Exploring the perception of stress in childhood and early adolescence.

Stressful life experiences may jeopardize the healthy development of children. To improve interventions, more knowledge is needed on the perception of stress by children. In adults, stress is regarded as a state of low valence and high arousal. It is unclear whether children perceive stress similarly. In the current study, 35 children of the general population completed three tasks aiming to provide insight into their knowledge of the concept stress. In the first task, participants were asked about their verbal knowledge of the concept stress. In the second task, they rated the valence and arousal of eight emotion-evoking vignettes. In the final task, participants completed an experience sampling survey for at least 1 day, consisting of a stress thermometer and pictorial scales of valence and arousal. Participants' perception of stress was found to be mainly valence focused. Age and sex were found to play a role in the degree of arousal focus. Older participants differentiated more in arousal levels than younger participants, as did girls in comparison with boys. Because the perception of stress depends on developmental and other individual factors, using stress as a single measurement dimension in a survey is not recommended.

Eat-Radar: Continuous Fine-Grained Intake Gesture Detection Using FMCW Radar and 3D Temporal Convolutional Network With Attention.

Unhealthy dietary habits are considered as the primary cause of various chronic diseases, including obesity and diabetes. The automatic food intake monitoring system has the potential to improve the quality of life (QoL) of people with diet-related diseases through dietary assessment. In this work, we propose a novel contactless radar-based approach for food intake monitoring. Specifically, a Frequency Modulated Continuous Wave (FMCW) radar sensor is employed to recognize fine-grained eating and drinking gestures. The fine-grained eating/drinking gesture contains a series of movements from raising the hand to the mouth until putting away the hand from the mouth. A 3D temporal convolutional network with self-attention (3D-TCN-Att) is developed to detect and segment eating and drinking gestures in meal sessions by processing the Range-Doppler Cube (RD Cube). Unlike previous radar-based research, this work collects data in continuous meal sessions (more realistic scenarios). We create a public dataset comprising 70 meal sessions (4,132 eating gestures and 893 drinking gestures) from 70 participants with a total duration of 1,155 minutes. Four eating styles (fork & knife, chopsticks, spoon, hand) are included in this dataset. To validate the performance of the proposed approach, seven-fold cross-validation method is applied. The 3D-TCN-Att model achieves a segmental F1-score of 0.896 and 0.868 for eating and drinking gestures, respectively. The results of the proposed approach indicate the feasibility of using radar for fine-grained eating and drinking gesture detection and segmentation in meal sessions.

Eating Speed Measurement Using Wrist-Worn IMU Sensors Towards Free-Living Environments.

Eating speed is an important indicator that has been widely investigated in nutritional studies. The relationship between eating speed and several intake-related problems such as obesity, diabetes, and oral health has received increased attention from researchers. However, existing studies mainly use self-reported questionnaires to obtain participants' eating speed, where they choose options from slow, medium, and fast. Such a non-quantitative method is highly subjective and coarse at the individual level. This study integrates two classical tasks in automated food intake monitoring domain: bite detection and eating episode detection, to advance eating speed measurement in near-free-living environments automatically and objectively. Specifically, a temporal convolutional network combined with a multi-head attention module (TCN-MHA) is developed to detect bites (including eating and drinking gestures) from IMU data. The predicted bite sequences are then clustered into eating episodes. Eating speed is calculated by using the time taken to finish the eating episode to divide the number of bites. To validate the proposed approach on eating speed measurement, a 7-fold cross validation is applied to the self-collected fine-annotated full-day-I (FD-I) dataset, and a holdout experiment is conducted on the full-day-II (FD-II) dataset. The two datasets are collected from 61 participants with a total duration of 513 h, which are publicly available. Experimental results show that the proposed approach achieves a mean absolute percentage error (MAPE) of 0.110 and 0.146 in the FD-I and FD-II datasets, respectively, showcasing the feasibility of automated eating speed measurement in near-free-living environments.

Otago Exercises Monitoring for Older Adults by a Single IMU and Hierarchical Machine Learning Models.

