Transformer-Based Sleep Staging Using Continuous Photoplethysmography Signals

• Joseph A. P. Quino USP
• Diego A. C. Cardenas USP
• Marcelo A. F. Toledo USP
• Felipe M. Dias USP
• Estela Ribeiro USP
• José E. Krieger USP
• Marco A. Gutierrez USP

DOI: https://doi.org/10.5753/sbcas.2026.21548

Resumo

Sleep disturbances impair health by disrupting the structure of sleep staging. Although polysomnography is the gold standard, its limited availability has driven photoplethysmography (PPG) alternatives. Transformer models have shown strong performance in sleep staging, though mainly with EEG data. In this work, the TransSleepNet is proposed as a hybrid convolutional–transformer architecture that leverages both approaches, along with a flatline detector to identify and manage invalid PPG segments. It achieved Kappa scores of 0.68 (CFS), 0.61 (ABC), and 0.61 (HomePAP). Results show the flatline detector consistently improves performance, while the proposed architecture matches or outperforms baseline models in generalization datasets.

Referências

Attia, S., Hershkovich, R. S., Tabakhov, A., Ang, A., Oksenberg, A., Tauman, R., and Behar, J. A. (2025). SleepPPG-Net2: Deep learning generalization for sleep staging from photoplethysmography. Physiological Measurement, page 23.

Bakker, J. P., Tavakkoli, A., Rueschman, M., Wang, W., Andrews, R., Malhotra, A., Owens, R. L., Anand, A., Dudley, K. A., and Patel, S. R. (2018). Gastric Banding Surgery versus Continuous Positive Airway Pressure for Obstructive Sleep Apnea: A Randomized Controlled Trial. American Journal of Respiratory and Critical Care Medicine, 197(8):1080–1083.

Berry, R. B., Brooks, R., Gamaldo, C., Harding, S. M., Lloyd, R. M., Quan, S. F., Troester, M. T., and Vaughn, B. V. (2017). AASM Scoring Manual Updates for 2017 (Version 2.4). Journal of clinical sleep medicine: JCSM: official publication of the American Academy of Sleep Medicine, 13(5):665–666.

Bishop, C. M. and Bishop, H. (2024). Deep Learning: Foundations and Concepts. Springer International Publishing, Cham, 1 edition.

Byun, J.-H., Kim, K. T., Moon, H.-j., Motamedi, G. K., and Cho, Y. W. (2019). The first night effect during polysomnography, and patients’ estimates of sleep quality. Psychiatry Research, 274:27–29.

Carter, J. F. and Tarassenko, L. (2024). Wav2sleep: A Unified Multi-Modal Approach to Sleep Stage Classification from Physiological Signals.

Chen, X., Wang, R., Zee, P., Lutsey, P. L., Javaheri, S., Alcántara, C., Jackson, C. L., Williams, M. A., and Redline, S. (2015). Racial/Ethnic Differences in Sleep Disturbances: The Multi-Ethnic Study of Atherosclerosis (MESA). Sleep, 38(6):877–888.

Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Elgendi, M. (2012). On the Analysis of Fingertip Photoplethysmogram Signals. Current Cardiology Reviews, 8(1):12.

Elgendi, M. (2021). PPG Signal Analysis; An Introduction Using MATLAB. Taylor & Francis, London, 1 edition.

Gottesman, R. F., Lutsey, P. L., Benveniste, H., Brown, D. L., Full, K. M., Lee, J.-M., Osorio, R. S., Pase, M. P., Redeker, N. S., Redline, S., Spira, A. P., and on behalf of the American Heart Association Stroke Council; Council on Cardiovascular and Stroke Nursing; and Council on Hypertension (2024). Impact of Sleep Disorders and Disturbed Sleep on Brain Health: A Scientific Statement From the American Heart Association. Stroke, 55(3).

Hendrycks, D. and Gimpel, K. (2023). Gaussian Error Linear Units (GELUs).

