Exploring the feasibility of modeling next-day fatigue and sleepiness using digital sleep tracker data in neurodegenerative and immune-mediated inflammatory diseases

Bing Zhai; Luan Chen; Xujun Ma; Clémence Pinaud; Meenakshi Chatterjee; Juha M. Kortelainen; Rana Zia Ur Rehman; Teemu Ahmaniemi; Stefan Avey; Yu Guan; Victoria Macrae; Chloe Hinchliffe; Silvia Del Din; Nikolay V. Manyakov; Robert Göder; Robbin Romijnders; Walter Maetzler; Ralf Reilmann; Svenja Aufenberg; Robin Schubert; C. Janneke van der Woude; Daqing Zhang; Wan Fai Ng

doi:10.3389/fdgth.2026.1752629

Exploring the feasibility of modeling next-day fatigue and sleepiness using digital sleep tracker data in neurodegenerative and immune-mediated inflammatory diseases

Bing Zhai
, Luan Chen
, Xujun Ma
, Clémence Pinaud
, Meenakshi Chatterjee
, Juha M. Kortelainen
, Rana Zia Ur Rehman
, Teemu Ahmaniemi
, Stefan Avey
, Yu Guan
, Victoria Macrae
, Chloe Hinchliffe
, Silvia Del Din
, Nikolay V. Manyakov
, Robert Göder
, Robbin Romijnders
, Walter Maetzler
, Ralf Reilmann
, Svenja Aufenberg
, Robin Schubert

C. Janneke van der Woude, Daqing Zhang, Wan Fai Ng^*

^*Corresponding author for this work

BA6307 Human sensing solutions

Newcastle University
Northumbria University
Télécom SudParis
CY Cergy Paris University
Let It Care
Johnson & Johnson
University of Warwick (WMG)
Johnson & Johnson Innovative Medicine
University of Kiel
University of Münster
Erasmus University Rotterdam

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

Abstract

BACKGROUND: Fatigue and sleep disturbances are highly prevalent in neurodegenerative diseases (NDDs) and immune-mediated inflammatory diseases (IMIDs). Conventional patient-reported outcomes (PROs) are subjective and prone to recall bias; Digital health technologies and wearable sleep trackers offer objective, continuous monitoring of sleep and physiology at home.

OBJECTIVE: This study evaluated the feasibility of using consumer- and research- grade sleep trackers to predict next-day physical and mental fatigue and daytime sleepiness in individuals with NDDs and IMIDs as an exploratory analysis, and examined whether machine-learning models could identify preliminary sleep features to inform future fatigue monitoring research in chronic disease populations.

METHODS: The IDEA-FAST feasibility study enrolled 134 participants (42 healthy adults, 39 NDD, 53 IMID) across four European centres. Over 3,062 nights, participants wore three sleep trackers (BedSensor, ZKONE, DREEM 2) and completed daily fatigue and sleepiness PROs at home. A polysomnography sub-study ( n = 28 ) validated tracker performance. Machine learning models using physiological and sleep-architecture features were evaluated with leave-one-subject-out cross-validation.

RESULTS: Sleep trackers showed moderate PSG agreement. Models demonstrated preliminary discriminative capacity for next-day physical fatigue in healthy adults (AUC = 0.75), driven mainly by respiratory rate and REM sleep duration. In NDD, physical fatigue AUC reached 0.62 under enriched training, with REM latency and deep sleep as key features. Mental fatigue prediction reached AUC = 0.66 in healthy adults; daytime sleepiness AUC = 0.66 in NDD. Findings should be interpreted as exploratory, as outcome binarisation using a global threshold may conflate between-person disease-group differences with within-person symptom variation.

CONCLUSIONS: Wearable sleep trackers show feasibility for objective home-based sleep monitoring, with preliminary evidence supporting sleep physiology as a candidate predictor of next-day physical fatigue in healthy adults. Predictive performance in chronic disease cohorts remains limited, underscoring the need for larger, multimodal studies to establish disease-specific digital fatigue endpoints.

