Single-subject anxiety treatment outcome prediction using functional neuroimaging

A novel approach to anxiety level prediction using small sets of judgment and survey variables

Anxiety, a condition characterized by intense fear and persistent worry, affects millions each year and, when severe, is distressing and functionally impairing. Numerous machine learning frameworks have been developed and tested to predict features of anxiety and anxiety traits. This study extended these approaches by using a small set of interpretable judgment variables (n = 15) and contextual variables (demographics, perceived loneliness, COVID-19 history) to (1) understand the relationships between these variables and (2) develop a framework to predict anxiety levels [derived from the State Trait Anxiety Inventory (STAI)]. This set of 15 judgment variables, including loss aversion and risk aversion, models biases in reward/aversion judgments extracted from an unsupervised, short (2-3 min) picture rating task (using the International Affective Picture System) that can be completed on a smartphone. The study cohort consisted of 3476 de-identified adult participants from across the United States who were recruited using an email survey database. Using a balanced Random Forest approach with these judgment and contextual variables, STAI-derived anxiety levels were predicted with up to 81% accuracy and 0.71 AUC ROC. Normalized Gini scores showed that the most important predictors (age, loneliness, household income, employment status) contributed a total of 29-31% of the cumulative relative importance and up to 61% was contributed by judgment variables. Mediation/moderation statistics revealed that the interactions between judgment and contextual variables appears to be important for accurately predicting anxiety levels. Median shifts in judgment variables described a behavioral profile for individuals with higher anxiety levels that was characterized by less resilience, more avoidance, and more indifference behavior. This study supports the hypothesis that distinct constellations of 15 interpretable judgment variables, along with contextual variables, could yield an efficient and highly scalable system for mental health assessment. These results contribute to our understanding of underlying psychological processes that are necessary to characterize what causes variance in anxiety conditions and its behaviors, which can impact treatment development and efficacy.

Shared and distinctive neural substrates of generalized anxiety disorder with or without depressive symptoms and their roles in prognostic prediction

BACKGROUND

The neurophysiological mechanisms underlying generalized anxiety disorder (GAD) with or without depressive symptoms are obscure. This study aimed to uncover them and assess their predictive value for treatment response.

METHODS

We enrolled 98 GAD patients [58 (age: 33.22 ± 10.23 years old, males/females: 25/33) with and 40 (age: 33.65 ± 10.49 years old, males/females: 14/26) without depressive symptoms] and 54 healthy controls (HCs, age: 32.28 ± 10.56 years old, males/females: 21/33). Patients underwent clinical assessments and resting-state functional MRI (rs-fMRI) at baseline and after 4-week treatment with paroxetine, while HCs underwent rs-fMRI at baseline only. Regional homogeneity (ReHo) was employed to measure intrinsic brain activity. We compared ReHo in patients to HCs and examined changes in ReHo within the patient groups after treatment. Support vector regression (SVR) analyses were conducted separately for each patient group to predict the patients' treatment response.

RESULTS

Both patient groups exhibited higher ReHo in the middle/superior frontal gyrus decreased ReHo in different brain regions compared to HCs. Furthermore, differences in ReHo were detected between the two patient groups. After treatment, the patient groups displayed distinct ReHo change patterns. By utilizing SVR based on baseline abnormal ReHo, we effectively predicted treatment response of patients (p-value for correlation < 0.05).

LIMITATIONS

The dropout rate was relatively high.

CONCLUSIONS

This study identified shared and unique neural substrates in GAD patients with or without depressive symptoms, potentially serving as biomarkers for treatment response prediction. Comorbid depressive symptoms were associated with differences in disease manifestation and treatment response compared to pure GAD cases.

Individual cognitive therapy reduces frontal-thalamic resting-state functional connectivity in social anxiety disorder

Introduction

Previous neuroimaging studies in social anxiety disorders (SAD) have reported potential neural predictors of cognitive behavioral therapy (CBT)-related brain changes. However, several meta-analyses have demonstrated that cognitive therapy (CT) was superior to traditional exposure-based CBT for SAD.