Kotzen, K., Charlton, P. H., Salabi, S., Amar, L., Landesberg, A., and Behar, J. A. (2023). SleepPPG-Net: A Deep Learning Algorithm for Robust Sleep Staging From Continuous Photoplethysmography. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 27(2):9.

Landis, J. R. and Koch, G. G. (1977). The measurement of observer agreement for categorical data. Biometrics, 33(1):159–174.

Lee, Y. J., Lee, J. Y., Cho, J. H., and Choi, J. H. (2022). Interrater reliability of sleep stage scoring: A meta-analysis. Journal of Clinical Sleep Medicine, 18(1):193–202.

Loshchilov, I. and Hutter, F. (2019). Decoupled Weight Decay Regularization.

Nam, B., Bark, B., Lee, J., and Kim, I. Y. (2024). InsightSleepNet: The interpretable and uncertainty-aware deep learning network for sleep staging using continuous Photoplethysmography. BMC Medical Informatics and Decision Making, 24(1):15.

Panossian, L. A. and Avidan, A. Y. (2009). Review of sleep disorders. The Medical Clinics of North America, 93(2):407–425, ix.

Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., and Chintala, S. (2019). PyTorch: An imperative style, high-performance deep learning library. In Wallach, H., Larochelle, H., Beygelzimer, A., dAlché-Buc, F., Fox, E., and Garnett, R., editors, Advances in Neural Information Processing Systems, volume 32, New York. Curran Associates, Inc.

Phan, H., Mikkelsen, K., Chén, O. Y., Koch, P., Mertins, A., and De Vos, M. (2022). SleepTransformer: Automatic Sleep Staging with Interpretability and Uncertainty Quantification. IEEE Transactions on Biomedical Engineering, 69(8):2456–2467.

Quan, S. F., Howard, B. V., Iber, C., Kiley, J. P., Nieto, F. J., O’Connor, G. T., Rapoport, D. M., Redline, S., Robbins, J., Samet, J. M., and Wahl, P. W. (1997). The Sleep Heart Health Study: Design, rationale, and methods. Sleep, 20(12):1077–1085.

Quino, J. A. P., Cardenas, D. A. C., Toledo, M. A. F., Dias, F. M., Ribeiro, E., Krieger, J. E., and Gutierrez, M. A. (2025). Enhancing Photoplethysmography-Based Sleep Staging Models Through Temporal Context Optimization. In MEDINFO, Studies in Health Technology and Informatics, page 5, Bristol. IOP Publishing.

Redline, S., Tishler, P. V., Tosteson, T. D., Williamson, J., Kump, K., Browner, I., Ferrette, V., and Krejci, P. (1995). The familial aggregation of obstructive sleep apnea. American Journal of Respiratory and Critical Care Medicine, 151(3 Pt 1):682–687.

Rosen, C. L., Auckley, D., Benca, R., Foldvary-Schaefer, N., Iber, C., Kapur, V., Rueschman, M., Zee, P., and Redline, S. (2012). A Multisite Randomized Trial of Portable Sleep Studies and Positive Airway Pressure Autotitration Versus Laboratory-Based Polysomnography for the Diagnosis and Treatment of Obstructive Sleep Apnea: The HomePAP Study. Sleep, 35(6):757–767.

Silva, D. I. C. D., Corrêa, C. D. C., Barros, J. L. D., Marão, A. C., and Weber, S. A. T. (2024). Accessibility to manage the obstructive sleep apnea within the Brazilian Unified Health System. Brazilian Journal of Otorhinolaryngology, 90(1):101338.

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2023). Attention Is All You Need.

Yilmaz, G., Ong, J. L., Ling, L.-H., and Chee, M. W. L. (2023). Insights into vascular physiology from sleep photoplethysmography. Sleep, 46(10):11.

Zhang, G.-Q., Cui, L., Mueller, R., Tao, S., Kim, M., Rueschman, M., Mariani, S., Mobley, D., and Redline, S. (2018). The National Sleep Research Resource: Towards a sleep data commons. Journal of the American Medical Informatics Association, 25(10):1351–1358.