Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 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

Addressing Data Quality Challenges in Observational Ambulatory Studies: Analysis, Methodologies and Practical Solutions for Wrist-worn Wearable Monitoring (2401.13518v1)

Published 24 Jan 2024 in cs.CE

Abstract: Chronic disease management and follow-up are vital for realizing sustained patient well-being and optimal health outcomes. Recent advancements in wearable sensing technologies, particularly wrist-worn devices, offer promising solutions for longitudinal patient follow-up by shifting from subjective, intermittent self-reporting to objective, continuous monitoring. However, collecting and analyzing wearable data presents unique challenges, such as data entry errors, non-wear periods, missing wearable data, and wearable artifacts. We therefore present an in-depth exploration of data analysis challenges tied to wrist-worn wearables and ambulatory label acquisition, using two real-world datasets (i.e., mBrain21 and ETRI lifelog2020). We introduce novel practical countermeasures, including participant compliance visualizations, interaction-triggered questionnaires to assess personal bias, and an optimized wearable non-wear detection pipeline. Further, we propose a visual analytics approach to validate processing pipelines using scalable tools such as tsflex and Plotly-Resampler. Lastly, we investigate the impact of missing wearable data on "window-of-interest" analysis methodologies. Prioritizing transparency and reproducibility, we offer open access to our detailed code examples, facilitating adaptation in future wearable research. In conclusion, our contributions provide actionable approaches for wearable data collection and analysis in chronic disease management.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (68)
  1. Heikenfeld, J. et al. Wearable sensors: modalities, challenges, and prospects. \JournalTitleLab on a Chip 18, 217–248, DOI: 10.1039/C7LC00914C (2018).
  2. A Systematic Review of Wearable Patient Monitoring Systems – Current Challenges and Opportunities for Clinical Adoption. \JournalTitleJournal of Medical Systems 41, 115, DOI: 10.1007/s10916-017-0760-1 (2017).
  3. Klonoff, D. C. Continuous glucose monitoring: roadmap for 21st century diabetes therapy. \JournalTitleDiabetes care 28, 1231–1239 (2005). Publisher: Citeseer.
  4. Bayoumy, K. et al. Smart wearable devices in cardiovascular care: where we are and how to move forward. \JournalTitleNature Reviews Cardiology DOI: 10.1038/s41569-021-00522-7 (2021). ZSCC: 0000000.
  5. Does remote patient monitoring reduce acute care use? A systematic review. \JournalTitleBMJ Open 11, e040232, DOI: 10.1136/bmjopen-2020-040232 (2021).
  6. Recent Advances in Wearable Sensors for Health Monitoring. \JournalTitleIEEE Sensors Journal 15, 3119–3126, DOI: 10.1109/JSEN.2014.2357257 (2015).
  7. Wearable sensors for reliable fall detection. In 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, 3551–3554 (IEEE, 2006).
  8. Wearable biosensors for healthcare monitoring. \JournalTitleNature Biotechnology 37, 389–406, DOI: 10.1038/s41587-019-0045-y (2019). ZSCC: 0000319.
  9. De Brouwer, M. et al. mBrain: towards the continuous follow-up and headache classification of primary headache disorder patients. \JournalTitleBMC Medical Informatics and Decision Making 22, 87, DOI: 10.1186/s12911-022-01813-w (2022).
  10. Using Sleep Time Data from Wearable Sensors for Early Detection of Migraine Attacks. \JournalTitleSensors 18, 1374, DOI: 10.3390/s18051374 (2018).
  11. Stubberud, A. et al. Forecasting migraine with machine learning based on mobile phone diary and wearable data. \JournalTitleCephalalgia 43, 033310242311692, DOI: 10.1177/03331024231169244 (2023).
  12. Böttcher, S. et al. Detecting Tonic-Clonic Seizures in Multimodal Biosignal Data From Wearables: Methodology Design and Validation. \JournalTitleJMIR mHealth and uHealth 9, e27674, DOI: 10.2196/27674 (2021).
  13. Wearable-Based Affect Recognition—A Review. \JournalTitleSensors 19, 4079, DOI: 10.3390/s19194079 (2019). ZSCC: 0000022.
