Occupational Stress Monitoring Using Biomarkers and Smartwatches: A Systematic Review

The Effects of Self-Monitoring Using a Smartwatch and Smartphone App on Stress Awareness, Self-Efficacy, and Well-Being-Related Outcomes in Police Officers: Longitudinal Mixed Design Study

Background

Wearable sensor technologies, often referred to as "wearables," have seen a rapid rise in consumer interest in recent years. Initially often seen as "activity trackers," wearables have gradually expanded to also estimate sleep, stress, and physiological recovery. In occupational settings, there is a growing interest in applying this technology to promote health and well-being, especially in professions with highly demanding working conditions such as first responders. However, it is not clear to what extent self-monitoring with wearables can positively influence stress- and well-being-related outcomes in real-life conditions and how wearable-based interventions should be designed for high-risk professionals.

Objective

The aim of this study was to investigate (1) whether offering a 5-week wearable-based intervention improves stress- and well-being-related outcomes in police officers and (2) whether extending a basic "off-the-shelf" wearable-based intervention with ecological momentary assessment (EMA) questionnaires, weekly personalized feedback reports, and peer support groups improves its effectiveness.

Methods

A total of 95 police officers from 5 offices participated in the study. The data of 79 participants were included for analysis. During the first 5 weeks, participants used no self-monitoring technology (control period). During the following 5 weeks (intervention period), 41 participants used a Garmin Forerunner 255 smartwatch with a custom-built app (comparable to that of the consumer-available wearable), whereas the other 38 participants used the same system, but complemented by daily EMA questionnaires, weekly personalized feedback reports, and access to peer support groups. At baseline (T0) and after the control (T1) and intervention (T2) periods, questionnaires were administered to measure 15 outcomes relating to stress awareness, stress management self-efficacy, and outcomes related to stress and general well-being. Linear mixed models that accounted for repeated measures within subjects, the control and intervention periods, and between-group differences were used to address both research questions.

Results

The results of the first analysis showed that the intervention had a small (absolute Hedges g=0.25-0.46) but consistent effect on 8 of 15 of the stress- and well-being-related outcomes in comparison to the control group. The second analysis provided mixed results; the extended intervention was more effective than the basic intervention at improving recovery after work but less effective at improving self-efficacy in behavior change and sleep issues, and similarly effective in the remaining 12 outcomes.

Conclusions

Offering a 5-week wearable-based intervention to police officers can positively contribute to optimizing their stress-related, self-efficacy, and well-being-related outcomes. Complementing the basic "off-the-shelf" wearable-based intervention with additional EMA questionnaires, weekly personalized feedback reports, and peer support groups did not appear to improve the effectiveness of the intervention. Future work is needed to investigate how different aspects of these interventions can be tailored to specific characteristics and needs of employees to optimize these effects.

Depression Recognition Using Daily Wearable-Derived Physiological Data

The objective identification of depression using physiological data has emerged as a significant research focus within the field of psychiatry. The advancement of wearable physiological measurement devices has opened new avenues for the identification of individuals with depression in everyday-life contexts. Compared to other objective measurement methods, wearables offer the potential for continuous, unobtrusive monitoring, which can capture subtle physiological changes indicative of depressive states. The present study leverages multimodal wristband devices to collect data from fifty-eight participants clinically diagnosed with depression during their normal daytime activities over six hours. Data collected include pulse wave, skin conductance, and triaxial acceleration. For comparison, we also utilized data from fifty-eight matched healthy controls from a publicly available dataset, collected using the same devices over equivalent durations. Our aim was to identify depressive individuals through the analysis of multimodal physiological measurements derived from wearable devices in daily life scenarios. We extracted static features such as the mean, variance, skewness, and kurtosis of physiological indicators like heart rate, skin conductance, and acceleration, as well as autoregressive coefficients of these signals reflecting the temporal dynamics. Utilizing a Random Forest algorithm, we distinguished depressive and non-depressive individuals with varying classification accuracies on data aggregated over 6 h, 2 h, 30 min, and 5 min segments, as 90.0%, 84.7%, 80.1%, and 76.0%, respectively. Our results demonstrate the feasibility of using daily wearable-derived physiological data for depression recognition. The achieved classification accuracies suggest that this approach could be integrated into clinical settings for the early detection and monitoring of depressive symptoms. Future work will explore the potential of these methods for personalized interventions and real-time monitoring, offering a promising avenue for enhancing mental health care through the integration of wearable technology.

