Decoding attentional states for neurofeedback: Mindfulness vs. wandering thoughts

Closed-Loop Systems and Real-Time Neurofeedback in Mindfulness Meditation Research

Mindfulness meditation has numerous purported benefits for psychological well-being; however, problems such as adherence to mindfulness tasks, quality of mindfulness sessions, or dosage of mindfulness interventions may hinder individuals from accessing the purported benefits of mindfulness. Methodologies including closed-loop systems and real-time neurofeedback may provide tools to help bolster success in mindfulness task performance, titrate the exposure to mindfulness interventions, or improve engagement with mindfulness sessions. In this review, we explore the use of closed-loop systems and real-time neurofeedback to influence, augment, or promote mindfulness interventions. Various closed-loop neurofeedback signals from functional magnetic resonance imaging and electroencephalography have been used to provide subjective correlates of mindfulness states including functional magnetic resonance imaging region-of-interest-based signals (e.g., posterior cingulate cortex), functional magnetic resonance imaging network-based signals (e.g., default mode network, central executive network, salience network), and electroencephalography spectral-based signals (e.g., alpha, theta, and gamma bands). Past research has focused on how successful interventions have aligned with the subjective mindfulness meditation experience. Future research may pivot toward using appropriate control conditions (e.g., mindfulness only or sham neurofeedback) to quantify the effects of closed-loop systems and neurofeedback-guided mindfulness meditation in improving cognition and well-being.

Decoding Mindfulness With Multivariate Predictive Models

Identifying the brain mechanisms that underlie the salutary effects of mindfulness meditation and related practices is a critical goal of contemplative neuroscience. Here, we suggest that the use of multivariate predictive models represents a promising and powerful methodology that could be better leveraged to pursue this goal. This approach incorporates key principles of multivariate decoding, predictive classification, and model-based analyses, all of which represent a strong departure from conventional brain mapping approaches. We highlight 2 such research strategies-state induction and neuromarker identification-and provide illustrative examples of how these approaches have been used to examine central questions in mindfulness, such as the distinction between internally directed focused attention and mind wandering and the effects of mindfulness interventions on somatic pain and drug-related cravings. We conclude by discussing important issues to be addressed with future research, including key tradeoffs between using a personalized versus population-based approach to predictive modeling.

Penalized canonical correlation analysis reveals a relationship between temperament traits and brain oscillations during mind wandering

INTRODUCTION

There has been a growing interest in studying brain activity under naturalistic conditions. However, the relationship between individual differences in ongoing brain activity and psychological characteristics is not well understood. We investigated this connection, focusing on the association between oscillatory activity in the brain and individually characteristic dispositional traits. Given the variability of unconstrained resting states among individuals, we devised a paradigm that could harmonize the state of mind across all participants.

METHODS

We constructed task contrasts that included focused attention (FA), self-centered future planning, and rumination on anxious thoughts triggered by visual imagery. Magnetoencephalography was recorded from 28 participants under these 3 conditions for a duration of 16 min. The oscillatory power in the alpha and beta bands was converted into spatial contrast maps, representing the difference in brain oscillation power between the two conditions. We performed permutation cluster tests on these spatial contrast maps. Additionally, we applied penalized canonical correlation analysis (CCA) to study the relationship between brain oscillation patterns and behavioral traits.

RESULTS

The data revealed that the FA condition, as compared to the other conditions, was associated with higher alpha and beta power in the temporal areas of the left hemisphere and lower alpha and beta power in the parietal areas of the right hemisphere. Interestingly, the penalized CCA indicated that behavioral inhibition was positively correlated, whereas anxiety was negatively correlated, with a pattern of high oscillatory power in the bilateral precuneus and low power in the bilateral temporal regions. This unique association was found in the anxious-thoughts condition when contrasted with the focused-attention condition.

CONCLUSION

Our findings suggest individual temperament traits significantly affect brain engagement in naturalistic conditions. This research underscores the importance of considering individual traits in neuroscience and offers an effective method for analyzing brain activity and psychological differences.

