Objective detection of chronic stress using physiological parameters

Task-evoked pulse wave amplitude tracks cognitive load

Cognitive load is a crucial factor in mentally demanding activities and holds significance across various research fields. This study aimed to investigate the effectiveness of pulse wave amplitude (PWA) as a measure for tracking cognitive load and associated mental effort in comparison to heart rate (HR) during a digit span task. The data from 78 participants were included in the analyses. Participants performed a memory task in which they were asked to memorize sequences of 5, 9, or 13 digits, and a control task where they passively listened to the sequences. PWA and HR were quantified from photoplethysmography (PPG) and electrocardiography (ECG), respectively. Pupil dilation was also assessed as a measure of cognitive load. We found that PWA showed a strong suppression with increasing memory load, indicating sensitivity to cognitive load. In contrast, HR did not show significant changes with task difficulty. Moreover, when memory load exceeded the capacity of working memory, a reversal of the PWA pattern was observed, indicating cognitive overload. In this respect, changes in PWA in response to cognitive load correlated with the dynamics of pupil dilation, suggesting a potential shared underlying mechanism. Additionally, both HR and PWA demonstrated a relationship with behavioral performance, with higher task-evoked HR and lower PWA associated with better memory performance. Our findings suggest that PWA is a more sensitive measure than HR for tracking cognitive load and overload. PWA, measured through PPG, holds significant potential for practical applications in assessing cognitive load due to its ease of use and sensitivity to cognitive overload. The findings contribute to the understanding of psychophysiological indicators of cognitive load and offer insights into the use of PWA as a non-invasive measure in various contexts.

Real-World Driver Stress Recognition and Diagnosis Based on Multimodal Deep Learning and Fuzzy EDAS Approaches

Mental stress is known as a prime factor in road crashes. The devastation of these crashes often results in damage to humans, vehicles, and infrastructure. Likewise, persistent mental stress could lead to the development of mental, cardiovascular, and abdominal disorders. Preceding research in this domain mostly focuses on feature engineering and conventional machine learning approaches. These approaches recognize different levels of stress based on handcrafted features extracted from various modalities including physiological, physical, and contextual data. Acquiring good quality features from these modalities using feature engineering is often a difficult job. Recent developments in the form of deep learning (DL) algorithms have relieved feature engineering by automatically extracting and learning resilient features. This paper proposes different CNN and CNN-LSTSM-based fusion models using physiological signals (SRAD dataset) and multimodal data (AffectiveROAD dataset) for the driver's two and three stress levels. The fuzzy EDAS (evaluation based on distance from average solution) approach is used to evaluate the performance of the proposed models based on different classification metrics (accuracy, recall, precision, F-score, and specificity). Fuzzy EDAS performance estimation shows that the proposed CNN and hybrid CNN-LSTM models achieved the first ranks based on the fusion of BH, E4-Left (E4-L), and E4-Right (E4-R). Results showed the significance of multimodal data for designing an accurate and trustworthy stress recognition diagnosing model for real-world driving conditions. The proposed model can also be used for the diagnosis of the stress level of a subject during other daily life activities.

Inconclusive evidence that breathing shapes pupil dynamics in humans: a systematic review

More than 50 years ago, it was proposed that breathing shapes pupil dynamics. This widespread idea is also the general understanding currently. However, there has been no attempt at synthesizing the progress on this topic since. We therefore conducted a systematic review of the literature on how breathing affects pupil dynamics in humans. We assessed the effect of breathing phase, depth, rate, and route (nose/mouth). We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, and conducted a systematic search of the scientific literature databases MEDLINE, Web of Science, and PsycInfo in November 2021. Thirty-one studies were included in the final analyses, and their quality was assessed with QualSyst. The study findings were summarized in a descriptive manner, and the strength of the evidence for each parameter was estimated following the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) approach. The effect of breathing phase on pupil dynamics was rated as "low" (6 studies). The effect of breathing depth and breathing rate (6 and 20 studies respectively) were rated as "very low". Breathing route was not investigated by any of the included studies. Overall, we show that there is, at best, inconclusive evidence for an effect of breathing on pupil dynamics in humans. Finally, we suggest some possible confounders to be considered, and outstanding questions that need to be addressed, to answer this fundamental question. Trial registration: This systematic review has been registered in the international prospective register of systematic reviews (PROSPERO) under the registration number: CRD42022285044.

