Establishing moderators and biosignatures of antidepressant response in clinical care (EMBARC): Rationale and design

DeepComBat: A statistically motivated, hyperparameter-robust, deep learning approach to harmonization of neuroimaging data

Neuroimaging data acquired using multiple scanners or protocols are increasingly available. However, such data exhibit technical artifacts across batches which introduce confounding and decrease reproducibility. This is especially true when multi-batch data are analyzed using complex downstream models which are more likely to pick up on and implicitly incorporate batch-related information. Previously proposed image harmonization methods have sought to remove these batch effects; however, batch effects remain detectable in the data after applying these methods. We present DeepComBat, a deep learning harmonization method based on a conditional variational autoencoder and the ComBat method. DeepComBat combines the strengths of statistical and deep learning methods in order to account for the multivariate relationships between features while simultaneously relaxing strong assumptions made by previous deep learning harmonization methods. As a result, DeepComBat can perform multivariate harmonization while preserving data structure and avoiding the introduction of synthetic artifacts. We apply this method to cortical thickness measurements from a cognitive-aging cohort and show DeepComBat qualitatively and quantitatively outperforms existing methods in removing batch effects while preserving biological heterogeneity. Additionally, DeepComBat provides a new perspective for statistically motivated deep learning harmonization methods.

Neuroimaging for precision medicine in psychiatry

Although the lifetime burden due to mental disorders is increasing, we lack tools for more precise diagnosing and treating prevalent and disabling disorders such as major depressive disorder. We lack strategies for selecting among available treatments or expediting access to new treatment options. This critical review concentrates on functional neuroimaging as a modality of measurement for precision psychiatry, focusing on major depressive and anxiety disorders. We begin by outlining evidence for the use of functional neuroimaging to stratify the heterogeneity of these disorders, based on underlying circuit dysfunction. We then review the current landscape of how functional neuroimaging-derived circuit predictors can predict treatment outcomes and clinical trajectories in depression and anxiety. Future directions for advancing clinically appliable neuroimaging measures are considered. We conclude by considering the opportunities and challenges of translating neuroimaging measures into practice. As an illustration, we highlight one approach for quantifying brain circuit function at an individual level, which could serve as a model for clinical translation.

Breakthroughs and challenges for generating brain network-based biomarkers of treatment response in depression

Treatment outcomes widely vary for individuals diagnosed with major depressive disorder, implicating a need for deeper understanding of the biological mechanisms conferring a greater likelihood of response to a particular treatment. Our improved understanding of intrinsic brain networks underlying depression psychopathology via magnetic resonance imaging and other neuroimaging modalities has helped reveal novel and potentially clinically meaningful biological markers of response. And while we have made considerable progress in identifying such biomarkers over the last decade, particularly with larger, multisite trials, there are significant methodological and practical obstacles that need to be overcome to translate these markers into the clinic. The aim of this review is to review current literature on brain network structural and functional biomarkers of treatment response or selection in depression, with a specific focus on recent large, multisite trials reporting predictive accuracy of candidate biomarkers. Regarding pharmaco- and psychotherapy, we discuss candidate biomarkers, reporting that while we have identified candidate biomarkers of response to a single intervention, we need more trials that distinguish biomarkers between first-line treatments. Further, we discuss the ways prognostic neuroimaging may help to improve treatment outcomes to neuromodulation-based therapies, such as transcranial magnetic stimulation and deep brain stimulation. Lastly, we highlight obstacles and technical developments that may help to address the knowledge gaps in this area of research. Ultimately, integrating neuroimaging-derived biomarkers into clinical practice holds promise for enhancing treatment outcomes and advancing precision psychiatry strategies for depression management. By elucidating the neural predictors of treatment response and selection, we can move towards more individualized and effective depression interventions, ultimately improving patient outcomes and quality of life.

An automated approach for predicting HAMD-17 scores via divergent selective focused multi-heads self-attention network

This study introduces the Divergent Selective Focused Multi-heads Self-Attention Network (DSFMANet), an innovative deep learning model devised to automatically predict Hamilton Depression Rating Scale-17 (HAMD-17) scores in patients with depression. This model introduces a multi-branch structure for sub-bands and artificially configures attention focus factors on various branches, resulting in distinct attention distributions for different sub-bands. Experimental results demonstrate that when DSFMANet processes sub-band data, its performance surpasses current benchmarks in key metrics such as mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). This success is particularly evident in terms of MSE and MAE, where the performance of sub-band data is significantly superior, highlighting the model's potential in accurately predicting HAMD-17 scores. Concurrently, the experiment also compared the model's performance with sub-band and full-band data, affirming the superiority of the selective focus attention mechanism in electroencephalography (EEG) signal processing. DSFMANet, when utilizing sub-band data, exhibits higher data processing efficiency and reduced model complexity. The findings of this study underscore the significance of employing deep learning models based on sub-band analysis in depression diagnosis. The DSFMANet model not only effectively enhances the accuracy of depression diagnosis but also offers valuable research directions for similar applications in the future. This deep learning-based automated approach can effectively ascertain the HAMD-17 scores of patients with depression, thus offering more accurate and reliable support for clinical decision-making.

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.

Machine learning for antidepressant treatment selection in depression

Finding the right antidepressant for the individual patient with major depressive disorder can be a difficult endeavor and is mostly based on trial-and-error. Machine learning (ML) is a promising tool to personalize antidepressant prescription. In this review, we summarize the current evidence of ML in the selection of antidepressants and conclude that its value for clinical practice is still limited. Apart from the current focus on effectiveness, several other factors should be taken into account to make ML-based prediction models useful for clinical application.

Individualized Functional Brain System Topologies and Major Depression: Relationships Among Patch Sizes and Clinical Profiles and Behavior

BACKGROUND

Neuroimaging studies of major depression have typically been conducted using group-level approaches. However, given interindividual differences in brain systems, there is a need for individualized approaches to brain systems mapping and putative links toward diagnosis, symptoms, and behavior.

METHODS

We used an iterative parcellation approach to map individualized brain systems in 328 participants from a multisite, placebo-controlled clinical trial. We hypothesized that participants with depression would show abnormalities in salience, control, default, and affective systems, which would be associated with higher levels of self-reported anhedonia, anxious arousal, and worse cognitive performance. Within hypothesized brain systems, we compared patch sizes (number of vertices) between depressed and healthy control groups. Within depressed groups, abnormal patches were correlated with hypothesized clinical and behavioral measures.

RESULTS

Significant group differences emerged in hypothesized patches of 1) the lateral salience system (parietal operculum; t326 = -3.11, p = .002) and 2) the control system (left medial posterior prefrontal cortex region; z = -3.63, p < .001), with significantly smaller patches in these regions in participants with depression than in healthy control participants. Results suggest that participants with depression with significantly smaller patch sizes in the lateral salience system and control system regions experience greater anxious arousal and cognitive deficits.

CONCLUSIONS

The findings imply that neural features mapped at the individual level may relate meaningfully to diagnosis, symptoms, and behavior. There is strong clinical relevance in taking an individualized brain systems approach to mapping neural functional connectivity because these associated region patch sizes may help advance our understanding of neural features linked to psychopathology and foster future patient-specific clinical decision making.

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.