Nonlinear independent component analysis for principled disentanglement in unsupervised deep learning

A central problem in unsupervised deep learning is how to find useful representations of high-dimensional data, sometimes called "disentanglement." Most approaches are heuristic and lack a proper theoretical foundation. In linear representation learning, independent component analysis (ICA) has been successful in many applications areas, and it is principled, i.e., based on a well-defined probabilistic model. However, extension of ICA to the nonlinear case has been problematic because of the lack of identifiability, i.e., uniqueness of the representation. Recently, nonlinear extensions that utilize temporal structure or some auxiliary information have been proposed. Such models are in fact identifiable, and consequently, an increasing number of algorithms have been developed. In particular, some self-supervised algorithms can be shown to estimate nonlinear ICA, even though they have initially been proposed from heuristic perspectives. This paper reviews the state of the art of nonlinear ICA theory and algorithms.

Mind wandering state detection during video-based learning via EEG

The aim of this study is to explore the potential of technology for detecting mind wandering, particularly during video-based distance learning, with the ultimate benefit of improving learning outcomes. To overcome the challenges of previous mind wandering research in ecological validity, sample balance, and dataset size, this study utilized practical electroencephalography (EEG) recording hardware and designed a paradigm consisting of viewing short-duration video lectures under a focused learning condition and a future planning condition. Participants estimated statistics of their attentional state at the end of each video, and we combined this rating scale feedback with self-caught key press responses during video watching to obtain binary labels for classifier training. EEG was recorded using an 8-channel system, and spatial covariance features processed by Riemannian geometry were employed. The results demonstrate that a radial basis function kernel support vector machine classifier, using Riemannian-processed covariance features from delta, theta, alpha, and beta bands, can detect mind wandering with a mean area under the receiver operating characteristic curve (AUC) of 0.876 for within-participant classification and AUC of 0.703 for cross-lecture classification. Furthermore, our results suggest that a short duration of training data is sufficient to train a classifier for online decoding, as cross-lecture classification remained at an average AUC of 0.689 when using 70% of the training set (about 9 min). The findings highlight the potential for practical EEG hardware in detecting mind wandering with high accuracy, which has potential application to improving learning outcomes during video-based distance learning.

Unsupervised representation learning of spontaneous MEG data with Nonlinear ICA

Resting-state magnetoencephalography (MEG) data show complex but structured spatiotemporal patterns. However, the neurophysiological basis of these signal patterns is not fully known and the underlying signal sources are mixed in MEG measurements. Here, we developed a method based on the nonlinear independent component analysis (ICA), a generative model trainable with unsupervised learning, to learn representations from resting-state MEG data. After being trained with a large dataset from the Cam-CAN repository, the model has learned to represent and generate patterns of spontaneous cortical activity using latent nonlinear components, which reflects principal cortical patterns with specific spectral modes. When applied to the downstream classification task of audio-visual MEG, the nonlinear ICA model achieves competitive performance with deep neural networks despite limited access to labels. We further validate the generalizability of the model across different datasets by applying it to an independent neurofeedback dataset for decoding the subject's attentional states, providing a real-time feature extraction and decoding mindfulness and thought-inducing tasks with an accuracy of around 70% at the individual level, which is much higher than obtained by linear ICA or other baseline methods. Our results demonstrate that nonlinear ICA is a valuable addition to existing tools, particularly suited for unsupervised representation learning of spontaneous MEG activity which can then be applied to specific goals or tasks when labelled data are scarce.

Computational Methods in Psychotherapy: A Scoping Review

BACKGROUND

The study of complex systems, such as the psychotherapeutic encounter, transcends the mechanistic and reductionist methods for describing linear processes and needs suitable approaches to describe probabilistic and scarcely predictable phenomena.

OBJECTIVE

The present study undertakes a scoping review of research on the computational methods in psychotherapy to gather new developments in this field and to better understand the phenomena occurring in psychotherapeutic interactions as well as in human interaction more generally.

DESIGN

Online databases were used to identify papers published 2011-2022, from which we selected 18 publications from different resources, selected according to criteria established in advance and described in the text. A flow chart and a summary table of the articles consulted have been created.

RESULTS

The majority of publications (44.4%) reported combined computational and experimental approaches, so we grouped the studies according to the types of computational methods used. All but one of the studies collected measured data. All the studies confirmed the usefulness of predictive and learning models in the study of complex variables such as those belonging to psychological, psychopathological and psychotherapeutic processes.

CONCLUSIONS

Research on computational methods will benefit from a careful selection of reference methods and standards. Therefore, this review represents an attempt to systematise the empirical literature on the applications of computational methods in psychotherapy research in order to offer clinicians an overview of the usefulness of these methods and the possibilities of their use in the various fields of application, highlighting their clinical implications, and ultimately attempting to identify potential opportunities for further research.