  14. Challenges and recommendations for wearable devices in digital health: Data quality, interoperability, health equity, fairness. \JournalTitlePLOS Digital Health 1, e0000104, DOI: 10.1371/journal.pdig.0000104 (2022).
  15. Factors Affecting the Quality of Person-Generated Wearable Device Data and Associated Challenges: Rapid Systematic Review. \JournalTitleJMIR mHealth and uHealth 9, e20738, DOI: 10.2196/20738 (2021).
  16. The Future of Wearable Technologies and Remote Monitoring in Health Care. \JournalTitleAmerican Society of Clinical Oncology Educational Book 115–121, DOI: 10.1200/EDBK_238919 (2019).
  17. Chung, S. et al. Real-world multimodal lifelog dataset for human behavior study. \JournalTitleETRI Journal 44, 426–437, DOI: 10.4218/etrij.2020-0446 (2022).
  18. Labelling Affective States "in the Wild": Practical Guidelines and Lessons Learned. In Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers, 654–659, DOI: 10.1145/3267305.3267551 (ACM, Singapore Singapore, 2018). ZSCC: 0000010.
  19. Balbim, G. M. et al. Using Fitbit as an mHealth Intervention Tool to Promote Physical Activity: Potential Challenges and Solutions. \JournalTitleJMIR mHealth and uHealth 9, e25289, DOI: 10.2196/25289 (2021).
  20. Böttcher, S. et al. Data quality evaluation in wearable monitoring. \JournalTitleScientific Reports 12, 21412, DOI: 10.1038/s41598-022-25949-x (2022).
  21. Van Der Donckt, J. et al. From self-reporting to monitoring for improved migraine management. In Engineer meets Physician (EmP) (2022).
  22. Vandenbussche, N. et al. Patients with chronic cluster headache may show reduced activity energy expenditure on ambulatory wrist actigraphy recordings during daytime attacks. \JournalTitleBrain and Behavior 14, e3360, DOI: 10.1002/brb3.3360 (2024).
  23. S.R.L, E. E4 data - BVP expected signal.
  24. Kaggle. Kaggle State of Machine Learning and Data Science Report 2022.pdf. survey (2022).
  25. Perkel, J. M. Why Jupyter is data scientists’ computational notebook of choice. \JournalTitleNature 563, 145–146, DOI: 10.1038/d41586-018-07196-1 (2018).
  26. PyPoetry. Poetry - Python dependency management and packaging made easy.
  27. The Impact of Missing Data and Imputation Methods on the Analysis of 24-Hour Activity Patterns. \JournalTitleClocks & Sleep 4, 497–507, DOI: 10.3390/clockssleep4040039 (2022).
  28. Heger, I. et al. Using mHealth for Primary Prevention of Dementia: A Proof-of-Concept Study on Usage Patterns, Appreciation, and Beliefs and Attitudes Regarding Prevention. \JournalTitleJournal of Alzheimer’s Disease 94, 935–948, DOI: 10.3233/JAD-230225 (2023).
  29. Towards Measuring Stress with Smartphones and Wearable Devices During Workday and Sleep. \JournalTitleBioNanoScience 3, 172–183, DOI: 10.1007/s12668-013-0089-2 (2013). ZSCC: 0000245.
  30. Multiple surveys of students and survey fatigue. \JournalTitleNew Directions for Institutional Research 2004, 63–73, DOI: 10.1002/ir.101 (2004).
  31. Out of the Lab and into the Fray: Towards Modeling Emotion in Everyday Life. In Hutchison, D. et al. (eds.) Pervasive Computing, vol. 6030, 156–173, DOI: 10.1007/978-3-642-12654-3_10 (Springer Berlin Heidelberg, Berlin, Heidelberg, 2010). Series Title: Lecture Notes in Computer Science.
  32. Compliance in Ambulatory Assessment Studies: Investigating Study and Sample Characteristics as Predictors. \JournalTitleAssessment 29, 1765–1776, DOI: 10.1177/10731911211032718 (2022).
  33. Gamification of Mobile Experience Sampling Improves Data Quality and Quantity. \JournalTitleProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 1, 1–21, DOI: 10.1145/3130972 (2017).
  34. Gloster, A. T. et al. Daily fluctuation of emotions and memories thereof: Design and methods of an experience sampling study of major depression, social phobia, and controls. \JournalTitleInternational Journal of Methods in Psychiatric Research 26, e1578, DOI: 10.1002/mpr.1578 (2017).
