Continuous Detection of Physiological Stress with Commodity Hardware

Perceived stress and associations between physical activity, sedentary time, and interstitial glucose in healthy adolescents

BACKGROUND

Less moderate to vigorous physical activity (MVPA), more sedentary time (ST), and higher perceived stress are related to type 2 diabetes mellitus (T2DM) occurrence, but observational evidence addressing the interaction of these factors is lacking in youth. This pilot study investigated momentary stress as a moderator in the acute associations of MVPA and ST with subsequent glucose in healthy adolescents.

METHODS

Participants (N=15, Mage=13.1±1.0 years, 10 girls, 5 with overweight/obesity) simultaneously wore a continuous glucose monitor (CGM), thigh-mounted accelerometer, and reported momentary stress via random ecological momentary assessments (EMA; Time T) for 7-14 days. MVPA and ST (min) were calculated for 60- and 120-minute time windows before each EMA prompt (Time T-1). Mean CGM-measured interstitial glucose (mg/dL) was calculated after each prompt (Mmin=120.0±25.4; Time T+1). Multilevel models assessed whether within-subject MVPA and ST (Time T-1) predicted mean glucose (Time T+1), with momentary stress as a moderator (Time T).

RESULTS

There were 513 time-matched EMA reports of stress, accelerometer, and CGM data. Momentary stress moderated the effects of MVPA 60 (β=-0.22, p=.001) and 120 min (β=-0.08, p=.02) before the prompt on subsequent glucose levels. When youth spent more time in MVPA than their average and when momentary stress was higher than their average, subsequent glucose was lower. Stress did not moderate associations of ST with glucose (p>.05).

CONCLUSIONS

Higher momentary stress may interact with higher MVPA to lower subsequent glucose in youth. Accelerometers, EMA, and CGMs can be integrated in future studies to further understand these associations in free-living environments.

Predicting stress levels using physiological data: Real-time stress prediction models utilizing wearable devices

Stress has emerged as a prominent and multifaceted health concern in contemporary society, manifesting detrimental effects on individuals' physical and mental health and well-being. The ability to accurately predict stress levels in real time holds significant promise for facilitating timely interventions and personalized stress management strategies. The increasing incidence of stress-related physical and mental health issues highlights the importance of thoroughly understanding stress prediction mechanisms. Given that stress is a contributing factor to a wide array of mental and physical health problems, objectively assessing stress is crucial for behavioral and physiological studies. While numerous studies have assessed stress levels in controlled environments, the objective evaluation of stress in everyday settings still needs to be explored, primarily due to contextual factors and limitations in self-report adherence. This short review explored the emerging field of real-time stress prediction, focusing on utilizing physiological data collected by wearable devices. Stress was examined from a comprehensive standpoint, acknowledging its effects on both physical and mental well-being. The review synthesized existing research on the development and application of stress prediction models, underscoring advancements, challenges, and future directions in this rapidly evolving domain. Emphasis was placed on examining and critically evaluating the existing research and literature on stress prediction, physiological data analysis, and wearable devices for stress monitoring. The synthesis of findings aimed to contribute to a better understanding of the potential of wearable technology in objectively assessing and predicting stress levels in real time, thereby informing the design of effective interventions and personalized stress management approaches.

Explainable stress type classification captures physiologically relevant responses in the Maastricht Acute Stress Test

Introduction

Current stress detection methods concentrate on identification of stress and non-stress states despite the existence of various stress types. The present study performs a more specific, explainable stress classification, which could provide valuable information on the physiological stress reactions.

Methods

Physiological responses were measured in the Maastricht Acute Stress Test (MAST), comprising alternating trials of cold pressor (inducing physiological stress and pain) and mental arithmetics (eliciting cognitive and social-evaluative stress). The responses in these subtasks were compared to each other and to the baseline through mixed model analysis. Subsequently, stress type detection was conducted with a comprehensive analysis of several machine learning components affecting classification. Finally, explainable artificial intelligence (XAI) methods were applied to analyze the influence of physiological features on model behavior.

Results

Most of the investigated physiological reactions were specific to the stressors, and the subtasks could be distinguished from baseline with up to 86.5% balanced accuracy. The choice of the physiological signals to measure (up to 25%-point difference in balanced accuracy) and the selection of features (up to 7%-point difference) were the two key components in classification. Reflection of the XAI analysis to mixed model results and human physiology revealed that the stress detection model concentrated on physiological features relevant for the two stressors.

Discussion

The findings confirm that multimodal machine learning classification can detect different types of stress reactions from baseline while focusing on physiologically sensible changes. Since the measured signals and feature selection affected classification performance the most, data analytic choices left limited input information uncompensated.