Objective

To explore resting-state functional connectivity (rsFC) to evaluate the response to individual CT for SAD patients.

Methods

Twenty SAD patients who attended 16-week individual CT were scanned pre- and post-therapy along with twenty healthy controls (HCs). The severity of social anxiety was assessed with the Liebowitz Social Anxiety Scale (LSAS). Multi-voxel pattern analysis (MVPA) was performed on the pre-CT data to extract regions associated with a change in LSAS (∆LSAS). Group comparisons of the seed-based rsFC analysis were performed between the HCs and pre-CT patients and between the pre-and post-CT patients.

Results

MVPA-based regression analysis revealed that rsFC between the left thalamus and the frontal pole/inferior frontal gyrus was significantly correlated with ∆LSAS (adjusted R2 = 0.65; p = 0.00002). Compared with HCs, the pre-CT patients had higher rsFCs between the thalamus and temporal pole and between the thalamus and superior/middle temporal gyrus/planum temporale (p < 0.05). The rsFC between the thalamus and the frontal pole decreased post-CT (p < 0.05).

Conclusion

SAD patients had significant rsFC between the thalamus and temporal pole, superior/middle temporal gyrus, and planum temporale, which may be indicators of extreme anxiety in social situations. In addition, rsFC between the thalamus and the frontal pole may be a neuromarker for the effectiveness of individual CT.

Can Brain Activities of Guided Metaphorical Restructuring Predict Therapeutic Changes?

The present study examined whether brain activities of metaphorical restructuring could predict improvements in emotion and general self-efficacy (GSES). Sixty-two anxious graduates were randomly assigned to either the metaphor group (n = 31) or the literal group (n = 31). After completing the pretest (T1), the participants were first presented with micro-counseling dialogues (MCD) to guide metaphorical or literal restructuring, and their functional brain activities were simultaneously recorded. They then completed the posttest (T2) and 1 week's follow-up (T3). It was found that (1) compared with the literal group, the metaphor group had more insightful experiences, a greater increase in positive affect and GSES at T2, and a greater decrease in psychological distress at T2 and T3; (2) the metaphor group showed a greater activation in the left inferior frontal gyrus (IFG) and bilateral temporal gyrus, and further activation in the left hippocampus positively predicted T2 GSES scores while that in the IFG and left hippocampus positively predicted the reduction slope of distress over the three time points. One important limitation is that the results should be interpreted with caution when generalizing to clinical anxiety samples due to the participants were graduate students with anxiety symptoms rather than clinical sample. These results indicated that metaphor restructuring produced greater symptom improvements, and activation in the hippocampus and IFG could predict these symptom improvements. This suggests that the activation of the two regions during the restructuring intervention may be a neural marker for symptom improvements.

Predicting non-improvement of symptoms in daily mental healthcare practice using routinely collected patient-level data: a machine learning approach

Objectives

Anxiety and mood disorders greatly affect the quality of life for individuals worldwide. A substantial proportion of patients do not sufficiently improve during evidence-based treatments in mental healthcare. It remains challenging to predict which patients will or will not benefit. Moreover, the limited research available on predictors of treatment outcomes comes from efficacy RCTs with strict selection criteria which may limit generalizability to a real-world context. The current study evaluates the performance of different machine learning (ML) models in predicting non-improvement in an observational sample of patients treated in routine specialized mental healthcare.

Methods

In the current longitudinal exploratory prediction study diagnosis-related, sociodemographic, clinical and routinely collected patient-reported quantitative outcome measures were acquired during treatment as usual of 755 patients with a primary anxiety, depressive, obsessive compulsive or trauma-related disorder in a specialized outpatient mental healthcare center. ML algorithms were trained to predict non-response (< 0.5 standard deviation improvement) in symptomatic distress 6 months after baseline. Different models were trained, including models with and without early change scores in psychopathology and well-being and models with a trimmed set of predictor variables. Performance of trained models was evaluated in a hold-out sample (30%) as a proxy for unseen data.