Examining factors related to low performance of predicting remission in participants with major depressive disorder using neuroimaging data and other clinical features

Major depressive disorder (MDD), a prevalent mental health issue, affects more than 8% of the US population, and almost 17% in the young group of 18-25 years old. Since Covid-19, its prevalence has become even more significant. However, the remission (being free of depression) rates of first-line antidepressant treatments on MDD are only about 30%. To improve treatment outcomes, researchers have built various predictive models for treatment responses and yet none of them have been adopted in clinical use. One reason is that most predictive models are based on data from subjective questionnaires, which are less reliable. Neuroimaging data are promising objective prognostic factors, but they are expensive to obtain and hence predictive models using neuroimaging data are limited and such studies were usually in small scale (N<100). In this paper, we proposed an advanced machine learning (ML) pipeline for small training dataset with large number of features. We implemented multiple imputation for missing data and repeated K-fold cross validation (CV) to robustly estimate predictive performances. Different feature selection methods and stacking methods using 6 general ML models including random forest, gradient boosting decision tree, XGBoost, penalized logistic regression, support vector machine (SVM), and neural network were examined to evaluate the model performances. All predictive models were compared using model performance metrics such as accuracy, balanced accuracy, area under ROC curve (AUC), sensitivity and specificity. Our proposed ML pipeline was applied to a training dataset and obtained an accuracy and AUC above 0.80. But such high performance failed while applying our ML pipeline using an external validation dataset from the EMBARC study which is a multi-center study. We further examined the possible reasons especially the site heterogeneity issue.

Brain Circuit-Derived Biotypes for Treatment Selection in Mood Disorders: A Critical Review and Illustration of a Functional Neuroimaging Tool for Clinical Translation

Although the lifetime burden due to major depressive disorder is increasing, we lack tools for selecting the most effective treatments for each patient. One-third to one-half of patients with major depressive disorder do not respond to treatment, and we lack strategies for selecting among available treatments or expediting access to new treatment options. This critical review concentrates on functional neuroimaging as a modality of measurement for precision psychiatry. We begin by summarizing the current landscape of how functional neuroimaging-derived circuit predictors can forecast treatment outcomes in depression. Then, we outline the opportunities and challenges in integrating circuit predictors into clinical practice. We highlight one standardized and reproducible approach for quantifying brain circuit function at an individual level, which could serve as a model for clinical translation. We conclude by evaluating the prospects and practicality of employing neuroimaging tools, such as the one that we propose, in routine clinical practice.

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.

Treatment Response Prediction in Major Depressive Disorder Using Multimodal MRI and Clinical Data: Secondary Analysis of a Randomized Clinical Trial

OBJECTIVE

Response to antidepressant treatment in major depressive disorder varies substantially between individuals, which lengthens the process of finding effective treatment. The authors sought to determine whether a multimodal machine learning approach could predict early sertraline response in patients with major depressive disorder. They assessed the predictive contribution of MR neuroimaging and clinical assessments at baseline and after 1 week of treatment.

METHODS

This was a preregistered secondary analysis of data from the Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC) study, a multisite double-blind, placebo-controlled randomized clinical trial that included 296 adult outpatients with unmedicated recurrent or chronic major depressive disorder. MR neuroimaging and clinical data were collected before and after 1 week of treatment. Performance in predicting response and remission, collected after 8 weeks, was quantified using balanced accuracy (bAcc) and area under the receiver operating characteristic curve (AUROC) scores.

RESULTS

A total of 229 patients were included in the analyses (mean age, 38 years [SD=13]; 66% female). Internal cross-validation performance in predicting response to sertraline (bAcc=68% [SD=10], AUROC=0.73 [SD=0.03]) was significantly better than chance. External cross-validation on data from placebo nonresponders (bAcc=62%, AUROC=0.66) and placebo nonresponders who were switched to sertraline (bAcc=65%, AUROC=0.68) resulted in differences that suggest specificity for sertraline treatment compared with placebo treatment. Finally, multimodal models outperformed unimodal models.

CONCLUSIONS

The study results confirm that early sertraline treatment response can be predicted; that the models are sertraline specific compared with placebo; that prediction benefits from integrating multimodal MRI data with clinical data; and that perfusion imaging contributes most to these predictions. Using this approach, a lean and effective protocol could individualize sertraline treatment planning to improve psychiatric care.

Features of immunometabolic depression as predictors of antidepressant treatment outcomes: pooled analysis of four clinical trials

BACKGROUND

Profiling patients on a proposed 'immunometabolic depression' (IMD) dimension, described as a cluster of atypical depressive symptoms related to energy regulation and immunometabolic dysregulations, may optimise personalised treatment.

AIMS

To test the hypothesis that baseline IMD features predict poorer treatment outcomes with antidepressants.

METHOD

Data on 2551 individuals with depression across the iSPOT-D (n = 967), CO-MED (n = 665), GENDEP (n = 773) and EMBARC (n = 146) clinical trials were used. Predictors included baseline severity of atypical energy-related symptoms (AES), body mass index (BMI) and C-reactive protein levels (CRP, three trials only) separately and aggregated into an IMD index. Mixed models on the primary outcome (change in depressive symptom severity) and logistic regressions on secondary outcomes (response and remission) were conducted for the individual trial data-sets and pooled using random-effects meta-analyses.

RESULTS

Although AES severity and BMI did not predict changes in depressive symptom severity, higher baseline CRP predicted smaller reductions in depressive symptoms (n = 376, βpooled = 0.06, P = 0.049, 95% CI 0.0001-0.12, I2 = 3.61%); this was also found for an IMD index combining these features (n = 372, βpooled = 0.12, s.e. = 0.12, P = 0.031, 95% CI 0.01-0.22, I2= 23.91%), with a higher - but still small - effect size compared with CRP. Confining analyses to selective serotonin reuptake inhibitor users indicated larger effects of CRP (βpooled = 0.16) and the IMD index (βpooled = 0.20). Baseline IMD features, both separately and combined, did not predict response or remission.

CONCLUSIONS

Depressive symptoms of people with more IMD features improved less when treated with antidepressants. However, clinical relevance is limited owing to small effect sizes in inconsistent associations. Whether these patients would benefit more from treatments targeting immunometabolic pathways remains to be investigated.

Towards Outcome-Driven Patient Subgroups: A Machine Learning Analysis Across Six Depression Treatment Studies

BACKGROUND

Major depressive disorder (MDD) is a heterogeneous condition; multiple underlying neurobiological and behavioral substrates are associated with treatment response variability. Understanding the sources of this variability and predicting outcomes has been elusive. Machine learning (ML) shows promise in predicting treatment response in MDD, but its application is limited by challenges to the clinical interpretability of ML models, and clinicians often lack confidence in model results. In order to improve the interpretability of ML models in clinical practice, our goal was to demonstrate the derivation of treatment-relevant patient profiles comprised of clinical and demographic information using a novel ML approach.

METHODS

We analyzed data from six clinical trials of pharmacological treatment for depression (total n = 5438) using the Differential Prototypes Neural Network (DPNN), a ML model that derives patient prototypes which can be used to derive treatment-relevant patient clusters while learning to generate probabilities for differential treatment response. A model classifying remission and outputting individual remission probabilities for five first-line monotherapies and three combination treatments was trained using clinical and demographic data. Prototypes were evaluated for interpretability by assessing differences in feature distributions (e.g. age, sex, symptom severity) and treatment-specific outcomes.

RESULTS

A 3-prototype model achieved an area under the receiver operating curve of 0.66 and an expected absolute improvement in remission rate for those receiving the best predicted treatment of 6.5% (relative improvement of 15.6%) compared to the population remission rate. We identified three treatment-relevant patient clusters. Cluster A patients tended to be younger, to have increased levels of fatigue, and more severe symptoms. Cluster B patients tended to be older, female, have less severe symptoms, and the highest remission rates. Cluster C patients had more severe symptoms, lower remission rates, more psychomotor agitation, more intense suicidal ideation, and more somatic genital symptoms.

