Towards Disentangling the Contribution of Different Pathways for the Regulation of Cardiac Activity: A Pilot Study

Ghiasi, Shadi; Greco, Alberto; Faes, Luca; Javorka, Michal; Barbieri, Riccardo; Scilingo, E.P.; Valenza, Gaetano

doi:10.1109/esgco49734.2020.9158187

Cited by 1 publication

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies, such as Mozos et al (2017), Schmidt et al (2018), and Aristizabal et al (2021), have employed the Trier Social Stress Test (TSST) (Kirschbaum et al, 1993), which comprises a public speaking and a mental arithmetic (MA) task. A cold pressor test (CPT), where participants hold their right hand in cold water for a short period (1-3 min), has been used to deliver physical stress (Daniels and Georgiou, 2019;Ghiasi et al, 2020;Mishra et al, 2020a). These protocols have typically had resting sessions between the different stressors and each subtask has been completed just once.…”

Section: Introductionmentioning

confidence: 99%

“…Stressors including social-evaluative or cognitive elements increase blood pressure, HR, blink rate, and EDA activity, decrease HRV (Schuri and von Cramon, 1981;Hellhammer and Schubert, 2012;Aristizabal et al, 2021), and cause significant changes in some spectral EEG parameters (Vanhollebeke et al, 2022). Since CPT triggers a sympathetic activation (Mourot et al, 2008), it causes changes in EDA (Mourot et al, 2008;Ghiasi et al, 2020) and in blink rate (Paparella et al, 2020). However, the HR response to the CPT varies individually: Mourot et al (2008) reported that HR increased continuously during the 3-min CPT for 20 out of 39 participants and decreased for the others after a short initial increase.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Explainable stress type classification captures physiologically relevant responses in the Maastricht Acute Stress Test

Tervonen,

Närväinen,

Mäntyjärvi

et al. 2023

Front. Neuroergonomics

View full text Add to dashboard Cite

IntroductionCurrent stress detection methods concentrate on identification of stress and non-stress states despite the existence of various stress types. The present study performs a more specific, explainable stress classification, which could provide valuable information on the physiological stress reactions.MethodsPhysiological responses were measured in the Maastricht Acute Stress Test (MAST), comprising alternating trials of cold pressor (inducing physiological stress and pain) and mental arithmetics (eliciting cognitive and social-evaluative stress). The responses in these subtasks were compared to each other and to the baseline through mixed model analysis. Subsequently, stress type detection was conducted with a comprehensive analysis of several machine learning components affecting classification. Finally, explainable artificial intelligence (XAI) methods were applied to analyze the influence of physiological features on model behavior.ResultsMost of the investigated physiological reactions were specific to the stressors, and the subtasks could be distinguished from baseline with up to 86.5% balanced accuracy. The choice of the physiological signals to measure (up to 25%-point difference in balanced accuracy) and the selection of features (up to 7%-point difference) were the two key components in classification. Reflection of the XAI analysis to mixed model results and human physiology revealed that the stress detection model concentrated on physiological features relevant for the two stressors.DiscussionThe findings confirm that multimodal machine learning classification can detect different types of stress reactions from baseline while focusing on physiologically sensible changes. Since the measured signals and feature selection affected classification performance the most, data analytic choices left limited input information uncompensated.

show abstract