Salivary cortisol, perceived stress and coping strategies: A comparative study of working and nonworking women

AIMS

This study investigated stress levels and coping strategies among working and nonworking women in the United Arab Emirates.

BACKGROUND

Stress levels in working and nonworking women have previously been studied, but few studies used cortisol to measure stress or examined how coping strategies affect stress levels.

METHODS

We employed a cross-sectional design with a convenience sample of women aged 20-65 years. Information on women's sociodemographic characteristics, perceived stress (using the Perceived Stress Scale) and coping strategies (using the Brief-COPE) was collected. Participants' morning (07:00-08:00) and evening (19:00-20:00) cortisol levels were measured using unstimulated saliva samples.

RESULTS

In total, 417 working and 403 nonworking women participated in this study. More nonworking women reported high stress levels than working women (14.1% vs. 4.1%, p = .001). Working women reported more use of informational support and venting to cope with stress compared with nonworking women (94.0% vs. 88.1%, p = .001). More nonworking women had impaired morning (<0.094 mg/dl) and evening (>0.359 mg/dl) cortisol compared with working women (58.1% vs. 28.5% and 41.7% vs. 18.0%, respectively). Compared with working women, nonworking women had 3.25 (95%CI: 2.38, 4.47) and 3.78 (95%CI: 2.65, 5.43) times the odds of impaired morning and evening cortisol, respectively.

CONCLUSION

Nonworking women exhibited higher levels of stress than working women. There is an urgent need to support nonworking women to manage stress through appropriate awareness campaigns and public health policies.

IMPLICATIONS FOR MANAGEMENT

Policymakers and community leaders should consider the mental health of nonworking women as a priority in planning public health policies and programmes. Nurse managers must have a voice in reforming public health policy to support early assessment and management of stress among nonworking women.

Stress and Violence in Video Games: Their Influence on Aggression

This study investigated whether stress or violent content in video games plays a greater role in aggressiveness towards a cooperative partner while playing a video game. It was hypothesized that participants, when exposed to stress, would demonstrate greater aggressiveness toward an incompetent partner than a competent partner. Furthermore, it was hypothesized that participants, when exposed to a violent video game, would demonstrate greater aggression toward an incompetent partner than those exposed to a non-violent video game. Stress was provoked in half of the participants using the Paced Auditory Serial Addition Test (PASAT), while others took a simple math quiz. Participants were then assigned to a video game condition, violent or non-violent with a competent or incompetent confederate and completed a reaction time task to measure aggression. Results indicated that provoked stress and violent content are not linked to aggression in this context.

Towards a Non-Contact Method for Identifying Stress Using Remote Photoplethysmography in Academic Environments

Stress has become a common condition and is one of the chief causes of university course disenrollment. Most of the studies and tests on academic stress have been conducted in research labs or controlled environments, but these tests can not be extended to a real academic environment due to their complexity. Academic stress presents different associated symptoms, anxiety being one of the most common. This study focuses on anxiety derived from academic activities. This study aims to validate the following hypothesis: by using a non-contact method based on the use of remote photoplethysmography (rPPG), it is possible to identify academic stress levels with an accuracy greater than or equal to that of previous works which used contact methods. rPPG signals from 56 first-year engineering undergraduate students were recorded during an experimental task. The results show that the rPPG signals combined with students' demographic data and psychological scales (the State-Trait Anxiety Inventory) improve the accuracy of different classification methods. Moreover, the results demonstrate that the proposed method provides 96% accuracy by using K-nearest neighbors, J48, and random forest classifiers. The performance metrics show better or equal accuracy compared to other contact methods. In general, this study demonstrates that it is possible to implement a low-cost method for identifying academic stress levels in educational environments.