CONCLUSION

It is possible to produce novel treatment-relevant patient profiles using ML models; doing so may improve interpretability of ML models and the quality of precision medicine treatments for MDD.

Precision psychiatry and Research Domain Criteria: Implications for clinical trials and future practice

Psychiatric disorders are associated with significant social and economic burdens, many of which are related to issues with current diagnosis and treatments. The coronavirus (COVID-19) pandemic is estimated to have increased the prevalence and burden of major depressive and anxiety disorders, indicating an urgent need to strengthen mental health systems globally. To date, current approaches adopted in drug discovery and development for psychiatric disorders have been relatively unsuccessful. Precision psychiatry aims to tailor healthcare more closely to the needs of individual patients and, when informed by neuroscience, can offer the opportunity to improve the accuracy of disease classification, treatment decisions, and prevention efforts. In this review, we highlight the growing global interest in precision psychiatry and the potential for the National Institute of Health-devised Research Domain Criteria (RDoC) to facilitate the implementation of transdiagnostic and improved treatment approaches. The need for current psychiatric nosology to evolve with recent scientific advancements and increase awareness in emerging investigators/clinicians of the value of this approach is essential. Finally, we examine current challenges and future opportunities of adopting the RDoC-associated translational and transdiagnostic approaches in clinical studies, acknowledging that the strength of RDoC is that they form a dynamic framework of guiding principles that is intended to evolve continuously with scientific developments into the future. A collaborative approach that recruits expertise from multiple disciplines, while also considering the patient perspective, is needed to pave the way for precision psychiatry that can improve the prognosis and quality of life of psychiatric patients.

Brain ventricle and choroid plexus morphology as predictor of treatment response in major depression: Findings from the EMBARC study

Recent observations suggest a role of the volume of the cerebral ventricle volume, corpus callosum (CC) segment volume, in particular that of the central-anterior part, and choroid plexus (CP) volume for treatment resistance of major depressive disorder (MDD). An increased CP volume has been associated with increased inflammatory activity and changes in the structure of the ventricles and corpus callosum. We attempt to replicate and confirm that these imaging markers are associated with clinical outcome in subjects from the EMBARC study, as implied by a recent pilot study. The EMBARC study is a placebo controlled randomized study comparing sertraline vs. placebo in patients with MDD to identify biological markers of therapy resistance. Association of baseline volumes of the lateral ventricles (LVV), choroid plexus volume (CPV) and volume of segments of the CC with treatment response after 4 weeks treatment was evaluated. 171 subjects (61 male, 110 female) completed the 4 week assessments; gender and age were taken into account for this analyses. As previously reported, no treatment effect of sertraline vs. placebo was observed, therefore the study characterized prognostic markers of response in the pooled population. Change in depression severity was identified by the ratio of the Hamilton-Depression rating scale 17 (HAMD-17) at week 4 divided by the HAMD-17 at baseline (HAMD-17 ratio). Volumes of the lateral ventricles and choroid plexi were positively correlated with the HAMD-17 ratio, indication worse outcome with larger ventricles and choroid plexus volumes, whereas the volume of the central-anterior corpus callosum was negatively correlated with the HAMD-17 ratio. Responders (n = 54) had significantly smaller volumes of the lateral ventricles and CP compared to non-responders (n = 117), whereas the volume of mid-anterior CC was significantly larger compared to non-responders (n = 117), confirming our previous findings. In an exploratory way associations between enlarged LVV and CPV and signs of lipid dysregulation were observed. In conclusion, we confirmed that volumes of lateral ventricles, choroid plexi and the mid-anterior corpus callosum are associated with clinical improvement of depression and may be indicators of metabolic/inflammatory activity.

Neuroanatomical dimensions in medication-free individuals with major depressive disorder and treatment response to SSRI antidepressant medications or placebo

Major depressive disorder (MDD) is a heterogeneous clinical syndrome with widespread subtle neuroanatomical correlates. Our objective was to identify the neuroanatomical dimensions that characterize MDD and predict treatment response to selective serotonin reuptake inhibitor (SSRI) antidepressants or placebo. In the COORDINATE-MDD consortium, raw MRI data were shared from international samples (N = 1,384) of medication-free individuals with first-episode and recurrent MDD (N = 685) in a current depressive episode of at least moderate severity, but not treatment-resistant depression, as well as healthy controls (N = 699). Prospective longitudinal data on treatment response were available for a subset of MDD individuals (N = 359). Treatments were either SSRI antidepressant medication (escitalopram, citalopram, sertraline) or placebo. Multi-center MRI data were harmonized, and HYDRA, a semi-supervised machine-learning clustering algorithm, was utilized to identify patterns in regional brain volumes that are associated with disease. MDD was optimally characterized by two neuroanatomical dimensions that exhibited distinct treatment responses to placebo and SSRI antidepressant medications. Dimension 1 was characterized by preserved gray and white matter (N = 290 MDD), whereas Dimension 2 was characterized by widespread subtle reductions in gray and white matter (N = 395 MDD) relative to healthy controls. Although there were no significant differences in age of onset, years of illness, number of episodes, or duration of current episode between dimensions, there was a significant interaction effect between dimensions and treatment response. Dimension 1 showed a significant improvement in depressive symptoms following treatment with SSRI medication (51.1%) but limited changes following placebo (28.6%). By contrast, Dimension 2 showed comparable improvements to either SSRI (46.9%) or placebo (42.2%) (β = -18.3, 95% CI (-34.3 to -2.3), P = 0.03). Findings from this case-control study indicate that neuroimaging-based markers can help identify the disease-based dimensions that constitute MDD and predict treatment response.

Placebo stimulates neuroplasticity in depression: implications for clinical practice and research

Neither psychological nor neuroscientific investigations have been able to fully explain the paradox that placebo is designed to be inert in randomized controlled trials (RCTs), yet appears to be effective in evaluations of clinical interventions in all fields of medicine and alternative medicine. This article develops the Neuroplasticity Placebo Theory, which posits that neuroplasticity in fronto-limbic areas is the unifying factor in placebo response (seen in RCTs) and placebo effect (seen in clinical interventions) where it is not intended to be inert. Depression is the disorder that has the highest placebo response of any medical condition and has the greatest potential for understanding how placebos work: recent developments in understanding of the pathophysiology of depression suggest that fronto-limbic areas are sensitized in depression which is associated with a particularly strong placebo phenomenon. An innovative linkage is made between diverse areas of the psychology and the translational psychiatry literature to provide supportive evidence for the Neuroplasticity Placebo Theory. This is underpinned by neuro-radiological evidence of fronto-limbic change in the placebo arm of antidepressant trials. If placebo stimulates neuroplasticity in fronto-limbic areas in conditions other than depression - and results in a partially active treatment in other areas of medicine - there are far reaching consequences for the day-to-day use of placebo in clinical practice, the future design of RCTs in all clinical conditions, and existing unwarranted assertions about the efficacy of antidepressant medications. If fronto-limbic neuroplasticity is the common denominator in designating placebo as a partially active treatment, the terms placebo effect and placebo response should be replaced by the single term "placebo treatment."

A common symptom geometry of mood improvement under sertraline and placebo associated with distinct neural patterns

Importance

Understanding the mechanisms of major depressive disorder (MDD) improvement is a key challenge to determine effective personalized treatments.

Objective

To perform a secondary analysis quantifying neural-to-symptom relationships in MDD as a function of antidepressant treatment.

Design

Double blind randomized controlled trial.

Setting

Multicenter.

Participants

Patients with early onset recurrent depression from the public Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC) study.

