Article

cHRV Uncovering Daily Stress Dynamics Using Bio-Signal from Consumer Wearables

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Knowing the dynamics of one's daily stress is essential to effective stress management in the context of smart and connected health. However, there lacks a practical and unobtrusive means to obtain real-time and longitudinal stress information. In this paper, we attempt to derive a convenient HRV-based (heart rate variability) biomarker named cHRV, which can be used to reliably reflect stress dynamics. cHRV's key advantage lies in its low maintenance and high practicality. It can be efficiently calculated only using data from photoplethysmography (PPG) sensors, the mainstream heart rate sensor embedded in most of the consumer wearables like Apple Watch. Benefiting from the proliferation of wearables, cHRV is ideal for day-to-day stress monitoring. To evaluate its feasibility and performance, we have conducted 14 in-lab controlled experiments. The result shows that the proposed cHRV has strong correlation with the stress dynamics (r > 0.95), therefore exhibits great potential for continuous stress assessment.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Twelve out of the 20 stress-related studies used only a PPG sensor to monitor stress [7,[12][13][14][15][16][17][18][19][20][21][22]. Of these 12 studies, HRV was the most common health parameter. ...
... Of these 12 studies, HRV was the most common health parameter. Three separate studies [12,13,15] reported observing the same behavior for HRV from different PPG sensors on different locations: during times of increased stress, HRV decreased. The remaining HRV papers did not specify the behavior of HRV during moments of stress vs. no stress (e.g., if the HRV decreased during moments of stress) but simply reported that they were successfully able to use the parameter to classify moments of stress vs. non stress. ...
... Studies that utilized solely PPG used two primary locations of sensors: ear [15,19,22,26] and wrist [7,[12][13][14]18,[23][24][25]27,29]. Sensors located at the ear were less prone to motion artifacts [22]. ...
Article
Full-text available
Background: Mental and physical health are both important for overall health. Mental health includes emotional, psychological, and social well-being; however, it is often difficult to monitor remotely. The objective of this scoping review is to investigate studies that focus on mental health and stress detection and monitoring using PPG-based wearable sensors. Methods: A literature review for this scoping review was conducted using the PRISMA (Preferred Reporting Items for the Systematic Reviews and Meta-analyses) framework. A total of 290 studies were found in five medical databases (PubMed, Medline, Embase, CINAHL, and Web of Science). Studies were deemed eligible if non-invasive PPG-based wearables were worn on the wrist or ear to measure vital signs of the heart (heart rate, pulse transit time, pulse waves, blood pressure, and blood volume pressure) and analyzed the data qualitatively. Results: Twenty-three studies met the inclusion criteria, with four real-life studies, eighteen clinical studies, and one joint clinical and real-life study. Out of the twenty-three studies, seventeen were published as journal-based articles, and six were conference papers with full texts. Because most of the articles were concerned with physiological and psychological stress, we decided to only include those that focused on stress. In twelve of the twenty articles, a PPG-based sensor alone was used to monitor stress, while in the remaining eight papers, a PPG sensor was used in combination with other sensors. Conclusion: The growing demand for wearable devices for mental health monitoring is evident. However, there is still a significant amount of research required before wearable devices can be used easily and effectively for such monitoring. Although the results of this review indicate that mental health monitoring and stress detection using PPG is possible, there are still many limitations within the current literature, such as a lack of large and diverse studies and ground-truth methods, that need to be addressed before wearable devices can be globally useful to patients.
... Previous studies have used PPG sensors to monitor stress signals with these sensors primarily located at the ear [26][27][28] and wrist [29][30][31][32][33][34]. In those studies, heart rate variability (HRV) was the most used health parameter for stress assessment because it is sensitive to variations in psychological and physical well-being and can distinguish between healthy and unhealthy individuals. ...
Article
Full-text available
This study presents an ear-mounted photoplethysmography (PPG) system that is designed to detect mental stress. Mental stress is a prevalent condition that can negatively impact an individual's health and well-being. Early detection and treatment of mental stress are crucial for preventing related illnesses and maintaining overall wellness. The study used data from 14 participants that were collected in a controlled environment. The participants were subjected to stress-inducing tasks such as the Stroop color-word test and mathematical calculations. The raw PPG signal was then preprocessed and transformed into scalograms using continuous wavelet transform (CWT). A convolutional neural network classifier was then used to classify the transformed signals as stressed or non-stressed. The results of the study show that the PPG system achieved high levels of accuracy (92.04%) and F1-score (90.8%). Furthermore, by adding white Gaussian noise to the raw PPG signals, the results were improved even more, with an accuracy of 96.02% and an F1-score of 95.24%. The proposed ear-mounted device shows great promise as a reliable tool for the early detection and treatment of mental stress, potentially revolutionizing the field of mental health and well-being.
... When HRV is obtained by a CW, I term it a 'convenience HRV' or cHRV. (9) Another company is using the camera on the smart phone itself in what it calls 'smartphone photoplethysmography (PPG)' with which it determines values for HRV. Plews et al showed the validity of this approach. ...
