Investigating Employees’ Concerns and Wishes for Digital Stress Management Interventions with Value Sensitive Design: Mixed Methods Study (Preprint)

Effectiveness of Digital Mental Health Interventions in the Workplace: Umbrella Review of Systematic Reviews

BACKGROUND

There is potential for digital mental health interventions to provide affordable, efficient, and scalable support to individuals. Digital interventions, including cognitive behavioral therapy, stress management, and mindfulness programs, have shown promise when applied in workplace settings.

OBJECTIVE

The aim of this study is to conduct an umbrella review of systematic reviews in order to critically evaluate, synthesize, and summarize evidence of various digital mental health interventions available within a workplace setting.

METHODS

A systematic search was conducted to identify systematic reviews relating to digital interventions for the workplace, using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis). The review protocol was registered in the Open Science Framework. The following databases were searched: PubMed, Web of Science, MEDLINE, PsycINFO, and Cochrane Library. Data were extracted using a predefined extraction table. To assess the methodological quality of a study, the AMSTAR-2 tool was used to critically appraise systematic reviews of health care interventions.

RESULTS

The literature search resulted in 11,875 records, which was reduced to 14 full-text systematic literature reviews with the use of Covidence to remove duplicates and screen titles and abstracts. The 14 included reviews were published between 2014 and 2023, comprising 9 systematic reviews and 5 systematic reviews and meta-analyses. AMSTAR-2 was used to complete a quality assessment of the reviews, and the results were critically low for 7 literature reviews and low for the other 7 literature reviews. The most common types of digital intervention studied were cognitive behavioral therapy, mindfulness/meditation, and stress management followed by other self-help interventions. Effectiveness of digital interventions was found for many mental health symptoms and conditions in employee populations, such as stress, anxiety, depression, burnout, and psychological well-being. Factors such as type of technology, guidance, recruitment, tailoring, and demographics were found to impact effectiveness.

CONCLUSIONS

This umbrella review aimed to critically evaluate, synthesize, and summarize evidence of various digital mental health interventions available within a workplace setting. Despite the low quality of the reviews, best practice guidelines can be derived from factors that impact the effectiveness of digital interventions in the workplace.

TRIAL REGISTRATION

OSF Registries osf.io/rc6ds; https://doi.org/10.17605/OSF.IO/RC6DS.

The Impact of Perceived Emotional Intelligence on Occupational Stress Among Nurses: Empirical Evidence From a Saudi Health Cluster

Background: Occupational stress is a significant challenge for healthcare systems worldwide. It compromises the quality of healthcare and jeopardizes patient safety. Globally, the estimated economic impact of occupational stress in the healthcare system ranges from US $221.13 million to US $187 billion. Emotional intelligence has been recognized as a behavioral buffer against occupational stress. Hence, this study investigated whether nurses' perceptions of emotional intelligence impact their self-perceived occupational stress. Design: A predictive correlational design was utilized. Method: A prior power analysis using G ∗ Power 3.1 was conducted. A convenience sample of 734 nurses was recruited from Taif Health Cluster. Data were coded and analyzed using IBM® SPSS® Statistics for Windows v.25. Descriptive and inferential statistics were used. A hierarchical regression technique was used. The level of significance was established at p < 0.05. The process of data collection started at August 2022 and continued through October 2022. Results: The results indicated that nurses' age and working area predicted occupational stress perceptions in the first model (β = -0.28 and β = 0.21, p = 0.001, respectively). The second model showed a significant improvement (ΔF(7,727) = 162.35, p < 0.000, ΔR 2 = 0.226) and indicated a negative correlation between nurses' perceptions of emotional intelligence and occupational stress (β = -0.45, t = -12.8, p < 0.000). The nurses' sociodemographic characteristics in the first model explained 2.4% of the variance. The second model represented 25.0% of the variance when nurses' emotional intelligence perception was included. Conclusion: Our study shows a novel framework that indicates a positive perceived effect of emotional intelligence on nurses' perceptions of occupational stress in Saudi Arabia. Our findings propose that emotional intelligence is a significantly effective mechanism against occupational stress.

Searching for Value Sensitive Design in Applied Health AI: A Narrative Review

OBJECTIVE

Recent advances in the implementation of healthcare artificial intelligence (AI) have drawn attention toward design methods to address the impacts on workflow. Lesser known than human-centered design, Value Sensitive Design (VSD) is an established framework integrating values into conceptual, technical, and empirical investigations of technology. We sought to study the current state of the literature intersecting elements of VSD with practical applications of healthcare AI.

METHODS

Using a modified VSD framework attentive to AI-specific values, we conducted a narrative review informed by PRISMA guidelines and assessed VSD elements across design and implementation case studies.

RESULTS

Our search produced 819 articles that went through multiple rounds of review. Nine studies qualified for full-text review. Most of the studies focused on values for the individual or professional practice such as trust and autonomy. Attention to organizational (e.g., stewardship, employee well-being) and societal (e.g., equity, justice) values was lacking. Studies were primarily from the U.S. and Western Europe.

CONCLUSION

Future design studies might better incorporate components of VSD by considering larger domains, organizational and societal, in value identification and to bridge to design processes that are not just human-centered but value sensitive. The small number of heterogeneous studies underlines the importance of broader studies of elements of VSD to inform healthcare AI in practice.

Understanding reminiscence and its negative functions in the everyday conversations of young adults: A machine learning approach

Reminiscence is the act of recalling or telling others about relevant personal past experiences. It is an important activity for all individuals, young and old alike. In fact, reminiscence can serve different functions that can support or be detrimental to one's well-being. Although previous studies have extensively investigated older adults' recalling of autobiographical memories, the evidence for young adults remains scarce. Therefore, in this work, we analyze young adults' production of reminiscence and their functions with a naturalistic observation method. Furthermore, we demonstrate that natural language processing and machine learning can automatically detect reminiscence and its negative functions in young adults' everyday conversations. We interpret machine learning model results using Shapley explanations. Our results indicate that young adults reminisce in everyday life mostly to connect with others through conversation, to compensate for a lack of stimulation or to recall difficult past experiences. Moreover, our models improve existing benchmarks from the literature on the automated detection of older adults' reminiscence in everyday life. Finally, our results may support the development of digital health intervention programs that detect reminiscence and its functions in young adults to support their well-being.