Interventions

Either sertraline or placebo during 8 weeks (stage 1), and according to response a second line of treatment for 8 additional weeks (stage 2).

Main Outcomes and Measures

To identify a data-driven pattern of symptom variations during these two stages, we performed a Principal Component Analysis (PCA) on the variations of individual items of four clinical scales measuring depression, anxiety, suicidal ideas and manic-like symptoms, resulting in a univariate measure of clinical improvement. We then investigated how initial clinical and neural factors predicted this measure during stage 1. To do so, we extracted resting-state global brain connectivity (GBC) at baseline at the individual level using a whole-brain functional network parcellation. In turn, we computed a linear model for each brain parcel with individual data-driven clinical improvement scores during stage 1 for each group.

Results

192 patients (127 women), age 37.7 years old (standard deviation: 13.5), were included. The first PC (PC1) capturing 20% of clinical variation was similar across treatment groups at stage 1 and stage 2, suggesting a reproducible pattern of symptom improvement. PC1 patients' scores significantly differed according to treatment during stage 1, whereas no difference of response was evidenced between groups with the Clinical Global Impressions (CGI). Baseline GBC correlated to stage 1 PC1 scores in the sertraline, but not in the placebo group.

Conclusions and Relevance

Using data-driven reduction of symptoms scales, we identified a common profile of symptom improvement across placebo and sertraline. However, the neural patterns of baseline that mapped onto symptom improvement distinguished between treatment and placebo. Our results underscore that mapping from data-driven symptom improvement onto neural circuits is vital to detect treatment-responsive neural profiles that may aid in optimal patient selection for future trials.

A Semiparametric Inverse Reinforcement Learning Approach to Characterize Decision Making for Mental Disorders

Major depressive disorder (MDD) is one of the leading causes of disability-adjusted life years. Emerging evidence indicates the presence of reward processing abnormalities in MDD. An important scientific question is whether the abnormalities are due to reduced sensitivity to received rewards or reduced learning ability. Motivated by the probabilistic reward task (PRT) experiment in the EMBARC study, we propose a semiparametric inverse reinforcement learning (RL) approach to characterize the reward-based decision-making of MDD patients. The model assumes that a subject's decision-making process is updated based on a reward prediction error weighted by the subject-specific learning rate. To account for the fact that one favors a decision leading to a potentially high reward, but this decision process is not necessarily linear, we model reward sensitivity with a non-decreasing and nonlinear function. For inference, we estimate the latter via approximation by I-splines and then maximize the joint conditional log-likelihood. We show that the resulting estimators are consistent and asymptotically normal. Through extensive simulation studies, we demonstrate that under different reward-generating distributions, the semiparametric inverse RL outperforms the parametric inverse RL. We apply the proposed method to EMBARC and find that MDD and control groups have similar learning rates but different reward sensitivity functions. There is strong statistical evidence that reward sensitivity functions have nonlinear forms. Using additional brain imaging data in the same study, we find that both reward sensitivity and learning rate are associated with brain activities in the negative affect circuitry under an emotional conflict task.

Influences of resting-state intrinsic functional brain connectivity on the antidepressant treatment response in late-life depression

BACKGROUND

Late-life depression (LLD) is characterized by differences in resting state functional connectivity within and between intrinsic functional networks. This study examined whether clinical improvement to antidepressant medications is associated with pre-randomization functional connectivity in intrinsic brain networks.

METHODS

Participants were 95 elders aged 60 years or older with major depressive disorder. After clinical assessments and baseline MRI, participants were randomized to escitalopram or placebo with a two-to-one allocation for 8 weeks. Non-remitting participants subsequently entered an 8-week trial of open-label bupropion. The main clinical outcome was depression severity measured by MADRS. Resting state functional connectivity was measured between a priori key seeds in the default mode (DMN), cognitive control, and limbic networks.

RESULTS

In primary analyses of blinded data, lower post-treatment MADRS score was associated with higher resting connectivity between: (a) posterior cingulate cortex (PCC) and left medial prefrontal cortex; (b) PCC and subgenual anterior cingulate cortex (ACC); (c) right medial PFC and subgenual ACC; (d) right orbitofrontal cortex and left hippocampus. Lower post-treatment MADRS was further associated with lower connectivity between: (e) the right orbitofrontal cortex and left amygdala; and (f) left dorsolateral PFC and left dorsal ACC. Secondary analyses associated mood improvement on escitalopram with anterior DMN hub connectivity. Exploratory analyses of the bupropion open-label trial associated improvement with subgenual ACC, frontal, and amygdala connectivity.

CONCLUSIONS

Response to antidepressants in LLD is related to connectivity in the DMN, cognitive control and limbic networks. Future work should focus on clinical markers of network connectivity informing prognosis.

REGISTRATION

ClinicalTrials.gov NCT02332291.

Brain Growth Charts for Quantitative Analysis of Pediatric Clinical Brain MRI Scans with Limited Imaging Pathology

Background Clinically acquired brain MRI scans represent a valuable but underused resource for investigating neurodevelopment due to their technical heterogeneity and lack of appropriate controls. These barriers have curtailed retrospective studies of clinical brain MRI scans compared with more costly prospectively acquired research-quality brain MRI scans. Purpose To provide a benchmark for neuroanatomic variability in clinically acquired brain MRI scans with limited imaging pathology (SLIPs) and to evaluate if growth charts from curated clinical MRI scans differed from research-quality MRI scans or were influenced by clinical indication for the scan. Materials and Methods In this secondary analysis of preexisting data, clinical brain MRI SLIPs from an urban pediatric health care system (individuals aged ≤22 years) were scanned across nine 3.0-T MRI scanners. The curation process included manual review of signed radiology reports and automated and manual quality review of images without gross pathology. Global and regional volumetric imaging phenotypes were measured using two image segmentation pipelines, and clinical brain growth charts were quantitatively compared with charts derived from a large set of research controls in the same age range by means of Pearson correlation and age at peak volume. Results The curated clinical data set included 532 patients (277 male; median age, 10 years [IQR, 5-14 years]; age range, 28 days after birth to 22 years) scanned between 2005 and 2020. Clinical brain growth charts were highly correlated with growth charts derived from research data sets (22 studies, 8346 individuals [4947 male]; age range, 152 days after birth to 22 years) in terms of normative developmental trajectories predicted by the models (median r = 0.979). Conclusion The clinical indication of the scans did not significantly bias the output of clinical brain charts. Brain growth charts derived from clinical controls with limited imaging pathology were highly correlated with brain charts from research controls, suggesting the potential of curated clinical MRI scans to supplement research data sets. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Ertl-Wagner and Pai in this issue.

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.

Multi-study evaluation of neuroimaging-based prediction of medication class in mood disorders

Clinicians often face a dilemma in diagnosing bipolar disorder patients with complex symptoms who spend more time in a depressive state than a manic state. The current gold standard for such diagnosis, the Diagnostic and Statistical Manual (DSM), is not objectively grounded in pathophysiology. In such complex cases, relying solely on the DSM may result in misdiagnosis as major depressive disorder (MDD). A biologically-based classification algorithm that can accurately predict treatment response may help patients suffering from mood disorders. Here we used an algorithm to do so using neuroimaging data. We used the neuromark framework to learn a kernel function for support vector machine (SVM) on multiple feature subspaces. The neuromark framework achieves up to 95.45% accuracy, 0.90 sensitivity, and 0.92 specificity in predicting antidepressant (AD) vs. mood stabilizer (MS) response in patients. We incorporated two additional datasets to evaluate the generalizability of our approach. The trained algorithm achieved up to 89% accuracy, 0.88 sensitivity, and 0.89 specificity in predicting the DSM-based diagnosis on these datasets. We also translated the model to distinguish responders to treatment from nonresponders with up to 70% accuracy. This approach reveals multiple salient biomarkers of medication-class of response within mood disorders.

