Large-scale wearable data reveal digital phenotypes for daily-life stress detection

Elena Smets, Emmanuel Rios Velazquez, Giuseppina Schiavone, Imen Chakroun, Ellie D'Hondt, Walter De Raedt, Jan Cornelis, Olivier Janssens, Sofie Van Hoecke, Stephan Claes, Ilse Van Diest, Chris Van Hoof, Elena Smets, Emmanuel Rios Velazquez, Giuseppina Schiavone, Imen Chakroun, Ellie D'Hondt, Walter De Raedt, Jan Cornelis, Olivier Janssens, Sofie Van Hoecke, Stephan Claes, Ilse Van Diest, Chris Van Hoof

Abstract

Physiological signals have shown to be reliable indicators of stress in laboratory studies, yet large-scale ambulatory validation is lacking. We present a large-scale cross-sectional study for ambulatory stress detection, consisting of 1002 subjects, containing subjects' demographics, baseline psychological information, and five consecutive days of free-living physiological and contextual measurements, collected through wearable devices and smartphones. This dataset represents a healthy population, showing associations between wearable physiological signals and self-reported daily-life stress. Using a data-driven approach, we identified digital phenotypes characterized by self-reported poor health indicators and high depression, anxiety and stress scores that are associated with blunted physiological responses to stress. These results emphasize the need for large-scale collections of multi-sensor data, to build personalized stress models for precision medicine.

Keywords: Predictive markers; Preventive medicine.

Conflict of interest statement

Competing interestsThe authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Physiology and context timeline. a Healthy-population physiological data over 5 days of measurements depicting smoothed daily profiles of high quality (Quality > 0.8) physiological signals (mean HR, SC, and ST) and activity (ACC SD), averaged in 1 min windows. b Self-reported annotations (stress, pleasure, activity, consumptions, and wake up/bed times) and location, as indicated with vertical lines when available for a representative subject. Location data are indicated as unique stay locations or commuting locations. An online version of a and b can be downloaded from https://drive.google.com/open?id=1Z1q0YLG8cvUllSM84X3mgwmCCBjfO0M7
Fig. 2
Fig. 2
Associations between physiological features and self-reported stress levels. Each row represents a physiological feature, columns represent the difference of the median of normalized features during the night (N) (00–06 am) and stress levels (S1, S2, and S3). Colors indicate positive (blue) or negative (red) differences. For example, SC phasic is significantly higher (blue) during the night as compared to during all reported stress levels, and significantly lower (red) during S1 as compared to S2 and S3. Symbols: *p < 0.05, **p < 0.005, ***p < 0.0005
Fig. 3
Fig. 3
Comparison of subjects with low, medium and high classification performance. In a–c average features ECG mean HR, SC phasic, and ST median are shown respectively for low (red), medium (yellow), and high performance (green) groups and compared with the entire population average (black) in phases of no, light and high stress. In d–f baseline psychological information of subjects in low, medium, and high performance groups are compared
Fig. 4
Fig. 4
Study protocol. a Protocol timeline: starting with online intake questionnaires, followed by a 5-day trial, ending with a follow-up questionnaire just after the experiment and 1 year later. b Ecological momentary assessments (EMAs): once per subject the Montreal Imaging Stress Task is performed containing a series of mental arithmetic challenges. Once per day a sleep diary and gastro-intestinal symptoms diary are filled in and 12 times a day stress levels are recorded. c Physiological recordings: Chillband and chest patch to measure SC, ST, ECG, and acceleration. d Smartphone sensor data: overview of the data recorded

References

    1. Selye H. Stress and the general adaptation syndrome. Br. Med. J. 1950;1:1383–1392. doi: 10.1136/bmj.1.4667.1383.
    1. Cohen S, Janicki-deverts D, Miller GE. Psychological stress and disease. JAMA. 2015;298:1685–1687. doi: 10.1001/jama.298.14.1685.
    1. Dimsdale JE. Psychological stress and cardiovascular disease. J. Am. Coll. Cardiol. 2008;51:1237–1246. doi: 10.1016/j.jacc.2007.12.024.
    1. Khoury MJ, Iademarco MF, Riley WT. Precision public health for the era of precision medicine. Am. J. Prev. Med. 2016;50:398–401. doi: 10.1016/j.amepre.2015.08.031.
    1. Jain SH, Powers BW, Hawkins JB, Brownstein JS. The digital phenotype. Nat. Biotechnol. 2015;33:462–463. doi: 10.1038/nbt.3223.
    1. Lee EH. Review of the psychometric evidence of the perceived stress scale. Asian Nurs. Res. (Korean Soc. Nurs. Sci.). 2012;6:121–127. doi: 10.1016/j.anr.2012.08.004.
    1. Alberdi A, Aztiria A, Basarab A. Towards an automatic early stress recognition system for office environments based on multimodal measurements: a review. J. Biomed. Inform. 2016;59:49–75. doi: 10.1016/j.jbi.2015.11.007.
    1. Lovallo, W. R. Stress & Health: Biological and Psychological Interactions. SAGE Publications: California, US (2016).
    1. Sharma N, Gedeon T. Objective measures, sensors and computational techniques for stress recognition and classification: a survey. Comput. Methods Prog. Biomed. 2012;108:1287–1301. doi: 10.1016/j.cmpb.2012.07.003.
    1. Healey JA, Picard RW. Detecting stress during real-world dring tasks using physiological sensors. IEEE Trans. Intell. Transp. Syst. 2005;6:156–166. doi: 10.1109/TITS.2005.848368.
    1. Muaremi A, Arnrich B, Tröster G. Towards measuring stress with smartphones and wearable devices during workday and sleep. Bionanoscience. 2013;3:172–183. doi: 10.1007/s12668-013-0089-2.
    1. Hovsepian, K. et al. cStress: towards a gold standard for continuous stress assessment in the mobile environment. in Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing—UbiComp '15 493–504 (2015).
    1. Sun, F.-T. et al. Activity-aware mental stress detection using physiological sensors. in Proc. International Conference on Mobile Computing, Applications, and Services (MobiCASE), Vol. 76, 1–20 (2010).
    1. Smets E, et al. Comparison of machine learning techniques for psychophysiological stress detection. Comp. Mach. Learn. Tech. 2016;604:13–22.
    1. Sun FFT, et al. Activity-aware mental stress detection using physiological sensors. Mob. Comput. 2012;76:211–230.
    1. Rahman, M. M. et al. Are we there yet? Feasibility of continuous stress assessment via wireless physiological sensors. in Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics—BCB’14, 479–488 (2014).
    1. Wang, R. et al. Studentlife: assessing mental health, academic performance and behavioral trends of college students using smartphones. in Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing 3–14 (2014).
    1. Finke JB, Kalinowski GI, Larra MF, Schächinger H. The socially evaluated handgrip test: Introduction of a novel, time-efficient stress protocol. Psychoneuroendocrinology. 2018;87:141–146. doi: 10.1016/j.psyneuen.2017.10.013.
    1. Kirschbaum C, Pirke KM, Hellhammer DH. The ‘Trier Social Stress Test’—a tool for investigating psychobiological stress responses in a laboratory setting. Neuropsychobiology. 1993;28:76–81. doi: 10.1159/000119004.
    1. Billman GE. The LF/HF ratio does not accurately measure cardiac sympatho-vagal balance. Front. Physiol. 2013;4:26.
    1. McNames J, Aboy M. Reliability and accuracy of heart rate variability metrics versus ECG segment duration. Med. Biol. Eng. Comput. 2006;44:747–756. doi: 10.1007/s11517-006-0097-2.
    1. Healey, J. A. Wearable and Automotive Systems for Affect Recognition from Physiology. Ph.D. Thesis 158 (2000).
    1. Singh R, Conjeti S, Banerjee R. A comparative evaluation of neural network classifiers for stress level analysis of automotive drivers using physiological signals. Biomed. Signal Process. 2013;8:740–754. doi: 10.1016/j.bspc.2013.06.014.
    1. Greco, A., Valenza, G. & Scilingo, E. P. Advances in Electrodermal Activity Processing with Applications for Mental Health. Springer International Publishing: New York, US (2016).
    1. Kistler A, Mariauzouls C, Von Berlepsch K. Fingertip temperature as an indicator for sympathetic responses. Int. J. Psychophysiol. 1998;29:35–41. doi: 10.1016/S0167-8760(97)00087-1.
    1. Carroll D, Ginty AT, Whittaker AC, Lovallo WR, de Rooij SR. The behavioural, cognitive, and neural corollaries of blunted cardiovascular and cortisol reactions to acute psychological stress. Neurosci. Biobehav. Rev. 2017;77:74–86. doi: 10.1016/j.neubiorev.2017.02.025.
    1. Buysse DJ, et al. Quantification of subjective sleep quality in healthy elderly men and women using the Pittsburgh Sleep Quality Index (PSQI) Sleep. 1991;14:331–338.
    1. Henry JD, Crawford JR. The short-form version of the Depression Anxiety Stress Scales (DASS-21): construct validity and normative data in a large non-clinical sample. Br. J. Clin. Psychol. 2005;44:227–239. doi: 10.1348/014466505X29657.
    1. Hays RD, Morales LS. The RAND-36 measure of health-related quality of life. Ann. Med. 2001;33:350–357. doi: 10.3109/07853890109002089.
    1. Petersen H, Kecklund G, D’Onofrio P, Nilsson J, Åkerstedt T. Stress vulnerability and the effects of moderate daily stress on sleep polysomnography and subjective sleepiness. J. Sleep. Res. 2013;22:50–57. doi: 10.1111/j.1365-2869.2012.01034.x.
    1. Lee SP, et al. The effect of emotional stress and depression on the prevalence of digestive diseases. J. Neurogastroenterol. Motil. 2015;21:273–282. doi: 10.5056/jnm14116.
    1. Carbone F, et al. Validation of the Leuven Postprandial Distress Scale, a questionnaire for symptom assessment in the functional dyspepsia/postprandial distress syndrome. Aliment. Pharmacol. Ther. 2016;44:989–1001. doi: 10.1111/apt.13753.
    1. Morris JD. Observations: SAM: the self-assessment manikin: an efficient cross-cultural measurement of emotional response. J. Advert. Res. 1995;35:63–68.
    1. Kupriyanov RV, Sholokhov MA, Kupriyanov R, Zhdanov R. The eustress concept: problems and outlooks. World J. Med. Sci. 2014;11:179–185.
    1. Acharya UR, Joseph KP, Kannathal N, Lim CM, Suri JS. Heart rate variability: a review. Med. Biol. Eng. Comput. 2006;44:1031–1051. doi: 10.1007/s11517-006-0119-0.
    1. Dedovic K, Renwick R, Mahani NK, Engert V. The Montreal Imaging Stress Task: using functional imaging to investigate the effects of perceiving and processing psychosocial stress in the human brain. Psychiatry Neurosci. 2005;30:319–325.
    1. Van der Doef M, Maes S. The Job Demand-Control (-Support) Model and psychological well-being: a review of 20 years of empirical research. Work Stress. 1999;13:87–114. doi: 10.1080/026783799296084.
    1. Vetrugno R, Liguori R, Cortelli P, Montagna P. Sympathetic skin response. Clin. Auton. Res. 2003;13:256–270. doi: 10.1007/s10286-003-0107-5.
    1. Orphanidou, C. et al. Signal quality indices for the electrocardiogram and photoplethysmogram: derivation and applications to wireless monitoring. IEEE J. Biomed. Health Inform.19, 832–838 (2014).
    1. Kocielnik, R., Sidorova, N., Maggi, F. M., Ouwerkerk, M. & Westerink, J. H. D. M. Smart technologies for long-term stress monitoring at work. in Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems 53–58 (IEEE, 2013).
    1. Boucsein W, et al. Publication recommendations for electrodermal measurements. Psychophysiology. 2012;49:1017–1034. doi: 10.1111/j.1469-8986.2012.01384.x.
    1. Jones, L. A. & Lederman, S. J. Human Hand Function. Oxford University Press: Oxford, UK (2006).
    1. Han L, et al. Detecting work-related stress with a wearable device. Comput. Ind. 2017;90:42–49. doi: 10.1016/j.compind.2017.05.004.
    1. Xu Q, Nwe TL, Guan C. Cluster-based analysis for personalized stress evaluation using physiological signals. IEEE J. Biomed. Health Inform. 2015;19:275–281. doi: 10.1109/JBHI.2014.2311044.
    1. Zhai, J. & Barreto, A. Stress detection in computer users based on digital signal processing of noninvasive physiological variables. in Proc. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 1355–1358 (2006).
    1. de Vries GJJ, Pauws SC, Biehl M. Insightful stress detection from physiology modalities using Learning Vector Quantization. Neurocomputing. 2015;151:873–882. doi: 10.1016/j.neucom.2014.10.008.
    1. Karthikeyan P, Murugappan M, Yaacob S. Multiple physiological signal-based human stress identification using non-linear classifiers. Elektron. Elektrotech. 2013;19:80–85.
    1. Sano, A. & Picard, R. W. Stress recognition using wearable sensors and mobile phones. in Proc.Humaine Association Conference on Affective Computing and Intelligent Interaction 671–676 (2013).
    1. Wijsman, J., Grundlehner, B., Liu, H., Penders, J. & Hermens, H. Wearable physiological sensors reflect mental stress state in office-like situations. in Proc. Humaine Association Conference on Affective Computing and Intelligent Interaction, ACII 2013 600–605 (2013).
    1. Guidelines: Heart rate variability standards of measurement, physiological interpretation, and clinical use. Eur. Heart J. 17, 354–381 (1996).
    1. Grant CC, van Rensburg DCJ, Strydom N, Viljoen M. Importance of tachogram length and period of recording during noninvasive investigation of the autonomic nervous system. Ann. Noninvasive Electrocardiol. 2011;16:131–139. doi: 10.1111/j.1542-474X.2011.00422.x.
    1. Bates D, Mächler M, Bolker B, Walker S. Fitting linear mixed-effects models using lme4. J. Stat. Softw. 2015;67:1–48. doi: 10.18637/jss.v067.i01.
    1. Symonds MRE, Moussalli A. A brief guide to model selection, multimodel inference and model averaging in behavioural ecology using Akaike's information criterion. Behav. Ecol. Sociobiol. 2011;65:13–21. doi: 10.1007/s00265-010-1037-6.
    1. Steptoe A, Butler N. Sports participation and emotional wellbeing in adolescents. Lancet. 1996;347:1789–1792. doi: 10.1016/S0140-6736(96)91616-5.
    1. Stubbs B, et al. Perceived stress and smoking across 41 countries: a global perspective across Europe, Africa, Asia and the Americas. Sci. Rep. 2017;7:7597. doi: 10.1038/s41598-017-07579-w.
    1. Rius C, Fernandez E, Schiaffino A, Borràs JM, Rodríguez-Artalejo F. Self perceived health and smoking in adolescents. J. Epidemiol. Community Health. 2004;58:698–699. doi: 10.1136/jech.2003.008516.
    1. Watson EJ, Coates AM, Kohler M, Banks S. Caffeine consumption and sleep quality in Australian adults. Nutrients. 2016;8:E479. doi: 10.3390/nu8080479.
    1. Smagula SF, Stone KL, Fabio A, Cauley JA. Risk factors for sleep disturbances in older adults: evidence from prospective studies. Sleep Med. Rev. 2016;25:21–30. doi: 10.1016/j.smrv.2015.01.003.
    1. Irish LA, Kline CE, Gunn HE, Buysse DJ, Hall MH. The role of sleep hygiene in promoting public health: a review of empirical evidence. Sleep Med. Rev. 2015;22:23–36. doi: 10.1016/j.smrv.2014.10.001.
    1. Stewart, A. & Ware, J. Measuring Functioning and Well-Being: The Medical Outcomes Study Approach. Duke University Press: Durham, North Carolina, US (1992).

Source: PubMed

Sponsor e collaboratori

Condizioni mediche

Interventi farmacologici

3
Sottoscrivi