The heartbeat evoked potential does not support strong interoceptive sensibility in trait mindfulness

The enhancement of body awareness is proposed as one of the cognitive mechanisms that characterize mindfulness. To date, this hypothesis is supported by self-report and behavioral measures but still lacks physiological evidence. The current study investigated relation between trait mindfulness (i.e., individual differences in the ability to be mindful in daily life) and body awareness in combining a self-report measure (Multidimensional Assessment of Interoceptive Awareness [MAIA] questionnaire) with analysis of the heartbeat evoked potential (HEP), which is an event-related potential reflecting the cortical processing of the heartbeat. The HEP data were collected from 17 healthy participants under five minutes of resting-state condition. In addition, each participant completed the Freiburg Mindfulness Inventory and the MAIA questionnaire. Taking account of the important variability of HEP effects, analyses were replicated with the same participants three times (in three distinct sessions). First, group-level analyses showed that HEP amplitude and trait mindfulness do not correlate. Secondly, we observed that HEP amplitude could positively correlate with self-reported body awareness; however, this association was unreliable over time. Interestingly, we found that HEP measure shows very poor reliability over time at the individual level, potentially explaining the lack of reliable association between HEP and psychological traits. Lastly, a reliable positive correlation was found between self-reported trait mindfulness and body awareness. Taken together, these findings provide preliminary evidence that the HEP might not support the increased subjective body awareness in trait mindfulness, thus suggesting that perhaps objective and subjective measures of body awareness could be independent.

Mind-Wandering in Adolescents Predicts Worse Affect and Is Linked to Aberrant Default Mode Network-Salience Network Connectivity

OBJECTIVE

Understanding the fluctuating emotional and cognitive states of adolescents with depressive symptoms requires fine-grained and naturalistic measurements. This study used ecological momentary assessment (EMA) to investigate the affective correlates and consequences of mind-wandering in adolescents with anhedonia (AH) and typically developing (TD) controls. In addition, we examined the association between mind-wandering and resting state functional connectivity between the medial prefrontal cortex (mPFC), a core hub of the default mode network (DMN) linked to internally oriented mentation, and networks linked to attentional control (dorsal attention network [DAN]) and affect/salience detection (salience network [SN]).

METHOD

A total of 65 adolescents, aged 12 to 18 years (TD = 36; AH = 29), completed a resting state functional magnetic resonance imaging scan and subsequently used a smartphone application for ecological momentary assessment (EMA) data collection (2-3 times/d for 5 days). Each survey (N = 678) prompted adolescents to report on their current positive and negative affect (PA and NA), cognition, and activity.

RESULTS

The frequency of mind-wandering was higher for AH (70.0% of EMA samples) relative to TD (59.2%) participants, and the participants with AH were more likely to mind-wander to unpleasant content. Mind-wandering was associated with higher concurrent NA, even when controlling for plausible confounds (eg, current activity, social companion, rumination). Time-lagged analyses revealed a bidirectional association between mind-wandering and PA. Greater levels of mind-wandering within the AH group were associated with stronger mPFC-SN/DAN connectivity.

CONCLUSION

Rates of mind-wandering were high, especially among adolescents with anhedonia, and predicted worse affect. The relation between mind-wandering and enhanced mPFC-SN coupling may reflect heightened bottom-up influence of affective and sensory salience on DMN-mediated internally oriented thought.

Decoding working memory task condition using magnetoencephalography source level long-range phase coupling patterns

OBJECTIVE

The objective of the study is to identify phase coupling patterns that are shared across subjects via a machine learning approach that utilises source space magnetoencephalography (MEG) phase coupling data from a working memory (WM) task. Indeed, phase coupling of neural oscillations is putatively a key factor for communication between distant brain areas and is therefore crucial in performing cognitive tasks, including WM. Previous studies investigating phase coupling during cognitive tasks have often focused on a few a priori selected brain areas or a specific frequency band, and the need for data-driven approaches has been recognised. Machine learning techniques have emerged as valuable tools for the analysis of neuroimaging data since they catch fine-grained differences in the multivariate signal distribution. Here, we expect that these techniques applied to MEG phase couplings can reveal WM-related processes that are shared across individuals.