Heart Rate Variability in Concussed College Athletes: Follow-Up Study and Biological Sex Differences

Finding reliable biomarkers to assess concussions could play a pivotal role in diagnosis, monitoring, and predicting associated risks. The present study aimed to explore the use of heart rate variability (HRV) in the follow-up of concussions among college athletes and to investigate the relationships between biological sex, symptomatology, and HRV values at baseline and after a concussion. Correlations between measures were also analyzed. A total of 169 (55 females) athletes aged 16 to 22 years old completed baseline testing, and 30 (8 females) concussion cases were followed. Baseline assessment (T1) included psychosocial and psychological questionnaires, symptoms report, and four minutes of HRV recording. In the event of a concussion, athletes underwent re-testing within 72 h (T2) and before returning to play (T3). Baseline findings revealed that girls had higher %VLF while sitting than boys, and a small negligible correlation was identified between %HF and total symptoms score as well as %HF and affective sx. Post-concussion analyses demonstrated a significant effect of time × position × biological sex for %HF, where girls exhibited higher %HF at T3. These findings suggest disruptions in HRV following a concussion and underscore biological sex as an important factor in the analysis of HRV variation in concussion recovery trajectory.

Predicting Emotion with Biosignals: A Comparison of Classification and Regression Models for Estimating Valence and Arousal Level Using Wearable Sensors

This study aims to predict emotions using biosignals collected via wrist-worn sensor and evaluate the performance of different prediction models. Two dimensions of emotions were considered: valence and arousal. The data collected by the sensor were used in conjunction with target values obtained from questionnaires. A variety of classification and regression models were compared, including Long Short-Term Memory (LSTM) models. Additionally, the effects of different normalization methods and the impact of using different sensors were studied, and the way in which the results differed between the study subjects was analyzed. The results revealed that regression models generally performed better than classification models, with LSTM regression models achieving the best results. The normalization method called baseline reduction was found to be the most effective, and when used with an LSTM-based regression model it achieved high accuracy in detecting valence (mean square error = 0.43 and R2-score = 0.71) and arousal (mean square error = 0.59 and R2-score = 0.81). Moreover, it was found that even if all biosignals were not used in the training phase, reliable models could be obtained; in fact, for certain study subjects the best results were obtained using only a few of the sensors.

Early Life Stress Detection Using Physiological Signals and Machine Learning Pipelines

Pregnancy and early childhood are two vulnerable times when immunological plasticity is at its peak and exposure to stress may substantially raise health risks. However, to separate the effects of adversity during vulnerable times of the lifetime from those across the entire lifespan, we require deeper phenotyping. Stress is one of the challenges which everyone can face with this issue. It is a type of feeling which contains mental pressure and comes from daily life matters. There are many research and investments regarding this problem to overcome or control this complication. Pregnancy is a susceptible period for the child and the mother taking stress can affect the child's health after birth. The following matter can happen based on natural disasters, war, death or separation of parents, etc. Early Life Stress (ELS) has a connection with psychological development and metabolic and cardiovascular diseases. In the following research, the main focus is on Early Life Stress control during pregnancy of a healthy group of women that are at risk of future disease during their pregnancy. This study looked at the relationship between retrospective recollections of childhood or pregnancy hardship and inflammatory imbalance in a group of 53 low-income, ethnically diverse women who were seeking family-based trauma treatment after experiencing interpersonal violence. Machine learning Convolutional Neural Networks (CNNs) are applied for stress detection using short-term physiological signals in terms of non-linear and for a short term. The focus concepts are heart rate, and hand and foot galvanic skin response.

Detecting Physiological Responses Using Multimodal Earbud Sensors

Continuous stress exposure negatively impacts mental and physical well-being. Physiological arousal due to stress affects heartbeat frequency, changes breathing pattern and peripheral temperature, among several other bodily responses. Traditionally stress detection is performed by collecting signals such as electrocardiogram (ECG), respiration, and skin conductance response using uncomfortable sensors such as a chestband. In this study, we use earbuds that passively measure photoplethysmography (PPG), core body temperature, and inertial measurements. We have conducted a lab study exposing 18 participants to an evaluated speech task and additional tasks aimed at increasing stress or promoting relaxation. We simultaneously collected PPG, ECG, impedance cardiography (ICG), and blood pressure using laboratory grade equipment as reference measurements. We show that the earbud PPG sensor can reliably capture heart rate and heart rate variability. We further show that earbud signals can be used to classify the physiological responses associated with stress with 91.30% recall, 80.52% precision, and 85.12% F1-score using a random forest classifier with leave-one-subject-out cross-validation. The accuracy can further be improved through multi-modal sensing. These findings demonstrate the feasibility of using earbuds for passively monitoring users' physiological responses.

