Pattern classification of valence in depression

MEDIC: Development and validation of a new instrument to assess emotional reactivity to medical stimuli in a representative community sample of adults

To support investigation of the etiology and psychophysiology of medical traumatic stress, we developed a standardized set of emotionally-salient medical images, called the 'MEDical Image Collection' (MEDIC), for use in neuroimaging or psychological research. This study aimed to establish internal consistency, test re-test reliability, and congruent validity of the image set. A representative sample of 300 adults in the United States were recruited via research recruitment platform, Prolific. Participants rated 124 images depicting medical stimuli on one of two dimensions: emotional arousal (i.e., how strongly an evoked emotion is felt) or affective valence (i.e., how positive or negative the evoked emotion is). Sociodemographic and health-related characteristics, including experiences during the COVID-19 pandemic, were also assessed. To assess test re-test reliability, a subset (n = 200) rated the images on the same dimension a second time, 3 months later. The MEDIC image set was found to: (a) elicit a range of emotional arousal and valence ratings, (b) have excellent inter-rater reliability, (c) moderate test-retest reliability, and (d) good face validity. Results indicate the new MEDIC 124-image set is a reliable and valid instrument, enabling researchers to provide context-specific and emotionally-salient stimuli to individuals when studying affective responses in relation to health and medicine.

Preclinical Models of Chronic Stress: Adaptation or Pathology?

The experience of prolonged stress changes how individuals interact with their environment and process interoceptive cues, with the end goal of optimizing survival and well-being in the face of a now-hostile world. The chronic stress response includes numerous changes consistent with limiting further damage to the organism, including development of passive or active behavioral strategies and metabolic adjustments to alter energy mobilization. These changes are consistent with symptoms of pathology in humans, and as a result, chronic stress has been used as a translational model for diseases such as depression. While it is of heuristic value to understand symptoms of pathology, we argue that the chronic stress response represents a defense mechanism that is, at its core, adaptive in nature. Transition to pathology occurs only after the adaptive capacity of an organism is exhausted. We offer this perspective as a means of framing interpretations of chronic stress studies in animal models and how these data relate to adaptation as opposed to pathology.

A neural network approach to optimising treatments for depression using data from specialist and community psychiatric services in Australia, New Zealand and Japan

This study investigated the application of a recurrent neural network for optimising pharmacological treatment for depression. A clinical dataset of 458 participants from specialist and community psychiatric services in Australia, New Zealand and Japan were extracted from an existing custom-built, web-based tool called Psynary . This data, which included baseline and self-completed reviews, was used to train and refine a novel algorithm which was a fully connected network feature extractor and long short-term memory algorithm was firstly trained in isolation and then integrated and annealed using slow learning rates due to the low dimensionality of the data. The accuracy of predicting depression remission before processing patient review data was 49.8%. After processing only 2 reviews, the accuracy was 76.5%. When considering a change in medication, the precision of changing medications was 97.4% and the recall was 71.4% . The medications with predicted best results were antipsychotics (88%) and selective serotonin reuptake inhibitors (87.9%). This is the first study that has created an all-in-one algorithm for optimising treatments for all subtypes of depression. Reducing treatment optimisation time for patients suffering with depression may lead to earlier remission and hence reduce the high levels of disability associated with the condition. Furthermore, in a setting where mental health conditions are increasing strain on mental health services, the utilisation of web-based tools for remote monitoring and machine/deep learning algorithms may assist clinicians in both specialist and primary care in extending specialist mental healthcare to a larger patient community.

Integrating Multilevel Functional Characteristics Reveals Aberrant Neural Patterns during Audiovisual Emotional Processing in Depression

Emotion dysregulation is one of the core features of major depressive disorder (MDD). However, most studies in depression have focused on unimodal emotion processing, whereas emotional perception in daily life is highly dependent on multimodal sensory inputs. Here, we proposed a novel multilevel discriminative framework to identify the altered neural patterns in processing audiovisual emotion in MDD. Seventy-four participants underwent an audiovisual emotional task functional magnetic resonance imaging scanning. Three levels of whole-brain functional features were extracted for each subject, including the task-evoked activation, task-modulated connectivity, combined activation and connectivity. Support vector machine classification and prediction models were built to identify MDD from controls and evaluate clinical relevance. We revealed that complex neural networks including the emotion regulation network (prefrontal areas and limbic-subcortical regions) and the multisensory integration network (lateral temporal cortex and motor areas) had the discriminative power. Moreover, by integrating comprehensive information of local and interactive processes, multilevel models could lead to a substantial increase in classification accuracy and depression severity prediction. Together, we highlight the high representational capacity of machine learning algorithms to characterize the complex network abnormalities associated with emotional regulation and multisensory integration in MDD. These findings provide novel evidence for the neural mechanisms underlying multimodal emotion dysregulation of depression.