Results

ML models without early change scores performed poorly in predicting six-month non-response in the hold-out sample with Area Under the Curves (AUCs) < 0.63. Including early change scores slightly improved the models' performance (AUC range: 0.68-0.73). Computationally-intensive ML models did not significantly outperform logistic regression (AUC: 0.69). Reduced prediction models performed similar to the full prediction models in both the models without (AUC: 0.58-0.62 vs. 0.58-0.63) and models with early change scores (AUC: 0.69-0.73 vs. 0.68-0.71). Across different ML algorithms, early change scores in psychopathology and well-being consistently emerged as important predictors for non-improvement.

Conclusion

Accurately predicting treatment outcomes in a mental healthcare context remains challenging. While advanced ML algorithms offer flexibility, they showed limited additional value compared to traditional logistic regression in this study. The current study confirmed the importance of taking early change scores in both psychopathology and well-being into account for predicting longer-term outcomes in symptomatic distress.

Neural Predictors of Improvement With Cognitive Behavioral Therapy for Adolescents With Depression: An Examination of Reward Responsiveness and Emotion Regulation

Earlier depression onsets are associated with more debilitating courses and poorer life quality, highlighting the importance of effective early intervention. Many youths fail to improve with evidence-based treatments for depression, likely due in part to heterogeneity within the disorder. Multi-method assessment of individual differences in positive and negative emotion processing could improve predictions of treatment outcomes. The current study examined self-report and neurophysiological measures of reward responsiveness and emotion regulation as predictors of response to cognitive-behavioral therapy (CBT). Adolescents (14-18 years) with depression (N = 70) completed monetary reward and emotion regulation tasks while electroencephalogram (EEG) was recorded, and self-report measures of reward responsiveness, emotion regulation, and depressive symptoms at intake. Adolescents then completed a 16-session group CBT program, with depressive symptoms and clinician-rated improvement assessed across treatment. Lower reward positivity amplitudes, reflecting reduced neural reward responsiveness, predicted lower depressive symptoms with treatment. Larger late positive potential residuals during reappraisal, potentially reflecting difficulty with emotion regulation, predicted greater clinician-rated improvement. Self-report measures were not significant predictors. Results support the clinical utility of EEG measures, with impairments in positive and negative emotion processing predicting greater change with interventions that target these processes.

Pre-treatment amygdala activation and habituation predict symptom change in post-traumatic stress disorder

Trauma-focused psychotherapy approaches are the first-line treatment option for post-traumatic stress disorder (PTSD); however, up to a third of patients remain symptomatic even after completion of the treatment. Predicting which patients will respond to a given treatment option would support personalized treatments and improve the efficiency of healthcare systems. Although previous neuroimaging studies have examined possible pre-treatment predictors of response to treatment, the findings have been somewhat inconsistent, and no other study has examined habituation to stimuli as a predictor. In this study, 16 treatment-seeking adults (M_Age = 43.63, n = 10 women) with a primary diagnosis of PTSD passively viewed pictures of emotional facial expressions during functional magnetic resonance imaging (fMRI). After scanning, participants rated facial expressions on both valence and arousal. Participants then completed eight weekly sessions of prolonged exposure (PE) therapy. PTSD symptom severity was measured before and after treatment. Overall, participants showed symptomatic improvement with PE. Consistent with hypotheses, lesser activation in the amygdala and greater activation in the ventromedial prefrontal cortex during the presentation of fearful vs. happy facial expressions, as well as a greater decline in amygdala activation across blocks of fearful facial expressions at baseline, were associated with greater reduction of PTSD symptoms. Given that the repeated presentation of emotional material underlies PE, changes in brain responses with repeated stimulus presentations warrant further studies as potential predictors of response to exposure therapies.

