity. The discussion culminates in a forward-looking perspective on sustainable deployment, clinical validation pathways, and the alignment of multi-label retrieval systems with evolving regulatory frameworks.
References
1. 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
2. Liang, Y., Chen, Z., Liu, G., & Elgendi, M. (2018). A new, short-recorded photoplethysmogram dataset for blood pressure monitoring in China. Scientific Data, 5, 180020. https://doi.org/10.1038/sdata.2018.20
3. Ribeiro, A. H., Ribeiro, M. H., Paixão, G. M., Oliveira, D. M., Gomes, P. R., Canazart, J. A., ... & Ribeiro, A. L. P. (2020). Automatic diagnosis of the 12-lead ECG using a deep neural network. Nature Communications, 11, 1760. https://doi.org/10.1038/s41467-020-15432-4
4. Kiyasseh, D., Zhu, T., & Clifton, D. A. (2021). CLOCS: Contrastive learning of cardiac signals across space, time, and patients. In Proceedings of the 38th International Conference on Machine Learning (pp. 5607–5618). PMLR.
5. Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M. (2023). TimesNet: Temporal 2D-variation modeling for general time series analysis. In International Conference on Learning Representations.
6. Sarkar, P., & Etemad, A. (2020). Self-supervised ECG representation learning for emotion recognition. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 1234–1238). IEEE.
7. Zhu, H., Long, M., Wang, J., & Cao, Y. (2016). Deep hashing network for efficient similarity retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence (pp. 2415–2421).
8. Liu, W., Wang, J., Ji, R., Jiang, Y. G., & Chang, S. F. (2012). Supervised hashing with kernels. In 2012 IEEE Conference on Computer Vision and Pattern Recognition (pp. 2074–2081). IEEE.
9. Chen, Y., Lai, Z., Ding, Y., Lin, K., & Wong, W. K. (2020). Deep supervised hashing with anchor graph for large-scale image retrieval. IEEE Transactions on Image Processing, 29, 179–194. https://doi.org/10.1109/TIP.2019.2927632
10. Rajkomar, A., Hardt, M., Howell, M. D., Corrado, G., & Chin, M. H. (2018). Ensuring fairness in machine learning to advance health equity. Annals of Internal Medicine, 169(12), 866–872. https://doi.org/10.7326/M18-1990
11. Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., ... & 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
12. Wan, J., Al-awlaqi, M., Li, M., O’Grady, M., Gu, X., Wang, J., & Cao, N. (2018). Wearable IoT enabled real-time health monitoring system. IEEE Access, 6, 4248–4258. https://doi.org/10.1109/ACCESS.2017.2788297
13. He, J., Baxter, S. L., Xu, J., Xu, J., Zhou, X., & Zhang, K. (2019). The practical implementation of artificial intelligence technologies in medicine. Nature Medicine, 25(1), 30–36. https://doi.org/10.1038/s41591-018-0307-0
14. Guo, Z., Chen, T., Jiao, Y., Pan, Y., Hu, X., & Ferrario, M. (2026). SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model. arXiv preprint arXiv:2601.21031.
15. Yu, Z., Wu, S., Dou, Z., & Bakker, E. M. (2022). Deep hashing with self-supervised asymmetric semantic excavation and margin-scalable constraint. Neurocomputing, 483, 87-104.
16. Guan, Y., & Plötz, T. (2017). Ensembles of deep LSTM learners for activity recognition using wearables. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 1(2), 28. https://doi.org/10.1145/3090076
17. Han, S., Mao, H., & Dally, W. J. (2016). Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. In International Conference on Learning Representations.
18. Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), 50–60. https://doi.org/10.1109/MSP.2020.2975749
19. Schmidt, P., Reiss, A., Dürichen, R., & Laerhoven, K. V. (2018). Introducing WeSAD, a multimodal dataset for wearable stress and affect detection. In Proceedings of the 20th ACM International Conference on Multimodal Interaction (pp. 400–408). ACM.
20. Tison, G. H., Sanchez, J. M., Ballinger, B., Singh, A., Olgin, J. E., Pletcher, M. J., ... & Marcus, G. M. (2019). Passive detection of atrial fibrillation using a commercially available smartwatch. JAMA Cardiology, 4(6), 610–617. https://doi.org/10.1001/jamacardio.2019.1329
21. Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017). A survey on mobile edge computing: The communication perspective. IEEE Communications Surveys & Tutorials, 19(3), 1622–1657. https://doi.org/10.1109/COMST.2017.2702372
22. Liang, Z., Chapa-Martell, M., & Cakmak, A. (2021). An FHIR-based framework for integrating wearable sensor data into electronic health records. JMIR Medical Informatics, 9(1), e23399. https://doi.org/10.2196/23399
23. Sjoding, M. W., Dickson, R. P., Iwashyna, T. J., Gay, S. E., & Valley, T. S. (2020). Racial bias in pulse oximetry measurement. New England Journal of Medicine, 383, 2477–2478. https://doi.org/10.1056/NEJMc2029240
24. Yue, Y., Khanal, A., Lyu, T., Weissman, S., & Liang, C. (2025, May). EHR Phenotyping Methods for Measuring Treatment Adherence Among People Living With HIV in All of Us: Towards Disparities and Inequalities in HIV Care Continuum. In AMIA Annual Symposium Proceedings (Vol. 2024, p. 1294).
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.