Efficacy of a program in increasing coping strategies in firefighters: randomized clinical trial

OBJECTIVE

to evaluate the effectiveness of a program in increasing coping strategies focused on military firefighters' problems and emotions.

METHOD

randomized, parallel, single-masked clinical trial. The sample consisted of 51 participants in the intervention group and 49 in the control group. The intervention group received the intervention program including coping strategies based on the Nursing Interventions Classification, lasting six consecutive weeks, one day a week. The control group followed the Service Unit routine. Descriptive statistics, Student's T test with Welch's correction and the Mann-Whitney test were used for the analyses. The magnitude of the intervention effect was calculated using Cohen's d index. A p-value of ≤0.05% was considered.

RESULTS

in the analysis of the mean difference between the scores in the groups, the means of the intervention group increased significantly for the coping strategies: social support (p = 0.009), acceptance of responsibility (p = 0.03), problem solving (p = 0.05) and positive reappraisal (p = 0.05). The impact of the intervention was moderate in magnitude for social support (d = 0.54).

CONCLUSION

the intervention program enabled the increase of coping strategies focused on military firefighters' problems and emotions. ReBEC: RBR-8dmbzc. (1) The intervention program increases coping strategies. (2) The study included military firefighters. (3) Social support was the main strategy of the study. (4) Intervention group presented better results than the control group. (5) The use of the Nursing Intervention Classification was effective.

Natural Language Processing for Work-Related Stress Detection Among Health Professionals: Protocol for a Scoping Review

BACKGROUND

There is an urgent need worldwide for qualified health professionals. High attrition rates among health professionals, combined with a predicted rise in life expectancy, further emphasize the need for additional health professionals. Work-related stress is a major concern among health professionals, affecting both the well-being of health professionals and the quality of patient care.

OBJECTIVE

This scoping review aims to identify processes and methods for the automatic detection of work-related stress among health professionals using natural language processing (NLP) and text mining techniques.

METHODS

This review follows Joanna Briggs Institute Methodology and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. The inclusion criteria for this scoping review encompass studies involving health professionals using NLP for work-related stress detection while excluding studies involving other professions or children. The review focuses on various aspects, including NLP applications for stress detection, criteria for stress identification, technical aspects of NLP, and implications of stress detection through NLP. Studies within health care settings using diverse NLP techniques are considered, including experimental and observational designs, aiming to provide a comprehensive understanding of NLP's role in detecting stress among health professionals. Studies published in English, German, or French from 2013 to present will be considered. The databases to be searched include MEDLINE (via PubMed), CINAHL, PubMed, Cochrane, ACM Digital Library, and IEEE Xplore. Sources of unpublished studies and gray literature to be searched will include ProQuest Dissertations & Theses and OpenGrey. Two reviewers will independently retrieve full-text studies and extract data. The collected data will be organized in tables, graphs, and a qualitative narrative summary. This review will use tables and graphs to present data on studies' distribution by year, country, activity field, and research methods. Results synthesis involves identifying, grouping, and categorizing. The final scoping review will include a narrative written report detailing the search and study selection process, a visual representation using a PRISMA-ScR flow diagram, and a discussion of implications for practice and research.

RESULTS

We anticipate the outcomes will be presented in a systematic scoping review by June 2024.

CONCLUSIONS

This review fills a literature gap by identifying automated work-related stress detection among health professionals using NLP and text mining, providing insights on an innovative approach, and identifying research needs for further systematic reviews. Despite promising outcomes, acknowledging limitations in the reviewed studies, including methodological constraints, sample biases, and potential oversight, is crucial to refining methodologies and advancing automatic stress detection among health professionals.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/56267.