  35. Handling missing data in self-report measures. \JournalTitleResearch in Nursing & Health 28, 488–495, DOI: 10.1002/nur.20100 (2005).
  36. Colls, J. et al. Patient adherence with a smartphone app for patient-reported outcomes in rheumatoid arthritis. \JournalTitleRheumatology 60, 108–112, DOI: 10.1093/rheumatology/keaa202 (2021).
  37. Mobile healthcare applications: system design review, critical issues and challenges. \JournalTitleAustralasian Physical & Engineering Sciences in Medicine 38, 23–38, DOI: 10.1007/s13246-014-0315-4 (2015).
  38. Human factors error and patient monitoring. \JournalTitlePhysiological Measurement 23, R111–R132, DOI: 10.1088/0967-3334/23/3/201 (2002).
  39. Validity and reliability of the experience-sampling method. \JournalTitleFlow and the foundations of positive psychology: The collected works of Mihaly Csikszentmihalyi 35–54 (2014). Publisher: Springer.
  40. A Matter of Annotation: An Empirical Study on In Situ and Self-Recall Activity Annotations from Wearable Sensors (2023). ArXiv:2305.08752 [cs].
  41. Bracke, V. et al. Design and evaluation of a scalable Internet of Things backend for smart ports. \JournalTitleSoftware: Practice and Experience 51, 1557–1579, DOI: 10.1002/spe.2973 (2021).
  42. Sun, S. et al. The utility of wearable devices in assessing ambulatory impairments of people with multiple sclerosis in free-living conditions. \JournalTitleComputer Methods and Programs in Biomedicine 227, 107204, DOI: 10.1016/j.cmpb.2022.107204 (2022).
  43. Identifying medical wearables and sensor technologies that deliver data on clinical endpoints: Editorial. \JournalTitleBritish Journal of Clinical Pharmacology 81, 196–198, DOI: 10.1111/bcp.12818 (2016).
  44. Out of sight, out of mind: a prospective observational study to estimate the duration of the Hawthorne effect on hand hygiene events. \JournalTitleBMJ Quality & Safety 29, 932–938, DOI: 10.1136/bmjqs-2019-010310 (2020).
  45. Berger, A. M. et al. Methodological Challenges When Using Actigraphy in Research. \JournalTitleJournal of Pain and Symptom Management 36, 191–199, DOI: 10.1016/j.jpainsymman.2007.10.008 (2008).
  46. Development and Evaluation of an Ambulatory Stress Monitor Based on Wearable Sensors. \JournalTitleIEEE Transactions on Information Technology in Biomedicine 16, 279–286, DOI: 10.1109/TITB.2011.2169804 (2012). ZSCC: NoCitationData[s0] Conference Name: IEEE Transactions on Information Technology in Biomedicine.
  47. Non-wear or sleep? Evaluation of five non-wear detection algorithms for raw accelerometer data. \JournalTitleJournal of Sports Sciences 38, 399–404, DOI: 10.1080/02640414.2019.1703301 (2020).
  48. Vert, A. et al. Detecting accelerometer non-wear periods using change in acceleration combined with rate-of-change in temperature. \JournalTitleBMC Medical Research Methodology 22, 147, DOI: 10.1186/s12874-022-01633-6 (2022).
  49. Putting Temperature into the Equation: Development and Validation of Algorithms to Distinguish Non-Wearing from Inactivity and Sleep in Wearable Sensors. \JournalTitleSensors 22, 1117, DOI: 10.3390/s22031117 (2022).
  50. Validity of the Empatica E4 wristband to estimate resting-state heart rate variability in a lab-based context. \JournalTitleInternational Journal of Psychophysiology 182, 105–118, DOI: 10.1016/j.ijpsycho.2022.10.003 (2022).
  51. Innovations in Electrodermal Activity Data Collection and Signal Processing: A Systematic Review. \JournalTitleSensors 20, 479, DOI: 10.3390/s20020479 (2020).
  52. The use of wearable devices for predicting biphasic basal body temperature to estimate the date of ovulation in women. \JournalTitleJournal of Thermal Biology 108, 103290, DOI: 10.1016/j.jtherbio.2022.103290 (2022).