Applications and Techniques for Fast Machine Learning in Science

In this community review report, we discuss applications and techniques for fast machine learning (ML) in science-the concept of integrating powerful ML methods into the real-time experimental data processing loop to accelerate scientific discovery. The material for the report builds on two workshops held by the Fast ML for Science community and covers three main areas: applications for fast ML across a number of scientific domains; techniques for training and implementing performant and resource-efficient ML algorithms; and computing architectures, platforms, and technologies for deploying these algorithms. We also present overlapping challenges across the multiple scientific domains where common solutions can be found. This community report is intended to give plenty of examples and inspiration for scientific discovery through integrated and accelerated ML solutions. This is followed by a high-level overview and organization of technical advances, including an abundance of pointers to source material, which can enable these breakthroughs.

Driving Stress Detection Using Multimodal Convolutional Neural Networks with Nonlinear Representation of Short-Term Physiological Signals

Mental stress can lead to traffic accidents by reducing a driver’s concentration or increasing fatigue while driving. In recent years, demand for methods to detect drivers’ stress in advance to prevent dangerous situations increased. Thus, we propose a novel method for detecting driving stress using nonlinear representations of short-term (30 s or less) physiological signals for multimodal convolutional neural networks (CNNs). Specifically, from hand/foot galvanic skin response (HGSR, FGSR) and heart rate (HR) short-term input signals, first, we generate corresponding two-dimensional nonlinear representations called continuous recurrence plots (Cont-RPs). Second, from the Cont-RPs, we use multimodal CNNs to automatically extract FGSR, HGSR, and HR signal representative features that can effectively differentiate between stressed and relaxed states. Lastly, we concatenate the three extracted features into one integrated representation vector, which we feed to a fully connected layer to perform classification. For the evaluation, we use a public stress dataset collected from actual driving environments. Experimental results show that the proposed method demonstrates superior performance for 30-s signals, with an overall accuracy of 95.67%, an approximately 2.5–3% improvement compared with that of previous works. Additionally, for 10-s signals, the proposed method achieves 92.33% classification accuracy, which is similar to or better than the performance of other methods using long-term signals (over 100 s).

Ecological momentary interventions for mental health: A scoping review

BACKGROUND

The development of mobile computing technology has enabled the delivery of psychological interventions while people go about their everyday lives. The original visions of the potential of these "ecological momentary interventions" were presented over a decade ago, and the widespread adoption of smartphones in the intervening years has led to a variety of research studies exploring the feasibility of these aspirations. However, there is a dearth of research describing the different dimensions, characteristics, and features of these interventions, as constructed.

OBJECTIVE

To provide an overview of the definitions given for "ecological momentary interventions" in the treatment of common mental health disorders, and describe the set of technological and interaction possibilities which have been used in the design of these interventions.

METHODS

A systematic search identified relevant literature published between 2009 and 2020 in the PubMed, PsycInfo, and ACM Guide to the Computing Literature databases. Following screening, data were extracted from eligible articles using a standardized extraction worksheet. Selected articles were then thematically categorized.

RESULTS

The search identified 583 articles of which 64 met the inclusion criteria. The interventions target a range of mental health problems, with diverse aims, intervention designs and evaluation approaches. The studies employed a variety of features for intervention delivery, but recent research is overwhelmingly comprised of studies based on smartphone apps (30 of 42 papers that described an intervention). Twenty two studies employed sensors for the collection of data in order to provide just-in-time support or predict psychological states.

CONCLUSIONS

With the shift towards smartphone apps, the vision for EMIs has begun to be realised. Recent years have seen increased exploration of the use of sensors and machine learning, but the role of humans in the delivery of EMI is also varied. The variety of capabilities exhibited by EMIs motivates development of a more precise vocabulary for capturing both automatic and human tailoring of these interventions.

When Do Drivers Interact with In-Vehicle Well-being Interventions? An Exploratory Analysis of a Longitudinal Study on Public Roads

Recent developments of novel in-vehicle interventions show the potential to transform the otherwise routine and mundane task of commuting into opportunities to improve the drivers' health and well-being. Prior research has explored the effectiveness of various in-vehicle interventions and has identified moments in which drivers could be interruptible to interventions. All the previous studies, however, were conducted in either simulated or constrained real-world driving scenarios on a pre-determined route. In this paper, we take a step forward and evaluate when drivers interact with in-vehicle interventions in unconstrained free-living conditions. To this end, we conducted a two-month longitudinal study with 10 participants, in which each participant was provided with a study car for their daily driving needs. We delivered two in-vehicle interventions - each aimed at improving affective well-being - and simultaneously recorded the participants' driving behavior. In our analysis, we found that several pre-trip characteristics (like trip length, traffic flow, and vehicle occupancy) and the pre-trip affective state of the participants had significant associations with whether the participants started an intervention or canceled a started intervention. Next, we found that several in-the-moment driving characteristics (like current road type, past average speed, and future brake behavior) showed significant associations with drivers' responsiveness to the intervention. Further, we identified several driving behaviors that "negated" the effectiveness of interventions and highlight the potential of using such "negative" driving characteristics to better inform intervention delivery. Finally, we compared trips with and without intervention and found that both interventions employed in our study did not have a negative effect on driving behavior. Based on our analyses, we provide solid recommendations on how to deliver interventions to maximize responsiveness and effectiveness and minimize the burden on the drivers.

