Prediction of Self-Perceived Stress and Arousal Based on Electrodermal Activity

Individualized Stress Mobile Sensing Using Self-Supervised Pre-Training

Stress is widely recognized as a major contributor to a variety of health issues. Stress prediction using biosignal data recorded by wearables is a key area of study in mobile sensing research because real-time stress prediction can enable digital interventions to immediately react at the onset of stress, helping to avoid many psychological and physiological symptoms such as heart rhythm irregularities. Electrodermal activity (EDA) is often used to measure stress. However, major challenges with the prediction of stress using machine learning include the subjectivity and sparseness of the labels, a large feature space, relatively few labels, and a complex nonlinear and subjective relationship between the features and outcomes. To tackle these issues, we examined the use of model personalization: training a separate stress prediction model for each user. To allow the neural network to learn the temporal dynamics of each individual's baseline biosignal patterns, thus enabling personalization with very few labels, we pre-trained a one-dimensional convolutional neural network (1D CNN) using self-supervised learning (SSL). We evaluated our method using the Wearable Stress and Affect Detection(WESAD) dataset. We fine-tuned the pre-trained networks to the stress-prediction task and compared against equivalent models without any self-supervised pre-training. We discovered that embeddings learned using our pre-training method outperformed the supervised baselines with significantly fewer labeled data points: the models trained with SSL required less than 30% of the labels to reach equivalent performance without personalized SSL. This personalized learning method can enable precision health systems that are tailored to each subject and require few annotations by the end user, thus allowing for the mobile sensing of increasingly complex, heterogeneous, and subjective outcomes such as stress.

Impact of acute psychosocial stress on attentional control in humans. A study of evoked potentials and pupillary response

Psychosocial stress has increased considerably in our modern lifestyle, affecting global mental health. Deficits in attentional control are cardinal features of stress disorders and pathological anxiety. Studies suggest that changes in the locus coeruleus-norepinephrine system could underlie the effects of stress on top-down attentional control. However, the impact of psychosocial stress on attentional processes and its underlying neural mechanisms are poorly understood. This study aims to investigate the effect of psychosocial stress on attentional processing and brain signatures. Evoked potentials and pupillary activity related to the oddball auditory paradigm were recorded before and after applying the Montreal Imaging Stress Task (MIST). Electrocardiogram (ECG), salivary cortisol, and subjective anxiety/stress levels were measured at different experimental periods. The control group experienced the same physical and cognitive effort but without the psychosocial stress component. The results showed that stressed subjects exhibited decreased P3a and P3b amplitude, pupil phasic response, and correct responses. On the other hand, they displayed an increase in Mismatch Negativity (MMN). N1 amplitude after MIST only decreased in the control group. We found that differences in P3b amplitude between the first and second oddball were significantly correlated with pupillary dilation and salivary cortisol levels. Our results suggest that under social-evaluative threat, basal activity of the coeruleus-norepinephrine system increases, enhancing alertness and decreasing voluntary attentional resources for the cognitive task. These findings contribute to understanding the neurobiological basis of attentional changes in pathologies associated with chronic psychosocial stress.

Wearables measuring electrodermal activity to assess perceived stress in care: a scoping review

BACKGROUND

Chronic stress responses can lead to physical and behavioural health problems, often experienced and observed in the care of people with intellectual disabilities or people with dementia. Electrodermal activity (EDA) is a bio-signal for stress, which can be measured by wearables and thereby support stress management. However, the how, when and to what extent patients and healthcare providers can benefit is unclear. This study aims to create an overview of available wearables enabling the detection of perceived stress by using EDA.

METHODS

Following the PRISMA-SCR protocol for scoping reviews, four databases were included in the search of peer-reviewed studies published between 2012 and 2022, reporting detection of EDA in relation to self-reported stress or stress-related behaviours. Type of wearable, bodily location, research population, context, stressor type and the reported relationship between EDA and perceived stress were extracted.

RESULTS

Of the 74 included studies, the majority included healthy subjects in laboratory situations. Field studies and studies using machine learning (ML) to predict stress have increased in the last years. EDA is most often measured on the wrist, with offline data processing. Studies predicting perceived stress or stress-related behaviour using EDA features, reported accuracies between 42% and 100% with an average of 82.6%. Of these studies, the majority used ML.

CONCLUSION

Wearable EDA sensors are promising in detecting perceived stress. Field studies with relevant populations in a health or care context are lacking. Future studies should focus on the application of EDA-measuring wearables in real-life situations to support stress management.

Investigating the effectiveness of immersive VR skill training and its link to physiological arousal

This paper details the motivations, design, and analysis of a study using a fine motor skill training task in both VR and physical conditions. The objective of this between-subjects study was to (a) investigate the effectiveness of immersive virtual reality for training participants in the 'buzz-wire' fine motor skill task compared to physical training and (b) investigate the link between participants' arousal with their improvements in task performance. Physiological arousal levels in the form of  electro-dermal activity (EDA) and ECG (Electrocardiogram) data were collected from 87 participants, randomly distributed across the two conditions. Results indicated that VR training is as good as, or even slightly better than, training in physical training in improving task performance. Moreover, the participants in the VR condition reported an increase in self-efficacy and immersion, while marginally significant differences were observed in the presence and the temporal demand (retrieved from NASA-TLX measurements). Participants in the VR condition showed on average less arousal than those in the physical condition. Though correlation analyses between performance metrics and arousal levels did not depict any statistically significant results, a closer examination of EDA values revealed that participants with lower arousal levels during training, across conditions, demonstrated better improvements in performance than those with higher arousal. These findings demonstrate the effectiveness of VR in training and the potential of using arousal and training performance data for designing adaptive VR training systems. This paper also discusses implications for researchers who consider using biosensors and VR for motor skill experiments.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10055-022-00699-3.