  53. Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks. \JournalTitleSensors 19, 3079, DOI: 10.3390/s19143079 (2019). ZSCC: 0000012.
  54. Moser, B. A. Estimating the signal reconstruction error from threshold-based sampling without knowing the original signal. In 2017 3rd International Conference on Event-Based Control, Communication and Signal Processing (EBCCSP), 1–4, DOI: 10.1109/EBCCSP.2017.8022834 (IEEE, Funchal, Portugal, 2017).
  55. tsflex: Flexible time series processing & feature extraction. \JournalTitleSoftwareX 17, 100971, DOI: 10.1016/j.softx.2021.100971 (2022). ZSCC: 0000000.
  56. Plotly-Resampler: Effective Visual Analytics for Large Time Series. In 2022 IEEE Visualization and Visual Analytics (VIS), 21–25, DOI: 10.1109/VIS54862.2022.00013 (IEEE, Oklahoma City, OK, USA, 2022).
  57. Visual-interactive preprocessing of time series data. In Proceedings of SIGRAD 2012; Interactive Visual Analysis of Data; November 29-30; 2012; Växjö; Sweden, 39–48 (Citeseer, 2012). Issue: 081.
  58. A tutorial on human activity recognition using body-worn inertial sensors. \JournalTitleACM Computing Surveys 46, 1–33, DOI: 10.1145/2499621 (2014).
  59. Recent developments in bootstrapping time series. \JournalTitleEconometric Reviews 19, 1–48, DOI: 10.1080/07474930008800457 (2000).
  60. Efron, B. Missing Data, Imputation, and the Bootstrap. \JournalTitleJournal of the American Statistical Association 89, 463–475, DOI: 10.1080/01621459.1994.10476768 (1994).
  61. Bai, J. et al. An Activity Index for Raw Accelerometry Data and Its Comparison with Other Activity Metrics. \JournalTitlePLOS ONE 11, e0160644, DOI: 10.1371/journal.pone.0160644 (2016). ZSCC: NoCitationData[s0].
  62. Cornelissen, G. Cosinor-based rhythmometry. \JournalTitleTheoretical Biology and Medical Modelling 11, 16, DOI: 10.1186/1742-4682-11-16 (2014).
  63. Moškon, M. CosinorPy: a python package for cosinor-based rhythmometry. \JournalTitleBMC Bioinformatics 21, 485, DOI: 10.1186/s12859-020-03830-w (2020).
  64. Meaningfulness, Commitment, and Engagement:The Intersection of a Deeper Level of Intrinsic Motivation. \JournalTitleAdvances in Developing Human Resources 11, 189–203, DOI: 10.1177/1523422309333147 (2009).
  65. PulSync: The Heart Rate Variability as a Unique Fingerprint for the Alignment of Sensor Data Across Multiple Wearable Devices. In 2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops), 188–193, DOI: 10.1109/PerComWorkshops51409.2021.9431015 (IEEE, Kassel, Germany, 2021). ZSCC: 0000001.
  66. Van Remoortel, H. et al. Validity of Six Activity Monitors in Chronic Obstructive Pulmonary Disease: A Comparison with Indirect Calorimetry. \JournalTitlePLoS ONE 7, e39198, DOI: 10.1371/journal.pone.0039198 (2012).
  67. Validating Measures of Electrodermal Activity and Heart Rate Variability Derived From the Empatica E4 Utilized in Research Settings That Involve Interactive Dyadic States. \JournalTitleFrontiers in Behavioral Neuroscience 14, 148, DOI: 10.3389/fnbeh.2020.00148 (2020).
  68. Sweating on the palm and sole: physiological and clinical relevance. \JournalTitleClinical Autonomic Research 25, 153–159, DOI: 10.1007/s10286-015-0282-1 (2015).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (10)
  1. Jonas Van Der Donckt (9 papers)
  2. Nicolas Vandenbussche (2 papers)
  3. Jeroen Van Der Donckt (11 papers)
  4. Stephanie Chen (7 papers)
  5. Marija Stojchevska (1 paper)
  6. Mathias De Brouwer (1 paper)
  7. Bram Steenwinckel (5 papers)
  8. Koen Paemeleire (1 paper)
  9. Femke Ongenae (12 papers)
  10. Sofie Van Hoecke (24 papers)