Otago Exercise Program (OEP) is a rehabilitation program for older adults to improve frailty, sarcopenia, and balance. Accurate monitoring of patient involvement in OEP is challenging, as self-reports (diaries) are often unreliable. The development of wearable sensors and their use in Human Activity Recognition (HAR) systems has lead to a revolution in healthcare. However, the use of such HAR systems for OEP still shows limited performance. The objective of this study is to build an unobtrusive and accurate system to monitor OEP for older adults. Data was collected from 18 older adults wearing a single waist-mounted Inertial Measurement Unit (IMU). Two datasets were recorded, one in a laboratory setting, and one at the homes of the patients. A hierarchical system is proposed with two stages: 1) using a deep learning model to recognize whether the patients are performing OEP or activities of daily life (ADLs) using a 10-minute sliding window; 2) based on stage 1, using a 6-second sliding window to recognize the OEP sub-classes. Results showed that in stage 1, OEP could be recognized with window-wise f1-scores over 0.95 and Intersection-over-Union (IoU) f1-scores over 0.85 for both datasets. In stage 2, for the home scenario, four activities could be recognized with f1-scores over 0.8: ankle plantarflexors, abdominal muscles, knee bends, and sit-to-stand. These results showed the potential of monitoring the compliance of OEP using a single IMU in daily life. Also, some OEP sub-classes are possible to be recognized for further analysis.

DS-MS-TCN: Otago Exercises Recognition with a Dual-Scale Multi-Stage Temporal Convolutional Network.

The Otago Exercise Program (OEP) represents a crucial rehabilitation initiative tailored for older adults, aimed at enhancing balance and strength. Despite previous efforts utilizing wearable sensors for OEP recognition, existing studies have exhibited limitations in terms of accuracy and robustness. This study addresses these limitations by employing a single waist-mounted Inertial Measurement Unit (IMU) to recognize OEP exercises among community-dwelling older adults in their daily lives. A cohort of 36 older adults participated in laboratory settings, supplemented by an additional 7 older adults recruited for at-home assessments. The study proposes a Dual-Scale Multi-Stage Temporal Convolutional Network (DS-MS-TCN) designed for two-level sequence-to-sequence classification, incorporating them in one loss function. In the first stage, the model focuses on recognizing each repetition of the exercises (micro labels). Subsequent stages extend the recognition to encompass the complete range of exercises (macro labels). The DS-MS-TCN model surpasses existing state-of-the-art deep learning models, achieving f1-scores exceeding 80% and Intersection over Union (IoU) f1-scores surpassing 60% for all four exercises evaluated. Notably, the model outperforms the prior study utilizing the sliding window technique, eliminating the need for post-processing stages and window size tuning. To our knowledge, we are the first to present a novel perspective on enhancing Human Activity Recognition (HAR) systems through the recognition of each repetition of activities.

Dynamic Modelling of Mental Resilience in Young Adults: Protocol for a Longitudinal Observational Study (DynaM-OBS).

BACKGROUND: Stress-related mental disorders are highly prevalent and pose a substantial burden on individuals and society. Improving strategies for the prevention and treatment of mental disorders requires a better understanding of their risk and resilience factors. This multicenter study aims to contribute to this endeavor by investigating psychological resilience in healthy but susceptible young adults over 9 months. Resilience is conceptualized in this study as the maintenance of mental health or quick recovery from mental health perturbations upon exposure to stressors, assessed longitudinally via frequent monitoring of stressors and mental health. OBJECTIVE: This study aims to investigate the factors predicting mental resilience and adaptive processes and mechanisms contributing to mental resilience and to provide a methodological and evidence-based framework for later intervention studies. METHODS: In a multicenter setting, across 5 research sites, a sample with a total target size of 250 young male and female adults was assessed longitudinally over 9 months. Participants were included if they reported at least 3 past stressful life events and an elevated level of (internalizing) mental health problems but were not presently affected by any mental disorder other than mild depression. At baseline, sociodemographic, psychological, neuropsychological, structural, and functional brain imaging; salivary cortisol and α-amylase levels; and cardiovascular data were acquired. In a 6-month longitudinal phase 1, stressor exposure, mental health problems, and perceived positive appraisal were monitored biweekly in a web-based environment, while ecological momentary assessments and ecological physiological assessments took place once per month for 1 week, using mobile phones and wristbands. In a subsequent 3-month longitudinal phase 2, web-based monitoring was reduced to once a month, and psychological resilience and risk factors were assessed again at the end of the 9-month period. In addition, samples for genetic, epigenetic, and microbiome analyses were collected at baseline and at months 3 and 6. As an approximation of resilience, an individual stressor reactivity score will be calculated. Using regularized regression methods, network modeling, ordinary differential equations, landmarking methods, and neural net-based methods for imputation and dimension reduction, we will identify the predictors and mechanisms of stressor reactivity and thus be able to identify resilience factors and mechanisms that facilitate adaptation to stressors. RESULTS: Participant inclusion began in October 2020, and data acquisition was completed in June 2022. A total of 249 participants were assessed at baseline, 209 finished longitudinal phase 1, and 153 finished longitudinal phase 2. CONCLUSIONS: The Dynamic Modelling of Resilience-Observational Study provides a methodological framework and data set to identify predictors and mechanisms of mental resilience, which are intended to serve as an empirical foundation for future intervention studies. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/39817.

