AI-enabled remote and objective quantification of stress at scale

Al-Jebrni, Abdulrhman H.; Chwyl, Brendan; Wang, Xiao Yu; Wong, Alexander; Saab, Bechara J.

doi:10.1016/j.bspc.2020.101929

Cited by 10 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning techniques have also been used to analyse HRV signals, though less often than for ECG signals. Deep neural networks were used to measure stress levels from HRV records ( 199 ). CNNs were used in emotion recognition tasks, where HRV was integrated with multiple physiological signals ( 200 ).…”

Section: Discussionmentioning

confidence: 99%

A Proposal for a Data-Driven Approach to the Influence of Music on Heart Dynamics

Idrobo-Ávila

Correa

Muñoz-Bolaños

et al. 2021

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Electrocardiographic signals (ECG) and heart rate viability measurements (HRV) provide information in a range of specialist fields, extending to musical perception. The ECG signal records heart electrical activity, while HRV reflects the state or condition of the autonomic nervous system. HRV has been studied as a marker of diverse psychological and physical diseases including coronary heart disease, myocardial infarction, and stroke. HRV has also been used to observe the effects of medicines, the impact of exercise and the analysis of emotional responses and evaluation of effects of various quantifiable elements of sound and music on the human body. Variations in blood pressure, levels of stress or anxiety, subjective sensations and even changes in emotions constitute multiple aspects that may well-react or respond to musical stimuli. Although both ECG and HRV continue to feature extensively in research in health and perception, methodologies vary substantially. This makes it difficult to compare studies, with researchers making recommendations to improve experiment planning and the analysis and reporting of data. The present work provides a methodological framework to examine the effect of sound on ECG and HRV with the aim of associating musical structures and noise to the signals by means of artificial intelligence (AI); it first presents a way to select experimental study subjects in light of the research aims and then offers possibilities for selecting and producing suitable sound stimuli; once sounds have been selected, a guide is proposed for optimal experimental design. Finally, a framework is introduced for analysis of data and signals, based on both conventional as well as data-driven AI tools. AI is able to study big data at a single stroke, can be applied to different types of data, and is capable of generalisation and so is considered the main tool in the analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

A Proposal for a Data-Driven Approach to the Influence of Music on Heart Dynamics

Idrobo-Ávila

Correa

Muñoz-Bolaños

et al. 2021

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

show abstract

“… 40 This information is analyzed through a deep neural network trained on tens of thousands of video and stress pairings, categorizing cognitive stress as ‘very low’, ‘medium low’, ‘medium high’, and ‘very high’ with 86% accuracy. 41 Second, emotional stress levels are assessed via a digital 4-quadrant emotion mapping board (circumplex) that lists a range of emotions positioned along axes representing unpleasant to pleasant and mild to intense. Each emotion is assigned an undisclosed score to the user, which is utilized to calculate an implicit measure of mood.…”

Section: Methodsmentioning

confidence: 99%

Acceptability, usability, and credibility of a mindfulness-based digital therapeutic for pediatric concussion: A mixed-method study

Sicard,

O’Kane,

Brown

et al. 2024

DIGITAL HEALTH

View full text Add to dashboard Cite

Background The ability to cope with concussion symptoms and manage stress is an important determinant of risk for prolonged symptoms. Objective This open-label mixed-methods pilot study assessed the acceptability and credibility of a mindfulness-based intervention delivered through a digital therapeutic (DTx; therapeutic smartphone app) for pediatric concussion. Methods Participants aged 12 to 18 years were recruited from an emergency department within 48 hours of a concussion (acute cohort) or from a tertiary care clinic at least 1-month post-concussion (persisting symptoms cohort). Participants completed a novel 4-week mindfulness-based intervention, for 10 to 15 minutes/day, at a minimum of 4 days/week. At 2 weeks, participants completed a credibility and expectancy questionnaire. At 4 weeks, participants completed questionnaires assessing satisfaction, usability and working alliance, as well as a semi-structured phone interview. Results Ten participants completed the study outcomes (7 acute; 3 persisting symptoms). The intervention was perceived as credible (median/max possible = 6.50/9.00 [6.83,8.75]) and DTx was usable (median/max possible = 70.00/100.00 [55.00,82.50]). Participants rated their satisfaction with the DTx (median/max possible = 27.00/32.00 [24.50,29.50]) and the working alliance with the digital mindfulness guides (median/max possible = 3.92/5.00 [3.38–4.33]) as high. Four themes were identified from the qualitative data: (a) positive attributes; (b) negative attributes; (c) ideas for modifications; and (d) technical issues. Conclusion Results show modifications to the DTx, instructions and mindfulness intervention, and potential ways to increase adherence by leveraging positive attributes. A randomized control trial will assess the effectiveness of the DTx MBI to decrease the risk of persisting symptoms and reduce the symptom burden following pediatric concussion.

