An electroencephalographic signature predicts antidepressant response in major depression

Potentiation of Brain Bioavailability Using Thermoreversible Cubosomal Formulation

The aim of the present study was to develop and evaluate intranasal formulations of the thermoreversible fluoxetine cubosomal in situ gel. This gel was intended for permeation and bioavailability enhancement to target the brain effectively by bypassing the blood-brain barrier (BBB). Fluoxetine-loaded cubosomes were prepared by the homogenization method followed by the cold method approach to develop in situ gel. Fluoxetine-loaded cubosomes displayed a higher encapsulation efficiency (82.60 ± 1.25%) than fluoxetine. This might be due to the solubilizing activity of the polymer to cause partitioning of the lipophilic drug into the aqueous phase during the change from the cubic gel phase to cubosomes. In vitro analysis of fluoxetine-loaded cubosomal in situ gel showed a sustained release profile (93.22 ± 2.47%) due to limited diffusion of fluoxetine. The formation of strong affinity bonds of the drug with GMO (drug transporter) decreased the drug release in comparison to that with fluoxetine-loaded cubosomes (90.68 ± 1.74%). The ex vivo drug release profile revealed the drug release of 96.31 ± 2.88% by the end of 24 h. This is attributed to the higher capability of the intranasal cubosomal in situ gel to prolong the retention and enable better permeation through the nasal mucosa. In male Wistar rats, in vivo biodistribution studies for cubosomal in situ gel administered via the intranasal route at a dose of 3.5 mg/kg demonstrated an increase in pharmacokinetic parameters like the AUC (406 ± 75.35 μg/mL), Cmax (368.07 ± 0.23 μg/mL), Tmax (4 h), and t1/2 (14.06 h). The mucoadhesive nature of the in situ gel led to an increase in the residence time of the gel in the nasal mucosa. The biodistribution study of intranasal in situ cubosomal gel improved the bioavailability 2.21-fold in comparison to that with the cubosomal dispersion but 2.83-fold in comparison to that with the drug solution. Therefore, fluoxetine-loaded cubosomal in situ gel proved as a promising carrier for effective transportation of fluoxetine via the intranasal route with significant brain bioavailability.

Learning optimal biomarker-guided treatment policy for chronic disorders

Electroencephalogram (EEG) provides noninvasive measures of brain activity and is found to be valuable for the diagnosis of some chronic disorders. Specifically, pre-treatment EEG signals in the alpha and theta frequency bands have demonstrated some association with antidepressant response, which is well-known to have a low response rate. We aim to design an integrated pipeline that improves the response rate of patients with major depressive disorder by developing a treatment policy guided by the resting state pre-treatment EEG recordings and other treatment effects modifiers. First, we design an innovative automatic site-specific EEG preprocessing pipeline to extract features with stronger signals than raw data. We then estimate the conditional average treatment effect (CATE) using causal forests and use a doubly robust technique to improve efficiency in the estimation of the average treatment effect. We present evidence of heterogeneity in the treatment effect and the modifying power of the EEG features, as well as a significant average treatment effect, a result that cannot be obtained with conventional methods. Finally, we employ an efficient policy learning algorithm to learn an optimal depth-2 treatment assignment decision tree and compare its performance with Q-Learning and outcome-weighted learning via simulation studies and an application to a large multi-site, double-blind, randomized controlled clinical trial, EMBARC.

BPI-GNN: Interpretable brain network-based psychiatric diagnosis and subtyping

Converging evidence increasingly suggests that psychiatric disorders, such as major depressive disorder (MDD) and autism spectrum disorder (ASD), are not unitary diseases, but rather heterogeneous syndromes that involve diverse, co-occurring symptoms and divergent responses to treatment. This clinical heterogeneity has hindered the progress of precision diagnosis and treatment effectiveness in psychiatric disorders. In this study, we propose BPI-GNN, a new interpretable graph neural network (GNN) framework for analyzing functional magnetic resonance images (fMRI), by leveraging the famed prototype learning. In addition, we introduce a novel generation process of prototype subgraph to discover essential edges of distinct prototypes and employ total correlation (TC) to ensure the independence of distinct prototype subgraph patterns. BPI-GNN can effectively discriminate psychiatric patients and healthy controls (HC), and identify biological meaningful subtypes of psychiatric disorders. We evaluate the performance of BPI-GNN against 11 popular brain network classification methods on three psychiatric datasets and observe that our BPI-GNN always achieves the highest diagnosis accuracy. More importantly, we examine differences in clinical symptom profiles and gene expression profiles among identified subtypes and observe that our identified brain-based subtypes have the clinical relevance. It also discovers the subtype biomarkers that align with current neuro-scientific knowledge.

Individual deviations from normative electroencephalographic connectivity predict antidepressant response

BACKGROUND

Antidepressant medications yield unsatisfactory treatment outcomes in patients with major depressive disorder (MDD) with modest advantages over the placebo, partly due to the elusive mechanisms of antidepressant responses and unexplained heterogeneity in patient's response to treatment. Here we develop a novel normative modeling framework to quantify individual deviations in psychopathological dimensions that offers a promising avenue for the personalized treatment for psychiatric disorders.

METHODS

We built a normative model with resting-state electroencephalography (EEG) connectivity data from healthy controls of three independent cohorts. We characterized the individual deviation of MDD patients from the healthy norms, based on which we trained sparse predictive models for treatment responses of MDD patients (102 sertraline-medicated and 119 placebo-medicated). Hamilton depression rating scale (HAMD-17) was assessed at both baseline and after the eight-week antidepressant treatment.

RESULTS

We successfully predicted treatment outcomes for patients receiving sertraline (r = 0.43, p < 0.001) and placebo (r = 0.33, p < 0.001). We also showed that the normative modeling framework successfully distinguished subclinical and diagnostic variabilities among subjects. From the predictive models, we identified key connectivity signatures in resting-state EEG for antidepressant treatment, suggesting differences in neural circuit involvement between sertraline and placebo responses.

CONCLUSIONS

Our findings and highly generalizable framework advance the neurobiological understanding in the potential pathways of antidepressant responses, enabling more targeted and effective personalized MDD treatment.

TRIAL REGISTRATION

Establishing Moderators and Biosignatures of Antidepressant Response for Clinical Care for Depression (EMBARC), NCT#01407094.

Optimizing Antidepressant Efficacy: Multimodal Neuroimaging Biomarkers for Prediction of Treatment Response

Major depressive disorder (MDD) is a common and often severe condition that profoundly diminishes quality of life for individuals across ages and demographic groups. Unfortunately, current antidepressant and psychotherapeutic treatments exhibit limited efficacy and unsatisfactory response rates in a substantial number of patients. The development of effective therapies for MDD is hindered by the insufficiently understood heterogeneity within the disorder and its elusive underlying mechanisms. To address these challenges, we present a target-oriented multimodal fusion framework that robustly predicts antidepressant response by integrating structural and functional connectivity data (sertraline: R2 = 0.31; placebo: R2 = 0.22). Through the model, we identify multimodal neuroimaging biomarkers of antidepressant response and observe that sertraline and placebo show distinct predictive patterns. We further decompose the overall predictive patterns into constitutive network constellations with generalizable structural-functional co-variation, which exhibit treatment-specific association with personality traits and behavioral/cognitive task performance. Our innovative and interpretable multimodal framework provides novel insights into the intricate neuropsychopharmacology of antidepressant treatment and paves the way for advances in precision medicine and development of more targeted antidepressant therapeutics.

One size does not fit all: notable individual variation in brain activity correlates of antidepressant treatment response

Introduction

To date, no robust electroencephalography (EEG) markers of antidepressant treatment response have been identified. Variable findings may arise from the use of group analyses, which neglect individual variation. Using a combination of group and single-participant analyses, we explored individual variability in EEG characteristics of treatment response.

Methods

Resting-state EEG data and Montgomery-Åsberg Depression Rating Scale (MADRS) symptom scores were collected from 43 patients with depression before, at 1 and 12 weeks of pharmacotherapy. Partial least squares (PLS) was used to: 1) identify group differences in EEG connectivity (weighted phase lag index) and complexity (multiscale entropy) between eventual medication responders and non-responders, and 2) determine whether group patterns could be identified in individual patients.

Results

Responders showed decreased alpha and increased beta connectivity, and early, widespread decreases in complexity over treatment. Non-responders showed an opposite connectivity pattern, and later, spatially confined decreases in complexity. Thus, as in previous studies, our group analyses identified significant differences between groups of patients with different treatment outcomes. These group-level EEG characteristics were only identified in ~40-60% of individual patients, as assessed quantitatively by correlating the spatiotemporal brain patterns between groups and individual results, and by independent raters through visualization.

Discussion

Our single-participant analyses suggest that substantial individual variation exists, and needs to be considered when investigating characteristics of antidepressant treatment response for potential clinical applicability.

Clinical trial registration

https://clinicaltrials.gov, identifier NCT00519428.

