The Feasibility of Wearable and Self-Report Stress Detection Measures in a Semi-Controlled Lab Environment

Aristizabal, Sara; Byun, Kunjoon; Wood, Nadia; Mullan, Aidan F.; Porter, Paige; Campanella, Carolina; Jamrozik, Anja; Nenadic, Ivan; Bauer, Brent A.

doi:10.1109/access.2021.3097038

Cited by 28 publications

(19 citation statements)

References 103 publications

(104 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is also interesting to look at the influence of anxiety on skin temperature. Aristizabal et al [ 33 ] did not find a significant effect of anxiety on the ST. According to them, the body temperature can give information about the intensity of the stress response but is also highly influenced by environmental conditions such as the temperature or the humidity and is, therefore, more suitable for laboratory studies.…”

Section: Modelsmentioning

confidence: 96%

“…Neural networks are widely used, particularly CNNs, which are applied to both EEG and a combination of physiological signals. When working on EEG, a two-dimensional (2D) CNN was used [ 21 , 32 ]; for other signals, a one-dimensional (1D) CNN was used [ 16 , 33 ]. CNN is a multilayer perceptron with several convolution-pooling layers and fully connected layers at the output.…”

Section: Modelsmentioning

confidence: 99%

“…A combination of skin temperature (ST), EDA, RSP, and HR led to the best performance using SVM, followed by a study [ 28 ] using only EEG and a study [ 23 ] that combined ECG and EEG. For neural networks, the best accuracy was obtained with the study [ 33 ] that combined EDA, PPG, and ST. Good performance corresponding to accuracy above 85% was also achieved with EEG or EEG combined with ECG, EDA, and EMG. In contrast, a study [ 16 ] using ECG, ST, and RSP had lower accuracy results of 77%.…”

Section: Modelsmentioning

confidence: 99%

“…EDA = electrodermal activity; ECG = electrocardiogram; EEG = electroencephalography; RSP = respiration; ST = skin temperature; PPG = photoplethysmogram; N/R = not reported. The included studies are [ 15 , 16 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 ].…”

Section: Figurementioning

confidence: 99%

See 3 more Smart Citations

Machine Learning for Anxiety Detection Using Biosignals: A Review

2022

View full text Add to dashboard Cite

Anxiety disorder (AD) is a major mental health illness. However, due to the many symptoms and confounding factors associated with AD, it is difficult to diagnose, and patients remain untreated for a long time. Therefore, researchers have become increasingly interested in non-invasive biosignals, such as electroencephalography (EEG), electrocardiogram (ECG), electrodermal response (EDA), and respiration (RSP). Applying machine learning to these signals enables clinicians to recognize patterns of anxiety and differentiate a sick patient from a healthy one. Further, models with multiple and diverse biosignals have been developed to improve accuracy and convenience. This paper reviews and summarizes studies published from 2012 to 2022 that applied different machine learning algorithms with various biosignals. In doing so, it offers perspectives on the strengths and weaknesses of current developments to guide future advancements in anxiety detection. Specifically, this literature review reveals promising measurement accuracies ranging from 55% to 98% for studies with sample sizes of 10 to 102 participants. On average, studies using only EEG seemed to obtain the best performance, but the most accurate results were obtained with EDA, RSP, and heart rate. Random forest and support vector machines were found to be widely used machine learning methods, and they lead to good results as long as feature selection has been performed. Neural networks are also extensively used and provide good accuracy, with the benefit that no feature selection is needed. This review also comments on the effective combinations of modalities and the success of different models for detecting anxiety.

show abstract

Section: Modelsmentioning

confidence: 96%

Section: Modelsmentioning

confidence: 99%

Section: Modelsmentioning

confidence: 99%

Section: Figurementioning

confidence: 99%

See 2 more Smart Citations

Machine Learning for Anxiety Detection Using Biosignals: A Review

2022

View full text Add to dashboard Cite

show abstract

“…Wearable devices are one approach to measuring an individual’s physiological responses ( Can et al, 2019 ). Acute stress has been shown to increase heart rate ( Kirschbaum et al, 1993 ) and increase self-report of stress and anxiety ( Aristizabal et al, 2021b ). Neural activity recorded using electroencephalography (EEG) has been shown to detect changes in spectral power during different epochs of a stress induction task.…”

Section: Introductionmentioning

confidence: 99%

Investigating How Auditory and Visual Stimuli Promote Recovery After Stress With Potential Applications for Workplace Stress and Burnout: Protocol for a Randomized Trial

Byun

Aristizabal

et al. 2022

Front. Psychol.