Research
Full-text available
Objective: To present a pragmatic narrative of the measurements of my heart rate variability (HRV) gathered over a 6-week period. I propose both a meaning and a role for HRV in the clinical practice of chiropractic. Methods: A consumer-wearable was used to gather convenience recordings of HRV (cHRV) for 3 weeks leading up to a week in which chiropractic spinal correction was received, and then for 3 weeks after. Data management and analysis occurred via an electronic spreadsheet (Numbers, Apple). Results: The weekly mean of daily means for 3 weeks following 1 instance of chiropractic spinal correction showed a chance difference to the weekly mean of daily means over 3 weeks beforehand. The variance (VAR) of cHRV measurements taken over any 24h period show a high value of VAR, as do the weekly day-by-day means. Conclusion: The statistical mean of a gathering of measurements holds more clinical meaning than any single instantaneous measure. It is pointless to take a single reading of HRV in a patient at the time of consultation, whereas considering the mean value of a series of measures provides useful values that may be a marker of change associated with chiropractic spinal correction. The convenience of taking measurements of HRV by a consumer wearable must not overshadow the importance of a reliable method of gathering and interpreting the data it provides. (J Contemporary Chiropr 2022;5:85-96)
... Again, the roadmaps could be applied to generate case-finding outcome measures from any DHTT in any disease area. For example, such approaches are underway with smartwatch photoplethysmography data to identify individuals with potentially undiagnosed atrial fibrillation 35 , e.g., in the Apple Watch Study 36 , and to identify perceived stress levels 37 . ...
Article
Full-text available
Digital health technology tools (DHTT) are technologies such as apps, smartphones, and wearables that remotely acquire health-related information from individuals. They have the potential advantages of objectivity and sensitivity of measurement, richness of high-frequency sensor data, and opportunity for passive collection of health-related data. Thus, DHTTs promise to provide patient phenotyping at an order of granularity several times greater than is possible with traditional clinical research tools. While the conceptual development of novel DHTTs is keeping pace with technological and analytical advancements, an as yet unaddressed gap is how to develop robust and meaningful outcome measures based on sensor data. Here, we describe two roadmaps which were developed to generate outcome measures based on DHTT data: one using a data-centric approach and the second a patient-centric approach. The data-centric approach to develop digital outcome measures summarizes those sensor features maximally sensitive to the concept of interest, exemplified with the quantification of disease progression. The patient-centric approach summarizes those sensor features that are optimally relevant to patients’ functioning in everyday life. Both roadmaps are exemplified for use in tracking disease progression in observational and clinical interventional studies, and with a DHTT designed to evaluate motor symptom severity and symptom experience in Parkinson’s disease. Use cases other than disease progression (e.g., case-finding) are considered summarily. DHTT research requires methods to summarize sensor data into meaningful outcome measures. It is hoped that the concepts outlined here will encourage a scientific discourse and eventual consensus on the creation of novel digital outcome measures for both basic clinical research and clinical drug development.
... For example, wearable monitors (e.g., Empatica E4, sociometric badges, EEG bands) provide high-quality, real-time, ecologically valid physiological and social data streams in real-life contexts, often with minimal burden to participants. Data from wearables have shown promise to help identify psychological states such as stress [17,19], or emotional arousal [34]. These are relatively unobtrusive means to monitor individual's health indicators over time and provide data that may eventually serve as a solid basis for efficient interventions (e.g., by identifying moments of risk). ...
Article
Full-text available
With wearable, relatively unobtrusive health monitors and smartphone sensors, it is increasingly easy to collect continuously streaming physiological data in a passive mode without placing much burden on participants. At the same time, smartphones provide the ability to survey participants to provide “ground-truth” reporting on psychological states, although this comes at an increased cost in participant burden. In this paper, we examined how analytical approaches from the field of machine learning could allow us to distill the collected physiological data into actionable decision rules about each individual’s psychological state, with the eventual goal of identifying important psychological states (e.g., risk moments) without the need for ongoing burdensome active assessment (e.g., self-report). As a first step towards this goal, we compared two methods: (1) a k-nearest neighbor classifier that uses dynamic time warping distance, and (2) a random forests classifier to predict low and high states of affective arousal states based on features extracted using the tsfresh python package. Then, we compared random-forest-based predictive models tailored for the individual with individual-general models. Results showed that the individual-specific model outperformed the general one. Our results support the feasibility of using passively collected wearable data to predict psychological states, suggesting that by relying on both types of data, the active collection can be reduced or eliminated.
... After signing the consent form, the participants were asked to wear a commercially available smartwatch (Moto 360 [9]) for at least 3 days. The watch was pre-installed with an app to passively collect continuous HRV and accelerometer data from onboard sensors (while the Moto 360 does not have an HRV sensor, we use the approach described by Hao et al. to extract R-R intervals from the onboard Photoplethysmography (PPG) sensor [5]). The app also prompted the participants with self-reports about their in-situ perceived stress levels and context information. ...