Towards a brain-based predictome of mental illness

Neuroimaging-based approaches have been extensively applied to study mental illness in recent years and have deepened our understanding of both cognitively healthy and disordered brain structure and function. Recent advancements in machine learning techniques have shown promising outcomes for individualized prediction and characterization of patients with psychiatric disorders. Studies have utilized features from a variety of neuroimaging modalities, including structural, functional, and diffusion magnetic resonance imaging data, as well as jointly estimated features from multiple modalities, to assess patients with heterogeneous mental disorders, such as schizophrenia and autism. We use the term "predictome" to describe the use of multivariate brain network features from one or more neuroimaging modalities to predict mental illness. In the predictome, multiple brain network-based features (either from the same modality or multiple modalities) are incorporated into a predictive model to jointly estimate features that are unique to a disorder and predict subjects accordingly. To date, more than 650 studies have been published on subject-level prediction focusing on psychiatric disorders. We have surveyed about 250 studies including schizophrenia, major depression, bipolar disorder, autism spectrum disorder, attention-deficit hyperactivity disorder, obsessive-compulsive disorder, social anxiety disorder, posttraumatic stress disorder, and substance dependence. In this review, we present a comprehensive review of recent neuroimaging-based predictomic approaches, current trends, and common shortcomings and share our vision for future directions.

Multi-voxel pattern analysis of amygdala functional connectivity at rest predicts variability in posttraumatic stress severity

INTRODUCTION

Resting state functional magnetic resonance imaging (rsfMRI) studies demonstrate that individuals with posttraumatic stress disorder (PTSD) exhibit atypical functional connectivity (FC) between the amygdala, involved in the generation of emotion, and regions responsible for emotional appraisal (e.g., insula, orbitofrontal cortex [OFC]) and regulation (prefrontal cortex [PFC], anterior cingulate cortex). Consequently, atypical amygdala FC within an emotional processing and regulation network may be a defining feature of PTSD, although altered FC does not seem constrained to one brain region. Instead, altered amygdala FC involves a large, distributed brain network in those with PTSD. The present study used a machine-learning data-driven approach, multi-voxel pattern analysis (MVPA), to predict PTSD severity based on whole-brain patterns of amygdala FC.

METHODS

Trauma-exposed adults (N = 90) completed the PTSD Checklist-Civilian Version to assess symptoms and a 5-min rsfMRI. Whole-brain FC values to bilateral amygdala were extracted and used in a relevance vector regression analysis with a leave-one-out approach for cross-validation with permutation testing (1,000) to obtain significance values.

RESULTS

Results demonstrated that amygdala FC predicted PCL-C scores with statistically significant accuracy (r = .46, p = .001; mean sum of squares = 130.46, p = .001; R²  = 0.21, p = .001). Prediction was based on whole-brain amygdala FC, although regions that informed prediction (top 10%) included the OFC, amygdala, and dorsolateral PFC.

CONCLUSION

Findings demonstrate the utility of MVPA based on amygdala FC to predict individual severity of PTSD symptoms and that amygdala FC within a fear acquisition and regulation network contributed to accurate prediction.

Local glutamate in cingulate cortex subregions differentially correlates with affective network activations during face perception

