A machine-learning sleep-wake classification model using a reduced number of features derived from photoplethysmography and activity signals

• Douglas A. Almeida USP
• Felipe M. Dias USP
• Marcelo A. F. Toledo USP
• Diego A. C. Cardenas USP
• Filipe A. C. Oliveira USP
• Estela Ribeiro USP
• José E. Krieger USP
• Marco A. Gutierrez USP

DOI: https://doi.org/10.5753/sbcas.2024.1872

Resumo

Sleep is a crucial aspect to overall health, impacting mental and physical well-being. The classification of sleep stages is an important step to assess sleep quality, and Photoplethysmography (PPG) has been demonstrated to be an effective signal for this task. Recent works in this area usually employ complex methods that may be unfeasible to be deployed in wearable devices. In this work, we present a XGBoost model for sleep-wake classification based on features extracted from PPG signal and activity counts. The performance of our method achieved a Sensitivity of 91.15 ± 1.16%, Specificity of 53.66 ± 1.12%, F1-score of 83.88 ± 0.56%, and Kappa of 48.0 ± 0.86%. Our method offers a significant improvement over other approaches as it uses a reduced number of features, making it suitable for implementation in wearable devices that have limited computational power.

Referências

Banfi, T., Valigi, N., di Galante, M., d’Ascanio, P., Ciuti, G., and Faraguna, U. (2021). Efficient embedded sleep wake classification for open-source actigraphy. Scientific reports, 11(1):1–12.

Bishop, S. M. and Ercole, A. (2018). Multi-scale peak and trough detection optimised for periodic and quasi-periodic neuroscience data. In Intracranial Pressure & Neuromonitoring XVI, pages 189–195. Springer.

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.

Costa, T. B. D. S., Dias, F. M., Cardenas, D. A. C., Toledo, M. A. F. D., Lima, D. M. D., Krieger, J. E., and Gutierrez, M. A. (2023). Blood pressure estimation from photoplethysmography by considering intraand inter-subject variabilities: Guidelines for a fair assessment. IEEE Access, 11:57934–57950.

Eyal, S. and Baharav, A. (2017). Sleep insights from the finger tip: How photoplethysmography can help quantify sleep. In 2017 Computing in Cardiology (CinC), pages 1–4.

Fonseca, P., Weysen, T., Goelema, M. S., Møst, E. I., Radha, M., Lunsingh Scheurleer, C., van den Heuvel, L., and Aarts, R. M. (2017). Validation of Photoplethysmography-Based Sleep Staging Compared With Polysomnography in Healthy Middle-Aged Adults. Sleep, 40(7):zsx097.

Habib, A., Motin, M. A., Penzel, T., Palaniswami, M., Yearwood, J., and Karmakar, C. (2023). Performance of a convolutional neural network derived from ppg signal in classifying sleep stages. IEEE Transactions on Biomedical Engineering, 70(6):1717–1728.

Knutson, K. L. and Van Cauter, E. (2008). Associations between sleep loss and increased risk of obesity and diabetes. Annals of the New York Academy of Sciences, 1129(1):287–304.

Kotzen, K., Charlton, P. H., Salabi, S., Amar, L., Landesberg, A., and Behar, J. A. (2022). Sleepppg-net: a deep learning algorithm for robust sleep staging from continuous photoplethysmography. IEEE Journal of Biomedical and Health Informatics.

Krystal, A. D. and Edinger, J. D. (2008). Measuring sleep quality. Sleep Medicine, 9:S10–S17. The Art of Good Sleep Proceedings from the 5th International Sleep Disorders Forum: Novel Outcome Measures of Sleep, Sleep Loss and Insomnia.

Mejía-Mejía, E., Allen, J., Budidha, K., El-Hajj, C., Kyriacou, P. A., and Charlton, P. H. (2022). 4 photoplethysmography signal processing and synthesis. In Allen, J. and Kyriacou, P., editors, Photoplethysmography, pages 69–146. Academic Press.

Motin, M. A., Karmakar, C., Palaniswami, M., and Penzel, T. (2020). Photoplethysmographic-based automated sleep–wake classification using a support vector machine. Physiol. Meas., 41:075013.

Motin, M. A., Karmakar, C., Palaniswami, M., Penzel, T., and Kumar, D. (2023). Multi-stage sleep classification using photoplethysmographic sensor. Royal Society Open Science, 10(4):221517.

Motin, M. A., Karmakar, C. K., Penzel, T., and Palaniswami, M. (2019). Sleep-wake classification using statistical features extracted from photoplethysmographic signals. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 5564–5567. IEEE.

Palotti, J., Mall, R., Aupetit, M., Rueschman, M., Singh, M., Sathyanarayana, A., Taheri, S., and Fernandez-Luque, L. (2019). Benchmark on a large cohort for sleep-wake classification with machine learning techniques. NPJ digital medicine, 2(1):1–9.

Ramar, K., Malhotra, R. K., Carden, K. A., Martin, J. L., Abbasi-Feinberg, F., Aurora, R. N., Kapur, V. K., Olson, E. J., Rosen, C. L., Rowley, J. A., et al. (2021). Sleep is essential to health: an american academy of sleep medicine position statement. Journal of Clinical Sleep Medicine, 17(10):2115–2119.

Shrivastava, D., Jung, S., Saadat, M., Sirohi, R., and Crewson, K. (2014). How to interpret the results of a sleep study. Journal of community hospital internal medicine perspectives, 4(5):24983.

Silvani, A. (2008). Physiological sleep-dependent changes in arterial blood pressure: Central autonomic commands and baroreflex control. Clinical and Experimental Pharmacology and Physiology, 35(9):987–994.

Stein, P. K. and Pu, Y. (2012). Heart rate variability, sleep and sleep disorders. Sleep Medicine Reviews, 16(1):47–66.

Uçar, M. K., Bozkurt, M. R., Bilgin, C., and Polat, K. (2018). Automatic sleep staging in obstructive sleep apnea patients using photoplethysmography, heart rate variability signal and machine learning techniques. Neural Computing and Applications, 29:1–16.