Are Gyroscopes an Added Value in Leave-One-Subject-Out Activity Recognition with IMUs?

Inertial sensors have played a key role in the development of Human Activity Recognition (HAR) systems. Adding gyroscopes in HAR systems leads to increased battery and processing resources. Therefore, it is important to explore their added value compared with using accelerometers only. This study evaluates the added value of gyroscopes in activity recognition. Two public available datasets recorded by accelerometers and gyroscopes were studied. These datasets focus on multiple types of activities: UCI HAR dataset includes walking, walking upstairs, walking downstairs, sitting, standing, laying and WISDM dataset includes 18 hand-oriented and non-hand-oriented activities. Several machine learning models were applied to both datasets for activity recognition. Leave-one-subject-out cross-validation (LOSO) was applied to evaluate the models, where the training set and test set were from different subjects. For UCI HAR dataset, the multilayer perceptron (MLP) model obtained the highest f1-scores. Adding a gyroscope on the waist significantly improved the f1-scores of sitting and laying (both ). For WISDM dataset, the support vector machines (SVM) model obtained the highest f1-scores. The gyroscope on the wrist improved hand-oriented activities while the gyroscope in the pockets improved non-hand-oriented activities (all . The results showed the improvement for recognition performance by adding gyroscopes. However, the improvement was dependent on the type of activity and the mounting place of the gyroscope. Clinical relevance- Gyroscopes are common sensors for activity recognition in wearable healthcare systems. This study proves the added value by adding gyroscopes on different mounting places for recognition performance.

Drinking Gesture Detection Using Wrist-Worn IMU Sensors with Multi-Stage Temporal Convolutional Network in Free-Living Environments.

Maintaining adequate hydration is important for health. Inadequate liquid intake can cause dehydration problems. Despite the increasing development of liquid intake monitoring, there are still open challenges in drinking detection under free-living conditions. This paper proposes an automatic liquid intake monitoring system comprised of wrist-worn Inertial Measurement Units (IMU s) to recognize drinking gesture in free-living environments. We build an end-to-end approach for drinking gesture detection by employing a novel multi-stage temporal convolutional network (MS-TCN). Two datasets are collected in this research, one contains 8.9 hours data from 13 participants in semi-controlled environments, the other one contains 45.2 hours data from 7 participants in free-living environments. The Leave-One-Subject-Out (LOSO) evaluation shows that this method achieves a segmental F1-score of 0.943 and 0.900 in the semi-controlled and free-living datasets, respectively. The results also indicate that our approach outperforms the convolutional neural network and long-short-term-memory network combined model (CNN-LSTM) on our datasets. The dataset used in this paper is available at https://github.com/Pituohai/drinking-gesture-dataset/. Clinical Relevance- This automatic liquid intake monitoring system can detect drinking gesture in daily life. It has the potential to be used to record the frequency of drinking water for at-risk elderly or patients in the hospital.

Characterizing and Modeling Smoking Behavior Using Automatic Smoking Event Detection and Mobile Surveys in Naturalistic Environments: Observational Study.