Reward Behavior Disengagement, a Neuroeconomic Model-Based Objective Measure of Reward Pathology in Depression: Findings from the EMBARC Trial

The probabilistic reward task (PRT) has identified reward learning impairments in those with major depressive disorder (MDD), as well as anhedonia-specific reward learning impairments. However, attempts to validate the anhedonia-specific impairments have produced inconsistent findings. Thus, we seek to determine whether the Reward Behavior Disengagement (RBD), our proposed economic augmentation of PRT, differs between MDD participants and controls, and whether there is a level at which RBD is high enough for depressed participants to be considered objectively disengaged. Data were gathered as part of the Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care (EMBARC) study, a double-blind, placebo-controlled clinical trial of antidepressant response. Participants included 195 individuals with moderate to severe MDD (Quick Inventory of Depressive Symptomatology (QIDS-SR) score ≥ 15), not in treatment for depression, and with complete PRT data. Healthy controls (n = 40) had no history of psychiatric illness, a QIDS-SR score < 8, and complete PRT data. Participants with MDD were treated with sertraline or placebo for 8 weeks (stage I of the EMBARC trial). RBD was applied to PRT data using discriminant analysis, and classified MDD participants as reward task engaged (n = 137) or reward task disengaged (n = 58), relative to controls. Reward task engaged/disengaged groups were compared on sociodemographic features, reward-behavior, and sertraline/placebo response (Hamilton Depression Rating Scale scores). Reward task disengaged MDD participants responded only to sertraline, whereas those who were reward task engaged responded to sertraline and placebo (F(1293) = 4.33, p = 0.038). Reward task engaged/disengaged groups did not differ otherwise. RBD was predictive of reward impairment in depressed patients and may have clinical utility in identifying patients who will benefit from antidepressants.

Alterations in resting-state functional activity and connectivity for major depressive disorder appetite and weight disturbance phenotypes

BACKGROUND

Major depressive disorder (MDD) is often accompanied by changes in appetite and weight. Prior task-based functional magnetic resonance imaging (fMRI) findings suggest these MDD phenotypes are associated with altered reward and interoceptive processing.

METHODS

Using resting-state fMRI data, we compared the fractional amplitude of low-frequency fluctuations (fALFF) and seed-based connectivity (SBC) among hyperphagic (n = 77), hypophagic (n = 66), and euphagic (n = 42) MDD groups and a healthy comparison group (n = 38). We examined fALFF and SBC in a mask restricted to reward [nucleus accumbens (NAcc), putamen, caudate, ventral pallidum, and orbitofrontal cortex (OFC)] and interoceptive (anterior insula and hypothalamus) regions and also performed exploratory whole-brain analyses. SBC analyses included as seeds the NAcc and also regions demonstrating group differences in fALFF (i.e. right lateral OFC and right anterior insula). All analyses used threshold-free cluster enhancement.

RESULTS

Mask-restricted analyses revealed stronger fALFF in the right lateral OFC, and weaker fALFF in the right anterior insula, for hyperphagic MDD v. healthy comparison. We also found weaker SBC between the right lateral OFC and left anterior insula for hyperphagic MDD v. healthy comparison. Whole-brain analyses revealed weaker fALFF in the right anterior insula, and stronger SBC between the right lateral OFC and left precentral gyrus, for hyperphagic MDD v. healthy comparison. Findings were no longer significant after controlling for body mass index, which was higher for hyperphagic MDD.

CONCLUSIONS

Our results suggest hyperphagic MDD may be associated with altered activity in and connectivity between interoceptive and reward regions.

Transcriptomic and Macroscopic Architectures of Multimodal Covariance Network Reveal Molecular-Structural-Functional Co-alterations

Human cognition is usually underpinned by intrinsic structure and functional neural co-activation in spatially distributed brain regions. Owing to lacking an effective approach to quantifying the covarying of structure and functional responses, how the structural-functional circuits interact and how genes encode the relationships, to deepen our knowledge of human cognition and disease, are still unclear. Here, we propose a multimodal covariance network (MCN) construction approach to capture interregional covarying of the structural skeleton and transient functional activities for a single individual. We further explored the potential association between brain-wide gene expression patterns and structural-functional covarying in individuals involved in a gambling task and individuals with major depression disorder (MDD), adopting multimodal data from a publicly available human brain transcriptomic atlas and 2 independent cohorts. MCN analysis showed a replicable cortical structural-functional fine map in healthy individuals, and the expression of cognition- and disease phenotype-related genes was found to be spatially correlated with the corresponding MCN differences. Further analysis of cell type-specific signature genes suggests that the excitatory and inhibitory neuron transcriptomic changes could account for most of the observed correlation with task-evoked MCN differences. In contrast, changes in MCN of MDD patients were enriched for biological processes related to synapse function and neuroinflammation in astrocytes, microglia, and neurons, suggesting its promising application in developing targeted therapies for MDD patients. Collectively, these findings confirmed the correlations of MCN-related differences with brain-wide gene expression patterns, which captured genetically validated structural-functional differences at the cellular level in specific cognitive processes and psychiatric patients.

A general framework of nonparametric feature selection in high-dimensional data

Nonparametric feature selection for high-dimensional data is an important and challenging problem in the fields of statistics and machine learning. Most of the existing methods for feature selection focus on parametric or additive models which may suffer from model misspecification. In this paper, we propose a new framework to perform nonparametric feature selection for both regression and classification problems. Under this framework, we learn prediction functions through empirical risk minimization over a reproducing kernel Hilbert space. The space is generated by a novel tensor product kernel, which depends on a set of parameters that determines the importance of the features. Computationally, we minimize the empirical risk with a penalty to estimate the prediction and kernel parameters simultaneously. The solution can be obtained by iteratively solving convex optimization problems. We study the theoretical property of the kernel feature space and prove the oracle selection property and Fisher consistency of our proposed method. Finally, we demonstrate the superior performance of our approach compared to existing methods via extensive simulation studies and applications to two real studies.

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.

Individual Deviations from Normative Electroencephalographic Connectivity Predict Antidepressant Response

Antidepressant medications yield unsatisfactory treatment outcomes in patients with major depressive disorder (MDD) with modest advantages over the placebo. This modest efficacy is partly due to the elusive mechanisms of antidepressant responses and unexplained heterogeneity in patient's response to treatment - the approved antidepressants only benefit a portion of patients, calling for personalized psychiatry based on individual-level prediction of treatment responses. Normative modeling, a framework that quantifies individual deviations in psychopathological dimensions, offers a promising avenue for the personalized treatment for psychiatric disorders. In this study, 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. 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 treatment responses. Our findings and highly generalizable framework advance the neurobiological understanding in the potential pathways of antidepressant responses, enabling more targeted and effective MDD treatment.

Recent innovations in adaptive trial designs: A review of design opportunities in translational research

Clinical trials are constantly evolving in the context of increasingly complex research questions and potentially limited resources. In this review article, we discuss the emergence of "adaptive" clinical trials that allow for the preplanned modification of an ongoing clinical trial based on the accumulating evidence with application across translational research. These modifications may include terminating a trial before completion due to futility or efficacy, re-estimating the needed sample size to ensure adequate power, enriching the target population enrolled in the study, selecting across multiple treatment arms, revising allocation ratios used for randomization, or selecting the most appropriate endpoint. Emerging topics related to borrowing information from historic or supplemental data sources, sequential multiple assignment randomized trials (SMART), master protocol and seamless designs, and phase I dose-finding studies are also presented. Each design element includes a brief overview with an accompanying case study to illustrate the design method in practice. We close with brief discussions relating to the statistical considerations for these contemporary designs.

