Early warning signals observed in motor activity preceding mood state change in bipolar disorder

INTRODUCTION

Alterations in motor activity are well-established symptoms of bipolar disorder, and time series of motor activity can be considered complex dynamical systems. In such systems, early warning signals (EWS) occur in a critical transition period preceding a sudden shift (tipping point) in the system. EWS are statistical observations occurring due to a system's declining ability to maintain homeostasis when approaching a tipping point. The aim was to identify critical transition periods preceding bipolar mood state changes.

METHODS

Participants with a validated bipolar diagnosis were included to a one-year follow-up study, with repeated assessments of the participants' mood. Motor activity was recorded continuously by a wrist-worn actigraph. Participants assessed to have relapsed during follow-up were analyzed. Recognized EWS features were extracted from the motor activity data and analyzed by an unsupervised change point detection algorithm, capable of processing multi-dimensional data and developed to identify when the statistical property of a time series changes.

RESULTS

Of 49 participants, four depressive and four hypomanic/manic relapses among six individuals occurred, recording actigraphy for 23.8 ± 0.2 h/day, for 39.8 ± 4.6 days. The algorithm detected change points in the time series and identified critical transition periods spanning 13.5 ± 7.2 days. For depressions 11.4 ± 1.8, and hypomania/mania 15.6 ± 10.2 days.

CONCLUSION

The change point detection algorithm seems capable of recognizing impending mood episodes in continuous flowing data streams. Hence, we present an innovative method for forecasting approaching relapses to improve the clinical management of bipolar disorder.

Reduced heart rate variability during mania in a repeated naturalistic observational study

Background

Bipolar disorder (BD) is a chronic recurrent mood disorder associated with autonomic nervous system (ANS) dysfunction, indexed by heart rate variability (HRV). Changes in HRV between mood states are sparsely studied longitudinally. We aimed to compare HRV of hospitalized manic individuals with their own euthymic selves in a naturalistic observational study.

Methods

34 individuals were included, of which 16 were lost to follow-up. Ultimately 15 patients provided reliable heart rate data in both a manic and euthymic state, using photoplethysmography (PPG) sensor wristbands overnight. We calculated HRV measures Root Mean Square of Successive Differences (RMSSD), High-frequency (HF: 0.15-0.40 Hz), Low-frequency (LF: 0.40-0.15 Hz), Very low-frequency (VLF: 0.0033-0.04 Hz), Total power and Sample Entropy in 5-min night-time resting samples. We compared HRV measures by mood state within individuals using paired t-tests and linear regression to control for age and sex.

Results

HRV was lower in the manic state when compared to the euthymic state for all HRV metrics (p ≤ 0.02), with large to medium effect sizes (g = 1.24 to 0.65). HRV changes were not significantly affected by age or sex.

Conclusion

This longitudinal study provides evidence of lower HRV in manic states compared to euthymia, indicating an association between ANS dysregulation and changes in bipolar mood state. This corroborates previous cross-sectional studies, although the association may be less clear or reversed in hypomanic states. Further investigation in larger longitudinal samples is warranted.

Photoplethysmography-based derivation of physiological information using the BioPoint

The BioPoint is a new wireless and wearable device, targeting both the ambulatory and on-site monitoring of biosignals. It is described as being capable of streaming and recording the i) electromyography, ii) electrocardiography, iii) electrodermal activity, iv) photoplethysmography, v) skin temperature and vi) actigraphy simultaneously, while making the raw signals recorded by the sensors readily available. However, an in-depth assessment of the biophysical signals recorded by this device, as well as its ability to derive vital signs and other health metrics, remains to be carried out. Consequently, this work proposes a preliminary study to evaluate the quality of the signals that can be acquired by this wearable with a focus on the derivation of heart rate and peripheral blood oxygenation via photoplethysmography. The device is quantitatively compared to the medical-grade pulse oximeter NoninConnect 3245, by Nonin inc. This study was performed with participants wearing the BioPoint at different positions on the body (finger, wrist, forearm, biceps and plantar arch), while the NoninConnect was worn on the fingertip and used as the ground truth. The results show that the BioPoint can accurately determine both heart rate and oxygen saturation from various locations on the body. However, as the BioPoint's photoplethysmograph is not calibrated it cannot be used for medical purposes (non-medical-grade).