BACKGROUND: There are 1.1 billion smokers worldwide, and each year, more than 8 million die prematurely because of cigarette smoking. More than half of current smokers make a serious quit every year. Nonetheless, 90% of unaided quitters relapse within the first 4 weeks of quitting due to the lack of limited access to cost-effective and efficient smoking cessation tools in their daily lives. OBJECTIVE: This study aims to enable quantified monitoring of ambulatory smoking behavior 24/7 in real life by using continuous and automatic measurement techniques and identifying and characterizing smoking patterns using longitudinal contextual signals. This work also intends to provide guidance and insights into the design and deployment of technology-enabled smoking cessation applications in naturalistic environments. METHODS: A 4-week observational study consisting of 46 smokers was conducted in both working and personal life environments. An electric lighter and a smartphone with an experimental app were used to track smoking events and acquire concurrent contextual signals. In addition, the app was used to prompt smoking-contingent ecological momentary assessment (EMA) surveys. The smoking rate was assessed based on the timestamps of smoking and linked statistically to demographics, time, and EMA surveys. A Poisson mixed-effects model to predict smoking rate in 1-hour windows was developed to assess the contribution of each predictor. RESULTS: In total, 8639 cigarettes and 1839 EMA surveys were tracked over 902 participant days. Most smokers were found to have an inaccurate and often biased estimate of their daily smoking rate compared with the measured smoking rate. Specifically, 74% (34/46) of the smokers made more than one (mean 4.7, SD 4.2 cigarettes per day) wrong estimate, and 70% (32/46) of the smokers overestimated it. On the basis of the timestamp of the tracked smoking events, smoking rates were visualized at different hours and were found to gradually increase and peak at 6 PM in the day. In addition, a 1- to 2-hour shift in smoking patterns was observed between weekdays and weekends. When moderate and heavy smokers were compared with light smokers, their ages (P<.05), Fagerström Test of Nicotine Dependence (P=.01), craving level (P<.001), enjoyment of cigarettes (P<.001), difficulty resisting smoking (P<.001), emotional valence (P<.001), and arousal (P<.001) were all found to be significantly different. In the Poisson mixed-effects model, the number of cigarettes smoked in a 1-hour time window was highly dependent on the smoking status of an individual (P<.001) and was explained by hour (P=.02) and age (P=.005). CONCLUSIONS: This study reported the high potential and challenges of using an electronic lighter for smoking annotation and smoking-triggered EMAs in an ambulant environment. These results also validate the techniques for smoking behavior monitoring and pave the way for the design and deployment of technology-enabled smoking cessation applications. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1136/bmjopen-2018-028284.

The cumulative effect of chronic stress and depressive symptoms affects heart rate in a working population.

Background: Chronic stress and depressive symptoms have both been linked to increased heart rate (HR) and reduced HR variability. However, up to date, it is not clear whether chronic stress, the mechanisms intrinsic to depression or a combination of both cause these alterations. Subclinical cases may help to answer these questions. In a healthy working population, we aimed to investigate whether the effect of chronic stress on HR circadian rhythm depends on the presence of depressive symptoms and whether chronic stress and depressive symptoms have differential effects on HR reactivity to an acute stressor. Methods: 1,002 individuals of the SWEET study completed baseline questionnaires, including psychological information, and 5 days of electrocardiogram (ECG) measurements. Complete datasets were available for 516 individuals. In addition, a subset (n = 194) of these participants completed a stress task on a mobile device. Participants were grouped according to their scores for the Depression Anxiety Stress Scale (DASS) and Perceived Stress Scale (PSS). We explored the resulting groups for differences in HR circadian rhythm and stress reactivity using linear mixed effect models. Additionally, we explored the effect of stress and depressive symptoms on night-time HR variability [root mean square of successive differences (RMSSD)]. Results: High and extreme stress alone did not alter HR circadian rhythm, apart from a limited increase in basal HR. Yet, if depressive symptoms were present, extreme chronic stress levels did lead to a blunted circadian rhythm and a lower basal HR. Furthermore, blunted stress reactivity was associated with depressive symptoms, but not chronic stress. Night-time RMSSD data was not influenced by chronic stress, depressive symptoms or their interaction. Conclusion: The combination of stress and depressive symptoms, but not chronic stress by itself leads to a blunted HR circadian rhythm. Furthermore, blunted HR reactivity is associated with depressive symptoms and not chronic stress.