The cingulate cortex is involved in emotion recognition/perception and regulation. Rostral and caudal subregions belong to different brain networks with distinct roles in affective perception. Despite recent accounts of the relevance of cingulate cortex glutamate (Glu) on blood-oxygen-level-dependent (BOLD) responses, the specificity of the subregional Glu levels during emotional tasks remains unclear. Seventy-two healthy participants (age = 27.33 ± 6.67, 32 women) performed an affective face-matching task and underwent magnetic resonance spectroscopy (MRS) at 7 Tesla. Correlations between the BOLD response during emotion perception and Glu concentration in the pregenual anterior cingulate cortex (pgACC) and anterior midcingulate cortex (aMCC) were compared on a whole-brain level. Post hoc specificity of the association with an affect was assessed. Lower Glu in the pgACC correlated with stronger activation differences between negative and positive faces in the left inferior and superior frontal gyrus (L IFG and L SFG). In contrast, lower Glu in the aMCC correlated with BOLD contrasts in the posterior cingulate cortex (PCC). Furthermore, negative face detection was associated with prolonged response time (RT). Our results demonstrate a subregion-specific involvement of cingulate cortex Glu in interindividual differences during viewing of affective facial expressions. Glu levels in the pgACC were correlated with frontal area brain activations, whereas Glu in the salience network component aMCC modulated responses in the PCC-precuneus. We show that region-specific metabolite mapping enables specific activation of different BOLD signals in the brain underlying emotional perception.

Toward a unified framework for interpreting machine-learning models in neuroimaging

Machine learning is a powerful tool for creating computational models relating brain function to behavior, and its use is becoming widespread in neuroscience. However, these models are complex and often hard to interpret, making it difficult to evaluate their neuroscientific validity and contribution to understanding the brain. For neuroimaging-based machine-learning models to be interpretable, they should (i) be comprehensible to humans, (ii) provide useful information about what mental or behavioral constructs are represented in particular brain pathways or regions, and (iii) demonstrate that they are based on relevant neurobiological signal, not artifacts or confounds. In this protocol, we introduce a unified framework that consists of model-, feature- and biology-level assessments to provide complementary results that support the understanding of how and why a model works. Although the framework can be applied to different types of models and data, this protocol provides practical tools and examples of selected analysis methods for a functional MRI dataset and multivariate pattern-based predictive models. A user of the protocol should be familiar with basic programming in MATLAB or Python. This protocol will help build more interpretable neuroimaging-based machine-learning models, contributing to the cumulative understanding of brain mechanisms and brain health. Although the analyses provided here constitute a limited set of tests and take a few hours to days to complete, depending on the size of data and available computational resources, we envision the process of annotating and interpreting models as an open-ended process, involving collaborative efforts across multiple studies and laboratories.

Identifying Criteria for the Evaluation of the Implications of Brain Reading for Mental Privacy

Contemporary brain reading technologies promise to provide the possibility to decode and interpret mental states and processes. Brain reading could have numerous societally relevant implications. In particular, the private character of mind might be affected, generating ethical and legal concerns. This paper aims at equipping ethicists and policy makers with conceptual tools to support an evaluation of the potential applicability and the implications of current and near future brain reading technology. We start with clarifying the concepts of mind reading and brain reading, and the different kinds of mental states that could in principle be read. Subsequently, we devise an evaluative framework that is composed of five criteria-accuracy, reliability, informativity, concealability and enforceability-aimed at enabling a clearer estimation of the degree to which brain reading might be realistically deployed in contexts where mental privacy could be at stake. While accuracy and reliability capture how well a certain method can access mental content, informativity indicates the relevance the obtainable data have for practical purposes. Concealability and enforceability are particularly important for the evaluation of concerns about potential violations of mental privacy and civil rights. The former concerns the degree with which a brain reading method can be concealed from an individual's perception or awareness. The latter regards the extent to which a method can be used against somebody's will. With the help of these criteria, stakeholders can orient themselves in the rapidly developing field of brain reading.

Identify a shared neural circuit linking multiple neuropsychiatric symptoms with Alzheimer's pathology

Neuropsychiatric symptoms (NPS) are common in Alzheimer's disease (AD)-associated neurodegeneration. However, NPS lack a consistent relationship with AD pathology. It is unknown whether any common neural circuits can link these clinically disparate while mechanistically similar features with AD pathology. Here, we explored the neural circuits of NPS in AD-associated neurodegeneration using multivariate pattern analysis (MVPA) of resting-state functional MRI data. Data from 98 subjects (70 amnestic mild cognitive impairment and 28 AD subjects) were obtained. The top 10 regions differentiating symptom presence across NPS were identified, which were mostly the fronto-limbic regions (medial prefrontal cortex, caudate, etc.). These 10 regions' functional connectivity classified symptomatic subjects across individual NPS at 69.46-81.27%, and predicted multiple NPS (indexed by Neuropsychiatric Symptom Questionnaire-Inventory) and AD pathology (indexed by baseline and change of beta-amyloid/pTau ratio) all above 70%. Our findings suggest a fronto-limbic dominated neural circuit that links multiple NPS and AD pathology. With further examination of the structural and pathological changes within the circuit, the circuit may shed light on linking behavioral disturbances with AD-associated neurodegeneration.