Decoding emotion with phase-amplitude fusion features of EEG functional connectivity network

Decoding emotional neural representations from the electroencephalographic (EEG)-based functional connectivity network (FCN) is of great scientific importance for uncovering emotional cognition mechanisms and developing harmonious human-computer interactions. However, existing methods mainly rely on phase-based FCN measures (e.g., phase locking value [PLV]) to capture dynamic interactions between brain oscillations in emotional states, which fail to reflect the energy fluctuation of cortical oscillations over time. In this study, we initially examined the efficacy of amplitude-based functional networks (e.g., amplitude envelope correlation [AEC]) in representing emotional states. Subsequently, we proposed an efficient phase-amplitude fusion framework (PAF) to fuse PLV and AEC and used common spatial pattern (CSP) to extract fused spatial topological features from PAF for multi-class emotion recognition. We conducted extensive experiments on the DEAP and MAHNOB-HCI datasets. The results showed that: (1) AEC-derived discriminative spatial network topological features possess the ability to characterize emotional states, and the differential network patterns of AEC reflect dynamic interactions in brain regions associated with emotional cognition. (2) The proposed fusion features outperformed other state-of-the-art methods in terms of classification accuracy for both datasets. Moreover, the spatial filter learned from PAF is separable and interpretable, enabling a description of affective activation patterns from both phase and amplitude perspectives.

Evaluating Robustness of Brain Stimulation Biomarkers for Depression: A Systematic Review of Magnetic Resonance Imaging and Electroencephalography Studies

Noninvasive brain stimulation (NIBS) treatments have gained considerable attention as potential therapeutic intervention for psychiatric disorders. The identification of reliable biomarkers for predicting clinical response to NIBS has been a major focus of research in recent years. Neuroimaging techniques, such as electroencephalography (EEG) and functional magnetic resonance imaging (MRI), have been used to identify potential biomarkers that could predict response to NIBS. However, identifying clinically actionable brain biomarkers requires robustness. In this systematic review, we aimed to summarize the current state of brain biomarker research for NIBS in depression, focusing only on well-powered studies (N ≥ 88) and/or studies that aimed at independently replicating previous findings, either successfully or unsuccessfully. A total of 220 studies were initially identified, of which 18 MRI studies and 18 EEG studies met the inclusion criteria. All focused on repetitive transcranial magnetic stimulation treatment in depression. After reviewing the included studies, we found the following MRI and EEG biomarkers to be most robust: 1) functional MRI-based functional connectivity between the dorsolateral prefrontal cortex and subgenual anterior cingulate cortex, 2) functional MRI-based network connectivity, 3) task-induced EEG frontal-midline theta, and 4) EEG individual alpha frequency. Future prospective studies should further investigate the clinical actionability of these specific EEG and MRI biomarkers to bring biomarkers closer to clinical reality.

Network States in the Basolateral Amygdala Predicts Voluntary Alcohol Consumption

Although most adults in the United States will drink alcohol in their life, only about 6% will go on to develop an alcohol use disorder (AUD). While a great deal of work has furthered our understanding of the cycle of addiction, it remains unclear why certain people transition to disordered drinking. Altered activity in regions implicated in AUDs, like the basolateral amygdala (BLA), has been suggested to play a role in the pathophysiology of AUDs, but how these networks contribute to alcohol misuse remains unclear. Our recent work demonstrated that alcohol can modulate BLA network states and that GABAergic parvalbumin (PV) interneurons are crucial modulators of network activity in the BLA. Further, our lab has demonstrated that δ subunit-containing GABA A receptors, which are modulated by alcohol, are highly expressed on PV interneurons in the BLA. These receptors on PV interneurons have also been shown to influence alcohol intake in a voluntary binge drinking paradigm and anxiety-like behavior in withdrawal. Therefore, we hypothesized that alcohol may impact BLA network states via δ subunit-containing GABA A receptors on PV interneurons to impact the extent of alcohol use. To test this hypothesis, we measured the impact of acute alcohol exposure on oscillatory states in the basolateral amygdala and then assessed the relationship to the extent of voluntary ethanol consumption in the Intermittent Access, Drinking-in-the-Dark-Multiple Scheduled Access, and Chronic Intermittent Ethanol exposure paradigms. Remarkably, we demonstrate that the average alcohol intake negatively correlates with δ subunit-containing GABA A receptor expression on PV interneurons and gamma power in the BLA after the first exposure to alcohol. These data implicate δ subunit-containing GABA A receptor expression on PV interneurons in the BLA in voluntary alcohol intake and suggest that BLA network states may serve as a useful biomarker for those at risk for alcohol misuse.

Significance Statement

Oscillatory states in the BLA have been demonstrated to drive behavioral states involved in emotional processing, including negative valence processing. Given that negative emotional states/hyperkatifeia contribute to the cycle of AUDs, our previous work demonstrating the ability of alcohol to modulate BLA network states and thereby behavioral states suggests that this mechanism may influence alcohol intake. Here we demonstrate a relationship between the ability of alcohol to modulate oscillations in the BLA and future alcohol intake such that the extent to which alcohol influences BLA network states predict the extent of future voluntary alcohol intake. These findings suggest that individual variability in the sensitivity of the BLA network to alcohol influences voluntary alcohol consumption.

Electroencephalography oscillations can predict the cortical response following theta burst stimulation

BACKGROUND

Continuous theta burst stimulation and intermittent theta burst stimulation are clinically popular models of repetitive transcranial magnetic stimulation. However, they are limited by high variability between individuals in cortical excitability changes following stimulation. Although electroencephalography oscillations have been reported to modulate the cortical response to transcranial magnetic stimulation, their association remains unclear. This study aims to explore whether machine learning models based on EEG oscillation features can predict the cortical response to transcranial magnetic stimulation.

METHOD

Twenty-three young, healthy adults attended two randomly assigned sessions for continuous and intermittent theta burst stimulation. In each session, ten minutes of resting-state electroencephalography were recorded before delivering brain stimulation. Participants were classified as responders or non-responders based on changes in resting motor thresholds. Support vector machines and multi-layer perceptrons were used to establish predictive models of individual responses to transcranial magnetic stimulation.

RESULT

Among the evaluated algorithms, support vector machines achieved the best performance in discriminating responders from non-responders for intermittent theta burst stimulation (accuracy: 91.30%) and continuous theta burst stimulation (accuracy: 95.66%). The global clustering coefficient and global characteristic path length in the beta band had the greatest impact on model output.

CONCLUSION

These findings suggest that EEG features can serve as markers of cortical response to transcranial magnetic stimulation. They offer insights into the association between neural oscillations and variability in individuals' responses to transcranial magnetic stimulation, aiding in the optimization of individualized protocols.

An Electroencephalography Profile of Paroxysmal Kinesigenic Dyskinesia

Paroxysmal kinesigenic dyskinesia (PKD) is associated with a disturbance of neural circuit and network activities, while its neurophysiological characteristics have not been fully elucidated. This study utilized the high-density electroencephalogram (hd-EEG) signals to detect abnormal brain activity of PKD and provide a neural biomarker for its clinical diagnosis and PKD progression monitoring. The resting hd-EEGs are recorded from two independent datasets and then source-localized for measuring the oscillatory activities and function connectivity (FC) patterns of cortical and subcortical regions. The abnormal elevation of theta oscillation in wildly brain regions represents the most remarkable physiological feature for PKD and these changes returned to healthy control level in remission patients. Another remarkable feature of PKD is the decreased high-gamma FCs in non-remission patients. Subtype analyses report that increased theta oscillations may be related to the emotional factors of PKD, while the decreased high-gamma FCs are related to the motor symptoms. Finally, the authors established connectome-based predictive modelling and successfully identified the remission state in PKD patients in dataset 1 and dataset 2. The findings establish a clinically relevant electroencephalography profile of PKD and indicate that hd-EEG can provide robust neural biomarkers to evaluate the prognosis of PKD.

Resting-state EEG connectivity recorded before and after rTMS treatment in patients with treatment-resistant depression

Repetitive transcranial magnetic stimulation (rTMS) has shown efficacy and tolerability in Major Depressive Disorder (MDD). However, the underlying mechanisms of its antidepressant effects remain unclear. This open-label study investigated electroencephalography (EEG) functional connectivity markers associated with response and the antidepressant effects of rTMS. Resting-state EEG data were collected from 28 participants with MDD before and after a four-week rTMS course. Source-space functional connectivity between 38 cortical regions was compared using an orthogonalised amplitude approach. Depressive symptoms significantly improved following rTMS, with 43 % of participants classified as responders. While the study's functional connectivity findings did not withstand multiple comparison corrections, exploratory analyses suggest an association between theta band connectivity and rTMS treatment mechanisms. Fronto-parietal theta connectivity increased after treatment but did not correlate with antidepressant response. Notably, low baseline theta connectivity was associated with greater response. However, due to the exploratory nature and small sample size, further replication is needed. The findings provide preliminary evidence that EEG functional connectivity, particularly within the theta band, may reflect the mechanisms by which rTMS exerts its therapeutic effects.

