Papers
Topics
Authors
Recent
2000 character limit reached

Unsupervised Machine Learning Identifies Latent Ultradian States in Multi-Modal Wearable Sensor Signals (2405.03829v1)

Published 6 May 2024 in q-bio.NC

Abstract: Wearable sensors such as smartwatches have become ubiquitous in recent years, allowing the easy and continual measurement of physiological parameters such as heart rate, physical activity, body temperature, and blood glucose in an every-day setting. This multi-modal data offers the potential to identify latent states occurring across physiological measures, which may represent important bio-behavioural states that could not be observed in any single measure. Here we present an approach, utilising a hidden semi-Markov model, to identify such states in data collected using a smartwatch, electrocardiogram, and blood glucose monitor, over two weeks from a sample of 9 participants. We found 26 latent ultradian states across the sample, with many occurring at particular times of day. Here we describe some of these, as well as their association with subjective mood and time use diaries. These methods provide a novel avenue for developing insights into the physiology of everyday life.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. S. Upasham, N. K. M. Churcher, P. Rice, and S. Prasad, “Sweating out the circadian rhythm: A technical review,” ACS Sensors, vol. 6, pp. 659–672, 3 2021.
  2. N. Meyer, A. G. Harvey, S. W. Lockley, and D. J. Dijk, “Circadian rhythms and disorders of the timing of sleep,” The Lancet, vol. 400, pp. 1061–1078, 9 2022.
  3. M. Garcia-Constantino, A. Konios, M. A. Mustafa, C. Nugent, and G. Morrison, “Ambient and wearable sensor fusion for abnormal behaviour detection in activities of daily living,” in 2020 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops).   IEEE, 3 2020, pp. 1–6.
  4. N. Kolehmainen, C. Thornton, O. Craw, M. Pearce, L. Kudlek, K. Nazarpour, L. Cutler, E. V. Sluijs, and T. Rapley, “Physical activity in young children across developmental and health states: the activechild study,” eClinicalMedicine, vol. 60, 2023.
  5. T. G. Stavropoulos, G. Meditskos, I. Lazarou, L. Mpaltadoros, S. Papagiannopoulos, M. Tsolaki, and I. Kompatsiaris, “Detection of health-related events and behaviours from wearable sensor lifestyle data using symbolic intelligence: A proof-of-concept application in the care of multiple sclerosis,” Sensors, vol. 21, p. 6230, 9 2021.
  6. O. Perski, J. Keller, D. Kale, B. Y.-A. Asare, V. Schneider, D. Powell, F. Naughton, G. ten Hoor, P. Verboon, and D. Kwasnicka, “Understanding health behaviours in context: A systematic review and meta-analysis of ecological momentary assessment studies of five key health behaviours,” Health Psychology Review, vol. 16, pp. 576–601, 10 2022.
  7. Z. Zhang, P. M. Amegbor, and C. E. Sabel, “Assessing the current integration of multiple personalised wearable sensors for environment and health monitoring,” Sensors, vol. 21, p. 7693, 11 2021.
  8. A. Sano, S. Taylor, A. W. McHill, A. J. Phillips, L. K. Barger, E. Klerman, and R. Picard, “Identifying objective physiological markers and modifiable behaviors for self-reported stress and mental health status using wearable sensors and mobile phones: Observational study,” Journal of Medical Internet Research, vol. 20, p. e210, 6 2018.
  9. P. Schmidt, A. Reiss, R. Dürichen, and K. V. Laerhoven, “Wearable-based affect recognition—a review,” Sensors 2019, Vol. 19, Page 4079, vol. 19, p. 4079, 9 2019.
  10. J. Marín-Morales, J. L. Higuera-Trujillo, A. Greco, J. Guixeres, C. Llinares, E. P. Scilingo, M. Alcañiz, and G. Valenza, “Affective computing in virtual reality: emotion recognition from brain and heartbeat dynamics using wearable sensors,” Scientific Reports 2018 8:1, vol. 8, pp. 1–15, 9 2018.
  11. S. Gedam and S. Paul, “A review on mental stress detection using wearable sensors and machine learning techniques,” IEEE Access, vol. 9, pp. 84 045–84 066, 2021.
  12. K. Kyriakou, B. Resch, G. Sagl, A. Petutschnig, C. Werner, D. Niederseer, M. Liedlgruber, F. Wilhelm, T. Osborne, and J. Pykett, “Detecting moments of stress from measurements of wearable physiological sensors,” Sensors, vol. 19, p. 3805, 9 2019.
  13. S. Cui, Q. Lin, Y. Gui, Y. Zhang, H. Lu, H. Zhao, X. Wang, X. Li, and F. Jiang, “Care as a wearable derived feature linking circadian amplitude to human cognitive functions,” npj Digital Medicine 2023 6:1, vol. 6, pp. 1–11, 7 2023.