Machine learning in major depression: From classification to treatment outcome prediction

AIMS

Major depression disorder (MDD) is the single greatest cause of disability and morbidity, and affects about 10% of the population worldwide. Currently, there are no clinically useful diagnostic biomarkers that are able to confirm a diagnosis of MDD from bipolar disorder (BD) in the early depressive episode. Therefore, exploring translational biomarkers of mood disorders based on machine learning is in pressing need, though it is challenging, but with great potential to improve our understanding of these disorders.

DISCUSSIONS

In this study, we review popular machine-learning methods used for brain imaging classification and predictions, and provide an overview of studies, specifically for MDD, that have used magnetic resonance imaging data to either (a) classify MDDs from controls or other mood disorders or (b) investigate treatment outcome predictors for individual patients. Finally, challenges, future directions, and potential limitations related to MDD biomarker identification are also discussed, with a goal of offering a comprehensive overview that may help readers to better understand the applications of neuroimaging data mining in depression.

CONCLUSIONS

We hope such efforts may highlight the need for an urgently needed paradigm shift in treatment, to guide personalized optimal clinical care.

Reproducibility of importance extraction methods in neural network based fMRI classification

Recent advances in machine learning allow faster training, improved performance and increased interpretability of classification techniques. Consequently, their application in neuroscience is rapidly increasing. While classification approaches have proved useful in functional magnetic resonance imaging (fMRI) studies, there are concerns regarding extraction, reproducibility and visualization of brain regions that contribute most significantly to the classification. We addressed these issues using an fMRI classification scheme based on neural networks and compared a set of methods for extraction of category-related voxel importances in three simulated and two empirical datasets. The simulation data revealed that the proposed scheme successfully detects spatially distributed and overlapping activation patterns upon successful classification. Application of the proposed classification scheme to two previously published empirical fMRI datasets revealed robust importance maps that extensively overlap with univariate maps but also provide complementary information. Our results demonstrate increased statistical power of importance maps compared to univariate approaches for both detection of overlapping patterns and patterns with weak univariate information.

Detecting Neuroimaging Biomarkers for Depression: A Meta-analysis of Multivariate Pattern Recognition Studies

BACKGROUND

Multiple studies have examined functional and structural brain alteration in patients diagnosed with major depressive disorder (MDD). The introduction of multivariate statistical methods allows investigators to utilize data concerning these brain alterations to generate diagnostic models that accurately differentiate patients with MDD from healthy control subjects (HCs). However, there is substantial heterogeneity in the reported results, the methodological approaches, and the clinical characteristics of participants in these studies.

METHODS

We conducted a meta-analysis of all studies using neuroimaging (volumetric measures derived from T1-weighted images, task-based functional magnetic resonance imaging [MRI], resting-state MRI, or diffusion tensor imaging) in combination with multivariate statistical methods to differentiate patients diagnosed with MDD from HCs.

RESULTS

Thirty-three (k = 33) samples including 912 patients with MDD and 894 HCs were included in the meta-analysis. Across all studies, patients with MDD were separated from HCs with 77% sensitivity and 78% specificity. Classification based on resting-state MRI (85% sensitivity, 83% specificity) and on diffusion tensor imaging data (88% sensitivity, 92% specificity) outperformed classifications based on structural MRI (70% sensitivity, 71% specificity) and task-based functional MRI (74% sensitivity, 77% specificity).

CONCLUSIONS

Our results demonstrate the high representational capacity of multivariate statistical methods to identify neuroimaging-based biomarkers of depression. Future studies are needed to elucidate whether multivariate neuroimaging analysis has the potential to generate clinically useful tools for the differential diagnosis of affective disorders and the prediction of both treatment response and functional outcome.