Original language	English
Article number	1752629
Journal	Frontiers in Digital Health
Volume	8
DOIs	https://doi.org/10.3389/fdgth.2026.1752629
Publication status	Published - 2026
MoE publication type	A1 Journal article-refereed

Funding

The author(s) declared that financial support was received for this work and/or its publication. The IDEA-FAST project has received funding from the Innovative Medicines Initiative 2 Joint Undertaking under grant agreement No. 853981. This Joint Undertaking receives support from the European Union's Horizon 2020 research and innovation programme and EFPIA and associated partners. The IMI website can be accessed at https://www.ihi.europa.eu/. SDD (or this work for Mobilise-D papers) was supported by the Mobilise-D project that has received funding from the Innovative Medicines Initiative 2 Joint Undertaking (JU) under grant agreement No. 820820. This JU receives support from the European Union's Horizon 2020 research and innovation program and the European Federation of Pharmaceutical Industries and Associations (EFPIA). SDD was also supported by the Innovative Medicines Initiative 2 Joint Undertaking (IMI2 JU) project IDEA-FAST - Grant Agreement 853981. SDD and WFN were also supported by the National Institute for Health Research (NIHR) Newcastle Biomedical Research Centre (BRC) based at The Newcastle upon Tyne Hospital NHS Foundation Trust, Newcastle University and the Cumbria, Northumberland and Tyne and Wear (CNTW) NHS Foundation Trust. SDD and WFN were also supported by the NIHR/Wellcome Trust Clinical Research Facility (CRF) infrastructure at Newcastle upon Tyne Hospitals NHS Foundation Trust. SDD was supported by the UK Research and Innovation (UKRI) Engineering and Physical Sciences Research Council (EPSRC) (Grant Ref: EP/W031590/1, Grant Ref: EP/X031012/1 and Grant Ref: EP/X036146/1). WFN was also supported by the Health Research Board Ireland (Grant reference: CRFC 2021-005).

Keywords

digital health
IDEA-FAST
immune-mediated inflammatory diseases (IMID)
mental fatigue
neurodegenerative diseases (NDD)
physical fatigue
sleepiness

Access to Document

10.3389/fdgth.2026.1752629Licence: CC BY

Cite this

Zhai, B., Chen, L., Ma, X., Pinaud, C., Chatterjee, M., Kortelainen, J. M., Rehman, R. Z. U., Ahmaniemi, T., Avey, S., Guan, Y., Macrae, V., Hinchliffe, C., Del Din, S., Manyakov, N. V., Göder, R., Romijnders, R., Maetzler, W., Reilmann, R., Aufenberg, S., ... Ng, W. F. (2026). Exploring the feasibility of modeling next-day fatigue and sleepiness using digital sleep tracker data in neurodegenerative and immune-mediated inflammatory diseases. Frontiers in Digital Health, 8, Article 1752629. https://doi.org/10.3389/fdgth.2026.1752629

@article{2a5a92125b8f49c68efbfcdb865c1daf,

title = "Exploring the feasibility of modeling next-day fatigue and sleepiness using digital sleep tracker data in neurodegenerative and immune-mediated inflammatory diseases",

abstract = "BACKGROUND: Fatigue and sleep disturbances are highly prevalent in neurodegenerative diseases (NDDs) and immune-mediated inflammatory diseases (IMIDs). Conventional patient-reported outcomes (PROs) are subjective and prone to recall bias; Digital health technologies and wearable sleep trackers offer objective, continuous monitoring of sleep and physiology at home.OBJECTIVE: This study evaluated the feasibility of using consumer- and research- grade sleep trackers to predict next-day physical and mental fatigue and daytime sleepiness in individuals with NDDs and IMIDs as an exploratory analysis, and examined whether machine-learning models could identify preliminary sleep features to inform future fatigue monitoring research in chronic disease populations.METHODS: The IDEA-FAST feasibility study enrolled 134 participants (42 healthy adults, 39 NDD, 53 IMID) across four European centres. Over 3,062 nights, participants wore three sleep trackers (BedSensor, ZKONE, DREEM 2) and completed daily fatigue and sleepiness PROs at home. A polysomnography sub-study ( n = 28 ) validated tracker performance. Machine learning models using physiological and sleep-architecture features were evaluated with leave-one-subject-out cross-validation. RESULTS: Sleep trackers showed moderate PSG agreement. Models demonstrated preliminary discriminative capacity for next-day physical fatigue in healthy adults (AUC = 0.75), driven mainly by respiratory rate and REM sleep duration. In NDD, physical fatigue AUC reached 0.62 under enriched training, with REM latency and deep sleep as key features. Mental fatigue prediction reached AUC = 0.66 in healthy adults; daytime sleepiness AUC = 0.66 in NDD. Findings should be interpreted as exploratory, as outcome binarisation using a global threshold may conflate between-person disease-group differences with within-person symptom variation. CONCLUSIONS: Wearable sleep trackers show feasibility for objective home-based sleep monitoring, with preliminary evidence supporting sleep physiology as a candidate predictor of next-day physical fatigue in healthy adults. Predictive performance in chronic disease cohorts remains limited, underscoring the need for larger, multimodal studies to establish disease-specific digital fatigue endpoints.",