  14. M. Sevil, M. Rashid, I. Hajizadeh, M. Park, L. Quinn, and A. Cinar, “Physical activity and psychological stress detection and assessment of their effects on glucose concentration predictions in diabetes management.” IEEE transactions on bio-medical engineering, vol. 68, pp. 2251–2260, 7 2021.
  15. S. Ghiasi, A. Greco, R. Barbieri, E. P. Scilingo, and G. Valenza, “Assessing autonomic function from electrodermal activity and heart rate variability during cold-pressor test and emotional challenge.” Scientific reports, vol. 10, p. 5406, 3 2020.
  16. G. Goh, S. Maloney, P. Mark, and D. Blache, “Episodic ultradian events—ultradian rhythms,” Biology, vol. 8, p. 15, 3 2019.
  17. G. Russell and S. Lightman, “The human stress response.” Nature reviews. Endocrinology, vol. 15, pp. 525–534, 9 2019.
  18. C. Cajochen, C. F. Reichert, M. Münch, V. Gabel, O. Stefani, S. L. Chellappa, and C. Schmidt, “Ultradian sleep cycles: Frequency, duration, and associations with individual and environmental factors—a retrospective study,” Sleep Health, vol. 10, pp. S52–S62, 2 2024.
  19. S. Ruiz-Suarez, V. Leos-Barajas, and J. M. Morales, “Hidden markov and semi-markov models: When and why are these models useful for classifying states in time series data?” Journal of Agricultural, Biological, and Environmental Statistics, vol. 27, pp. 339–363, 5 2021.
  20. R. Langrock and W. Zucchini, “Hidden markov models with arbitrary state dwell-time distributions,” Computational Statistics and Data Analysis, vol. 55, pp. 715–724, 1 2011.
  21. J. Bulla and I. Bulla, “Stylized facts of financial time series and hidden semi-markov models,” Computational Statistics and Data Analysis, vol. 51, pp. 2192–2209, 12 2006.
  22. C. B. Thornton, N. Kolehmainen, and K. Nazarpour, “Using unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly changing population,” PLOS Digital Health, vol. 2, p. e0000220, 4 2023.
  23. D. V. Kuppevelt, J. Heywood, M. Hamer, S. Sabia, E. Fitzsimons, and V. V. Hees, “Segmenting accelerometer data from daily life with unsupervised machine learning,” PLoS ONE, vol. 14, pp. 1–19, 2019.
  24. Y. Yao, Y. Cao, J. Zhai, J. Liu, M. Xiang, and L. Wang, “Latent state recognition by an enhanced hidden markov model,” Expert Systems with Applications, vol. 161, p. 113722, 12 2020.
  25. G. Gerboni, G. Comunale, W. Chen, J. L. Taylor, M. Migliorini, R. Picard, M. Cruz, and G. Regalia, “Prospective clinical validation of the empatica embraceplus wristband as a reflective pulse oximeter,” Frontiers in Digital Health, vol. 5, 2023.
  26. M. J. Fokkert, P. R. V. Dijk, M. A. Edens, S. Abbes, D. D. Jong, R. J. Slingerland, and H. J. Bilo, “Performance of the freestyle libre flash glucose monitoring system in patients with type 1 and 2 diabetes mellitus,” BMJ Open Diabetes Research and Care, vol. 5, p. e000320, 2 2017.
  27. “Bittium faros manual,” 2019.
  28. F. Shaffer and J. P. Ginsberg, “An overview of heart rate variability metrics and norms,” Frontiers in Public Health, vol. 5, p. 258, 9 2017.
  29. M. Johnson, “pyhsmm.” [Online]. Available: https://github.com/mattjj/pyhsmm
  30. M. J. Johnson and A. S. Willsky, “Bayesian nonparametric hidden semi-markov models,” Journal of Machine Learning Research, vol. 14, pp. 673–701, 2013.
  31. “Avicenna research.” [Online]. Available: www.avicennaresearch.com
  32. E. Kańtoch, “Human activity recognition for physical rehabilitation using wearable sensors fusion and artificial neural networks,” Computing in Cardiology, vol. 44, pp. 1–4, 2017.
  33. T. Duong, D. Phung, H. Bui, and S. Venkatesh, “Efficient duration and hierarchical modeling for human activity recognition,” Artificial Intelligence, vol. 173, pp. 830–856, 5 2009.
  34. R. Fossion, A. L. Rivera, J. C. Toledo-Roy, J. Ellis, and M. Angelova, “Multiscale adaptive analysis of circadian rhythms and intradaily variability: Application to actigraphy time series in acute insomnia subjects,” PLOS ONE, vol. 12, p. e0181762, 7 2017.
  35. G. Cornelissen and K. Otsuka, “Chronobiology of aging: A mini-review,” Gerontology, vol. 63, pp. 118–128, 2 2017.
  36. W. J. Cheng, S. Puttonen, P. Vanttola, A. Koskinen, M. Kivimäki, and M. Härmä, “Association of shift work with mood disorders and sleep problems according to chronotype: a 17-year cohort study,” Chronobiology International, vol. 38, pp. 518–525, 4 2021.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now

Whiteboard

Video Overview

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Tweets

Sign up for free to view the 1 tweet with 2 likes about this paper.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up for Free