Evaluating the depression state during perinatal period by non-invasive scalp EEG

Perinatal depression, with a prevalence of 10 to 20% in United States, is usually missed as multiple symptoms of perinatal depression are common in pregnant women. Worse, the diagnosis of perinatal depression still largely relies on questionnaires, leaving the objective biomarker being unveiled yet. This study suggested a safe and non-invasive technique to diagnose perinatal depression and further explore its underlying mechanism. Considering the non-invasiveness and clinical convenience of electroencephalogram for mothers-to-be and fetuses, we collected the resting-state electroencephalogram of pregnant women at the 38th week of gestation. Subsequently, the difference in network topology between perinatal depression patients and healthy mothers-to-be was explored, with related spatial patterns being adopted to achieve the classification of pregnant women with perinatal depression from those healthy ones. We found that the perinatal depression patients had decreased brain network connectivity, which indexed impaired efficiency of information processing. By adopting the spatial patterns, the perinatal depression could be accurately recognized with an accuracy of 87.88%; meanwhile, the depression severity at the individual level was effectively predicted, as well. These findings consistently illustrated that the resting-state electroencephalogram network could be a reliable tool for investigating the depression state across pregnant women, and will further facilitate the clinical diagnosis of perinatal depression.

Dimensional and Categorical Solutions to Parsing Depression Heterogeneity in a Large Single-Site Sample

BACKGROUND

Recent studies have reported significant advances in modeling the biological basis of heterogeneity in major depressive disorder, but investigators have also identified important technical challenges, including scanner-related artifacts, a propensity for multivariate models to overfit, and a need for larger samples with more extensive clinical phenotyping. The goals of the current study were to evaluate dimensional and categorical solutions to parsing heterogeneity in depression that are stable and generalizable in a large, single-site sample.

METHODS

We used regularized canonical correlation analysis to identify data-driven brain-behavior dimensions that explain individual differences in depression symptom domains in a large, single-site dataset comprising clinical assessments and resting-state functional magnetic resonance imaging data for 328 patients with major depressive disorder and 461 healthy control participants. We examined the stability of clinical loadings and model performance in held-out data. Finally, hierarchical clustering on these dimensions was used to identify categorical depression subtypes.

RESULTS

The optimal regularized canonical correlation analysis model yielded 3 robust and generalizable brain-behavior dimensions that explained individual differences in depressed mood and anxiety, anhedonia, and insomnia. Hierarchical clustering identified 4 depression subtypes, each with distinct clinical symptom profiles, abnormal resting-state functional connectivity patterns, and antidepressant responsiveness to repetitive transcranial magnetic stimulation.

CONCLUSIONS

Our results define dimensional and categorical solutions to parsing neurobiological heterogeneity in major depressive disorder that are stable, generalizable, and capable of predicting treatment outcomes, each with distinct advantages in different contexts. They also provide additional evidence that regularized canonical correlation analysis and hierarchical clustering are effective tools for investigating associations between functional connectivity and clinical symptoms.

Development of Artificial Intelligence for Determining Major Depressive Disorder Based on Resting-State EEG and Single-Pulse Transcranial Magnetic Stimulation-Evoked EEG Indices

Depression is the disorder with the greatest socioeconomic burdens. Its diagnosis is still based on an operational diagnosis derived from symptoms, and no objective diagnostic indicators exist. Thus, the present study aimed to develop an artificial intelligence (AI) model to aid in the diagnosis of depression from electroencephalography (EEG) data by applying machine learning to resting-state EEG and transcranial magnetic stimulation (TMS)-evoked EEG acquired from patients with depression and healthy controls. Resting-state EEG and single-pulse TMS-EEG were acquired from 60 patients and 60 healthy controls. Power spectrum analysis, phase synchronization analysis, and phase-amplitude coupling analysis were conducted on EEG data to extract feature candidates to apply different types of machine learning algorithms. Furthermore, to address the limitation of the sample size, dimensionality reduction was performed in a manner to increase the quality of information by featuring robust neurophysiological metrics that showed significant differences between the two groups. Then, nine different machine learning models were applied to the data. For the EEG data, we created models combining four modalities, including (1) resting-state EEG, (2) pre-stimulus TMS-EEG, (3) post-stimulus TMS-EEG, and (4) differences between pre- and post-stimulus TMS-EEG, and evaluated their performance. We found that the best estimation performance (a mean area under the curve of 0.922) was obtained using receiver operating characteristic curve analysis when linear discriminant analysis (LDA) was applied to the combination of the four feature sets. This study showed that by using TMS-EEG neurophysiological indices as features, it is possible to develop a depression decision-support AI algorithm that exhibits high discrimination accuracy.

An electroencephalographic signature predicts craving for methamphetamine

Craving is central to methamphetamine use disorder (MUD) and both characterizes the disease and predicts relapse. However, there is currently a lack of robust and reliable biomarkers for monitoring craving and diagnosing MUD. Here, we seek to identify a neurobiological signature of craving based on individual-level functional connectivity pattern differences between healthy control and MUD subjects. We train high-density electroencephalography (EEG)-based models using data recorded during the resting state and then calculate imaginary coherence features between the band-limited time series across different brain regions of interest. Our prediction model demonstrates that eyes-open beta functional connectivity networks have significant predictive value for craving at the individual level and can also identify individuals with MUD. These findings advance the neurobiological understanding of craving through an EEG-tailored computational model of the brain connectome. Dissecting neurophysiological features provides a clinical avenue for personalized treatment of MUD.

Distinct mechanisms of allopregnanolone and diazepam underlie neuronal oscillations and differential antidepressant effect

The rapid relief of depressive symptoms is a major medical requirement for effective treatments for major depressive disorder (MDD). A decrease in neuroactive steroids contributes to the pathophysiological mechanisms associated with the neurological symptoms of MDD. Zuranolone (SAGE-217), a neuroactive steroid that acts as a positive allosteric modulator of synaptic and extrasynaptic δ-subunit-containing GABAA receptors, has shown rapid-onset, clinically effective antidepressant action in patients with MDD or postpartum depression (PPD). Benzodiazepines, on the other hand, act as positive allosteric modulators of synaptic GABAA receptors but are not approved for the treatment of patients with MDD. It remains unclear how differences in molecular mechanisms contribute to the alleviation of depressive symptoms and the regulation of associated neuronal activity. Focusing on the antidepressant-like effects and neuronal activity of the basolateral amygdala (BLA) and medial prefrontal cortex (mPFC), we conducted a head-to-head comparison study of the neuroactive steroid allopregnanolone and the benzodiazepine diazepam using a mouse social defeat stress (SDS) model. Allopregnanolone but not diazepam exhibited antidepressant-like effects in a social interaction test in SDS mice. This antidepressant-like effect of allopregnanolone was abolished in extrasynaptic GABAA receptor δ-subunit knockout mice (δko mice) subjected to the same SDS protocol. Regarding the neurophysiological mechanism associated with these antidepressant-like effects, allopregnanolone but not diazepam increased theta oscillation in the BLA of SDS mice. This increase did not occur in δko mice. Consistent with this, allopregnanolone potentiated tonic inhibition in BLA interneurons via δ-subunit-containing extrasynaptic GABAA receptors. Theta oscillation in the mPFC of SDS mice was also increased by allopregnanolone but not by diazepam. Finally, allopregnanolone but not diazepam increased frontal theta activity in electroencephalography recordings in naïve and SDS mice. Neuronal network alterations associated with MDD showed decreased frontal theta and beta activity in depressed SDS mice. These results demonstrated that, unlike benzodiazepines, neuroactive steroids increased theta oscillation in the BLA and mPFC through the activation of δ-subunit-containing GABAA receptors, and this change was associated with antidepressant-like effects in the SDS model. Our findings support the notion that the distinctive mechanism of neuroactive steroids may contribute to the rapid antidepressant effects in MDD.

No time to lose: the current state of research in rapid-acting psychotherapeutics

The vast majority of treatments for psychiatric and substance use disorders take weeks to work. Notable exceptions to this rule exist, with some treatments such as intravenous ketamine resolving symptoms in minutes to hours. Current research is focused on identifying novel approaches to rapid-acting psychotherapeutics. Promising results from studies of novel classes of drugs and innovative brain stimulation therapies are currently being studied through both clinical and pre-clinical research, as described here. Research focused on understanding neurobiological mechanisms, effective therapeutic context, and implementation approaches are needed to maximize the potential reach of these therapies.