Uninterrupted real-time cerebral stress level monitoring using wearable biosensors: A review

Stress is the major unseen bug for the health of humans with the increasing workaholic era. Long periods of avoidance are the main precursor for chronic disorders that are quite tough to treat. As precaution is better than cure, stress detection and monitoring are vital. Although there are ways to measure stress clinically, there is still a constant need and demand for methods that measure stress personally and in an ex vitro manner for the convenience of the user. The concept of continuous stress monitoring has been introduced to tackle the issue of unseen stress accumulating in the body simultaneously with being user-friendly and reliable. Stress biosensors nowadays provide real-time, noninvasive, and continuous monitoring of stress. These biosensors are innovative anthropogenic creations that are a combination of biomarkers and indicators like heart rate variation, electrodermal activity, skin temperature, galvanic skin response, and electroencephalograph of stress in the body along with machine learning algorithms and techniques. The collaboration of biological markers, artificial intelligence techniques, and data science tools makes stress biosensors a hot topic for research. These attributes have made continuous stress detection a possibility with ease. The advancement in stress biosensing technologies has made a great impact on the lives of human beings so far. This article focuses on the comprehensive study of stress-indicating biomarkers and the techniques along with principles of the biosensors used for continuous stress detection. The precise overview of wearable stress monitoring systems is also sectioned to pave a pathway for possible future research studies.

Smartwatches in healthcare medicine: assistance and monitoring; a scoping review

Smartwatches have become increasingly popular in recent times because of their capacity to track different health indicators, including heart rate, patterns of sleep, and physical movements. This scoping review aims to explore the utilisation of smartwatches within the healthcare sector. According to Arksey and O'Malley's methodology, an organised search was performed in PubMed/Medline, Scopus, Embase, Web of Science, ERIC and Google Scholar. In our search strategy, 761 articles were returned. The exclusion/inclusion criteria were applied. Finally, 35 articles were selected for extracting data. These included six studies on stress monitoring, six on movement disorders, three on sleep tracking, three on blood pressure, two on heart disease, six on covid pandemic, three on safety and six on validation. The use of smartwatches has been found to be effective in diagnosing the symptoms of various diseases. In particular, smartwatches have shown promise in detecting heart diseases, movement disorders, and even early signs of COVID-19. Nevertheless, it should be emphasised that there is an ongoing discussion concerning the reliability of smartwatch diagnoses within healthcare systems. Despite the potential advantages offered by utilising smartwatches for disease detection, it is imperative to approach their data interpretation with prudence. The discrepancies in detection between smartwatches and their algorithms have important implications for healthcare use. The accuracy and reliability of the algorithms used are crucial, as well as high accuracy in detecting changes in health status by the smartwatches themselves. This calls for the development of medical watches and the creation of AI-hospital assistants. These assistants will be designed to help with patient monitoring, appointment scheduling, and medication management tasks. They can educate patients and answer common questions, freeing healthcare providers to focus on more complex tasks.

Predicting Office Workers' Productivity: A Machine Learning Approach Integrating Physiological, Behavioral, and Psychological Indicators

This research pioneers the application of a machine learning framework to predict the perceived productivity of office workers using physiological, behavioral, and psychological features. Two approaches were compared: the baseline model, predicting productivity based on physiological and behavioral characteristics, and the extended model, incorporating predictions of psychological states such as stress, eustress, distress, and mood. Various machine learning models were utilized and compared to assess their predictive accuracy for psychological states and productivity, with XGBoost emerging as the top performer. The extended model outperformed the baseline model, achieving an R2 of 0.60 and a lower MAE of 10.52, compared to the baseline model's R2 of 0.48 and MAE of 16.62. The extended model's feature importance analysis revealed valuable insights into the key predictors of productivity, shedding light on the role of psychological states in the prediction process. Notably, mood and eustress emerged as significant predictors of productivity. Physiological and behavioral features, including skin temperature, electrodermal activity, facial movements, and wrist acceleration, were also identified. Lastly, a comparative analysis revealed that wearable devices (Empatica E4 and H10 Polar) outperformed workstation addons (Kinect camera and computer-usage monitoring application) in predicting productivity, emphasizing the potential utility of wearable devices as an independent tool for assessment of productivity. Implementing the model within smart workstations allows for adaptable environments that boost productivity and overall well-being among office workers.