Adherence Forecasting for Guided Internet-Delivered Cognitive Behavioral Therapy: A Minimally Data-Sensitive Approach

Internet-delivered psychological treatments (IDPT) are seen as an effective and scalable pathway to improving the accessibility of mental healthcare. Within this context, treatment adherence is an especially pertinent challenge to address due to the reduced interaction between healthcare professionals and patients. In parallel, the increase in regulations surrounding the use of personal data, such as the General Data Protection Regulation (GDPR), makes data minimization a core consideration for real-world implementation of IDPTs. Consequently, this work proposes a Self-Attention-based deep learning approach to perform automatic adherence forecasting, while only relying on minimally sensitive login/logout-timestamp data. This approach was tested on a dataset containing 342 patients undergoing Guided Internet-delivered Cognitive Behavioral Therapy (G-ICBT) treatment. Of these 342 patients, 101 (  ∼ 30%) were considered non-adherent (dropout) based on the adherence definition used in this work (i.e. at least eight connections to the platform lasting more than a minute over 56 days). The proposed model achieved over 70% average balanced accuracy, after only 20 out of the 56 days (  ∼ 1/3) of the treatment had elapsed. This study demonstrates that automatic adherence forecasting for G-ICBT, is achievable using only minimally sensitive data, thus facilitating the implementation of such tools within real-world IDPT platforms.

Environmental Adaptation of Robot Morphology and Control Through Real-World Evolution

Robots operating in the real world will experience a range of different environments and tasks. It is essential for the robot to have the ability to adapt to its surroundings to work efficiently in changing conditions. Evolutionary robotics aims to solve this by optimizing both the control and body (morphology) of a robot, allowing adaptation to internal, as well as external factors. Most work in this field has been done in physics simulators, which are relatively simple and not able to replicate the richness of interactions found in the real world. Solutions that rely on the complex interplay among control, body, and environment are therefore rarely found. In this article, we rely solely on real-world evaluations and apply evolutionary search to yield combinations of morphology and control for our mechanically self-reconfiguring quadruped robot. We evolve solutions on two distinct physical surfaces and analyze the results in terms of both control and morphology. We then transition to two previously unseen surfaces to demonstrate the generality of our method. We find that the evolutionary search finds high-performing and diverse morphology-controller configurations by adapting both control and body to the different properties of the physical environments. We additionally find that morphology and control vary with statistical significance between the environments. Moreover, we observe that our method allows for morphology and control parameters to transfer to previously unseen terrains, demonstrating the generality of our approach.

Challenges and possible solutions in cross-disciplinary and cross-sectorial research teams within the domain of e-mental health

Purpose

Mental illness presents a huge individual, societal and economic challenges, currently accounting for 20% of the worldwide burden of disease. There is a gap between the need for and access to services. Digital technology has been proven effective in e-mental health for preventing and treating mental health problems. However, there is a need for cross-disciplinary efforts to increase the impact of e-mental health services. This paper aims to report key challenges and possible solutions for cross-disciplinary and cross-sectorial research teams within the domain of e-mental health.

Design/methodology/approach

The key challenges and possible solutions will be discussed in light of the literature on effective cross-disciplinary research teams.

Findings

Six topics have been key challenges in our cross-disciplinary and cross-sectorial research team: to develop a shared understanding of the domain; to establish a common understanding of key concepts among the project participants; to involve the end-users in the research and development process; to collaborate across sectors; to ensure privacy and security of health data; and to obtain the right timing of activities according to project dependencies.

Research limitations/implications

This study focuses to increase knowledge and training in cross-disciplinary and cross-sectorial research, as this is often referred to as an important tool when developing sustainable solutions for major societal challenges.