Neurosteroids: mechanistic considerations and clinical prospects

Like other classes of treatments described in this issue's section, neuroactive steroids have been studied for decades but have risen as a new class of rapid-acting, durable antidepressants with a distinct mechanism of action from previous antidepressant treatments and from other compounds covered in this issue. Neuroactive steroids are natural derivatives of progesterone but are proving effective as exogenous treatments. The best understood mechanism is that of positive allosteric modulation of GABAA receptors, where subunit selectivity may promote their profile of action. Mechanistically, there is some reason to think that neuroactive steroids may separate themselves from liabilities of other GABA modulators, although research is ongoing. It is also possible that intracellular targets, including inflammatory pathways, may be relevant to beneficial actions. Strengths and opportunities for further development include exploiting non-GABAergic targets, structural analogs, enzymatic production of natural steroids, precursor loading, and novel formulations. The molecular mechanisms of behavioral effects are not fully understood, but study of brain network states involved in emotional processing demonstrate a robust influence on affective states not evident with at least some other GABAergic drugs including benzodiazepines. Ongoing studies with neuroactive steroids will further elucidate the brain and behavioral effects of these compounds as well as likely underpinnings of disease.

Disentanglement of Resting State Brain Networks for Localizing Epileptogenic Zone in Focal Epilepsy

The objective of this study is to extract pathological brain networks from interictal period of E/MEG recordings to localize epileptic foci for presurgical evaluation. We proposed here a resting state E/MEG analysis framework, to disentangle brain functional networks represented by neural oscillations. By using an Embedded Hidden Markov Model, we constructed a state space for resting state recordings consisting of brain states with different spatiotemporal patterns. Functional connectivity analysis along with graph theory was applied on the extracted brain states to quantify the network features of the extracted brain states, based on which the source location of pathological states is determined. The method is evaluated by computer simulations and our simulation results revealed the proposed framework can extract brain states with high accuracy regarding both spatial and temporal profiles. We further evaluated the framework as compared with intracranial EEG defined seizure onset zone in 10 patients with drug-resistant focal epilepsy who underwent MEG recordings and were seizure free after surgical resection. The real patient data analysis showed very good localization results using the extracted pathological brain states in 6/10 patients, with localization error of about 15 mm as compared to the seizure onset zone. We show that the pathological brain networks can be disentangled from the resting-state electromagnetic recording and could be identified based on the connectivity features. The framework can serve as a useful tool in extracting brain functional networks from noninvasive resting state electromagnetic recordings, and promises to offer an alternative to aid presurgical evaluation guiding intracranial EEG electrodes implantation.

Biomarkers predict the efficacy of closed-loop rTMS treatment for refractory depression

Transcranial magnetic stimulation (TMS) is a non-invasive FDA-approved therapy for major depressive disorder (MDD), specifically for treatment-resistant depression (TRD). Though offering promise for those with TRD, its effectiveness is less than one in two patients (i.e., less than 50%). Limits on efficacy may be due to individual patient variability, but to date, there are no established biomarkers or measures of target engagement that can predict efficacy. Additionally, TMS efficacy is typically not assessed until a six-week treatment ends, precluding interim re-evaluations of the treatment. Here, we report results using a closed-loop phase-locked repetitive TMS (rTMS) treatment that synchronizes the delivery of rTMS based on the timing of the pulses relative to a patient's individual electroencephalographic (EEG) prefrontal alpha oscillation indexed by functional magnetic resonance imaging (fMRI). Among responders, synchronized rTMS produces two systematic changes in brain dynamics: a reduction in global cortical excitability and enhanced phase entrainment of cortical dynamics. These effects predict clinical outcomes in the synchronized treatment group but not in an active-treatment unsynchronized control group. The systematic decrease in excitability and increase in entrainment correlated with treatment efficacy at the endpoint and intermediate weeks during the synchronized treatment. Specifically, we show that weekly biomarker tracking enables efficacy prediction and dynamic adjustments through a treatment course, improving the overall response rates. This innovative approach advances the prospects of individualized medicine in MDD and holds potential for application in other neuropsychiatric disorders.

Novel machine learning approaches for improving the reproducibility and reliability of functional and effective connectivity from functional MRI

Objective.New measures of human brain connectivity are needed to address gaps in the existing measures and facilitate the study of brain function, cognitive capacity, and identify early markers of human disease. Traditional approaches to measure functional connectivity (FC) between pairs of brain regions in functional MRI, such as correlation and partial correlation, fail to capture nonlinear aspects in the regional associations. We propose a new machine learning based measure of FC (ML.FC) which efficiently captures linear and nonlinear aspects.Approach.To capture directed information flow between brain regions, effective connectivity (EC) metrics, including dynamic causal modeling and structural equation modeling have been used. However, these methods are impractical to compute across the many regions of the whole brain. Therefore, we propose two new EC measures. The first, a machine learning based measure of effective connectivity (ML.EC), measures nonlinear aspects across the entire brain. The second, Structurally Projected Granger Causality (SP.GC) adapts Granger Causal connectivity to efficiently characterize and regularize the whole brain EC connectome to respect underlying biological structural connectivity. The proposed measures are compared to traditional measures in terms ofreproducibilityand theability to predict individual traitsin order to demonstrate these measures' internal validity. We use four repeat scans of the same individuals from the Human Connectome Project and measure the ability of the measures to predict individual subject physiologic and cognitive traits.Main results.The proposed new FC measure ofML.FCattains high reproducibility (mean intra-subjectR2of 0.44), while the proposed EC measure ofSP.GCattains the highest predictive power (meanR2across prediction tasks of 0.66).Significance.The proposed methods are highly suitable for achieving high reproducibility and predictiveness and demonstrate their strong potential for future neuroimaging studies.

Sparse Bayesian Learning for End-to-End EEG Decoding

Decoding brain activity from non-invasive electroencephalography (EEG) is crucial for brain-computer interfaces (BCIs) and the study of brain disorders. Notably, end-to-end EEG decoding has gained widespread popularity in recent years owing to the remarkable advances in deep learning research. However, many EEG studies suffer from limited sample sizes, making it difficult for existing deep learning models to effectively generalize to highly noisy EEG data. To address this fundamental limitation, this paper proposes a novel end-to-end EEG decoding algorithm that utilizes a low-rank weight matrix to encode both spatio-temporal filters and the classifier, all optimized under a principled sparse Bayesian learning (SBL) framework. Importantly, this SBL framework also enables us to learn hyperparameters that optimally penalize the model in a Bayesian fashion. The proposed decoding algorithm is systematically benchmarked on five motor imagery BCI EEG datasets ( N=192) and an emotion recognition EEG dataset ( N=45), in comparison with several contemporary algorithms, including end-to-end deep-learning-based EEG decoding algorithms. The classification results demonstrate that our algorithm significantly outperforms the competing algorithms while yielding neurophysiologically meaningful spatio-temporal patterns. Our algorithm therefore advances the state-of-the-art by providing a novel EEG-tailored machine learning tool for decoding brain activity.

Pre-treatment frontal beta events are associated with executive dysfunction improvement after repetitive transcranial magnetic stimulation for depression: A preliminary report

Repetitive transcranial magnetic stimulation (rTMS) is an established clinical treatment for major depressive disorder (MDD) that has also been found to improve aspects of executive functioning. The objective of this study was to examine whether oscillatory burst-like events within the beta band (15-29 Hz) prior to treatment could predict subsequent change in self-reported executive dysfunction (EDF) across a clinical course of rTMS for MDD. Twenty-eight adults (64% female) with MDD completed the self-report Frontal Systems Behavior Scale (FrSBe) and provided eyes-closed resting-state electroencephalography (EEG) before and after a clinical course of rTMS therapy for primary MDD. The rate, power, duration, and frequency span of transient EEG measured oscillatory beta events were calculated. Events within delta/theta and alpha bands were examined to assess for beta specificity. After controlling for improvement in primary depressive symptoms, a lower rate of beta events at F3, Fz, F4, and Cz prior to rTMS treatment was associated with a larger improvement in EDF after rTMS treatment. In addition, a decrease in beta event rate at Fz pre-to-post treatment was associated with a larger improvement in EDF after treatment. Results were largely specific to the beta band. In this study, the rate of frontrocentral beta events prior to treatment significantly predicted the likelihood of subsequent improvement in EDF symptoms following a clinical course of rTMS for MDD. These preliminary findings suggest the potential utility of EEG measured beta events and rTMS for targeting EDF across an array of neuropsychiatric disorders.

Transcranial alternating current stimulation ameliorates emotional attention through neural oscillations modulation

Background

Numerous clinical reports have suggested that psychopathy like schizophrenia, anxiety and depression is accompanied by early attentional abnormalities in emotional processing. Recently, the efficacy of transcranial alternating current stimulation (tACS) in changing emotional functioning has been repeatedly observed and demonstrated a causal relationship between endogenous oscillations and emotional processing.

Aims

Up to now, tACS effects on emotional attention have not yet been tested. To assess such ability, we delivered active-tACS at individual alpha frequency (IAF), 10 Hz or sham-tACS for 7 consecutive days in the bilaterally dorsolateral prefrontal cortex (dlPFC) to totally 79 healthy participants.