DeepComBat: A Statistically Motivated, Hyperparameter-Robust, Deep Learning Approach to Harmonization of Neuroimaging Data

Neuroimaging data from multiple batches (i.e. acquisition sites, scanner manufacturer, datasets, etc.) are increasingly necessary to gain new insights into the human brain. However, multi-batch data, as well as extracted radiomic features, exhibit pronounced technical artifacts across batches. These batch effects introduce confounding into the data and can obscure biological effects of interest, decreasing the generalizability and reproducibility of findings. This is especially true when multi-batch data is used alongside complex downstream analysis models, such as machine learning methods. Image harmonization methods seeking to remove these batch effects are important for mitigating these issues; however, significant multivariate batch effects remain in the data following harmonization by current state-of-the-art statistical and deep learning methods. We present DeepCombat, a deep learning harmonization method based on a conditional variational autoencoder architecture and the ComBat harmonization model. DeepCombat learns and removes subject-level batch effects by accounting for the multivariate relationships between features. Additionally, DeepComBat relaxes a number of strong assumptions commonly made by previous deep learning harmonization methods and is empirically robust across a wide range of hyperparameter choices. We apply this method to neuroimaging data from a large cognitive-aging cohort and find that DeepCombat outperforms existing methods, as assessed by a battery of machine learning methods, in removing scanner effects from cortical thickness measurements while preserving biological heterogeneity. Additionally, DeepComBat provides a new perspective for statistically-motivated deep learning harmonization methods.

Confidence in the treatment decision for an individual patient: strategies for sequential assessment

Evolving medical technologies have motivated the development of treatment decision rules (TDRs) that incorporate complex, costly data (e.g., imaging). In clinical practice, we aim for TDRs to be valuable by reducing unnecessary testing while still identifying the best possible treatment for a patient. Regardless of how well any TDR performs in the target population, there is an associated degree of uncertainty about its optimality for a specific patient. In this paper, we aim to quantify, via a confidence measure, the uncertainty in a TDR as patient data from sequential procedures accumulate in real-time. We first propose estimating confidence using the distance of a patient's vector of covariates to a treatment decision boundary, with further distances corresponding to higher certainty. We further propose measuring confidence through the conditional probabilities of ultimately (with all possible information available) being assigned a particular treatment, given that the same treatment is assigned with the patient's currently available data or given the treatment recommendation made using only the currently available patient data. As patient data accumulate, the treatment decision is updated and confidence reassessed until a sufficiently high confidence level is achieved. We present results from simulation studies and illustrate the methods using a motivating example from a depression clinical trial. Recommendations for practical use of the measures are proposed.

Accelerated Brain Aging in Adults With Major Depressive Disorder Predicts Poorer Outcome With Sertraline: Findings From the EMBARC Study

BACKGROUND

Major depressive disorder (MDD) may be associated with accelerated brain aging (higher brain age than chronological age). This report evaluated whether brain age is a clinically useful biomarker by checking its test-retest reliability using magnetic resonance imaging scans acquired 1 week apart and by evaluating the association of accelerated brain aging with symptom severity and antidepressant treatment outcomes.

METHODS

Brain age was estimated in participants of the EMBARC (Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care) study using T1-weighted structural magnetic resonance imaging (MDD n = 290; female n = 192; healthy control participants n = 39; female n = 24). Intraclass correlation coefficient was used for baseline-to-week-1 test-retest reliability. Association of baseline Δ brain age (brain age minus chronological age) with Hamilton Depression Rating Scale-17 and Concise Health Risk Tracking Self-Report domains (impulsivity, suicide propensity [measures: pessimism, helplessness, perceived lack of social support, and despair], and suicidal thoughts) were assessed at baseline (linear regression) and during 8-week-long treatment with either sertraline or placebo (repeated-measures mixed models).

RESULTS

Mean ± SD baseline chronological age, brain age, and Δ brain age were 37.1 ± 13.3, 40.6 ± 13.1, and 3.1 ± 6.1 years in MDD and 37.1 ± 14.7, 38.4 ± 12.9, and 0.6 ± 5.5 years in healthy control groups, respectively. Test-retest reliability was high (intraclass correlation coefficient = 0.98-1.00). Higher baseline Δ brain age in the MDD group was associated with higher baseline impulsivity and suicide propensity and predicted smaller baseline-to-week-8 reductions in Hamilton Depression Rating Scale-17, impulsivity, and suicide propensity with sertraline but not with placebo.

CONCLUSIONS

Brain age is a reliable and potentially clinically useful biomarker that can prognosticate antidepressant treatment outcomes.

BLENDS: Augmentation of Functional Magnetic Resonance Images for Machine Learning Using Anatomically Constrained Warping

Introduction: Data augmentation improves the accuracy of deep learning models when training data are scarce by synthesizing additional samples. This work addresses the lack of validated augmentation methods specific for synthesizing anatomically realistic four-dimensional (4D) (three-dimensional [3D] + time) images for neuroimaging, such as functional magnetic resonance imaging (fMRI), by proposing a new augmentation method. Methods: The proposed method, Brain Library Enrichment through Nonlinear Deformation Synthesis (BLENDS), generates new nonlinear warp fields by combining intersubject coregistration maps, computed using symmetric normalization, through spatial blending. These new warp fields can be applied to existing 4D fMRI to create new augmented images. BLENDS was tested on two neuroimaging problems using de-identified data sets: (1) the prediction of antidepressant response from task-based fMRI (original data set n = 163), and (2) the prediction of Parkinson's disease (PD) symptom trajectory from baseline resting-state fMRI regional homogeneity (original data set n = 43). Results: BLENDS readily generates hundreds of new fMRI from existing images, with unique anatomical variations from the source images, that significantly improve prediction performance. For antidepressant response prediction, augmenting each original image once (2 × the original training data) significantly increased prediction R2 from 0.055 to 0.098 (p < 1 e - 6 ), whereas at 10 × augmentation R2 increased to 0.103. For the prediction of PD trajectory, 10 × augmentation R2 increased from -0.044 to 0.472 (p < 1 e - 6 ). Conclusions: Augmentation of fMRI through nonlinear transformations with BLENDS significantly improved the performance of deep learning models on clinically relevant predictive tasks. This method will help neuroimaging researchers overcome data set size limitations and achieve more accurate predictive models.

Brain Ventricle and Choroid Plexus Morphology as Predictor of Treatment Response: Findings from the EMBARC Study

Recent observations suggest a role of the choroid plexus (CP) and cerebral ventricle volume (CV), to identify treatment resistance of major depressive disorder (MDD). We tested the hypothesis that these markers are associated with clinical improvement in subjects from the EMBARC study, as implied by a recent pilot study. The EMBARC study characterized biological markers in a randomized placebo-controlled trial of sertraline vs. placebo in patients with MDD. Association of baseline volumes of CV, CP and of the corpus callosum (CC) with treatment response after 4 weeks treatment were evaluated. 171 subjects (61 male, 110 female) completed the 4 week assessments; gender, site and age were taken into account for this analyses. As previously reported, no treatment effect of sertraline was observed, but prognostic markers for clinical improvement were identified. Responders (n = 54) had significantly smaller volumes of the CP and lateral ventricles, whereas the volume of mid-anterior and mid-posterior CC was significantly larger compared to non-responders (n = 117). A positive correlation between CV volume and CP volume was observed, whereas a negative correlation between CV volume and both central-anterior and central-posterior parts of the CC emerged. In an exploratory way correlations between enlarged VV and CP volume on the one hand and signs of metabolic syndrome, in particular triglyceride plasma concentrations, were observed. A primary abnormality of CP function in MDD may be associated with increased ventricles, compression of white matter volume, which may affect treatment response speed or outcome. Metabolic markers may mediate this relationship.