Conference Paper
The advances in mobile and wearable sensing have led to a myriad of approaches for stress detection in both laboratory and free-living settings. Most of these methods, however, rely on the usage of some combination of physiological signals measured by the sensors to detect stress. While these solutions work great in a lab or a controlled environment, the performance in free-living situations leaves much to be desired. In this work, we explore the role of context of the user in free-living conditions, and how that affects users' perceived stress levels. To this end, we conducted an 'in-the-wild' study with 23 participants, where we collected physiological data from the users, along with 'high-level' contextual labels, and perceived stress levels. Our analysis shows that context plays a significant role in the users' perceived stress levels, and when used in conjunction with physiological signals leads to much higher stress detection results, as compared to relying on just physiological data.
Article
Full-text available
Health maintenance and disease prevention strategies become increasingly prioritized with increasing health and economic burden of chronic, lifestyle-related diseases. A key element in these strategies is the empowerment of individuals to control their health. Self-measurement plays an essential role in achieving such empowerment. Digital measurements have the advantage of being measured non-invasively, passively, continuously, and in a real-world context. An important question is whether such measurement can sensitively measure subtle disbalances in the progression toward disease, as well as the subtle effects of, for example, nutritional improvement. The concept of resilience biomarkers, defined as the dynamic evaluation of the biological response to an external challenge, has been identified as a viable strategy to measure these subtle effects. In this review, we explore the potential of integrating this concept with digital physiological measurements to come to digital resilience biomarkers. Additionally, we discuss the potential of wearable, non-invasive, and continuous measurement of molecular biomarkers. These types of innovative measurements may, in the future, also serve as a digital resilience biomarker to provide even more insight into the personal biological dynamics of an individual. Altogether, digital resilience biomarkers are envisioned to allow for the measurement of subtle effects of health maintenance and disease prevention strategies in a real-world context and thereby give personalized feedback to improve health.
Article
Heart rate variability has been largely used for the assessment of cardiac autonomic activity, due to the direct relationship between cardiac rhythm and the activity of the sympathetic and parasympathetic nervous system. In recent years, another technique, pulse rate variability , has been used for assessing heart rate variability information from pulse wave signals, especially from photoplethysmography, a non-invasive, non-intrusive, optical technique that measures the blood volume in tissue. The relationship, however, between pulse rate variability and heart rate variability is not entirely understood, and the effects of cardiovascular changes in pulse rate variability have not been thoroughly dilucidated. In this review, a comprehensive summary of the applications in which pulse rate variability has been used, with a special focus on cardiovascular health, and of the studies that have compared heart rate variability and pulse rate variability is presented. It was found that the relationship between heart rate variability and pulse rate variability is not entirely understood yet, and that pulse rate variability might be influenced not only due to technical aspects but also by physiological factors that might affect the measurements obtained from pulse-to-pulse time series extracted from pulse waves. Hence, pulse rate variability must not be considered as a valid surrogate of heart rate variability in all scenarios, and care must be taken when using pulse rate variability instead of heart rate variability. Specifically, the way pulse rate variability is affected by cardiovascular changes does not necessarily reflect the same information as heart rate variability, and might contain further valuable information. More research regarding the relationship between cardiovascular changes and pulse rate variability should be performed to evaluate if pulse rate variability might be useful for the assessment of not only cardiac autonomic activity but also for the analysis of mechanical and vascular autonomic responses to these changes.
Article
Full-text available
Background: This paper examines the development of the Connected Health research landscape with a view on providing a historical perspective on existing Connected Health research. Connected Health has become a rapidly growing research field as our healthcare system is facing pressured to become more proactive and patient centred. Objective: We aimed to identify the extent and coverage of the current body of knowledge in Connected Health. With this, we want to identify which topics have drawn the attention of Connected health researchers, and if there are gaps or interdisciplinary opportunities for further research. Methods: We used a systematic mapping study that combines scientific contributions from research on medicine, business, computer science and engineering. We analyse the papers with seven classification criteria, publication source, publication year, research types, empirical types, contribution types research topic and the condition studied in the paper. Results: Altogether, our search resulted in 208 papers which were analysed by a multidisciplinary group of researchers. Our results indicate a slow start for Connected Health research but a more recent steady upswing since 2013. The majority of papers proposed healthcare solutions (37%) or evaluated Connected Health approaches (23%). Case studies (28%) and experiments (26%) were the most popular forms of scientific validation employed. Diabetes, cancer, multiple sclerosis, and heart conditions are among the most prevalent conditions studied. Conclusions: We conclude that Connected Health research seems to be an established field of research, which has been growing strongly during the last five years. There seems to be more focus on technology driven research with a strong contribution from medicine, but business aspects of Connected health are not as much studied.
ResearchGate has not been able to resolve any references for this publication.