Results

IAF-tACS group showed significant alpha entrainment at-rest, especially in open state around stimulation area and showed an obvious advantage compared to 10 Hz-tACS. Event-related potential revealed a significant larger P200 amplitude after active-tACS and IAF group showed wider range of emotions than 10 Hz-tACS, indicating the attentional improvement in facial emotion processing. A notable positive correlation between alpha power and P200 amplitude provided an electrophysiological interpretation regarding the role of tACS in emotional attention modulation instead of somatosensory effects.

Conclusion

These results support a seminal outcome for the effect of IAF-tACS on emotional attention modulation, demonstrating a feasible and individual-specific therapy for neuropsychiatric disorders related to emotion processing, especially regarding oscillatory disturbances.

Effects of rTMS Intervention on Functional Neuroimaging Activities in Adolescents with Major Depressive Disorder Measured Using Resting-State fMRI

Repetitive transcranial magnetic stimulation (rTMS) to the left dorsolateral prefrontal cortex (L-DLPFC) is commonly used for the clinical treatment of major depressive disorder (MDD). The neuroimaging biomarkers and mechanisms of rTMS are still not completely understood. This study aimed to explore the functional neuroimaging changes induced by rTMS in adolescents with MDD. A total of ten sessions of rTMS were administrated to the L-DLPFC in thirteen adolescents with MDD once a day for two weeks. All of them were scanned using resting-state functional magnetic resonance imaging at baseline and after rTMS treatment. The regional homogeneity (ReHo), amplitude of low-frequency fluctuation (ALFF), and the subgenual anterior cingulate cortex (sgACC)-based functional connectivity (FC) were computed as neuroimaging indicators. The correlation between changes in the sgACC-based FC and the improvement in depressive symptoms was also analyzed. After rTMS treatment, ReHo and ALFF were significantly increased in the L-DLPFC, the left medial prefrontal cortex, bilateral medial orbital frontal cortex, and the left ACC. ReHo and ALFF decreased mainly in the left middle occipital gyrus, the right middle cingulate cortex (MCC), bilateral calcarine, the left cuneus, and the left superior occipital gyrus. Furthermore, the FCs between the left sgACC and the L-DLPFC, the right IFGoper, the left MCC, the left precuneus, bilateral post-central gyrus, the left supplementary motor area, and the left superior marginal gyrus were enhanced after rTMS treatment. Moreover, the changes in the left sgACC-left MCC FC were associated with an improvement in depressive symptoms in early improvers. This study showed that rTMS treatment in adolescents with MDD causes changes in brain activities and sgACC-based FC, which may provide basic neural biomarkers for rTMS clinical trials.

Local and large-scale resting-state oscillatory dysfunctions for early antidepressant response prediction in major depressive disorder

BACKGROUND

Magnetoencephalography (MEG) could explore and resolve brain signals with realistic temporal resolution to investigate the underlying electrophysiology of major depressive disorder (MDD) and the treatment efficacy. Here, we explore whether neuro-electrophysiological features of MDD at baseline can be used as a neural marker to predict their early antidepressant response.

METHODS

Sixty-six medication-free patients with MDD and 48 healthy controls were enrolled and underwent resting-state MEG scans. Hamilton depression rating scale (HAMD-17) was assessed at both baseline and after two-week pharmacotherapy. We measured local and large-scale resting-state oscillatory dysfunctions with a data-driven model, the Fitting Oscillations & One-Over F algorithm. Then, we quantified band-limited regional power and functional connectivity between brain regions.

RESULTS

After two-week follow-up, 52 patients completed the re-interviews. Thirty-one patients showed early response (ER) to pharmacotherapy and 21 patients did not. Treatment response was defined as at least 50 % reduction of severity reflected by HAMD-17. We observed decreased regional periodic power in patients with MDD comparing to controls. However, patients with ER exhibited that functional couplings across brain regions in both alpha and beta band were increased and significantly correlated with severity of depressive symptoms after treatment. Receiver operating characteristic curves (ROC) further confirmed the predictive ability of baseline large-scale functional connectivity for early antidepressant efficacy (AUC = 0.9969).

LIMITATIONS

Relatively small sample size and not a double-blind design.

CONCLUSIONS

The current study demonstrated the electrophysiological dysfunctions of local neural oscillatory related with depression and highlighted the identification ability of large-scale couplings biomarkers in early antidepressant response prediction.

Increased entrainment and decreased excitability predict efficacious treatment of closed-loop phase-locked rTMS for treatment-resistant depression

Transcranial magnetic stimulation (TMS) is an FDA-approved therapy for major depressive disorder (MDD), specifically for patients who have treatment-resistant depression (TRD). However, TMS produces response or remission in about 50% of patients but is ineffective for the other 50%. Limits on efficacy may be due to individual patient variability, but to date, there are no good biomarkers or measures of target engagement. In addition, TMS efficacy is typically not assessed until a six-week treatment ends, precluding the evaluation of intermediate improvements during the treatment duration. Here, we report on results using a closed-loop phase-locked repetitive TMS (rTMS) treatment that synchronizes the delivery of rTMS based on the timing of the pulses relative to a patient's individual electroencephalographic (EEG) prefrontal alpha oscillation informed by functional magnetic resonance imaging (fMRI). We find that, in responders, synchronized delivery of rTMS produces two systematic changes in brain dynamics. The first change is a decrease in global cortical excitability, and the second is an increase in the phase entrainment of cortical dynamics. These two effects predict clinical outcomes in the synchronized treatment group but not in an active-treatment unsynchronized control group. The systematic decrease in excitability and increase in entrainment correlated with treatment efficacy at the endpoint and intermediate weeks during the synchronized treatment. Specifically, we show that weekly tracking of these biomarkers allows for efficacy prediction and potential of dynamic adjustments through a treatment course, improving the overall response rates.

Mental Stress Classification Based on Selected Electroencephalography Channels Using Correlation Coefficient of Hjorth Parameters

Electroencephalography (EEG) signals offer invaluable insights into diverse activities of the human brain, including the intricate physiological and psychological responses associated with mental stress. A major challenge, however, is accurately identifying mental stress while mitigating the limitations associated with a large number of EEG channels. Such limitations encompass computational complexity, potential overfitting, and the prolonged setup time for electrode placement, all of which can hinder practical applications. To address these challenges, this study presents the novel CCHP method, aimed at identifying and ranking commonly optimal EEG channels based on their sensitivity to the mental stress state. This method's uniqueness lies in its ability not only to find common channels, but also to prioritize them according to their responsiveness to stress, ensuring consistency across subjects and making it potentially transformative for real-world applications. From our rigorous examinations, eight channels emerged as universally optimal in detecting stress variances across participants. Leveraging features from the time, frequency, and time-frequency domains of these channels, and employing machine learning algorithms, notably RLDA, SVM, and KNN, our approach achieved a remarkable accuracy of 81.56% with the SVM algorithm outperforming existing methodologies. The implications of this research are profound, offering a stepping stone toward the development of real-time stress detection devices, and consequently, enabling clinicians to make more informed therapeutic decisions based on comprehensive brain activity monitoring.

DISCOVER-EEG: an open, fully automated EEG pipeline for biomarker discovery in clinical neuroscience

Biomarker discovery in neurological and psychiatric disorders critically depends on reproducible and transparent methods applied to large-scale datasets. Electroencephalography (EEG) is a promising tool for identifying biomarkers. However, recording, preprocessing, and analysis of EEG data is time-consuming and researcher-dependent. Therefore, we developed DISCOVER-EEG, an open and fully automated pipeline that enables easy and fast preprocessing, analysis, and visualization of resting state EEG data. Data in the Brain Imaging Data Structure (BIDS) standard are automatically preprocessed, and physiologically meaningful features of brain function (including oscillatory power, connectivity, and network characteristics) are extracted and visualized using two open-source and widely used Matlab toolboxes (EEGLAB and FieldTrip). We tested the pipeline in two large, openly available datasets containing EEG recordings of healthy participants and patients with a psychiatric condition. Additionally, we performed an exploratory analysis that could inspire the development of biomarkers for healthy aging. Thus, the DISCOVER-EEG pipeline facilitates the aggregation, reuse, and analysis of large EEG datasets, promoting open and reproducible research on brain function.

Developing an Electroencephalography-Based Model for Predicting Response to Antidepressant Medication

Importance

Untreated depression is a growing public health concern, with patients often facing a prolonged trial-and-error process in search of effective treatment. Developing a predictive model for treatment response in clinical practice remains challenging.

Objective

To establish a model based on electroencephalography (EEG) to predict response to 2 distinct selective serotonin reuptake inhibitor (SSRI) medications.

Design, Setting, and Participants

This prognostic study developed a predictive model using EEG data collected between 2011 and 2017 from 2 independent cohorts of participants with depression: 1 from the first Canadian Biomarker Integration Network in Depression (CAN-BIND) group and the other from the Establishing Moderators and Biosignatures of Antidepressant Response for Clinical Care (EMBARC) consortium. Eligible participants included those aged 18 to 65 years who had a diagnosis of major depressive disorder. Data were analyzed from January to December 2022.