APPROACH

We analysed WM data collected as part of the Human Connectome Project. The MEG data were collected while subjects (n = 83) performed N-back WM tasks in two different conditions, namely 2-back (WM condition) and 0-back (control condition). We estimated phase coupling patterns (multivariate phase slope index) for both conditions and for theta, alpha, beta, and gamma bands. The obtained phase coupling data were then used to train a linear support vector machine in order to classify which task condition the subject was performing with an across-subject cross-validation approach. The classification was performed separately based on the data from individual frequency bands and with all bands combined (multiband). Finally, we evaluated the relative importance of the different features (phase couplings) for classification by the means of feature selection probability.

MAIN RESULTS

The WM condition and control condition were successfully classified based on the phase coupling patterns in the theta (62% accuracy) and alpha bands (60% accuracy) separately. Importantly, the multiband classification showed that phase coupling patterns not only in the theta and alpha but also in the gamma bands are related to WM processing, as testified by improvement in classification performance (71%).

SIGNIFICANCE

Our study successfully decoded WM tasks using MEG source space functional connectivity. Our approach, combining across-subject classification and a multidimensional metric recently developed by our group, is able to detect patterns of connectivity that are shared across individuals. In other words, the results are generalisable to new individuals and allow meaningful interpretation of task-relevant phase coupling patterns.

Artificial intelligence for brain diseases: A systematic review

Artificial intelligence (AI) is a major branch of computer science that is fruitfully used for analyzing complex medical data and extracting meaningful relationships in datasets, for several clinical aims. Specifically, in the brain care domain, several innovative approaches have achieved remarkable results and open new perspectives in terms of diagnosis, planning, and outcome prediction. In this work, we present an overview of different artificial intelligent techniques used in the brain care domain, along with a review of important clinical applications. A systematic and careful literature search in major databases such as Pubmed, Scopus, and Web of Science was carried out using "artificial intelligence" and "brain" as main keywords. Further references were integrated by cross-referencing from key articles. 155 studies out of 2696 were identified, which actually made use of AI algorithms for different purposes (diagnosis, surgical treatment, intra-operative assistance, and postoperative assessment). Artificial neural networks have risen to prominent positions among the most widely used analytical tools. Classic machine learning approaches such as support vector machine and random forest are still widely used. Task-specific algorithms are designed for solving specific problems. Brain images are one of the most used data types. AI has the possibility to improve clinicians' decision-making ability in neuroscience applications. However, major issues still need to be addressed for a better practical use of AI in the brain. To this aim, it is important to both gather comprehensive data and build explainable AI algorithms.

Focus on the Breath: Brain Decoding Reveals Internal States of Attention During Meditation

Meditation practices are often used to cultivate interoception or internally-oriented attention to bodily sensations, which may improve health via cognitive and emotional regulation of bodily signals. However, it remains unclear how meditation impacts internal attention (IA) states due to lack of measurement tools that can objectively assess mental states during meditation practice itself, and produce time estimates of internal focus at individual or group levels. To address these measurement gaps, we tested the feasibility of applying multi-voxel pattern analysis (MVPA) to single-subject fMRI data to: (1) learn and recognize internal attentional states relevant for meditation during a directed IA task; and (2) decode or estimate the presence of those IA states during an independent meditation session. Within a mixed sample of experienced meditators and novice controls (N = 16), we first used MVPA to develop single-subject brain classifiers for five modes of attention during an IA task in which subjects were specifically instructed to engage in one of five states [i.e., meditation-related states: breath attention, mind wandering (MW), and self-referential processing, and control states: attention to feet and sounds]. Using standard cross-validation procedures, MVPA classifiers were trained in five of six IA blocks for each subject, and predictive accuracy was tested on the independent sixth block (iterated until all volumes were tested, N = 2,160). Across participants, all five IA states were significantly recognized well above chance (>41% vs. 20% chance). At the individual level, IA states were recognized in most participants (87.5%), suggesting that recognition of IA neural patterns may be generalizable for most participants, particularly experienced meditators. Next, for those who showed accurate IA neural patterns, the originally trained classifiers were applied to a separate meditation run (10-min) to make an inference about the percentage time engaged in each IA state (breath attention, MW, or self-referential processing). Preliminary group-level analyses demonstrated that during meditation practice, participants spent more time attending to breath compared to MW or self-referential processing. This paradigm established the feasibility of using MVPA classifiers to objectively assess mental states during meditation at the participant level, which holds promise for improved measurement of internal attention states cultivated by meditation.