Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A State-of-the-Art Review of Computational Models for Analyzing Longitudinal Wearable Sensor Data in Healthcare (2407.21665v1)

Published 31 Jul 2024 in cs.HC and cs.LG

Abstract: Wearable devices are increasingly used as tools for biomedical research, as the continuous stream of behavioral and physiological data they collect can provide insights about our health in everyday contexts. Long-term tracking, defined in the timescale of months of year, can provide insights of patterns and changes as indicators of health changes. These insights can make medicine and healthcare more predictive, preventive, personalized, and participative (The 4P's). However, the challenges in modeling, understanding and processing longitudinal data are a significant barrier to their adoption in research studies and clinical settings. In this paper, we review and discuss three models used to make sense of longitudinal data: routines, rhythms and stability metrics. We present the challenges associated with the processing and analysis of longitudinal wearable sensor data, with a special focus on how to handle the different temporal dynamics at various granularities. We then discuss current limitations and identify directions for future work. This review is essential to the advancement of computational modeling and analysis of longitudinal sensor data for pervasive healthcare.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (90)
  1. A call for open data to develop mental health digital biomarkers. BJPsych Open, 8, 3 2022.
  2. Quantifying daily rhythms with non-negative matrix factorization applied to mobile phone data. Scientific Reports, 12(1):5544, Apr 2022.
  3. A survey of methods for time series change point detection. Knowl. Inf. Syst., 51(2):339–367, May 2017.
  4. Flexibility versus routineness in multimodal health indicators: A sensor-based longitudinal in situ study of information workers. ACM Trans. Comput. Healthcare, 3(3), jul 2022.
  5. Detection of abnormal behaviour for dementia sufferers using convolutional neural networks. Artificial Intelligence in Medicine, 94:88–95, 3 2019.
  6. Mathematical modeling of circadian rhythms. WIREs Systems Biology and Medicine, 11, 3 2019.
  7. Learning frequent behaviors of the users in intelligent environments. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 43:1265–1278, 11 2013.
  8. Window size impact in human activity recognition. Sensors (Basel, Switzerland), 14:6474–99, 1 2014.
  9. Modeling and understanding human routine behavior. In Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, pages 248–260. ACM, 5 2016.
  10. A method for characterizing daily physiology from widely used wearables. Cell Rep. Methods, 1(4):100058, August 2021.
  11. Identifying routine and telltale activity patterns in knowledge work. In 2011 IEEE Fifth International Conference on Semantic Computing, pages 95–101. IEEE, 9 2011.
  12. A classification approach to estimating human circadian phase under circadian alignment from actigraphy and photometry data. Journal of Pineal Research, 71, 8 2021.
  13. Common multi-day rhythms in smartphone behavior. npj Digital Medicine, 6(1):49, Mar 2023.
  14. Deep learning for sensor-based human activity recognition. ACM Computing Surveys, 54:1–40, 2022.
  15. Sensor-based activity recognition. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42:790–808, 11 2012.
  16. Identifying and monitoring the daily routine of seniors living at home. Sensors, 22:992, 1 2022.
  17. Detecting depression and predicting its onset using longitudinal symptoms captured by passive sensing: A machine learning approach with robust feature selection. ACM Transactions on Computer-Human Interaction, 28:1–41, 2021.
  18. Factors affecting the quality of person-generated wearable device data and associated challenges: Rapid systematic review. JMIR mHealth and uHealth, 9:e20738, 3 2021.
  19. Personalized longitudinal assessment of multiple sclerosis using smartphones. IEEE Journal of Biomedical and Health Informatics, 27(7):3633–3644, 2023.
  20. Fusing ambient and mobile sensor features into a behaviorome for predicting clinical health scores. IEEE Access, 9:65033–65043, 2021.
  21. Analyzing activity behavior and movement in a naturalistic environment using smart home techniques. IEEE Journal of Biomedical and Health Informatics, 19:1882–1892, 11 2015.
  22. Detecting smartwatch-based behavior change in response to a multi-domain brain health intervention. ACM Trans. Comput. Healthcare, 3(3), apr 2022.
  23. Germaine Cornelissen. Cosinor-based rhythmometry, 4 2014.
  24. Indirectly supervised anomaly detection of clinically meaningful health events from smart home data. ACM Transactions on Intelligent Systems and Technology, 12, 3 2021.
  25. How routine learners can support family coordination. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pages 2461–2470. ACM, 4 2010.