Exposures

In an open-label trial, CAN-BIND participants received an 8-week treatment regimen of escitalopram treatment (10-20 mg), and EMBARC participants were randomized in a double-blind trial to receive an 8-week sertraline (50-200 mg) treatment or placebo treatment.

Main Outcomes and Measures

The model's performance was estimated using balanced accuracy, specificity, and sensitivity metrics. The model used data from the CAN-BIND cohort for internal validation, and data from the treatment group of the EMBARC cohort for external validation. At week 8, response to treatment was defined as a 50% or greater reduction in the primary, clinician-rated scale of depression severity.

Results

The CAN-BIND cohort included 125 participants (mean [SD] age, 36.4 [13.0] years; 78 [62.4%] women), and the EMBARC sertraline treatment group included 105 participants (mean [SD] age, 38.4 [13.8] years; 72 [68.6%] women). The model achieved a balanced accuracy of 64.2% (95% CI, 55.8%-72.6%), sensitivity of 66.1% (95% CI, 53.7%-78.5%), and specificity of 62.3% (95% CI, 50.1%-73.8%) during internal validation with CAN-BIND. During external validation with EMBARC, the model achieved a balanced accuracy of 63.7% (95% CI, 54.5%-72.8%), sensitivity of 58.8% (95% CI, 45.3%-72.3%), and specificity of 68.5% (95% CI, 56.1%-80.9%). Additionally, the balanced accuracy for the EMBARC placebo group (118 participants) was 48.7% (95% CI, 39.3%-58.0%), the sensitivity was 50.0% (95% CI, 35.2%-64.8%), and the specificity was 47.3% (95% CI, 35.9%-58.7%), suggesting the model's specificity in predicting SSRIs treatment response.

Conclusions and Relevance

In this prognostic study, an EEG-based model was developed and validated in 2 independent cohorts. The model showed promising accuracy in predicting treatment response to 2 distinct SSRIs, suggesting potential applications for personalized depression treatment.

Artificial intelligence in psychiatry research, diagnosis, and therapy

Psychiatric disorders are now responsible for the largest proportion of the global burden of disease, and even more challenges have been seen during the COVID-19 pandemic. Artificial intelligence (AI) is commonly used to facilitate the early detection of disease, understand disease progression, and discover new treatments in the fields of both physical and mental health. The present review provides a broad overview of AI methodology and its applications in data acquisition and processing, feature extraction and characterization, psychiatric disorder classification, potential biomarker detection, real-time monitoring, and interventions in psychiatric disorders. We also comprehensively summarize AI applications with regard to the early warning, diagnosis, prognosis, and treatment of specific psychiatric disorders, including depression, schizophrenia, autism spectrum disorder, attention-deficit/hyperactivity disorder, addiction, sleep disorders, and Alzheimer's disease. The advantages and disadvantages of AI in psychiatry are clarified. We foresee a new wave of research opportunities to facilitate and improve AI technology and its long-term implications in psychiatry during and after the COVID-19 era.

Influence of chronic stress on network states governing valence processing: Potential relevance to the risk for psychiatric illnesses

Stress is a major risk factor for psychiatric illnesses and understanding the mechanisms through which stress disrupts behavioral states is imperative to understanding the underlying pathophysiology of mood disorders. Both chronic stress and early life stress alter valence processing, the process of assigning value to sensory inputs and experiences (positive or negative), which determines subsequent behavior and is essential for emotional processing and ultimately survival. Stress disrupts valence processing in both humans and preclinical models, favoring negative valence processing and impairing positive valence processing. Valence assignment involves neural computations performed in emotional processing hubs, including the amygdala, prefrontal cortex, and ventral hippocampus, which can be influenced by neuroendocrine mediators. Oscillations within and between these regions are critical for the neural computations necessary to perform valence processing functions. Major advances in the field have demonstrated a role for oscillatory states in valence processing under physiological conditions and emerging studies are exploring how these network states are altered under pathophysiological conditions and impacted by neuroendocrine factors. The current review highlights what is currently known regarding the impact of stress and the role of neuroendocrine mediators on network states and valence processing. Further, we propose a model in which chronic stress alters information routing through emotional processing hubs, resulting in a facilitation of negative valence processing and a suppression of positive valence processing.

The evolution of Big Data in neuroscience and neurology

Neurological diseases are on the rise worldwide, leading to increased healthcare costs and diminished quality of life in patients. In recent years, Big Data has started to transform the fields of Neuroscience and Neurology. Scientists and clinicians are collaborating in global alliances, combining diverse datasets on a massive scale, and solving complex computational problems that demand the utilization of increasingly powerful computational resources. This Big Data revolution is opening new avenues for developing innovative treatments for neurological diseases. Our paper surveys Big Data's impact on neurological patient care, as exemplified through work done in a comprehensive selection of areas, including Connectomics, Alzheimer's Disease, Stroke, Depression, Parkinson's Disease, Pain, and Addiction (e.g., Opioid Use Disorder). We present an overview of research and the methodologies utilizing Big Data in each area, as well as their current limitations and technical challenges. Despite the potential benefits, the full potential of Big Data in these fields currently remains unrealized. We close with recommendations for future research aimed at optimizing the use of Big Data in Neuroscience and Neurology for improved patient outcomes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40537-023-00751-2.

From Computation to Clinic

Theory-driven and data-driven computational approaches to psychiatry have enormous potential for elucidating mechanism of disease and providing translational linkages between basic science findings and the clinic. These approaches have already demonstrated utility in providing clinically relevant understanding, primarily via back translation from clinic to computation, revealing how specific disorders or symptoms map onto specific computational processes. Nonetheless, forward translation, from computation to clinic, remains rare. In addition, consensus regarding specific barriers to forward translation-and on the best strategies to overcome these barriers-is limited. This perspective review brings together expert basic and computationally trained researchers and clinicians to 1) identify challenges specific to preclinical model systems and clinical translation of computational models of cognition and affect, and 2) discuss practical approaches to overcoming these challenges. In doing so, we highlight recent evidence for the ability of computational approaches to predict treatment responses in psychiatric disorders and discuss considerations for maximizing the clinical relevance of such models (e.g., via longitudinal testing) and the likelihood of stakeholder adoption (e.g., via cost-effectiveness analyses).

Multi-scale convolutional recurrent neural network for psychiatric disorder identification in resting-state EEG

Background

Accurate classification based on affordable objective neuroimaging biomarkers are important steps toward designing individualized treatment.

Methods

In this work, we investigated a deep learning classification model, multi-scale convolutional recurrent neural network (MCRNN), to explore psychiatric disorder-related biomarkers by leveraging the spatiotemporal information of resting-state EEG (rsEEG) using a multiple psychiatric disorder database containing 327 individuals diagnosed with schizophrenia, bipolar, major depressive disorders, and healthy controls. All subjects were mapped to a shared low-dimensional subspace for intuitively interpreting the inter-relationship and separation of psychiatric disorders.

Results

Psychiatric disorders were identified using rsEEG with high accuracy ranged from 78.6 to 91.3% in patient vs. controls two-class classification, and 68.2% in four-class classification. The control-to-schizophrenia trajectory interpretated by the model was consistent with the disease severity in clinical observation.

Conclusion

The MsRNN demonstrated a capability in extracting discriminative rsEEG biomarkers for psychiatric disorder classification, indicating its potential to facilitate our understanding of psychiatric disorders and monitoring interventions.

Network perturbation-based biomarkers of depression and treatment response

Using concurrent TMS-EEG, Han et al.¹ identified temporal and spectral signatures of depression in a prefrontal-orbitofrontal-hippocampal network, which renormalized after rTMS. This highlights the relevance of causal network perturbation for the assessment of disease-related network states and their therapeutic modulation.

Resting-state electroencephalography and magnetoencephalography as biomarkers of chronic pain: a systematic review

ABSTRACT

Reliable and objective biomarkers promise to improve the assessment and treatment of chronic pain. Resting-state electroencephalography (EEG) is broadly available, easy to use, and cost efficient and, therefore, appealing as a potential biomarker of chronic pain. However, results of EEG studies are heterogeneous. Therefore, we conducted a systematic review (PROSPERO CRD42021272622) of quantitative resting-state EEG and magnetoencephalography (MEG) studies in adult patients with different types of chronic pain. We excluded populations with severe psychiatric or neurologic comorbidity. Risk of bias was assessed using a modified Newcastle-Ottawa Scale. Semiquantitative data synthesis was conducted using modified albatross plots. We included 76 studies after searching MEDLINE, Web of Science Core Collection, Cochrane Central Register of Controlled Trials, and EMBASE. For cross-sectional studies that can serve to develop diagnostic biomarkers, we found higher theta and beta power in patients with chronic pain than in healthy participants. For longitudinal studies, which can yield monitoring and/or predictive biomarkers, we found no clear associations of pain relief with M/EEG measures. Similarly, descriptive studies that can yield diagnostic or monitoring biomarkers showed no clear correlations of pain intensity with M/EEG measures. Risk of bias was high in many studies and domains. Together, this systematic review synthesizes evidence on how resting-state M/EEG might serve as a diagnostic biomarker of chronic pain. Beyond, this review might help to guide future M/EEG studies on the development of pain biomarkers.