keywords = "digital health, IDEA-FAST, immune-mediated inflammatory diseases (IMID), mental fatigue, neurodegenerative diseases (NDD), physical fatigue, sleepiness",

author = "Bing Zhai and Luan Chen and Xujun Ma and Cl{\'e}mence Pinaud and Meenakshi Chatterjee and Kortelainen, \{Juha M.\} and Rehman, \{Rana Zia Ur\} and Teemu Ahmaniemi and Stefan Avey and Yu Guan and Victoria Macrae and Chloe Hinchliffe and \{Del Din\}, Silvia and Manyakov, \{Nikolay V.\} and Robert G{\"o}der and Robbin Romijnders and Walter Maetzler and Ralf Reilmann and Svenja Aufenberg and Robin Schubert and \{van der Woude\}, \{C. Janneke\} and Daqing Zhang and Ng, \{Wan Fai\}",

note = "{\textcopyright} 2026 Zhai, Chen, Ma, Pinaud, Chatterjee, Kortelainen, Rehman, Ahmaniemi, Avey, Guan, Macrae, Hinchliffe, Del Din, Manyakov, G{\"o}der, Romijnders, Maetzler, Reilmann, Aufenberg, Schubert, van der Woude, Zhang and Ng. on behalf of IDEA-FAST Project Consortium.",

year = "2026",

doi = "10.3389/fdgth.2026.1752629",

language = "English",

volume = "8",

journal = "Frontiers in Digital Health",

issn = "2673-253X",

publisher = "Frontiers Media",

}

Zhai, B, Chen, L, Ma, X, Pinaud, C, Chatterjee, M, Kortelainen, JM, Rehman, RZU, Ahmaniemi, T, Avey, S, Guan, Y, Macrae, V, Hinchliffe, C, Del Din, S, Manyakov, NV, Göder, R, Romijnders, R, Maetzler, W, Reilmann, R, Aufenberg, S, Schubert, R, van der Woude, CJ, Zhang, D & Ng, WF 2026, 'Exploring the feasibility of modeling next-day fatigue and sleepiness using digital sleep tracker data in neurodegenerative and immune-mediated inflammatory diseases', Frontiers in Digital Health, vol. 8, 1752629. https://doi.org/10.3389/fdgth.2026.1752629

TY - JOUR

T1 - Exploring the feasibility of modeling next-day fatigue and sleepiness using digital sleep tracker data in neurodegenerative and immune-mediated inflammatory diseases

AU - Zhai, Bing

AU - Chen, Luan

AU - Ma, Xujun

AU - Pinaud, Clémence

AU - Chatterjee, Meenakshi

AU - Kortelainen, Juha M.

AU - Rehman, Rana Zia Ur

AU - Ahmaniemi, Teemu

AU - Avey, Stefan

AU - Guan, Yu

AU - Macrae, Victoria

AU - Hinchliffe, Chloe

AU - Del Din, Silvia

AU - Manyakov, Nikolay V.

AU - Göder, Robert

AU - Romijnders, Robbin

AU - Maetzler, Walter

AU - Reilmann, Ralf

AU - Aufenberg, Svenja

AU - Schubert, Robin

AU - van der Woude, C. Janneke

AU - Zhang, Daqing

AU - Ng, Wan Fai

N1 - © 2026 Zhai, Chen, Ma, Pinaud, Chatterjee, Kortelainen, Rehman, Ahmaniemi, Avey, Guan, Macrae, Hinchliffe, Del Din, Manyakov, Göder, Romijnders, Maetzler, Reilmann, Aufenberg, Schubert, van der Woude, Zhang and Ng. on behalf of IDEA-FAST Project Consortium.

PY - 2026

Y1 - 2026

N2 - BACKGROUND: Fatigue and sleep disturbances are highly prevalent in neurodegenerative diseases (NDDs) and immune-mediated inflammatory diseases (IMIDs). Conventional patient-reported outcomes (PROs) are subjective and prone to recall bias; Digital health technologies and wearable sleep trackers offer objective, continuous monitoring of sleep and physiology at home.OBJECTIVE: This study evaluated the feasibility of using consumer- and research- grade sleep trackers to predict next-day physical and mental fatigue and daytime sleepiness in individuals with NDDs and IMIDs as an exploratory analysis, and examined whether machine-learning models could identify preliminary sleep features to inform future fatigue monitoring research in chronic disease populations.METHODS: The IDEA-FAST feasibility study enrolled 134 participants (42 healthy adults, 39 NDD, 53 IMID) across four European centres. Over 3,062 nights, participants wore three sleep trackers (BedSensor, ZKONE, DREEM 2) and completed daily fatigue and sleepiness PROs at home. A polysomnography sub-study ( n = 28 ) validated tracker performance. Machine learning models using physiological and sleep-architecture features were evaluated with leave-one-subject-out cross-validation. RESULTS: Sleep trackers showed moderate PSG agreement. Models demonstrated preliminary discriminative capacity for next-day physical fatigue in healthy adults (AUC = 0.75), driven mainly by respiratory rate and REM sleep duration. In NDD, physical fatigue AUC reached 0.62 under enriched training, with REM latency and deep sleep as key features. Mental fatigue prediction reached AUC = 0.66 in healthy adults; daytime sleepiness AUC = 0.66 in NDD. Findings should be interpreted as exploratory, as outcome binarisation using a global threshold may conflate between-person disease-group differences with within-person symptom variation. CONCLUSIONS: Wearable sleep trackers show feasibility for objective home-based sleep monitoring, with preliminary evidence supporting sleep physiology as a candidate predictor of next-day physical fatigue in healthy adults. Predictive performance in chronic disease cohorts remains limited, underscoring the need for larger, multimodal studies to establish disease-specific digital fatigue endpoints.

AB - BACKGROUND: Fatigue and sleep disturbances are highly prevalent in neurodegenerative diseases (NDDs) and immune-mediated inflammatory diseases (IMIDs). Conventional patient-reported outcomes (PROs) are subjective and prone to recall bias; Digital health technologies and wearable sleep trackers offer objective, continuous monitoring of sleep and physiology at home.OBJECTIVE: This study evaluated the feasibility of using consumer- and research- grade sleep trackers to predict next-day physical and mental fatigue and daytime sleepiness in individuals with NDDs and IMIDs as an exploratory analysis, and examined whether machine-learning models could identify preliminary sleep features to inform future fatigue monitoring research in chronic disease populations.METHODS: The IDEA-FAST feasibility study enrolled 134 participants (42 healthy adults, 39 NDD, 53 IMID) across four European centres. Over 3,062 nights, participants wore three sleep trackers (BedSensor, ZKONE, DREEM 2) and completed daily fatigue and sleepiness PROs at home. A polysomnography sub-study ( n = 28 ) validated tracker performance. Machine learning models using physiological and sleep-architecture features were evaluated with leave-one-subject-out cross-validation. RESULTS: Sleep trackers showed moderate PSG agreement. Models demonstrated preliminary discriminative capacity for next-day physical fatigue in healthy adults (AUC = 0.75), driven mainly by respiratory rate and REM sleep duration. In NDD, physical fatigue AUC reached 0.62 under enriched training, with REM latency and deep sleep as key features. Mental fatigue prediction reached AUC = 0.66 in healthy adults; daytime sleepiness AUC = 0.66 in NDD. Findings should be interpreted as exploratory, as outcome binarisation using a global threshold may conflate between-person disease-group differences with within-person symptom variation. CONCLUSIONS: Wearable sleep trackers show feasibility for objective home-based sleep monitoring, with preliminary evidence supporting sleep physiology as a candidate predictor of next-day physical fatigue in healthy adults. Predictive performance in chronic disease cohorts remains limited, underscoring the need for larger, multimodal studies to establish disease-specific digital fatigue endpoints.

KW - digital health

KW - IDEA-FAST

KW - immune-mediated inflammatory diseases (IMID)

KW - mental fatigue

KW - neurodegenerative diseases (NDD)

KW - physical fatigue

KW - sleepiness

UR - https://www.scopus.com/pages/publications/105044568132

U2 - 10.3389/fdgth.2026.1752629

DO - 10.3389/fdgth.2026.1752629

M3 - Article

C2 - 42388291

AN - SCOPUS:105044568132

SN - 2673-253X

VL - 8

JO - Frontiers in Digital Health

JF - Frontiers in Digital Health

M1 - 1752629

ER -

Exploring the feasibility of modeling next-day fatigue and sleepiness using digital sleep tracker data in neurodegenerative and immune-mediated inflammatory diseases

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

IDEA-FAST: Identifying Digital Endpoints to Assess FAtigue, Sleep and acTivities in daily living in Neurodegenerative disorders and Immune-mediated inflammatory diseases

Cite this

Exploring the feasibility of modeling next-day fatigue and sleepiness using digital sleep tracker data in neurodegenerative and immune-mediated inflammatory diseases

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Projects

IDEA-FAST: Identifying Digital Endpoints to Assess FAtigue, Sleep and acTivities in daily living in Neurodegenerative disorders and Immune-mediated inflammatory diseases

Cite this