Twenty-Four-Hour Heart Rate Is a Trait but Not State Marker for Depression in a Pilot Randomized Controlled Trial With a Single Infusion of Ketamine.

Background: Abnormalities of heart rate (HR) and its variability are characteristic of major depressive disorder (MDD). However, circadian rhythm is rarely taken into account when statistically exploring state or trait markers for depression. Methods: A 4-day electrocardiogram was recorded for 16 treatment-resistant patients with MDD and 16 age- and sex-matched controls before, and for the patient group only, after a single treatment with the rapid-acting antidepressant ketamine or placebo (clinical trial registration available on https://www.clinicaltrialsregister.eu/ with EUDRACT number 2016-001715-21). Circadian rhythm differences of HR and the root mean square of successive differences (RMSSD) were compared between groups and were explored for classification purposes. Baseline HR/RMSSD were tested as predictors for treatment response, and physiological measures were assessed as state markers. Results: Patients showed higher HR and lower RMSSD alongside marked reductions in HR amplitude and RMSSD variation throughout the day. Excellent classification accuracy was achieved using HR during the night, particularly between 2 and 3 a.m. (90.6%). A positive association between baseline HR and treatment response (r = 0.55, p = 0.046) pointed toward better treatment outcome in patients with higher HR. Heart rate also decreased significantly following treatment but was not associated with improved mood after a single infusion of ketamine. Limitations: Our study had a limited sample size, and patients were treated with concomitant antidepressant medication. Conclusion: Patients with depression show a markedly reduced amplitude for HR and dysregulated RMSSD fluctuation. Higher HR and lower RMSSD in depression remain intact throughout a 24-h day, with the highest classification accuracy during the night. Baseline HR levels show potential for treatment response prediction but did not show potential as state markers in this study. Clinical trial registration: EUDRACT number 2016-001715-21.

Assessing the signal quality of electrocardiograms from varied acquisition sources: A generic machine learning pipeline for model generation.

BACKGROUND AND OBJECTIVE: Long-term electrocardiogram monitoring comes at the expense of signal quality. During unconstrained movements, the electrocardiogram is often corrupted by motion artefacts, which can lead to inaccurate physiological information. In this situation, automated quality assessment methods are useful to increase the reliability of the measurements. A generic machine learning pipeline that generates classification models for electrocardiogram quality assessment is presented in this article. The presented pipeline is tested on signals from varied acquisition sources, towards selecting segments that can be used for heart rate analysis in lifestyle applications. METHODS: Electrocardiogram recordings from traditional, wearable and ubiquitous devices, are segmented in 10 s windows and manually labeled by experienced researchers into two quality classes. To capture the electrocardiogram dynamics, a comprehensive set of 43 features is extracted from each segment, based on the time-domain signal, its Fast Fourier Transform, the Autocorrelation function and the Stationary Wavelet Transform. To select the most relevant features for each acquisition source we employ both a customized hybrid approach and the state-of-the-art Neighborhood Component Analysis method and compare them. Support Vector Machines (SVM), Decision Trees, K-Nearest-Neighbors and supervised ensemble methods are tested as possible binary classifiers. RESULTS: The results for the best performing models on traditional, wearable and ubiquitous electrocardiogram datasets are, respectively: balanced-accuracy: 89%, F1-score: 93% with the Fine Gaussian SVM model and 10 features; balanced-accuracy: 93%, F1-score: 93% with the Fine Gaussian SVM model and 11 features; balanced-accuracy: 95%, F1-score: 86%, with the Fine Gaussian SVM model and 8 features. CONCLUSIONS: According to the results, our generic pipeline can generate classification models tailored to individual acquisition sources, provided that a standard Lead I or Lead II is available. Such models accurately establish whether the electrocardiogram quality is good or bad for heart rate analysis. Furthermore, removing bad quality segments decreases errors in heart rate calculation.

Into the Wild: The Challenges of Physiological Stress Detection in Laboratory and Ambulatory Settings.