Individualized fMRI connectivity defines signatures of antidepressant and placebo responses in major depression

Though sertraline is commonly prescribed in patients with major depressive disorder (MDD), its superiority over placebo is only marginal. This is in part due to the neurobiological heterogeneity of the individuals. Characterizing individual-unique functional architecture of the brain may help better dissect the heterogeneity, thereby defining treatment-predictive signatures to guide personalized medication. In this study, we investigate whether individualized brain functional connectivity (FC) can define more predictable signatures of antidepressant and placebo treatment in MDD. The data used in the present work were collected by the Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC) study. Patients (N = 296) were randomly assigned to antidepressant sertraline or placebo double-blind treatment for 8 weeks. The whole-brain FC networks were constructed from pre-treatment resting-state functional magnetic resonance imaging (rs-fMRI). Then, FC was individualized by removing the common components extracted from the raw baseline FC to train regression-based connectivity predictive models. With individualized FC features, the established prediction models successfully identified signatures that explained 22% variance for the sertraline group and 31% variance for the placebo group in predicting HAMD17 change. Compared with the raw FC-based models, the individualized FC-defined signatures significantly improved the prediction performance, as confirmed by cross-validation. For sertraline treatment, predictive FC metrics were predominantly located in the left middle temporal cortex and right insula. For placebo, predictive FC metrics were primarily located in the bilateral cingulate cortex and left superior temporal cortex. Our findings demonstrated that through the removal of common FC components, individualization of FC metrics enhanced the prediction performance compared to raw FC. Associated with previous MDD clinical studies, our identified predictive biomarkers provided new insights into the neuropathology of antidepressant and placebo treatment.

Stratification of responses to tDCS intervention in a healthy pediatric population based on resting-state EEG profiles

Transcranial Direct Current Stimulation (tDCS) is a non-invasive neuromodulation technique with a wide variety of clinical and research applications. As increasingly acknowledged, its effectiveness is subject dependent, which may lead to time consuming and cost ineffective treatment development phases. We propose the combination of electroencephalography (EEG) and unsupervised learning for the stratification and prediction of individual responses to tDCS. A randomized, sham-controlled, double-blind crossover study design was conducted within a clinical trial for the development of pediatric treatments based on tDCS. The tDCS stimulation (sham and active) was applied either in the left dorsolateral prefrontal cortex or in the right inferior frontal gyrus. Following the stimulation session, participants performed 3 cognitive tasks to assess the response to the intervention: the Flanker Task, N-Back Task and Continuous Performance Test (CPT). We used data from 56 healthy children and adolescents to implement an unsupervised clustering approach that stratify participants based on their resting-state EEG spectral features before the tDCS intervention. We then applied a correlational analysis to characterize the clusters of EEG profiles in terms of participant's difference in the behavioral outcome (accuracy and response time) of the cognitive tasks when performed after a tDCS-sham or a tDCS-active session. Better behavioral performance following the active tDCS session compared to the sham tDCS session is considered a positive intervention response, whilst the reverse is considered a negative one. Optimal results in terms of validity measures was obtained for 4 clusters. These results show that specific EEG-based digital phenotypes can be associated to particular responses. While one cluster presents neurotypical EEG activity, the remaining clusters present non-typical EEG characteristics, which seem to be associated with a positive response. Findings suggest that unsupervised machine learning can be successfully used to stratify and eventually predict responses of individuals to a tDCS treatment.

Resting-state EEG delta and alpha power predict response to cognitive behavioral therapy in depression: a Canadian biomarker integration network for depression study

Cognitive behavioral therapy (CBT) is often recommended as a first-line treatment in depression. However, access to CBT remains limited, and up to 50% of patients do not benefit from this therapy. Identifying biomarkers that can predict which patients will respond to CBT may assist in designing optimal treatment allocation strategies. In a Canadian Biomarker Integration Network for Depression (CAN-BIND) study, forty-one adults with depression were recruited to undergo a 16-week course of CBT with thirty having resting-state electroencephalography (EEG) recorded at baseline and week 2 of therapy. Successful clinical response to CBT was defined as a 50% or greater reduction in Montgomery-Åsberg Depression Rating Scale (MADRS) score from baseline to post-treatment completion. EEG relative power spectral measures were analyzed at baseline, week 2, and as early changes from baseline to week 2. At baseline, lower relative delta (0.5-4 Hz) power was observed in responders. This difference was predictive of successful clinical response to CBT. Furthermore, responders exhibited an early increase in relative delta power and a decrease in relative alpha (8-12 Hz) power compared to non-responders. These changes were also found to be good predictors of response to the therapy. These findings showed the potential utility of resting-state EEG in predicting CBT outcomes. They also further reinforce the promise of an EEG-based clinical decision-making tool to support treatment decisions for each patient.

Dissecting Symptom-linked Dimensions of Resting-State Electroencephalographic Functional Connectivity in Autism with Contrastive Learning

Autism spectrum disorder (ASD) is a common neurodevelopmental disorder characterized by social interaction deficits, communication difficulties, and restricted/repetitive behaviors or fixated interests. Despite its high prevalence, development of effective therapy for ASD is hindered by its symptomatic and neurophysiological heterogeneities. To collectively dissect the ASD heterogeneity in neurophysiology and symptoms, we develop a new analytical framework combining contrastive learning and sparse canonical correlation analysis to identify resting-state EEG connectivity dimensions linked to ASD behavioral symptoms within 392 ASD samples. Two dimensions are successfully identified, showing significant correlations with social/communication deficits (r = 0.70) and restricted/repetitive behaviors (r = 0.45), respectively. We confirm the robustness of these dimensions through cross-validation and further demonstrate their generalizability using an independent dataset of 223 ASD samples. Our results reveal that the right inferior parietal lobe is the core region displaying EEG activity associated with restricted/repetitive behaviors, and functional connectivity between the left angular gyrus and the right middle temporal gyrus is a promising biomarker of social/communication deficits. Overall, these findings provide a promising avenue to parse ASD heterogeneity with high clinical translatability, paving the way for treatment development and precision medicine for ASD.

AI-assisted prediction of differential response to antidepressant classes using electronic health records

Antidepressant selection is largely a trial-and-error process. We used electronic health record (EHR) data and artificial intelligence (AI) to predict response to four antidepressants classes (SSRI, SNRI, bupropion, and mirtazapine) 4 to 12 weeks after antidepressant initiation. The final data set comprised 17,556 patients. Predictors were derived from both structured and unstructured EHR data and models accounted for features predictive of treatment selection to minimize confounding by indication. Outcome labels were derived through expert chart review and AI-automated imputation. Regularized generalized linear model (GLM), random forest, gradient boosting machine (GBM), and deep neural network (DNN) models were trained and their performance compared. Predictor importance scores were derived using SHapley Additive exPlanations (SHAP). All models demonstrated similarly good prediction performance (AUROCs ≥ 0.70, AUPRCs ≥ 0.68). The models can estimate differential treatment response probabilities both between patients and between antidepressant classes for the same patient. In addition, patient-specific factors driving response probabilities for each antidepressant class can be generated. We show that antidepressant response can be accurately predicted from real-world EHR data with AI modeling, and our approach could inform further development of clinical decision support systems for more effective treatment selection.

The potential of electroencephalography coherence to predict the outcome of repetitive transcranial magnetic stimulation in insomnia disorder

BACKGROUND

It is unknown whether repetitive Transcranial Magnetic Stimulation (rTMS) could improve sleep quality by modulating electroencephalography (EEG) connectivity of insomnia disorder (ID) patients. Great heterogeneity had been found in the clinical outcomes of rTMS for ID. The study aimed to investigate the potential mechanisms of rTMS therapy for ID and develop models to predict clinical outcomes.

METHODS

In Study 1, 50 ID patients were randomly divided into active and sham groups, and subjected to 20 sessions of treatment with 1 Hz rTMS over the left dorsolateral prefrontal cortex. EEG during awake, Polysomnography, and clinical assessment were collected and analyzed before and after rTMS. In Study 2, 120 ID patients were subjected to active rTMS stimulation and were then separated into optimal and sub-optimal groups due to the median of Pittsburgh Sleep Quality Index reduction rate. Machine learning models were developed based on baseline EEG coherence to predict rTMS treatment effects.

RESULTS

In Study 1, decreased EEG coherence in theta and alpha bands were observed after rTMS treatment, and changes in theta band (F7-O1) coherence were correlated with changes in sleep efficiency. In Study 2, baseline EEG coherence in theta, alpha, and beta bands showed the potential to predict the treatment effects of rTMS for ID.

CONCLUSION

rTMS improved sleep quality of ID patients by modulating the abnormal EEG coherence. Baseline EEG coherence between certain channels in theta, alpha, and beta bands could act as potential biomarkers to predict the therapeutic effects.