Identifying Core Affect in Individuals from fMRI Responses to Dynamic Naturalistic Audiovisual Stimuli

Recent research has demonstrated that affective states elicited by viewing pictures varying in valence and arousal are identifiable from whole brain activation patterns observed with functional magnetic resonance imaging (fMRI). Identification of affective states from more naturalistic stimuli has clinical relevance, but the feasibility of identifying these states on an individual trial basis from fMRI data elicited by dynamic multimodal stimuli is unclear. The goal of this study was to determine whether affective states can be similarly identified when participants view dynamic naturalistic audiovisual stimuli. Eleven participants viewed 5s audiovisual clips in a passive viewing task in the scanner. Valence and arousal for individual trials were identified both within and across participants based on distributed patterns of activity in areas selectively responsive to audiovisual naturalistic stimuli while controlling for lower level features of the stimuli. In addition, the brain regions identified by searchlight analyses to represent valence and arousal were consistent with previously identified regions associated with emotion processing. These findings extend previous results on the distributed representation of affect to multimodal dynamic stimuli.

Altered Resting-State Amygdala Functional Connectivity after Real-Time fMRI Emotion Self-Regulation Training

Real-time fMRI neurofeedback (rtfMRI-nf) is a promising tool for enhancing emotion regulation capability of subjects and for the potential alleviation of neuropsychiatric disorders. The amygdala is composed of structurally and functionally distinct nuclei, such as the basolateral amygdala (BLA) and centromedial amygdala (CMA), both of which are involved in emotion processing, generation, and regulation. However, the effect of rtfMRI-nf on the resting-state functional connectivity (rsFC) of BLA and CMA remains to be elucidated. In our study, participants were provided with ongoing information on their emotion states by using real-time multivariate voxel pattern analysis. Results showed that participants presented significantly increased rsFC of BLA and CMA with prefrontal cortex, rostral anterior cingulate cortex, and some others related to emotion after rtfMRI-nf training. The findings provide important evidence for the emotion regulation effectiveness of rtfMRI-nf training and indicate its usefulness as a tool for the self-regulation of emotion.

Machine learning of structural magnetic resonance imaging predicts psychopathic traits in adolescent offenders

Classification models are becoming useful tools for finding patterns in neuroimaging data sets that are not observable to the naked eye. Many of these models are applied to discriminating clinical groups such as schizophrenic patients from healthy controls or from patients with bipolar disorder. A more nuanced model might be to discriminate between levels of personality traits. Here, as a proof of concept, we take an initial step toward developing prediction models to differentiate individuals based on a personality disorder: psychopathy. We included three groups of adolescent participants: incarcerated youth with elevated psychopathic traits (i.e., callous and unemotional traits and conduct disordered traits; n=71), incarcerated youth with low psychopathic traits (n=72), and non-incarcerated youth as healthy controls (n=21). Support vector machine (SVM) learning models were developed to separate these groups using an out-of-sample cross-validation method on voxel-based morphometry (VBM) data. Regions of interest from the paralimbic system, identified in an independent forensic sample, were successful in differentiating youth groups. Models seeking to classify incarcerated individuals to have high or low psychopathic traits achieved 69.23% overall accuracy. As expected, accuracy increased in models differentiating healthy controls from individuals with high psychopathic traits (82.61%) and low psychopathic traits (80.65%). Here we have laid the foundation for using neural correlates of personality traits to identify group membership within and beyond psychopathy. This is only the first step, of many, toward prediction models using neural measures as a proxy for personality traits. As these methods are improved, prediction models with neural measures of personality traits could have far-reaching impact on diagnosis, treatment, and prediction of future behavior.

Altered anatomical patterns of depression in relation to antidepressant treatment: Evidence from a pattern recognition analysis on the topological organization of brain networks

BACKGROUND

Accumulated evidence has illuminated the topological infrastructure of major depressive disorder (MDD). However, the changes of topological properties of anatomical brain networks in remitted major depressive disorder patients (rMDD) remain an open question. The present study provides an exploratory examination of pattern changes among current major depressive disorder patients (cMDD), rMDD patients and healthy controls (HC) by means of a pattern recognition analysis.

METHODS

Twenty-eight cMDD patients (age range: 22-54, mean age: 39.57), 15 rMDD patients (age range: 23-53, mean age: 38.40) and 30 HC (23-54, mean age: 35.57) were enrolled. For each subject, we computed five kinds of weighted white matter (WM) networks via employing five physiological parameters (i.e. fractional anisotropy, mean diffusivity, λ1, λ2 and λ3) and then calculated three network measures of these weighted networks. We treated these measures as features and fed into a feature selection mechanism to choose the most discriminative features for linear support vector machine (SVM) classifiers.