Stress and mental health have become major concerns worldwide. Research has already extensively investigated physiological signals as quantitative and continuous markers of stress. In recent years, the focus of the field has shifted from the laboratory to the ambulatory environment. We provide an overview of physiological stress detection in laboratory settings with a focus on identifying physiological sensing priorities, including electrocardiogram, skin conductance, and electromyogram, and the most suitable machine learning techniques, of which the choice depends on the context of the application. Additionally, an overview is given of new challenges ahead to move toward the ambulant environment, including the influence of physical activity, lower signal quality due to motion artifacts, the lack of a stress reference, and the subject-dependent nature of the physiological stress response. Finally, several recommendations for future research are listed, focusing on large-scale, longitudinal trials across different population groups and just-in-time interventions to move toward disease prevention and interception.

Toward Quantifying the Psychopathology of Eating Disorders From the Autonomic Nervous System Perspective: A Methodological Approach.

The phenomenology of Eating Disorders (ED) relates with altered functioning of the Autonomic Nervous System (ANS). The lack of agreement in what comes to the direction and significance of such alterations is possibly due to the variability in the ED spectrum. As the stress response system is an integral part of the ANS, we propose to investigate ANS tonic variations and phasic activations in response to stressors. We hypothesize that, while using stress as a test probe, characteristic ANS dysregulations in ED may be found when considering several physiological signals measured over time, and weighted by the individual psychological profiles. In this article we describe a novel methodological approach to investigate this hypothesis with the aim of providing further clarification on the ED spectrum conceptualization. The proposed methodology has been designed to be easily integrated in clinical practice and, eventually, in daily life. The population under observation includes both patients in treatment for ED, and matched controls. The study session has the duration of 1 day, including: (1) the administration of a stress task in a controlled environment and (2) naturalistic data collection. The stress task is designed to elicit both mentally and physically driven ANS activation. The naturalistic component intends to illustrate the psychophysiology in everyday life. We use wearable devices to continuously and non-invasively measure bio-signals related to ANS functioning. This information is complemented with psychometric information from validated stress and ED scales and ecological momentary assessments. The protocol has received ethical approval and has been implemented in practice, currently accounting for 37 patients (out of 120) and 16 controls (out of 60). Ongoing work focus on the definition and implementation of a data processing pipeline to quantitatively test our hypothesis, both standard statistical methods and more exploratory machine learning approaches will be considered.

Bioimpedance Method for Human Body Hydration Assessment.

A high-precision wearable bioimpedance sensor developed at Imec was extensively tested. Unlike known bioimpedance sensors on the market, the new device enables hydration shift measurement in a single person, with no need for averaging over a population. For reaching this target, a method for hydration monitoring in case of altered hydration is tested. An assessment of fluid shift with sensitivity of about 700 ml has been demonstrated, which is comparable with the capabilities of known methods because of the device accuracy, immunity to electrode-skin impedance variation, and due to establishing the impedance baseline prior to fluid shift.

Artefact detection and quality assessment of ambulatory ECG signals.

BACKGROUND AND OBJECTIVES: The presence of noise sources could reduce the diagnostic capability of the ECG signal and result in inappropriate treatment decisions. To mitigate this problem, automated algorithms to detect artefacts and quantify the quality of the recorded signal are needed. In this study we present an automated method for the detection of artefacts and quantification of the signal quality. The suggested methodology extracts descriptive features from the autocorrelation function and feeds these to a RUSBoost classifier. The posterior probability of the clean class is used to create a continuous signal quality assessment index. Firstly, the robustness of the proposed algorithm is investigated and secondly, the novel signal quality assessment index is evaluated. METHODS: Data were used from three different studies: a Sleep study, the PhysioNet 2017 Challenge and a Stress study. Binary labels, clean or contaminated, were available from different annotators with experience in ECG analysis. Two types of realistic ECG noise from the MIT-BIH Noise Stress Test Database (NSTDB) were added to the Sleep study to test the quality index. Firstly, the model was trained on the Sleep dataset and subsequently tested on a subset of the other two datasets. Secondly, all recording conditions were taken into account by training the model on a subset derived from the three datasets. Lastly, the posterior probabilities of the model for the different levels of agreement between the annotators were compared. RESULTS: AUC values between 0.988 and 1.000 were obtained when training the model on the Sleep dataset. These results were further improved when training on the three datasets and thus taking all recording conditions into account. A Pearson correlation coefficient of 0.8131 was observed between the score of the clean class and the level of agreement. Additionally, significant quality decreases per noise level for both types of added noise were observed. CONCLUSIONS: The main novelty of this study is the new approach to ECG signal quality assessment based on the posterior clean class probability of the classifier.