Personalized Repetitive Transcranial Magnetic Stimulation for Depression

Personalized treatments are gaining momentum across all fields of medicine. Precision medicine can be applied to neuromodulatory techniques, in which focused brain stimulation treatments such as repetitive transcranial magnetic stimulation (rTMS) modulate brain circuits and alleviate clinical symptoms. rTMS is well tolerated and clinically effective for treatment-resistant depression and other neuropsychiatric disorders. Despite its wide stimulation parameter space (location, angle, pattern, frequency, and intensity can be adjusted), rTMS is currently applied in a one-size-fits-all manner, potentially contributing to its suboptimal clinical response (∼50%). In this review, we examine components of rTMS that can be optimized to account for interindividual variability in neural function and anatomy. We discuss current treatment options for treatment-resistant depression, the neural mechanisms thought to underlie treatment, targeting strategies, stimulation parameter selection, and adaptive closed-loop treatment. We conclude that a better understanding of the wide and modifiable parameter space of rTMS will greatly improve the clinical outcome.

Discovering Themes in Deep Brain Stimulation Research Using Explainable Artificial Intelligence

Deep brain stimulation is a treatment that controls symptoms by changing brain activity. The complexity of how to best treat brain dysfunction with deep brain stimulation has spawned research into artificial intelligence approaches. Machine learning is a subset of artificial intelligence that uses computers to learn patterns in data and has many healthcare applications, such as an aid in diagnosis, personalized medicine, and clinical decision support. Yet, how machine learning models make decisions is often opaque. The spirit of explainable artificial intelligence is to use machine learning models that produce interpretable solutions. Here, we use topic modeling to synthesize recent literature on explainable artificial intelligence approaches to extracting domain knowledge from machine learning models relevant to deep brain stimulation. The results show that patient classification (i.e., diagnostic models, precision medicine) is the most common problem in deep brain stimulation studies that employ explainable artificial intelligence. Other topics concern attempts to optimize stimulation strategies and the importance of explainable methods. Overall, this review supports the potential for artificial intelligence to revolutionize deep brain stimulation by personalizing stimulation protocols and adapting stimulation in real time.

Prediction of Behavioral Improvement Through Resting-State Electroencephalography and Clinical Severity in a Randomized Controlled Trial Testing Bumetanide in Autism Spectrum Disorder

BACKGROUND

Mechanism-based treatments such as bumetanide are being repurposed for autism spectrum disorder. We recently reported beneficial effects on repetitive behavioral symptoms that might be related to regulating excitation-inhibition (E/I) balance in the brain. Here, we tested the neurophysiological effects of bumetanide and the relationship to clinical outcome variability and investigated the potential for machine learning-based predictions of meaningful clinical improvement.

METHODS

Using modified linear mixed models applied to intention-to-treat population, we analyzed E/I-sensitive electroencephalography (EEG) measures before and after 91 days of treatment in the double-blind, randomized, placebo-controlled Bumetanide in Autism Medication and Biomarker study. Resting-state EEG of 82 subjects out of 92 participants (7-15 years) were available. Alpha frequency band absolute and relative power, central frequency, long-range temporal correlations, and functional E/I ratio treatment effects were related to the Repetitive Behavior Scale-Revised (RBS-R) and the Social Responsiveness Scale 2 as clinical outcomes.

RESULTS

We observed superior bumetanide effects on EEG, reflected in increased absolute and relative alpha power and functional E/I ratio and in decreased central frequency. Associations between EEG and clinical outcome change were restricted to subgroups with medium to high RBS-R improvement. Using machine learning, medium and high RBS-R improvement could be predicted by baseline RBS-R score and EEG measures with 80% and 92% accuracy, respectively.

CONCLUSIONS

Bumetanide exerts neurophysiological effects related to clinical changes in more responsive subsets, in whom prediction of improvement was feasible through EEG and clinical measures.

Pursuing personalized medicine for depression by targeting the lateral or medial prefrontal cortex with Deep TMS

BACKGROUNDMajor depressive disorder (MDD) can benefit from novel interventions and personalization. Deep transcranial magnetic stimulation (Deep TMS) targeting the lateral prefrontal cortex (LPFC) using the H1 coil was FDA cleared for treatment of MDD. However, recent preliminary data indicate that targeting the medial prefrontal cortex (MPFC) using the H7 coil might induce outcomes that are as good or even better. Here, we explored whether Deep TMS targeting the MPFC is noninferior to targeting the LPFC and whether electrophysiological or clinical markers for patient selection can be identified.METHODSThe present prospective, multicenter, randomized study enrolled 169 patients with MDD for whom antidepressants failed in the current episode. Patients were randomized to receive 24 Deep TMS sessions over 6 weeks, using either the H1 coil or the H7 coil. The primary efficacy endpoint was the change from baseline to week 6 in Hamilton Depression Rating Scale scores.RESULTSClinical efficacy and safety profiles were similar and not significantly different between groups, with response rates of 60.9% for the H1 coil and 64.2% for the H7 coil. Moreover, brain activity measured by EEG during the first treatment session correlated with clinical outcomes in a coil-specific manner, and a cluster of baseline clinical symptoms was found to potentially distinguish between patients who can benefit from each Deep TMS target.CONCLUSIONThis study provides a treatment option for MDD, using the H7 coil, and initial guidance to differentiate between patients likely to respond to LPFC versus MPFC stimulation targets, which require further validation studies.TRIAL REGISTRATIONClinicalTrials.gov NCT03012724.FUNDINGBrainsWay Ltd.

Methodological and Quality Flaws in the Use of Artificial Intelligence in Mental Health Research: Systematic Review

BACKGROUND

Artificial intelligence (AI) is giving rise to a revolution in medicine and health care. Mental health conditions are highly prevalent in many countries, and the COVID-19 pandemic has increased the risk of further erosion of the mental well-being in the population. Therefore, it is relevant to assess the current status of the application of AI toward mental health research to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

This study aims to perform a systematic overview of AI applications in mental health in terms of methodologies, data, outcomes, performance, and quality.

METHODS

A systematic search in PubMed, Scopus, IEEE Xplore, and Cochrane databases was conducted to collect records of use cases of AI for mental health disorder studies from January 2016 to November 2021. Records were screened for eligibility if they were a practical implementation of AI in clinical trials involving mental health conditions. Records of AI study cases were evaluated and categorized by the International Classification of Diseases 11th Revision (ICD-11). Data related to trial settings, collection methodology, features, outcomes, and model development and evaluation were extracted following the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) guideline. Further, evaluation of risk of bias is provided.

RESULTS

A total of 429 nonduplicated records were retrieved from the databases and 129 were included for a full assessment-18 of which were manually added. The distribution of AI applications in mental health was found unbalanced between ICD-11 mental health categories. Predominant categories were Depressive disorders (n=70) and Schizophrenia or other primary psychotic disorders (n=26). Most interventions were based on randomized controlled trials (n=62), followed by prospective cohorts (n=24) among observational studies. AI was typically applied to evaluate quality of treatments (n=44) or stratify patients into subgroups and clusters (n=31). Models usually applied a combination of questionnaires and scales to assess symptom severity using electronic health records (n=49) as well as medical images (n=33). Quality assessment revealed important flaws in the process of AI application and data preprocessing pipelines. One-third of the studies (n=56) did not report any preprocessing or data preparation. One-fifth of the models were developed by comparing several methods (n=35) without assessing their suitability in advance and a small proportion reported external validation (n=21). Only 1 paper reported a second assessment of a previous AI model. Risk of bias and transparent reporting yielded low scores due to a poor reporting of the strategy for adjusting hyperparameters, coefficients, and the explainability of the models. International collaboration was anecdotal (n=17) and data and developed models mostly remained private (n=126).

CONCLUSIONS

These significant shortcomings, alongside the lack of information to ensure reproducibility and transparency, are indicative of the challenges that AI in mental health needs to face before contributing to a solid base for knowledge generation and for being a support tool in mental health management.

EEG-based spatio-temporal relation signatures for the diagnosis of depression and schizophrenia

The diagnosis of psychiatric disorders is currently based on a clinical and psychiatric examination (intake). Ancillary tests are used minimally or only to exclude other disorders. Here, we demonstrate a novel mathematical approach based on the field of p-adic numbers and using electroencephalograms (EEGs) to identify and differentiate patients with schizophrenia and depression from healthy controls. This novel approach examines spatio-temporal relations of single EEG electrode signals and characterizes the topological structure of these relations in the individual patient. Our results indicate that the relational topological structures, characterized by either the personal universal dendrographic hologram (DH) signature (PUDHS) or personal block DH signature (PBDHS), form a unique range for each group of patients, with impressive correspondence to the clinical condition. This newly developed approach results in an individual patient signature calculated from the spatio-temporal relations of EEG electrodes signals and might help the clinician with a new objective tool for the diagnosis of a multitude of psychiatric disorders.