Detection of Stress in Naturalistic Settings Through Passive Mobile Sensing
- 1Donders Center for Cognitive Neuroscience
Abstract
Unobtrusive stress detection using wearable sensors could enable scalable, continuous mental-health monitoring. However, stress is an inherently subjective state that can only be inferred indirectly from physiological signals, making generalizable detection in naturalistic settings challenging. Although prior work has focused on improving model performance, it remains unclear whether wearable physiology supports a shared cross-individual mapping to subjective stress or whether this relationship is fundamentally person-specific. We evaluated feature-based and deep-learning models across multiple physiological modalities using ecological momentary assessment (EMA) as the reference standard, comparing within- and between-individual modeling approaches. Within-individual models achieved modest but consistent improvements in stress detection, whereas between-individual models consistently failed to generalize, yielding negative R2 values despite multimodal fusion and high-capacity architectures. Error analyses revealed regression to the mean, reduced sensitivity to high-stress states, and residual associations with general physiological activation, highlighting the limited stress specificity of wearable physiology. These findings suggest that wearable stress detection is fundamentally a personalized inference problem and that future systems should prioritize individual adaptation and contextual modeling over universal stress predictors.
Related
- Passive Cell-Flux Partitioning Enables Single-Cell-Constrained Impedance Sensing From High-Density Microbial Cultures
- Combined active-passive remote sensing inversion of grassland aboveground biomass on the Qinghai-Tibet plateaus and exploration of its driving mechanisms with optical-radar-meteorological systems
- From Passive Drift to Olfactory Detection? A Late‐Stage Oceanic Juvenile Hawksbill's 9000‐km Journey Across the Western Indian Ocean
- Low-intensity ultrasound drives offline neuromodulation through passive membrane mechanisms in synaptically isolated hippocampal neurons
- Discovery and promotion of unknown sounds into operational detection targets for underwater passive acoustic monitoring under false alarm constraints
BibTeX
@misc{acan2026detection,
title = {{Detection of Stress in Naturalistic Settings Through Passive Mobile Sensing}},
author = {S. Acan and M. Dresler and E. Hermans and P. De Looff and M. Baratchi},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.28.745906},
url = {https://www.biorxiv.org/content/10.64898/2026.08.28.745906v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Detection of Stress in Naturalistic Settings Through Passive Mobile Sensing
AU - S. Acan
AU - M. Dresler
AU - E. Hermans
AU - P. De Looff
AU - M. Baratchi
PY - 2026
DA - 2026/08/28
PB - bioRxiv
DO - 10.64898/2026.08.28.745906
UR - https://www.biorxiv.org/content/10.64898/2026.08.28.745906v1
AB - Unobtrusive stress detection using wearable sensors could enable scalable, continuous mental-health monitoring. However, stress is an inherently subjective state that can only be inferred indirectly from physiological signals, making generalizable detection in naturalistic settings challenging. Although prior work has focused on improving model performance, it remains unclear whether wearable physiology supports a shared cross-individual mapping to subjective stress or whether this relationship is fundamentally person-specific. We evaluated feature-based and deep-learning models across multiple physiological modalities using ecological momentary assessment (EMA) as the reference standard, comparing within- and between-individual modeling approaches. Within-individual models achieved modest but consistent improvements in stress detection, whereas between-individual models consistently failed to generalize, yielding negative R2 values despite multimodal fusion and high-capacity architectures. Error analyses revealed regression to the mean, reduced sensitivity to high-stress states, and residual associations with general physiological activation, highlighting the limited stress specificity of wearable physiology. These findings suggest that wearable stress detection is fundamentally a personalized inference problem and that future systems should prioritize individual adaptation and contextual modeling over universal stress predictors.
ER -