Assessing the added value of context during stress detection from wearable data

• Published in: BMC medical informatics and decision making Vol. 22; no. 1; pp. 1 - 268
• Main Authors: Stojchevska, Marija, Steenwinckel, Bram, Van Der Donckt, Jonas, De Brouwer, Mathias, Goris, Annelies, De Turck, Filip, Van Hoecke, Sofie, Ongenae, Femke
• Format: Journal Article
• Language: English
• Published: London BioMed Central Ltd 15.10.2022; BioMed Central; BMC
• Subjects: Automation; Chills; Context; Context-aware; Data entry; Diagnosis; Eating disorders; Electrocardiography; Evaluation; Experiments; Health informatics; Heart rate; Insomnia; Learning algorithms; Machine learning; Mental disorders; Methods; Physiology; Post traumatic stress disorder; Questionnaires; Sensors; Skin; Sleep; Sleep disorders; Smartphones; Stress; Stress (physiology); Stress (Psychology); Stress response; Sweating; Wearable computers; Wearable health; Wearable technology; United States
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-022-02010-5

Abstract Background Insomnia, eating disorders, heart problems and even strokes are just some of the illnesses that reveal the negative impact of stress overload on health and well-being. Early detection of stress is therefore of utmost importance. Whereas the gold-standard for detecting stress is by means of questionnaires, more recent work uses wearable sensors to find continuous and qualitative physical markers of stress. As some physiological stress responses, e.g. increased heart rate or sweating and chills, might also occur when doing sports, a more profound approach is needed for stress detection than purely considering physiological data. Methods In this paper, we analyse the added value of context information during stress detection from wearable data. We do so by comparing the performance of models trained purely on physiological data and models trained on physiological and context data. We consider the user’s activity and hours of sleep as context information, where we compare the influence of user-given context versus machine learning derived context. Results Context-aware models reach higher accuracy and lower standard deviations in comparison to the baseline (physiological) models. We also observe higher accuracy and improved weighted F1 score when incorporating machine learning predicted, instead of user-given, activities as context information. Conclusions In this paper we show that considering context information when performing stress detection from wearables leads to better performance. We also show that it is possible to move away from human labeling and rely only on the wearables for both physiology and context.