Functional additive models for optimizing individualized treatment rules

A novel functional additive model is proposed, which is uniquely modified and constrained to model nonlinear interactions between a treatment indicator and a potentially large number of functional and/or scalar pretreatment covariates. The primary motivation for this approach is to optimize individualized treatment rules based on data from a randomized clinical trial. We generalize functional additive regression models by incorporating treatment-specific components into additive effect components. A structural constraint is imposed on the treatment-specific components in order to provide a class of additive models with main effects and interaction effects that are orthogonal to each other. If primary interest is in the interaction between treatment and the covariates, as is generally the case when optimizing individualized treatment rules, we can thereby circumvent the need to estimate the main effects of the covariates, obviating the need to specify their form and thus avoiding the issue of model misspecification. The methods are illustrated with data from a depression clinical trial with electroencephalogram functional data as patients' pretreatment covariates.

Data driven clusters derived from resting state functional connectivity: Findings from the EMBARC study

BACKGROUND

To address the clinical heterogeneity of Major Depressive Disorder (MDD), this investigation determined whether resting state functional magnetic resonance imaging (fMRI) could be deployed to identify circuit based homogeneous subgroups, and whether subgroups identified show differential treatment outcomes.

METHODS

Pretreatment resting state fMRIs obtained from 278 outpatients with nonpsychotic MDD from Establishing Moderators and Biosignatures of Antidepressant Response for Clinical Care for Depression Study were used to create data-driven subgroups using CLICK clustering. These subgroups were then compared using baseline clinical data, as well as baseline-to-week 8 changes in depression severity measured using the 17-item Hamilton Rating Scale for Depression (HAMD17) and response/remission rates by treatment group.

RESULTS

Three subgroups were identified. Cluster-1 was characterized by overallhyperconnectivity coupled with profound hypoconnectivity between the supramarginal gyrus (executive control network; ECN) and the superior frontal cortex (dorsal attention network; DAN). Cluster-2 was characterized by overall hypoconnectivity coupled with hyperconnectivity between supramarginal gyrus (ECN) and superior frontal cortex (DAN). Cluster-3 showed hypoconnectivity, especially profound between the angular cortex (default mode network; DMN) and middle frontal cortex (ECN). While baseline clinical measures did not differentiate the three clusters, Cluster-3 had the remission rate (51.6%) compared to Cluster-1 and Cluster-2 (32.7% and 31.9%) when treated with sertraline.

LIMITATIONS

Due to the exploratory nature of these analyses, there were no adjustments for multiple comparisons.

CONCLUSIONS

Baseline functional connectivity can be used to subgroup patients with MDD that differ in acute phase treatment outcomes. Measures of connectivity may address the heterogeneity of MDD.

Symptoms that remain after depression treatment in patients with coronary heart disease

OBJECTIVE

Symptoms which commonly remain after treatment for major depression increase the risk of relapse and recurrence in medically well patients. The same symptoms predict major adverse cardiac events in observational studies of patients with coronary heart disease (CHD). The purpose of this study was to determine the prevalence and predictors of residual depression symptoms in depressed patients with CHD-.

METHODS

Beck Depression Inventory-II data from two randomized clinical trials and an uncontrolled treatment study of depression in patients with CHD were combined to determine the prevalence and predictors of residual symptoms.

RESULTS

Loss of energy, loss of pleasure, loss of interest, fatigue, and difficulty concentrating were the five most common residual symptoms in all three studies. They are also among the most common residual symptoms in medically well patients who are treated for depression. The severity of pre-treatment anxiety predicted the post-treatment persistence of all these symptoms except for loss of energy.

CONCLUSIONS

The most common post-treatment residual symptoms found in this study of patients with coronary heart disease and comorbid major depression are the same as those that have been reported in previous studies of medically-well depressed patients. This suggests that they may be resistant to standard depression treatments across diverse patient populations. More effective treatments for these symptoms are needed.

Multi-omics data integration methods and their applications in psychiatric disorders

To study mental illness and health, in the past researchers have often broken down their complexity into individual subsystems (e.g., genomics, transcriptomics, proteomics, clinical data) and explored the components independently. Technological advancements and decreasing costs of high throughput sequencing has led to an unprecedented increase in data generation. Furthermore, over the years it has become increasingly clear that these subsystems do not act in isolation but instead interact with each other to drive mental illness and health. Consequently, individual subsystems are now analysed jointly to promote a holistic understanding of the underlying biological complexity of health and disease. Complementing the increasing data availability, current research is geared towards developing novel methods that can efficiently combine the information rich multi-omics data to discover biologically meaningful biomarkers for diagnosis, treatment, and prognosis. However, clinical translation of the research is still challenging. In this review, we summarise conventional and state-of-the-art statistical and machine learning approaches for discovery of biomarker, diagnosis, as well as outcome and treatment response prediction through integrating multi-omics and clinical data. In addition, we describe the role of biological model systems and in silico multi-omics model designs in clinical translation of psychiatric research from bench to bedside. Finally, we discuss the current challenges and explore the application of multi-omics integration in future psychiatric research. The review provides a structured overview and latest updates in the field of multi-omics in psychiatry.

AI-based dimensional neuroimaging system for characterizing heterogeneity in brain structure and function in major depressive disorder: COORDINATE-MDD consortium design and rationale

BACKGROUND

Efforts to develop neuroimaging-based biomarkers in major depressive disorder (MDD), at the individual level, have been limited to date. As diagnostic criteria are currently symptom-based, MDD is conceptualized as a disorder rather than a disease with a known etiology; further, neural measures are often confounded by medication status and heterogeneous symptom states.

METHODS

We describe a consortium to quantify neuroanatomical and neurofunctional heterogeneity via the dimensions of novel multivariate coordinate system (COORDINATE-MDD). Utilizing imaging harmonization and machine learning methods in a large cohort of medication-free, deeply phenotyped MDD participants, patterns of brain alteration are defined in replicable and neurobiologically-based dimensions and offer the potential to predict treatment response at the individual level. International datasets are being shared from multi-ethnic community populations, first episode and recurrent MDD, which are medication-free, in a current depressive episode with prospective longitudinal treatment outcomes and in remission. Neuroimaging data consist of de-identified, individual, structural MRI and resting-state functional MRI with additional positron emission tomography (PET) data at specific sites. State-of-the-art analytic methods include automated image processing for extraction of anatomical and functional imaging variables, statistical harmonization of imaging variables to account for site and scanner variations, and semi-supervised machine learning methods that identify dominant patterns associated with MDD from neural structure and function in healthy participants.

RESULTS

We are applying an iterative process by defining the neural dimensions that characterise deeply phenotyped samples and then testing the dimensions in novel samples to assess specificity and reliability. Crucially, we aim to use machine learning methods to identify novel predictors of treatment response based on prospective longitudinal treatment outcome data, and we can externally validate the dimensions in fully independent sites.

CONCLUSION

We describe the consortium, imaging protocols and analytics using preliminary results. Our findings thus far demonstrate how datasets across many sites can be harmonized and constructively pooled to enable execution of this large-scale project.

