Physiological Measurements of Stress Preceding Incidents of Challenging Behavior in People With Severe to Profound Intellectual Disabilities: Longitudinal Study Protocol of Single-Case Studies

Real-time stress detection based on artificial intelligence for people with an intellectual disability

People with severe intellectual disabilities (ID) could have difficulty expressing their stress which may complicate timely responses from caregivers. The present study proposes an automatic stress detection system that can work in real-time. The system uses wearable sensors that record physiological signals in combination with machine learning to detect physiological changes related to stress. Four experiments were conducted to assess if the system could detect stress in people with and without ID. Three experiments were conducted with people without ID (n = 14, n = 18, and n = 48), and one observational study was done with people with ID (n = 12). To analyze if the system could detect stress, the performance of random, general, and personalized models was evaluated. The mixed ANOVA found a significant effect for model type, F(2, 134) = 116.50, p < .001. Additionally, the post-hoc t-tests found that the personalized model for the group with ID performed better than the random model, t(11) = 9.05, p < .001. The findings suggest that the personalized model can detect stress in people with and without ID. A larger-scale study is required to validate the system for people with ID.

Effect of stress-based interventions on the quality of life of people with an intellectual disability and their caregivers

PURPOSE

People with intellectual disabilities often show challenging behaviour, which can manifest itself in self-harm or aggression towards others. Real-time monitoring of stress in clients with challenging behaviour can help caregivers to promptly deploy interventions to prevent escalations, ultimately to improve the quality of life of client and caregiver. This study aimed to assess the impact of real-time stress monitoring with HUME, and the subsequent interventions deployed by the care team, on stress levels and quality of life.

MATERIALS AND METHODS

Real-time stress monitoring was used in 41 clients with intellectual disabilities in a long-term care setting over a period of six months. Stress levels were determined at the start and during the deployment of the stress monitoring system. The quality of life of the client and caregiver was measured with the Outcome Rating Scale at the start and at three months of use.

RESULTS

The results showed that the HUME-based interventions resulted in a stress reduction. The perceived quality of life was higher after three months for both the clients and caregivers. Furthermore, interventions to provide proximity were found to be most effective in reducing stress and increasing the client's quality of life.

CONCLUSIONS

The study demonstrates that real-time stress monitoring with the HUME and the following interventions were effective. There was less stress in clients with an intellectual disability and an increase in the perceived quality of life. Future larger and randomized controlled studies are needed to confirm these findings.

The geometry of synchronization: quantifying the coupling direction of physiological signals of stress between individuals using inter-system recurrence networks

In the study of synchronization dynamics between interacting systems, several techniques are available to estimate coupling strength and coupling direction. Currently, there is no general 'best' method that will perform well in most contexts. Inter-system recurrence networks (IRN) combine auto-recurrence and cross-recurrence matrices to create a graph that represents interacting networks. The method is appealing because it is based on cross-recurrence quantification analysis, a well-developed method for studying synchronization between 2 systems, which can be expanded in the IRN framework to include N > 2 interacting networks. In this study we examine whether IRN can be used to analyze coupling dynamics between physiological variables (acceleration, blood volume pressure, electrodermal activity, heart rate and skin temperature) observed in a client in residential care with severe to profound intellectual disabilities (SPID) and their professional caregiver. Based on the cross-clustering coefficients of the IRN conclusions about the coupling direction (client or caregiver drives the interaction) can be drawn, however, deciding between bi-directional coupling or no coupling remains a challenge. Constructing the full IRN, based on the multivariate time series of five coupled processes, reveals the existence of potential feedback loops. Further study is needed to be able to determine dynamics of coupling between the different layers.

Generalizable machine learning for stress monitoring from wearable devices: A systematic literature review

INTRODUCTION

Wearable sensors have shown promise as a non-intrusive method for collecting biomarkers that may correlate with levels of elevated stress. Stressors cause a variety of biological responses, and these physiological reactions can be measured using biomarkers including Heart Rate Variability (HRV), Electrodermal Activity (EDA) and Heart Rate (HR) that represent the stress response from the Hypothalamic-Pituitary-Adrenal (HPA) axis, the Autonomic Nervous System (ANS), and the immune system. While Cortisol response magnitude remains the gold standard indicator for stress assessment [1], recent advances in wearable technologies have resulted in the availability of a number of consumer devices capable of recording HRV, EDA and HR sensor biomarkers, amongst other signals. At the same time, researchers have been applying machine learning techniques to the recorded biomarkers in order to build models that may be able to predict elevated levels of stress.

OBJECTIVE

The aim of this review is to provide an overview of machine learning techniques utilized in prior research with a specific focus on model generalization when using these public datasets as training data. We also shed light on the challenges and opportunities that machine learning-enabled stress monitoring and detection face.

METHODS

This study reviewed published works contributing and/or using public datasets designed for detecting stress and their associated machine learning methods. The electronic databases of Google Scholar, Crossref, DOAJ and PubMed were searched for relevant articles and a total of 33 articles were identified and included in the final analysis. The reviewed works were synthesized into three categories of publicly available stress datasets, machine learning techniques applied using those, and future research directions. For the machine learning studies reviewed, we provide an analysis of their approach to results validation and model generalization. The quality assessment of the included studies was conducted in accordance with the IJMEDI checklist [2].

RESULTS

A number of public datasets were identified that are labeled for stress detection. These datasets were most commonly produced from sensor biomarker data recorded using the Empatica E4 device, a well-studied, medical-grade wrist-worn wearable that provides sensor biomarkers most notable to correlate with elevated levels of stress. Most of the reviewed datasets contain less than twenty-four hours of data, and the varied experimental conditions and labeling methodologies potentially limit their ability to generalize for unseen data. In addition, we discuss that previous works show shortcomings in areas such as their labeling protocols, lack of statistical power, validity of stress biomarkers, and model generalization ability.

CONCLUSION

Health tracking and monitoring using wearable devices is growing in popularity, while the generalization of existing machine learning models still requires further study, and research in this area will continue to provide improvements as newer and more substantial datasets become available.

Tourist Experiences Recommender System Based on Emotion Recognition with Wearable Data

The collection of physiological data from people has been facilitated due to the mass use of cheap wearable devices. Although the accuracy is low compared to specialized healthcare devices, these can be widely applied in other contexts. This study proposes the architecture for a tourist experiences recommender system (TERS) based on the user's emotional states who wear these devices. The issue lies in detecting emotion from Heart Rate (HR) measurements obtained from these wearables. Unlike most state-of-the-art studies, which have elicited emotions in controlled experiments and with high-accuracy sensors, this research's challenge consisted of emotion recognition (ER) in the daily life context of users based on the gathering of HR data. Furthermore, an objective was to generate the tourist recommendation considering the emotional state of the device wearer. The method used comprises three main phases: The first was the collection of HR measurements and labeling emotions through mobile applications. The second was emotional detection using deep learning algorithms. The final phase was the design and validation of the TERS-ER. In this way, a dataset of HR measurements labeled with emotions was obtained as results. Among the different algorithms tested for ER, the hybrid model of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks had promising results. Moreover, concerning TERS, Collaborative Filtering (CF) using CNN showed better performance.