show abstract

“…First, cognitive stress is objectively quantified via a 30-second "selfie" video that uses an algorithm to extract heart rate and heart rate variability from the biosignals inherent to the human face using photoplethysmographic imaging principles [40]. The amount of cognitive stress is determined via deep neural networks trained on tens of thousands of video and stress pairings and has reported 86% accuracy for determining an individual's stress as "very low," "medium low," "medium high," and "very high" [41]. Second, emotional stress levels are obtained via a digital 4-quadrant emotion mapping board (mood board) that lists emotions such as "happy," "sad," and "tense" ranging on one axis from unpleasant to pleasant, and along another axis from mild to intense; see Figure 3 for screenshots of the in-app stress assessments.…”

Section: Am's App-based Stress Measurementmentioning

confidence: 99%

A Smartphone App–Based Mindfulness Intervention for Cancer Survivors: Protocol for a Randomized Controlled Trial

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background Cancer patients transitioning to survivorship after completing cancer treatments need psychosocial interventions to manage stressors such as anxiety, depression, and fear of cancer recurrence. Mindfulness-based interventions (MBIs) are effective for treating these symptoms; however, cancer survivors are often unable to participate in face-to-face interventions because of difficulties such as work and family commitments, treatment-related side-effects, scheduling conflicts, and geography. Smartphone app–based MBIs are an innovative way to deliver psychosocial cancer care and can overcome several such difficulties, since patients can participate at their own convenience. Objective The SEAMLESS (Smartphone App–Based Mindfulness Intervention for Cancer Survivors) study aims to evaluate the efficacy of a tailored app-based mindfulness intervention for cancer survivors (the Am Mindfulness-Based Cancer Survivorship—MBCS—Journey) for treating (1) symptoms of stress (primary outcome), as well as (2) fear of cancer recurrence, anxiety, depression, fatigue, and overall physical functioning (secondary outcomes). This is the first Canadian efficacy trial of a tailored mindfulness app intervention in cancer survivors. Methods This is a randomized waitlist-controlled trial, which will evaluate the effectiveness of Am MBCS for impacting the primary and secondary outcomes in cancer survivors who have completed all their cancer treatments. Outcomes will be assessed using web-based surveys with validated psychometric instruments at (1) baseline, (2) mid-intervention (2 weeks later), (3) immediately postintervention (4 weeks), (4) 3 months postbaseline, (5) 6 months postbaseline, and (6) 12 months postbaseline. The waitlist group will complete all assessments and will cross over to the intervention condition after the 3-month assessment. In addition, data will be obtained by the smartphone app itself, which includes users’ engagement with the app-based intervention, their emotional state (eg, angry and elated) from a user-inputted digital emotion-mapping board, and psychobiometric data using photoplethysmography technology. Results The study received ethics approval in September 2018 and recruitment commenced in January 2019. Participants are being recruited through a provincial cancer registry, and the majority of participants currently enrolled are breast (44/83, 53%) or colorectal (17/83, 20%) cancer survivors, although some survivors of other cancer are also present. Data collection for analysis of the primary outcome time-point will be complete by September 2019, and the follow-up data will be collected and analyzed by September 2020. Data will be analyzed to determine group differences using linear mixed modelling statistical techniques. Conclusions Cancer care providers are uncertain about the efficacy of app-based mindfulness interventions for patients, which are available in great supply in today’s digital world. This study will provide rigorously evaluated efficacy data for an app-based mindfulness intervention for cancer survivors, which if helpful, could be made available for psychosocial care at cancer centers worldwide. Trial Registration ClinicalTrials.gov NCT03484000; https://clinicaltrials.gov/ct2/show/NCT03484000 International Registered Report Identifier (IRRID) DERR1-10.2196/15178

show abstract

AI-enabled remote and objective quantification of stress at scale

Cited by 10 publications

References 14 publications

A Proposal for a Data-Driven Approach to the Influence of Music on Heart Dynamics

A Proposal for a Data-Driven Approach to the Influence of Music on Heart Dynamics

Acceptability, usability, and credibility of a mindfulness-based digital therapeutic for pediatric concussion: A mixed-method study

A Smartphone App–Based Mindfulness Intervention for Cancer Survivors: Protocol for a Randomized Controlled Trial

Contact Info

Product

Resources

About