  26. Modeling patterns of activities using activity curves. Pervasive and Mobile Computing, 28:51–68, 2015.
  27. Espresso: Entropy and shape aware time-series segmentation for processing heterogeneous sensor data. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 4, 9 2020.
  28. Human activity recognition with smartphone-integrated sensors: A survey. Expert Systems with Applications, 246:123143, 7 2024.
  29. Novel approaches for assessing circadian rhythmicity in humans: A review, 10 2020.
  30. Wearable digital health technology for epilepsy. New England Journal of Medicine, 390(8):736–745, 2024.
  31. Eigenbehaviors: identifying structure in routine. Behavioral Ecology and Sociobiology, 63(7):1057–1066, May 2009.
  32. A behaviour monitoring system (bms) for ambient assisted living. Sensors (Switzerland), 17, 2017.
  33. Health management and pattern analysis of daily living activities of people with dementia using in-home sensors and machine learning techniques. PLoS ONE, 13, 5 2018.
  34. Jean eudes Ranvier. Routinesense : A mobile sensing framework for the reconstruction of user routines. Mobiquitous, 2015.
  35. Measuring sleep regularity: theoretical properties and practical usage of existing metrics. Sleep, 44(10):zsab103, 04 2021.
  36. Daniel B Forger. Biological Clocks, Rhythms, and Oscillations: The Theory of Biological Timekeeping. MIT Press, 2017.
  37. Measuring regularity of individual travel patterns. IEEE Transactions on Intelligent Transportation Systems, 19:1583–1592, 5 2018.
  38. Assessing the relationship between routine and schizophrenia symptoms with passively sensed measures of behavioral stability. npj Schizophrenia, 6:35, 12 2020.
  39. On the role of context length for feature extraction and sequence modeling in human activity recognition. In 2021 International Symposium on Wearable Computers, pages 13–17. ACM, 9 2021.
  40. Crosshar: Generalizing cross-dataset human activity recognition via hierarchical self-supervised pretraining. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 8(2), may 2024.
  41. Discovery of activity patterns using topic models. In Proceedings of the 10th International Conference on Ubiquitous Computing, UbiComp ’08, page 10–19, New York, NY, USA, 2008. Association for Computing Machinery.
  42. Learning and managing context enriched behavior patterns in smart homes. Future Generation Computer Systems, 91:191–205, 2 2019.
  43. A survey on human activity recognition using wearable sensors. IEEE Communications Surveys & Tutorials, 15:1192–1209, 2013.
  44. Learning daily activity patterns with probabilistic grammars. Transportation, 2015. A pattern is expressed as a grammar ruleIf an observation corresponds to the grammar it is ”well”. Context-free grammar!!symbols correspond to activity typeLatent variables as context features??
  45. Learning and inferring transportation routines. Artificial Intelligence, 171:311–331, 4 2007.
  46. Daily routine disruptions and psychiatric symptoms amid covid-19: a systematic review and meta-analysis of data from 0.9 million individuals in 32 countries. BMC Medicine, 22:49, 2 2024.
  47. Wearable health devices in health care: Narrative systematic review. JMIR mHealth and uHealth, 8:e18907, 11 2020.
  48. Stability and fragmentation of the activity rhythm across the sleep-wake cycle: the importance of age, lifestyle, and mental health. Chronobiol. Int., 30(10):1223–1230, December 2013.
  49. Validation of the sleep regularity index in older adults and associations with cardiometabolic risk. Scientific Reports, 8:14158, 9 2018.
  50. Early detection of mild cognitive impairment with in-home monitoring sensor technologies using functional measures: A systematic review. IEEE Journal of Biomedical and Health Informatics, 23:838–847, 3 2019.
  51. Wearable monitoring of physical functioning and disability changes, circadian rhythms and sleep patterns in nursing home residents. IEEE Journal of Biomedical and Health Informatics, 20(3):856–864, 2016.
  52. A life of data: Characteristics and challenges of very long term self-tracking for health and wellness. ACM Trans. Comput. Healthcare, 1(2), mar 2020.
  53. A nonparametric approach for mild cognitive impairment to ad conversion prediction: Results on longitudinal data. IEEE Journal of Biomedical and Health Informatics, 21(5):1403–1410, 2017.
  54. Pre-symptomatic detection of covid-19 from smartwatch data. Nature Biomedical Engineering, 4:1208–1220, 11 2020.
  55. Personal sensing: Understanding mental health using ubiquitous sensors and machine learning. Annual Review of Clinical Psychology, 13:23–47, 2017.
  56. Sleep variability and regularity as contributors to obesity and cardiometabolic health in adolescence. Obesity, 31(3):597–614, 2023.