Self Cite

View full text Add to dashboard Cite

BackgroundWork-related stress is one of the top sources of stress amongst working adults. Relaxation rooms are one organizational strategy being used to reduce workplace stress. Amongst healthcare workers, relaxation rooms have been shown to improve perceived stress levels after 15 min of use. However, few studies have examined physiological and cognitive changes after stress, which may inform why relaxation rooms reduce perceived stress. Understanding the biological mechanisms governing why perceived stress improves when using a relaxation room could lead to more effective strategies to address workplace stress.ObjectiveThe purpose of this research study is to understand how physiological measures, cognitive performance, and perceived stress change after acute stress and whether certain sensory features of a relaxation room are more effective at promoting recovery from stress.Methods80 healthy adults will perform a stress induction task (Trier Social Stress Test, TSST) to evaluate how physiological and cognitive responses after stress are affected by sensory features of a relaxation room. After the stress induction task, participants will recover for 40 min in a MindBreaks™ relaxation room containing auditory and visual stimuli designed to promote relaxation. Participants will be randomized into four cohorts to experience auditory and visual stimuli; auditory stimuli; visual stimuli; or no stimuli in the room. Measures of heart rate and neural activity will be continuously monitored using wearable devices. Participants will perform working memory assessments and rate their perceived stress levels throughout the experiment. These measures will be compared before and after the stress induction task to determine how different sensory stimuli affect the rate at which individuals recover.ResultsRecruitment started in December 2021 and will continue until December 2022 or until enrollment is completed. Final data collection and subsequent analysis are anticipated by December 2022. We expect all trial results will be available by early 2023.DiscussionFindings will provide data and information about which sensory features of a relaxation room are most effective at promoting recovery after acute stress. This information will be useful in determining how these features might be effective at creating individualized and organizational strategies for mitigating the effects of workplace stress.

show abstract

Automatic detection of the mental state in responses towards relaxation

Sagastibeltza

Salazar-Ramirez

Martínez

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

Nowadays, considering society’s highly demanding lifestyles, it is important to consider the usefulness of relaxation from the perspective of both psychology and clinical practice. The response towards relaxation (RResp) is a mind-body interaction that relaxes the organism or compensates for the physiological effects caused by stress. This work aims to automatically detect the different mental states (relaxation, rest and stress) in which RResps may occur so that complete feedback about the quality of the relaxation can be given to the subject itself, the psychologist or the doctor. To this end, an experiment was conducted to induce both states of stress and relaxation in a sample of 20 university students (average age of $$25.76\pm 3.7$$ 25.76 ± 3.7 years old). The electrocardiographic and electrodermal activity signals collected from the participants produced a dataset with 1641 episodes or instances in which the previously mentioned mental states take place. This data was used to extract up to 50 features and train several supervised learning algorithms (rule-based, trees, probabilistic, ensemble classifiers, etc.) using and not using feature selection techniques. Besides, the authors synthesised the cardiac activity information into a single new feature and discretised it down to three levels. The experimentation revealed which features were most discriminating, reaching a classification average accuracy of up to $$94.01\pm 1.73$$ 94.01 ± 1.73 % with the 6 most relevant features for the own-collected dataset. Finally, being restrictive, the same solution/subspace was tested with a dataset referenced in the bibliography (WESAD) and scored an average accuracy of $$90.36\pm 1.62$$ 90.36 ± 1.62 %.

show abstract

The Feasibility of Wearable and Self-Report Stress Detection Measures in a Semi-Controlled Lab Environment

Abstract: This work was supported by Delos Living, Limited Liability Company (LLC). This work involved human subjects or animals in its research. Approval of all ethical and experimental procedures and protocols was granted by the Mayo Clinic Institutional Review Board under IRB No. 17-009303.

Cited by 28 publications

References 103 publications

Machine Learning for Anxiety Detection Using Biosignals: A Review

Machine Learning for Anxiety Detection Using Biosignals: A Review

Investigating How Auditory and Visual Stimuli Promote Recovery After Stress With Potential Applications for Workplace Stress and Burnout: Protocol for a Randomized Trial

Automatic detection of the mental state in responses towards relaxation

Contact Info

Product

Resources

About