Prediction of Stress Coping Capabilities from Nightly Heart Rate Patterns using Machine Learning


Linda Vorberg; Siri Pflueger; Robert Richer; Katharina M Jaeger; Arne Küderle; Nicolas Rohleder; Bjoern M Eskofier

Abstract


Stress is related to short- and long-term alterations in stress systems, including the hypothalamic-pituitary-adrenal (HPA) axis and the sympathetic nervous system (SNS). While it is well established that stress experienced during the day can affect sleep quality, less is known about how it affects stress systems during the night. We assume that stress coping strategies can have an impact on how stress carries over into the night and that individuals with bad coping mechanisms show elevated activation of stress systems during sleep. For that reason, we recorded the heart rate (HR) and heart rate variability (HRV) of 21 healthy participants on two consecutive nights during sleep and the first hour after awakening, Additionally, we extracted cortisol and alpha-amylase from saliva samples collected in the first hour after awakening and assessed stress coping capabilities using self-reports. To analyze the relationship between HR(V) parameters and stress coping we performed backward stepwise regression models and trained different machine learning-based regression algorithms to predict positive (SVF_Pos) and negative (SVF_Neg) stress coping capabilities, respectively. Our results show that individuals with higher SVF_Neg scores showed higher SNS activity during the night, whereas higher SVF_Pos scores indicated lower SNS activity. SVF_Pos was predicted with a mean absolute error (MAE) of 1.51±0.73 and SVF_Neg with an MAE of 2.79±1.53. Our findings indicate an association between nightly HR(V) and the individual's capability of coping with stress. This provides further information about how stress influences sleep and might be used for tailored intervention and feedback on successful stress coping.

Keywords: Stress Coping; Sleep; Cortisol Awakening Response; Heart Rate Variability; Machine Learning

Links

[Full text PDF][Bibtex]