  57. Aroma: A deep multi-task learning based simple and complex human activity recognition method using wearable sensors. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol, 2, 2018.
  58. Irregular sleep/wake patterns are associated with poorer academic performance and delayed circadian and sleep/wake timing. Scientific Reports, 7:3216, 12 2017.
  59. Kathryn J. Reid. Assessment of circadian rhythms, 8 2019.
  60. Continuous assessment of schizophrenia using heart rate and accelerometer data. Physiological Measurement, 38:1456–1471, 6 2017.
  61. Analysis of long-term abnormal behaviors for early detection of cognitive decline. In 2016 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops), pages 1–6. IEEE, 3 2016.
  62. Behavior analysis of elderly using topic models. Pervasive and Mobile Computing, 15:181–199, 12 2014.
  63. Multi-task self-supervised learning for human activity detection. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 3(2), jun 2019.
  64. M3sense: Affect-agnostic multitask representation learning using multimodal wearable sensors. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 6, 2022. cited By 0.
  65. Measuring regularity of human physical activities with entropy models. Journal of Big Data, 11:37, 2 2024.
  66. The emerging clinical role of wearables: factors for successful implementation in healthcare. npj Digital Medicine, 4:45, 3 2021.
  67. Unsupervised Detection and Analysis of Changes in Everyday Physical Activity Data, pages 97–122. Springer International Publishing, 2018.
  68. Smart devices are different: Assessing and mitigating mobile sensing heterogeneities for activity recognition. In Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems - SenSys ’15, pages 127–140. ACM Press, 2015.
  69. The reproducibility crisis in the age of digital medicine. npj Digital Medicine, 2:2, 1 2019.
  70. The routineness of routines: Measuring rhythms of media interaction. Human–Computer Interaction, 28:287–334, 7 2013.
  71. Birds of a feather clock together: A study of person–organization fit through latent activity routines. Proceedings of the ACM on Human-Computer Interaction, 3, 11 2019.
  72. Automated cognitive health assessment using partially complete time series sensor data. Methods of Information in Medicine, 61:99–110, 1 2022.
  73. Investigating the association of anxiety disorders with heart rate variability measured using a wearable device. Journal of Affective Disorders, 351:569–578, 4 2024.
  74. Biological rhythms. Fish physiology, 21:101–153, 2005.
  75. Generalizable machine learning for stress monitoring from wearable devices: A systematic literature review. International Journal of Medical Informatics, 173:105026, 2023.
  76. Sensor-based estimation of dim light melatonin onset using features of two time scales. ACM Transactions on Computing for Healthcare, 2, 7 2021.
  77. Deep learning for sensor-based activity recognition: A survey. Pattern Recognition Letters, 2019.
  78. Tracking depression dynamics in college students using mobile phone and wearable sensing. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 2(1), mar 2018.
  79. Sensing behavioral change over time: Using within-person variability features from mobile sensing to predict personality traits. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2:1–21, 9 2018.
  80. Windows into human health through wearables data analytics, 3 2019.
  81. Alterations in the circadian rest-activity rhythm in aging and alzheimer’s disease. Biological Psychiatry, 27(6):563–572, 1990.
  82. circadian rhythms are not captured equal: Exploring circadian metrics extracted by different computational methods from smartphone accelerometer and gps sensors in daily life tracking. Digital Health, 8, 2022.
  83. Identifying links between productivity and biobehavioral rhythms modeled from multimodal sensor streams: Exploratory quantitative study. JMIR AI, 3:e47194, 4 2024.
  84. Leveraging collaborative-filtering for personalized behavior modeling: A case study of depression detection among college students. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 5:1–27, 2021.
  85. Leveraging routine behavior and contextually-filtered features for depression detection among college students. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 3:1–33, 9 2019.
  86. Globem: Cross-dataset generalization of longitudinal human behavior modeling. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 6(4), jan 2023.
  87. Understanding practices and needs of researchers in human state modeling by passive mobile sensing. CCF Transactions on Pervasive Computing and Interaction, 3:344–366, 12 2021.
  88. A computational framework for modeling biobehavioral rhythms from mobile and wearable data streams. ACM Transactions on Intelligent Systems and Technology, 13:1–27, 2022.
  89. Detecting abnormal events on binary sensors in smart home environments. Pervasive and Mobile Computing, 2015.
  90. Challenges and opportunities of deep learning for wearable-based objective sleep assessment. NPJ Digit. Med., 7(1):85, April 2024.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (1)
  1. Paula Lago (4 papers)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets