Predicting Emotional Exhaustion with Multimodal Sensor Data During Return‑to‑Work Trajectories: A 6‑Month Longitudinal Study

Lea Berkemeier; Wim  Kamphuis; Hilbrand Oldenhuis; Robin N Kok; Ruud Verdaasdonk; Lisette van Gemert-Pijnen

doi:10.1007/s10926-026-10395-7

Predicting Emotional Exhaustion with Multimodal Sensor Data During Return‑to‑Work Trajectories: A 6‑Month Longitudinal Study

Lea Berkemeier (First author)
, Wim Kamphuis
, Hilbrand Oldenhuis
, Robin N Kok
, Ruud Verdaasdonk
, Lisette van Gemert-Pijnen

Digital Transformation

University of Twente, Psychology, Health & Technology, Centre for eHealth Research and Wellbeing
TNO
Human Total Care
University of Twente - Faculty of Science and Technology (S&T)

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Purpose: Emotional exhaustion is a core component of burnout and impacts return-to-work trajectories following sick leave due to burnout or stress. Previous research identified links between emotional exhaustion and sleep, physical activity, mobility, and smartphone usage, yet little is known about how these associations vary within and between individuals over time. This study examined how emotional exhaustion can be monitored and predicted using multimodal data from smartphones and smart rings during return-to-work trajectories. Methods: Eighteen employees on sick leave in the Netherlands due to stress or burnout symptoms were recruited via occupational physicians. For six months, participants completed daily Ecological Momentary Assessments (EMAs) of emotional exhaustion and provided multimodal sensor data on sleep and physical activity (Oura ring), mobility, and phone usage patterns (Avicenna app). Between- and within-person associations were examined using correlational analyses and linear mixed models. Subject-dependent Random Forest (RF) models were trained to assess the predictive performance of multimodal features. Results: Subject-dependent RF models achieved an average Spearman’s ρ̄ of 0.38 (range: 0.10–0.72). Sleep and physical activity features showed more consistent associations with emotional exhaustion than mobility and smartphone usage patterns, which were more heterogeneous. The strength and direction of associations, as well as the most predictive features, varied substantially between participants. Conclusions: Multimodal device data can modestly predict emotional exhaustion, with performance varying by individual. Results indicate that emotional exhaustion patterns are highly variable among employees, necessitating individualized approaches to return-to-work counselling. Future research should incorporate longer monitoring periods and examine inter- and intra-individual variability.

Translated title of the contribution	Emotionele uitputting tijdens re-integratietrajecten voorspellen met behulp van multimodale sensordata: Een 6-maanden lange longitudinale studie
Original language	English
Pages (from-to)	1-13
Number of pages	13
Journal	Journal of Occupational Rehabilitation
DOIs	https://doi.org/10.1007/s10926-026-10395-7
Publication status	Published - 22 Apr 2026

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 03 Good Health and Well-being

Keywords

Emotional exhaustion
Employee
Longitudinal
Return-to-work
Sick-listed
Wearable sensors

Research Focus Areas Hanze University of Applied Sciences * (mandatory by Hanze)

Entrepreneurship
Healthy Ageing

Research Focus Areas Research Centre or Centre of Expertise * (mandatory by Hanze)

Digital Transformation

Publinova themes

Technology
Health
People and Society
Language, Culture and Arts
Economics and Management
Law

Access to Document

10.1007/s10926-026-10395-7Licence: CC BY

https://link.springer.com/article/10.1007/s10926-026-10395-7Licence: CC BY

5 Article
1 Contribution to conference proceeding
1 Paper
1 Poster

Does Wearable-Measured Heart Rate Variability During Sleep Predict Perceived Morning Mental and Physical Fitness?
de Vries, H., Oldenhuis, H., van der Schans, C., Sanderman, R. & Kamphuis, W., 9 Jan 2023, In: Applied Psychophysiology Biofeedback. 48, 2, p. 247-257 11 p.
Research output: Contribution to journal › Article › Academic › peer-review

Open Access
Predicting subjective stress using wearable-measured sleep and resting HRV
de Vries, H., Pennings, H. J. M., van der Schans, C., Sanderman, R., Oldenhuis, H. & Kamphuis, W., 20 Apr 2023. 1 p.
Research output: Contribution to conference › Poster › Academic

Open Access
File
Towards continuous mental state detection in everyday settings: investigating between-subjects variations in a longitudinal study
Berkemeier, L. (First author), Kamphuis, W., de Vries, H., Brouwer, A.-M., van Baardewijk, J. U., Schadd, M., Oldenhuis, H., Verdaasdonk, R. & van Gemert-Pijnen, L., 1 Jan 2023, Towards continuous mental state detection in everyday settings: investigating between-subjects variations in a longitudinal study. AHFE International, Vol. 102. p. 131-140 9 p. 10.54941/ahfe1003013
Research output: Chapter in Book/Report/Conference proceeding › Contribution to conference proceeding › Academic › peer-review

Open Access
File
115 Downloads (Pure)

Cite this

@article{e5b2ff9e4fc34fd7905d7f81740a6aa5,

title = "Predicting Emotional Exhaustion with Multimodal Sensor Data During Return‑to‑Work Trajectories: A 6‑Month Longitudinal Study",

abstract = "Purpose: Emotional exhaustion is a core component of burnout and impacts return-to-work trajectories following sick leave due to burnout or stress. Previous research identified links between emotional exhaustion and sleep, physical activity, mobility, and smartphone usage, yet little is known about how these associations vary within and between individuals over time. This study examined how emotional exhaustion can be monitored and predicted using multimodal data from smartphones and smart rings during return-to-work trajectories. Methods: Eighteen employees on sick leave in the Netherlands due to stress or burnout symptoms were recruited via occupational physicians. For six months, participants completed daily Ecological Momentary Assessments (EMAs) of emotional exhaustion and provided multimodal sensor data on sleep and physical activity (Oura ring), mobility, and phone usage patterns (Avicenna app). Between- and within-person associations were examined using correlational analyses and linear mixed models. Subject-dependent Random Forest (RF) models were trained to assess the predictive performance of multimodal features. Results: Subject-dependent RF models achieved an average Spearman{\textquoteright}s {\=ρ} of 0.38 (range: 0.10–0.72). Sleep and physical activity features showed more consistent associations with emotional exhaustion than mobility and smartphone usage patterns, which were more heterogeneous. The strength and direction of associations, as well as the most predictive features, varied substantially between participants. Conclusions: Multimodal device data can modestly predict emotional exhaustion, with performance varying by individual. Results indicate that emotional exhaustion patterns are highly variable among employees, necessitating individualized approaches to return-to-work counselling. Future research should incorporate longer monitoring periods and examine inter- and intra-individual variability.",

keywords = "emotionele uitputting, werknemer, longitudionaal, werkhervatting, arbeidsongeschikt, draagbare sensoren, Emotional exhaustion, Employee, Longitudinal, Return-to-work, Sick-listed, Wearable sensors",

author = "Lea Berkemeier and Wim Kamphuis and Hilbrand Oldenhuis and Kok, \{Robin N\} and Ruud Verdaasdonk and \{van Gemert-Pijnen\}, Lisette",

year = "2026",

month = apr,

day = "22",

doi = "10.1007/s10926-026-10395-7",

language = "English",

pages = "1--13",

journal = "Journal of Occupational Rehabilitation",

issn = "1053-0487",

publisher = "Springer New York",

}

TY - JOUR

T1 - Predicting Emotional Exhaustion with Multimodal Sensor Data During Return‑to‑Work Trajectories

T2 - A 6‑Month Longitudinal Study

AU - Berkemeier, Lea

AU - Kamphuis, Wim

AU - Oldenhuis, Hilbrand

AU - Kok, Robin N

AU - Verdaasdonk, Ruud

AU - van Gemert-Pijnen, Lisette

PY - 2026/4/22

Y1 - 2026/4/22

N2 - Purpose: Emotional exhaustion is a core component of burnout and impacts return-to-work trajectories following sick leave due to burnout or stress. Previous research identified links between emotional exhaustion and sleep, physical activity, mobility, and smartphone usage, yet little is known about how these associations vary within and between individuals over time. This study examined how emotional exhaustion can be monitored and predicted using multimodal data from smartphones and smart rings during return-to-work trajectories. Methods: Eighteen employees on sick leave in the Netherlands due to stress or burnout symptoms were recruited via occupational physicians. For six months, participants completed daily Ecological Momentary Assessments (EMAs) of emotional exhaustion and provided multimodal sensor data on sleep and physical activity (Oura ring), mobility, and phone usage patterns (Avicenna app). Between- and within-person associations were examined using correlational analyses and linear mixed models. Subject-dependent Random Forest (RF) models were trained to assess the predictive performance of multimodal features. Results: Subject-dependent RF models achieved an average Spearman’s ρ̄ of 0.38 (range: 0.10–0.72). Sleep and physical activity features showed more consistent associations with emotional exhaustion than mobility and smartphone usage patterns, which were more heterogeneous. The strength and direction of associations, as well as the most predictive features, varied substantially between participants. Conclusions: Multimodal device data can modestly predict emotional exhaustion, with performance varying by individual. Results indicate that emotional exhaustion patterns are highly variable among employees, necessitating individualized approaches to return-to-work counselling. Future research should incorporate longer monitoring periods and examine inter- and intra-individual variability.

AB - Purpose: Emotional exhaustion is a core component of burnout and impacts return-to-work trajectories following sick leave due to burnout or stress. Previous research identified links between emotional exhaustion and sleep, physical activity, mobility, and smartphone usage, yet little is known about how these associations vary within and between individuals over time. This study examined how emotional exhaustion can be monitored and predicted using multimodal data from smartphones and smart rings during return-to-work trajectories. Methods: Eighteen employees on sick leave in the Netherlands due to stress or burnout symptoms were recruited via occupational physicians. For six months, participants completed daily Ecological Momentary Assessments (EMAs) of emotional exhaustion and provided multimodal sensor data on sleep and physical activity (Oura ring), mobility, and phone usage patterns (Avicenna app). Between- and within-person associations were examined using correlational analyses and linear mixed models. Subject-dependent Random Forest (RF) models were trained to assess the predictive performance of multimodal features. Results: Subject-dependent RF models achieved an average Spearman’s ρ̄ of 0.38 (range: 0.10–0.72). Sleep and physical activity features showed more consistent associations with emotional exhaustion than mobility and smartphone usage patterns, which were more heterogeneous. The strength and direction of associations, as well as the most predictive features, varied substantially between participants. Conclusions: Multimodal device data can modestly predict emotional exhaustion, with performance varying by individual. Results indicate that emotional exhaustion patterns are highly variable among employees, necessitating individualized approaches to return-to-work counselling. Future research should incorporate longer monitoring periods and examine inter- and intra-individual variability.

KW - emotionele uitputting

KW - werknemer

KW - longitudionaal

KW - werkhervatting

KW - arbeidsongeschikt

KW - draagbare sensoren

KW - Emotional exhaustion

KW - Employee

KW - Longitudinal

KW - Return-to-work

KW - Sick-listed

KW - Wearable sensors

U2 - 10.1007/s10926-026-10395-7

DO - 10.1007/s10926-026-10395-7

M3 - Article

SN - 1053-0487

SP - 1

EP - 13

JO - Journal of Occupational Rehabilitation

JF - Journal of Occupational Rehabilitation

ER -

Predicting Emotional Exhaustion with Multimodal Sensor Data During Return‑to‑Work Trajectories: A 6‑Month Longitudinal Study

Abstract

UN SDGs

Keywords

Research Focus Areas Hanze University of Applied Sciences * (mandatory by Hanze)

Research Focus Areas Research Centre or Centre of Expertise * (mandatory by Hanze)

Publinova themes

Access to Document

Fingerprint

Research output

Does Wearable-Measured Heart Rate Variability During Sleep Predict Perceived Morning Mental and Physical Fitness?

Predicting subjective stress using wearable-measured sleep and resting HRV

Towards continuous mental state detection in everyday settings: investigating between-subjects variations in a longitudinal study

Cite this