Practical implications

This study needs to include theory and skills training in cross-disciplinary research in research training.

Social implications

Cross-disciplinary teams have the potential to address major societal challenges, including more perspectives and more stakeholders than single disciplinary research teams.

Originality/value

Major societal challenges require complex and sustainable solutions. However, there is a lack of knowledge about how cross-disciplinary and cross-sectorial research teams may work productively to solve these challenges. This paper shares experiences regarding the challenges and possible solutions for productive collaboration in cross-disciplinary and cross-sectorial research teams within the domain of e-mental health services.

Semantic Active Visual Search System Based on Text Information for Large and Unknown Environments

Different high-level robotics tasks require the robot to manipulate or interact with objects that are in an unexplored part of the environment or not already in its field of view. Although much works rely on searching for objects based on their colour or 3D context, we argue that text information is a useful and functional visual cue to guide the search. In this paper, we study the problem of active visual search (AVS) in large unknown environments. In this paper, we present an AVS system that relies on semantic information inferred from texts found in the environment, which allows the robot to reduce the search costs by avoiding not promising regions for the target object. Our semantic planner reasons over the numbers detected from door signs to decide either perform a goal-directed exploration towards unknown parts of the environment or carefully search in the already known parts. We compared the performance of our semantic AVS system with two other search systems in four simulated environments. First, we developed a greedy search system that does not consider any semantic information, and second, we invited human participants to teleoperate the robot while performing the search. Our results from simulation and real-world experiments show that text is a promising source of information that provides different semantic cues for AVS systems.

Applying machine learning in motor activity time series of depressed bipolar and unipolar patients compared to healthy controls

Current practice of assessing mood episodes in affective disorders largely depends on subjective observations combined with semi-structured clinical rating scales. Motor activity is an objective observation of the inner physiological state expressed in behavior patterns. Alterations of motor activity are essential features of bipolar and unipolar depression. The aim was to investigate if objective measures of motor activity can aid existing diagnostic practice, by applying machine-learning techniques to analyze activity patterns in depressed patients and healthy controls. Random Forrest, Deep Neural Network and Convolutional Neural Network algorithms were used to analyze 14 days of actigraph recorded motor activity from 23 depressed patients and 32 healthy controls. Statistical features analyzed in the dataset were mean activity, standard deviation of mean activity and proportion of zero activity. Various techniques to handle data imbalance were applied, and to ensure generalizability and avoid overfitting a Leave-One-User-Out validation strategy was utilized. All outcomes reports as measures of accuracy for binary tests. A Deep Neural Network combined with SMOTE class balancing technique performed a cut above the rest with a true positive rate of 0.82 (sensitivity) and a true negative rate of 0.84 (specificity). Accuracy was 0.84 and the Matthews Correlation Coefficient 0.65. Misclassifications appear related to data overlapping among the classes, so an appropriate future approach will be to compare mood states intra-individualistically. In summary, machine-learning techniques present promising abilities in discriminating between depressed patients and healthy controls in motor activity time series.

Understanding Musical Predictions With an Embodied Interface for Musical Machine Learning

Machine-learning models of music often exist outside the worlds of musical performance practice and abstracted from the physical gestures of musicians. In this work, we consider how a recurrent neural network (RNN) model of simple music gestures may be integrated into a physical instrument so that predictions are sonically and physically entwined with the performer's actions. We introduce EMPI, an embodied musical prediction interface that simplifies musical interaction and prediction to just one dimension of continuous input and output. The predictive model is a mixture density RNN trained to estimate the performer's next physical input action and the time at which this will occur. Predictions are represented sonically through synthesized audio, and physically with a motorized output indicator. We use EMPI to investigate how performers understand and exploit different predictive models to make music through a controlled study of performances with different models and levels of physical feedback. We show that while performers often favor a model trained on human-sourced data, they find different musical affordances in models trained on synthetic, and even random, data. Physical representation of predictions seemed to affect the length of performances. This work contributes new understandings of how musicians use generative ML models in real-time performance backed up by experimental evidence. We argue that a constrained musical interface can expose the affordances of embodied predictive interactions.