RESULTS

Linear SVM could excellently distinguish the three groups with the 100% classification accuracy of recognizing cMDD/rMDD from HC, and 97.67% classification accuracy of recognizing cMDD from rMDD. The further pattern analysis found two types of discriminative patterns among cMDD, rMDD and HC. (i) Compared with HC, both cMDD and rMDD exhibited the similar deficit patterns of node strength primarily involving the salience network (SN), default mode network (DMN) and frontoparietal network (FPN). (ii) Compared with cMDD and rMDD showed the altered pattern of intra-communicability within DMN and inter-communicability between DMN and the other sub-networks including the visual recognition network (VRN) and SN.

LIMITATIONS

The present study had a limited sample size and a lack of larger independent data set to validate the methods and confirm the findings.

CONCLUSIONS

These findings implied that the impairment of MDD was closely associated with the alterations of connections within SN, DMN and FPN, whereas the remission of MDD was benefitted from the network compensatory of intra-communication within DMN and inter-communication between DMN and the other sub-networks (i.e., VRN and SN).

A Bayesian model of category-specific emotional brain responses

Understanding emotion is critical for a science of healthy and disordered brain function, but the neurophysiological basis of emotional experience is still poorly understood. We analyzed human brain activity patterns from 148 studies of emotion categories (2159 total participants) using a novel hierarchical Bayesian model. The model allowed us to classify which of five categories--fear, anger, disgust, sadness, or happiness--is engaged by a study with 66% accuracy (43-86% across categories). Analyses of the activity patterns encoded in the model revealed that each emotion category is associated with unique, prototypical patterns of activity across multiple brain systems including the cortex, thalamus, amygdala, and other structures. The results indicate that emotion categories are not contained within any one region or system, but are represented as configurations across multiple brain networks. The model provides a precise summary of the prototypical patterns for each emotion category, and demonstrates that a sufficient characterization of emotion categories relies on (a) differential patterns of involvement in neocortical systems that differ between humans and other species, and (b) distinctive patterns of cortical-subcortical interactions. Thus, these findings are incompatible with several contemporary theories of emotion, including those that emphasize emotion-dedicated brain systems and those that propose emotion is localized primarily in subcortical activity. They are consistent with componential and constructionist views, which propose that emotions are differentiated by a combination of perceptual, mnemonic, prospective, and motivational elements. Such brain-based models of emotion provide a foundation for new translational and clinical approaches.

Neurofeedback and networks of depression

Recent advances in imaging technology and in the understanding of neural circuits relevant to emotion, motivation, and depression have boosted interest and experimental work in neuromodulation for affective disorders. Real-time functional magnetic resonance imaging (fMRI) can be used to train patients in the self regulation of these circuits, and thus complement existing neurofeedback technologies based on electroencephalography (EEG). EEG neurofeedback for depression has mainly been based on models of altered hemispheric asymmetry. fMRI-based neurofeedback (fMRI-NF) can utilize functional localizer scans that allow the dynamic adjustment of the target areas or networks for self-regulation training to individual patterns of emotion processing. An initial application of fMRI-NF in depression has produced promising clinical results, and further clinical trials are under way. Challenges lie in the design of appropriate control conditions for rigorous clinical trials, and in the transfer of neurofeedback protocols from the laboratory to mobile devices to enhance the sustainability of any clinical benefits.

Neurofeedback and networks of depression

Recent advances in imaging technology and in the understanding of neural circuits relevant to emotion, motivation, and depression have boosted interest and experimental work in neuromodulation for affective disorders. Real-time functional magnetic resonance imaging (fMRI) can be used to train patients in the self regulation of these circuits, and thus complement existing neurofeedback technologies based on electroencephalography (EEG). EEG neurofeedback for depression has mainly been based on models of altered hemispheric asymmetry. fMRI-based neurofeedback (fMRI-NF) can utilize functional localizer scans that allow the dynamic adjustment of the target areas or networks for self-regulation training to individual patterns of emotion processing. An initial application of fMRI-NF in depression has produced promising clinical results, and further clinical trials are under way. Challenges lie in the design of appropriate control conditions for rigorous clinical trials, and in the transfer of neurofeedback protocols from the laboratory to mobile devices to enhance the sustainability of any clinical benefits.