Workshop on Implementation Science and Digital Therapeutics for Behavioral Health

Digital therapeutics can overcome many of the barriers to translation of evidence-based treatment for substance use, mental health, and other behavioral health conditions. Delivered via nearly ubiquitous platforms such as the web, smartphone applications, text messaging, and videoconferencing, digital therapeutics can transcend the time and geographic boundaries of traditional clinical settings so that individuals can access care when and where they need it. There is strong empirical support for digital therapeutic approaches for behavioral health, yet implementation science with regard to scaling use of digital therapeutics for behavioral health is still in its early stages. In this paper, we summarize the proceedings of a day-long workshop, "Implementation Science and Digital Therapeutics," sponsored and hosted by the Center for Technology and Behavioral Health at Dartmouth College. The Center for Technology and Behavioral Health is an interdisciplinary P30 Center of Excellence funded by the National Institute on Drug Abuse, with the mission of promoting state-of-the-technology and state-of-the-science for the development, evaluation, and sustainable implementation of digital therapeutic approaches for substance use and related conditions. Workshop presentations were grounded in current models of implementation science. Directions and opportunities for collaborative implementation science research to promote broad adoption of digital therapeutics for behavioral health are offered.

Evaluating the Reproducibility of Physiological Stress Detection Models

Recent advances in wearable sensor technologies have led to a variety of approaches for detecting physiological stress. Even with over a decade of research in the domain, there still exist many significant challenges, including a near-total lack of reproducibility across studies. Researchers often use some physiological sensors (custom-made or off-the-shelf), conduct a study to collect data, and build machine-learning models to detect stress. There is little effort to test the applicability of the model with similar physiological data collected from different devices, or the efficacy of the model on data collected from different studies, populations, or demographics. This paper takes the first step towards testing reproducibility and validity of methods and machine-learning models for stress detection. To this end, we analyzed data from 90 participants, from four independent controlled studies, using two different types of sensors, with different study protocols and research goals. We started by evaluating the performance of models built using data from one study and tested on data from other studies. Next, we evaluated new methods to improve the performance of stress-detection models and found that our methods led to a consistent increase in performance across all studies, irrespective of the device type, sensor type, or the type of stressor. Finally, we developed and evaluated a clustering approach to determine the stressed/not-stressed classification when applying models on data from different studies, and found that our approach performed better than selecting a threshold based on training data. This paper's thorough exploration of reproducibility in a controlled environment provides a critical foundation for deeper study of such methods, and is a prerequisite for tackling reproducibility in free-living conditions.

Exploring the State-of-Receptivity for mHealth Interventions

Recent advancements in sensing techniques for mHealth applications have led to successful development and deployments of several mHealth intervention designs, including Just-In-Time Adaptive Interventions (JITAI). JITAIs show great potential because they aim to provide the right type and amount of support, at the right time. Timing the delivery of a JITAI such as the user is receptive and available to engage with the intervention is crucial for a JITAI to succeed. Although previous research has extensively explored the role of context in users' responsiveness towards generic phone notifications, it has not been thoroughly explored for actual mHealth interventions. In this work, we explore the factors affecting users' receptivity towards JITAIs. To this end, we conducted a study with 189 participants, over a period of 6 weeks, where participants received interventions to improve their physical activity levels. The interventions were delivered by a chatbot-based digital coach - Ally - which was available on Android and iOS platforms. We define several metrics to gauge receptivity towards the interventions, and found that (1) several participant-specific characteristics (age, personality, and device type) show significant associations with the overall participant receptivity over the course of the study, and that (2) several contextual factors (day/time, phone battery, phone interaction, physical activity, and location), show significant associations with the participant receptivity, in-the-moment. Further, we explore the relationship between the effectiveness of the intervention and receptivity towards those interventions; based on our analyses, we speculate that being receptive to interventions helped participants achieve physical activity goals, which in turn motivated participants to be more receptive to future interventions. Finally, we build machine-learning models to detect receptivity, with up to a 77% increase in F1 score over a biased random classifier.