Trends in Heart-Rate Variability Signal Analysis

Heart rate variability (HRV) is the rate of variability between each heartbeat with respect to time. It is used to analyse the Autonomic Nervous System (ANS), a control system used to modulate the body's unconscious action such as cardiac function, respiration, digestion, blood pressure, urination, and dilation/constriction of the pupil. This review article presents a summary and analysis of various research works that analyzed HRV associated with morbidity, pain, drowsiness, stress and exercise through signal processing and machine learning methods. The points of emphasis with regards to HRV research as well as the gaps associated with processes which can be improved to enhance the quality of the research have been discussed meticulously. Restricting the physiological signals to Electrocardiogram (ECG), Electrodermal activity (EDA), photoplethysmography (PPG), and respiration (RESP) analysis resulted in 25 articles which examined the cause and effect of increased/reduced HRV. Reduced HRV was generally associated with increased morbidity and stress. High HRV normally indicated good health, and in some instances, it could signify clinical events of interest such as drowsiness. Effective analysis of HRV during ambulatory and motion situations such as exercise, video gaming, and driving could have a significant impact toward improving social well-being. Detection of HRV in motion is far from perfect, situations involving exercise or driving reported accuracy as high as 85% and as low as 59%. HRV detection in motion can be improved further by harnessing the advancements in machine learning techniques.

Physiological Signal Analysis and Classification of Stress from Virtual Reality Video Game

Stress can affect a person's performance and health positively and negatively. A lot of the relaxation methods have been suggested to reduce the amount of stress. This study used virtual reality (VR) video games to alleviate stress. Physiological signals captured from Electrocardiogram (ECG), galvanic skin response (GSR), and respiration (RESP) were used to determine if the subject was stressed or relaxed. Time and frequency domain features were then extracted to evaluate stress levels. Frequency domain methods such as low-frequency (LF), high-frequency (HF), LF-HF ratio (LF/HF) are considered the most effective for HRV analysis, Poincare plots are moré discerning visually and shares a 81% correlation with LF/HF ratio. GSR is associated with EDA activity, which only increases due to stress. Stress and relax were classified using Linear Discriminant Analysis (LDA), Decision Tree, Support Vector machine (SVM), Gradient Boost (GB), and Naive Bayes. GB performed the best with an accuracy of 85% after 5 fold cross validation with 100 iterations, which is admirable from a small dataset with 50 samples.

Validation of the Raw National Aeronautics and Space Administration Task Load Index (NASA-TLX) Questionnaire to Assess Perceived Workload in Patient Monitoring Tasks: Pooled Analysis Study Using Mixed Models

Background

Patient monitoring is indispensable in any operating room to follow the patient’s current health state based on measured physiological parameters. Reducing workload helps to free cognitive resources and thus influences human performance, which ultimately improves the quality of care. Among the many methods available to assess perceived workload, the National Aeronautics and Space Administration Task Load Index (NASA-TLX) provides the most widely accepted tool. However, only few studies have investigated the validity of the NASA-TLX in the health care sector.

Objective

This study aimed to validate a modified version of the raw NASA-TLX in patient monitoring tasks by investigating its correspondence with expected lower and higher workload situations and its robustness against nonworkload-related covariates. This defines criterion validity.

Methods

In this pooled analysis, we evaluated raw NASA-TLX scores collected after performing patient monitoring tasks in four different investigator-initiated, computer-based, prospective, multicenter studies. All of them were conducted in three hospitals with a high standard of care in central Europe. In these already published studies, we compared conventional patient monitoring with two newly developed situation awareness–oriented monitoring technologies called Visual Patient and Visual Clot. The participants were resident and staff anesthesia and intensive care physicians, and nurse anesthetists with completed specialization qualification. We analyzed the raw NASA-TLX scores by fitting mixed linear regression models and univariate models with different covariates.

Results

We assessed a total of 1160 raw NASA-TLX questionnaires after performing specific patient monitoring tasks. Good test performance and higher self-rated diagnostic confidence correlated significantly with lower raw NASA-TLX scores and the subscores (all P<.001). Staff physicians rated significantly lower workload scores than residents (P=.001), whereas nurse anesthetists did not show any difference in the same comparison (P=.83). Standardized distraction resulted in higher rated total raw NASA-TLX scores (P<.001) and subscores. There was no gender difference regarding perceived workload (P=.26). The new visualization technologies Visual Patient and Visual Clot resulted in significantly lower total raw NASA-TLX scores and all subscores, including high self-rated performance, when compared with conventional monitoring (all P<.001).

Conclusions

This study validated a modified raw NASA-TLX questionnaire for patient monitoring tasks. The scores obtained correctly represented the assumed influences of the examined covariates on the perceived workload. We reported high criterion validity. The NASA-TLX questionnaire appears to be a reliable tool for measuring subjective workload. Further research should focus on its applicability in a clinical setting.