Comparing task-induced psychophysiological responses between persons with stress-related complaints and healthy controls: A methodological pilot study.

AIMS: Chronic stress is an important factor for a variety of health problems, highlighting the importance of early detection of stress-related problems. This methodological pilot study investigated whether the physiological response to and recovery from a stress task can differentiate healthy participants and persons with stress-related complaints. METHODS AND RESULTS: Healthy participants (n = 20) and participants with stress-related complaints (n = 12) participated in a laboratory stress test, which included 3 stress tasks. Three physiological signals were recorded: galvanic skin response (GSR), heart rate (HR), and skin temperature (ST). From these signals, 126 features were extracted, including static (eg, mean) and dynamic (eg, recovery time) features. Unsupervised feature selection reduced the set to 26 features. A logistic regression model was developed for 6 feature sets, analysing single-parameter and multiparameter models as well as models using recovery vs response-related features. The highest classification performance (accuracy = 78%) was obtained using the response-related feature set, including all physiological signals and using GSR-related features. A worse performance was obtained using single-signal feature sets based on HR (accuracy = 66%) and ST (accuracy = 59%). Response-related features outperformed recovery-related features (accuracy = 63%). CONCLUSION: Participants with stress-related complaints may be differentiated from healthy controls by physiological responses to stress tasks. We aimed to bring attention to new exploratory methodologies; further research is needed to validate and replicate the results on larger populations and patients on different areas along the stress continuum.

A 665 µW Silicon Photomultiplier-Based NIRS/EEG/EIT Monitoring ASIC for Wearable Functional Brain Imaging.

This paper presents a sub-mW ASIC for multimodal brain monitoring. The ASIC is co-integrated with electrode(s) and optodes (i.e., optical source and detector) as an active sensor to measure electroencephalography (EEG), bio-impedance (BioZ), and near-infrared spectroscopy (NIRS) on scalp. The target is to build a wearable EEG-NIRS headset for low-cost functional brain imaging. The proposed NIRS readout utilizes the near-infrared light to measure the pulse oximetry and blood oxygen saturation (SpO2). While traditional photodiodes are supported, the readout also allows the use of silicon photomultipliers (SiPMs) as optical detectors. The SiPM improves optical sensitivity while significantly reducing the average power of two LEDs to 150 µW. On circuit level, a SAR-based calibration compensates maximum 40 µA current from ambient light, while digital DC-servo loops reduces the baseline static SiPM current up to 400 µA, leading to an overall dynamic range of 87 dB. The EEG readout exhibits 720 MΩ input impedance at 50 Hz. The BioZ readout has 3 mΩ/√(Hz) impedance sensitivity by employing dynamic circuit techniques. When EEG, BioZ, and NIRS are enabled at the same time, one ASIC consumes 665 µW including the power of LEDs.

Large-scale wearable data reveal digital phenotypes for daily-life stress detection.

Physiological signals have shown to be reliable indicators of stress in laboratory studies, yet large-scale ambulatory validation is lacking. We present a large-scale cross-sectional study for ambulatory stress detection, consisting of 1002 subjects, containing subjects' demographics, baseline psychological information, and five consecutive days of free-living physiological and contextual measurements, collected through wearable devices and smartphones. This dataset represents a healthy population, showing associations between wearable physiological signals and self-reported daily-life stress. Using a data-driven approach, we identified digital phenotypes characterized by self-reported poor health indicators and high depression, anxiety and stress scores that are associated with blunted physiological responses to stress. These results emphasize the need for large-scale collections of multi-sensor data, to build personalized stress models for precision medicine.