The Precision in Psychiatry (PIP) study: Testing an internet-based methodology for accelerating research in treatment prediction and personalisation

BACKGROUND

Evidence-based treatments for depression exist but not all patients benefit from them. Efforts to develop predictive models that can assist clinicians in allocating treatments are ongoing, but there are major issues with acquiring the volume and breadth of data needed to train these models. We examined the feasibility, tolerability, patient characteristics, and data quality of a novel protocol for internet-based treatment research in psychiatry that may help advance this field.

METHODS

A fully internet-based protocol was used to gather repeated observational data from patient cohorts receiving internet-based cognitive behavioural therapy (iCBT) (N = 600) or antidepressant medication treatment (N = 110). At baseline, participants provided > 600 data points of self-report data, spanning socio-demographics, lifestyle, physical health, clinical and other psychological variables and completed 4 cognitive tests. They were followed weekly and completed another detailed clinical and cognitive assessment at week 4. In this paper, we describe our study design, the demographic and clinical characteristics of participants, their treatment adherence, study retention and compliance, the quality of the data gathered, and qualitative feedback from patients on study design and implementation.

RESULTS

Participant retention was 92% at week 3 and 84% for the final assessment. The relatively short study duration of 4 weeks was sufficient to reveal early treatment effects; there were significant reductions in 11 transdiagnostic psychiatric symptoms assessed, with the largest improvement seen for depression. Most participants (66%) reported being distracted at some point during the study, 11% failed 1 or more attention checks and 3% consumed an intoxicating substance. Data quality was nonetheless high, with near perfect 4-week test retest reliability for self-reported height (ICC = 0.97).

CONCLUSIONS

An internet-based methodology can be used efficiently to gather large amounts of detailed patient data during iCBT and antidepressant treatment. Recruitment was rapid, retention was relatively high and data quality was good. This paper provides a template methodology for future internet-based treatment studies, showing that such an approach facilitates data collection at a scale required for machine learning and other data-intensive methods that hope to deliver algorithmic tools that can aid clinical decision-making in psychiatry.

Biomarkers in Psychiatric Drug Development: From Precision Medicine to Novel Therapeutics

Burden of psychiatric disorders is compounded by their wide prevalence as well as the limited efficacy of currently available treatments and the current approaches for prescribing these treatments. The selection of treatments continues to be subjective and often results in a trial-and-error approach. Emerging research suggests that biological markers (or biomarkers) can be used to develop precision medicine approaches for psychiatric disorders. Furthermore, the biomarkers also promise to elucidate the underlying pathophysiological mechanisms which in turn can be used to develop novel therapeutic treatments. In this chapter we have focused on mood disorders and reviewed studies on electroencephalography (EEG), magnetic resonance imaging (MRI), and blood-based biomarkers that can guide selection of one treatment versus another (treatment-selection biomarker) as well as biomarkers that can guide the development of novel therapeutics. These studies suggest that the use of objective physiological data is poised to alter the landscape of psychiatric diagnosis and treatment. However, practical and economic barriers remain as major hurdles. The key to finding such translational diagnostic and therapeutic biomarkers is a better understanding of the underlying pathophysiology, and despite the tremendous advances in neuroscience, it is clear there remains much left to be elucidated.

A Single Index Model for Longitudinal Outcomes to Optimize Individual Treatment Decision Rules

A pressing challenge in medical research is to identify optimal treatments for individual patients. This is particularly challenging in mental health settings where mean responses are often similar across multiple treatments. For example, the mean longitudinal trajectories for patients treated with an active drug and placebo may be very similar but different treatments may exhibit distinctly different individual trajectory shapes. Most precision medicine approaches using longitudinal data often ignore information from the longitudinal data structure. This paper investigates a powerful precision medicine approach by examining the impact of baseline covariates on longitudinal outcome trajectories to guide treatment decisions instead of traditional scalar outcome measures derived from longitudinal data, such as a change score. We introduce a method of estimating "biosignatures" defined as linear combinations of baseline characteristics (i.e., a single index) that optimally separate longitudinal trajectories among different treatment groups. The criterion used is to maximize the Kullback-Leibler Divergence between different treatment outcome distributions. The approach is illustrated via simulation studies and a depression clinical trial. The approach is also contrasted with more traditional methods and compares performance in the presence of missing data.

Toward biophysical markers of depression vulnerability

A major difficulty with treating psychiatric disorders is their heterogeneity: different neural causes can lead to the same phenotype. To address this, we propose describing the underlying pathophysiology in terms of interpretable, biophysical parameters of a neural model derived from the electroencephalogram. We analyzed data from a small patient cohort of patients with depression and controls. Using DCM, we constructed biophysical models that describe neural dynamics in a cortical network activated during a task that is used to assess depression state. We show that biophysical model parameters are biomarkers, that is, variables that allow subtyping of depression at a biological level. They yield a low dimensional, interpretable feature space that allowed description of differences between individual patients with depressive symptoms. They could capture internal heterogeneity/variance of depression state and achieve significantly better classification than commonly used EEG features. Our work is a proof of concept that a combination of biophysical models and machine learning may outperform earlier approaches based on classical statistics and raw brain data.

Generalizability of treatment outcome prediction in major depressive disorder using structural MRI: A NeuroPharm study

Brain morphology has been suggested to be predictive of drug treatment outcome in major depressive disorders (MDD). The current study aims at evaluating the performance of pretreatment structural brain magnetic resonance imaging (MRI) measures in predicting the outcome of a drug treatment of MDD in a large single-site cohort, and, importantly, to assess the generalizability of these findings in an independent cohort. The random forest, boosted trees, support vector machines and elastic net classifiers were evaluated in predicting treatment response and remission following an eight week drug treatment of MDD using structural brain measures derived with FastSurfer (FreeSurfer). Models were trained and tested within a nested cross-validation framework using the NeuroPharm dataset (n = 79, treatment: escitalopram); their generalizability was assessed using an independent clinical dataset, EMBARC (n = 64, treatment: sertraline). Prediction of antidepressant treatment response in the Neuropharm cohort was statistically significant for the random forest (p = 0.048), whereas none of the models could significantly predict remission. Furthermore, none of the models trained using the entire NeuroPharm dataset could significantly predict treatment outcome in the EMBARC dataset. Although our primary findings in the NeuroPharm cohort support some, but limited value in using pretreatment structural brain MRI to predict drug treatment outcome in MDD, the models did not generalize to an independent cohort suggesting limited clinical applicability. This study emphasizes the importance of assessing model generalizability for establishing clinical utility.

Computational approaches to treatment response prediction in major depression using brain activity and behavioral data: A systematic review

Major depressive disorder is a heterogeneous diagnostic category with multiple available treatments. With the goal of optimizing treatment selection, researchers are developing computational models that attempt to predict treatment response based on various pretreatment measures. In this paper, we review studies that use brain activity data to predict treatment response. Our aim is to highlight and clarify important methodological differences between various studies that relate to the incorporation of domain knowledge, specifically within two approaches delineated as data-driven and theory-driven. We argue that theory-driven generative modeling, which explicitly models information processing in the brain and thus can capture disease mechanisms, is a promising emerging approach that is only beginning to be utilized in treatment response prediction. The predictors extracted via such models could improve interpretability, which is critical for clinical decision-making. We also identify several methodological limitations across the reviewed studies and provide suggestions for addressing them. Namely, we consider problems with dichotomizing treatment outcomes, the importance of investigating more than one treatment in a given study for differential treatment response predictions, the need for a patient-centered approach for defining treatment outcomes, and finally, the use of internal and external validation methods for improving model generalizability.