Animation Techniques in Human-Robot Interaction User Studies

There are many different ways a robot can move in Human-Robot Interaction. One way is to use techniques from film animation to instruct the robot to move. This article is a systematic literature review of human-robot trials, pilots, and evaluations that have applied techniques from animation to move a robot. Through 27 articles, we find that animation techniques improves an individual’s interaction with robots, improving the individual’s perception of qualities of a robot, understanding what a robot intends to do, and showing the robot’s state or possible emotion. Animation techniques also help people relate to robots that do not resemble a human or robot. The studies in the articles show further areas for research, such as applying animation principles in other types of robots and situations, combining animation techniques with other modalities, and testing robots moving with animation techniques over the long term.

Guiding Neuroevolution with Structural Objectives

The structure and performance of neural networks are intimately connected, and by use of evolutionary algorithms, neural network structures optimally adapted to a given task can be explored. Guiding such neuroevolution with additional objectives related to network structure has been shown to improve performance in some cases, especially when modular neural networks are beneficial. However, apart from objectives aiming to make networks more modular, such structural objectives have not been widely explored. We propose two new structural objectives and test their ability to guide evolving neural networks on two problems which can benefit from decomposition into subtasks. The first structural objective guides evolution to align neural networks with a user-recommended decomposition pattern. Intuitively, this should be a powerful guiding target for problems where human users can easily identify a structure. The second structural objective guides evolution towards a population with a high diversity in decomposition patterns. This results in exploration of many different ways to decompose a problem, allowing evolution to find good decompositions faster. Tests on our target problems reveal that both methods perform well on a problem with a very clear and decomposable structure. However, on a problem where the optimal decomposition is less obvious, the structural diversity objective is found to outcompete other structural objectives-and this technique can even increase performance on problems without any decomposable structure at all.

Ambient Sensors for Elderly Care and Independent Living: A Survey

Elderly care at home is a matter of great concern if the elderly live alone, since unforeseen circumstances might occur that affect their well-being. Technologies that assist the elderly in independent living are essential for enhancing care in a cost-effective and reliable manner. Elderly care applications often demand real-time observation of the environment and the resident’s activities using an event-driven system. As an emerging area of research and development, it is necessary to explore the approaches of the elderly care system in the literature to identify current practices for future research directions. Therefore, this work is aimed at a comprehensive survey of non-wearable (i.e., ambient) sensors for various elderly care systems. This research work is an effort to obtain insight into different types of ambient-sensor-based elderly monitoring technologies in the home. With the aim of adopting these technologies, research works, and their outcomes are reported. Publications have been included in this survey if they reported mostly ambient sensor-based monitoring technologies that detect elderly events (e.g., activities of daily living and falls) with the aim of facilitating independent living. Mostly, different types of non-contact sensor technologies were identified, such as motion, pressure, video, object contact, and sound sensors. Besides, multicomponent technologies (i.e., combinations of ambient sensors with wearable sensors) and smart technologies were identified. In addition to room-mounted ambient sensors, sensors in robot-based elderly care works are also reported. Research that is related to the use of elderly behavior monitoring technologies is widespread, but it is still in its infancy and consists mostly of limited-scale studies. Elderly behavior monitoring technology is a promising field, especially for long-term elderly care. However, monitoring technologies should be taken to the next level with more detailed studies that evaluate and demonstrate their potential to contribute to prolonging the independent living of elderly people.

The convergence of backpropagation trained neural networks for various weight update frequencies

One of the problems concerning the backpropagation training of feed-forward neural networks is the effect of the weight update frequency. This aspect influences the efficiency of parallel implementations of the training algorithm where the training vectors are distributed among processors. In this paper the convergence of two applications for various weight update intervals is reported. Further, several models are proposed for describing convergence and learning rate aspects in the context of a set of weight update intervals. The results show that the convergence by updating the weights after each training vector leads to about 10 times less number of training iterations compared to updating the weights only ones for the whole training set.