Current trends and opportunities in the methodology of electrodermal activity measurement

Electrodermal activity (EDA) has been measured in the laboratory since the late 1800s. Although the influence of sudomotor nerve activity and the sympathetic nervous system on EDA is well established, the mechanisms underlying EDA signal generation are not completely understood. Owing to simplicity of instrumentation and modern electronics, these measurements have recently seen a transfer from the laboratory to wearable devices, sparking numerous novel applications while bringing along both challenges and new opportunities. In addition to developments in electronics and miniaturization, current trends in material technology and manufacturing have sparked innovations in electrode technologies, and trends in data science such as machine learning and sensor fusion are expanding the ways that measurement data can be processed and utilized. Although challenges remain for the quality of wearable EDA measurement, ongoing research and developments may shorten the quality gap between wearable EDA and standardized recordings in the laboratory. In this topical review, we provide an overview of the basics of EDA measurement, discuss the challenges and opportunities of wearable EDA, and review recent developments in instrumentation, material technology, signal processing, modeling and data science tools that may advance the field of EDA research and applications over the coming years.

The Concept of Advanced Multi-Sensor Monitoring of Human Stress

Many people live under stressful conditions which has an adverse effect on their health. Human stress, especially long-term one, can lead to a serious illness. Therefore, monitoring of human stress influence can be very useful. We can monitor stress in strictly controlled laboratory conditions, but it is time-consuming and does not capture reactions, on everyday stressors or in natural environment using wearable sensors, but with limited accuracy. Therefore, we began to analyze the current state of promising wearable stress-meters and the latest advances in the record of related physiological variables. Based on these results, we present the concept of an accurate, reliable and easier to use telemedicine device for long-term monitoring of people in a real life. In our concept, we ratify with two synchronized devices, one on the finger and the second on the chest. The results will be obtained from several physiological variables including electrodermal activity, heart rate and respiration, body temperature, blood pressure and others. All these variables will be measured using a coherent multi-sensors device. Our goal is to show possibilities and trends towards the production of new telemedicine equipment and thus, opening the door to a widespread application of human stress-meters.

Development of a Web-Based Intervention Course to Promote Students' Well-Being and Studying in Universities: Protocol for an Experimental Study Design

BACKGROUND

The decline in the well-being among university students well as increasing dropouts has become a serious issue in universities around the world. Thus, effective ways to support students' well-being and their ability to study are highly needed.

OBJECTIVE

The purpose of this study was to build an intervention course for university students, which promotes both students' well-being as well as their learning and study skills, and to describe the experimental study design that explores the effects of this intervention course.

METHODS

Research has shown that psychological flexibility has a great effect on the well-being as well as the study skills of students pursuing higher education. The basis of our intervention course was to promote psychological flexibility and students' study skills with the help of peer support and reflection.

RESULTS

This course was offered as a voluntary course to all the students at the University of Helsinki twice during the academic year 2020-2021. The first course was from October to December and the second course was from January to March. This course was advertised in fall 2020 through social media and by different student organizations and program leaders at different faculties of the University of Helsinki. As of October 2020, we enrolled 566 students comprising 310 students for the course in fall 2020 and 256 students for the course in spring 2021. Of the 256 students who enrolled in the second course, 170 students voluntarily participated in this study and they answered the questionnaires, including all the measures, simultaneously with the participants in the first group and thus served as the control group. The effect of this course will be measured with multiple data, including questionnaire data, reflective journals, and physiological data of well-being with a longitudinal experimental design. This research very strictly follows the ethical guidelines drawn up by the Finnish National Board on Research Integrity. We expect to publish the results of this study in fall 2021 at the latest.

CONCLUSIONS

We argue that a web-based, 8-week intervention course, which promotes both student well-being and their study skills, is a good way to support students pursuing higher education, and both aspects should be considered when supporting university students.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/23613.

Reveal Temporal Patterns of Smoking Behavior in Real Life Using Data Acquired through Automatic Tracking Systems

Accurately monitoring and modeling smoking behavior in real life settings is critical for designing and delivering appropriate smoking-cessation interventions through mHealth applications. In this paper, we inspect smoking patterns based on data collected from 52 volunteers during a 4-week period of their everyday lives. These data are acquired by an automatic data acquisition system comprising an electric lighter, two wearable sensors and one mobile phone, which together can automatically track smoking events, collect concurrent context and physiology, and trigger pop-up questionnaires. We visualize temporal patterns of smoking at the level of the week, day and time of the day. Statistical analysis on all subjects has demonstrated significant differences at the levels evaluated. Distinct emotions during smoking at individual level are also found. Quantified smoking patterns can upgrade our understanding of individual behaviors and contribute to optimizing intervention plans.