Candidate biomarkers in psychiatric disorders: state of the field

The field of psychiatry is hampered by a lack of robust, reliable and valid biomarkers that can aid in objectively diagnosing patients and providing individualized treatment recommendations. Here we review and critically evaluate the evidence for the most promising biomarkers in the psychiatric neuroscience literature for autism spectrum disorder, schizophrenia, anxiety disorders and post-traumatic stress disorder, major depression and bipolar disorder, and substance use disorders. Candidate biomarkers reviewed include various neuroimaging, genetic, molecular and peripheral assays, for the purposes of determining susceptibility or presence of illness, and predicting treatment response or safety. This review highlights a critical gap in the biomarker validation process. An enormous societal investment over the past 50 years has identified numerous candidate biomarkers. However, to date, the overwhelming majority of these measures have not been proven sufficiently reliable, valid and useful to be adopted clinically. It is time to consider whether strategic investments might break this impasse, focusing on a limited number of promising candidates to advance through a process of definitive testing for a specific indication. Some promising candidates for definitive testing include the N170 signal, an event-related brain potential measured using electroencephalography, for subgroup identification within autism spectrum disorder; striatal resting-state functional magnetic resonance imaging (fMRI) measures, such as the striatal connectivity index (SCI) and the functional striatal abnormalities (FSA) index, for prediction of treatment response in schizophrenia; error-related negativity (ERN), an electrophysiological index, for prediction of first onset of generalized anxiety disorder, and resting-state and structural brain connectomic measures for prediction of treatment response in social anxiety disorder. Alternate forms of classification may be useful for conceptualizing and testing potential biomarkers. Collaborative efforts allowing the inclusion of biosystems beyond genetics and neuroimaging are needed, and online remote acquisition of selected measures in a naturalistic setting using mobile health tools may significantly advance the field. Setting specific benchmarks for well-defined target application, along with development of appropriate funding and partnership mechanisms, would also be crucial. Finally, it should never be forgotten that, for a biomarker to be actionable, it will need to be clinically predictive at the individual level and viable in clinical settings.

Common and exclusive spontaneous neural activity patterns underlying pure generalized anxiety disorder and comorbid generalized anxiety disorder and depression

BACKGROUND

This study aimed to identify common and exclusive neural substrates underlying pure generalized anxiety disorder (GAD, G0) and comorbid GAD and depression (G1), assess whether they could assist in diagnosis and prediction of treatment response, and determine whether comorbid depression in GAD patients would change their neural plasticity.

METHODS

A longitudinal study was conducted, involving 98 patients (40 in the G0 group and 58 in the G1 group) and 54 healthy controls (HCs). The fractional amplitude of low-frequency fluctuations (fALFF), support vector machine, and support vector regression were employed.

RESULTS

The shared neural underpinnings across the two subtypes of GAD were hyperactivity in the right cerebellar Crus II and inferior temporal gyrus and hypoactivity in the right postcentral gyrus. The G1 group showed hypoactivity in the frontal gyrus, compared with HCs, and hyperactivity in the middle temporal gyrus, compared with the G0 group or HCs. These alterations could aid in diagnosis and the prediction of treatment response with high accuracy. After treatment, both the G1 and G0 groups showed higher fALFF than those before treatment but were located in different brain regions.

LIMITATIONS

The study was performed in a single center and subjects showed a fairly homogeneous ethnicity.

CONCLUSIONS

Common and exclusive neural substrates underlying the two subtypes of GAD were identified, which could assist in diagnosis and the prediction of treatment response. Pharmacotherapy for the two subtypes of GAD recruited different pathways, suggesting that comorbid depression in GAD patients would change their neural plasticity.

Recent advances in psychoradiology

Psychiatry, as a field, lacks objective markers for diagnosis, progression, treatment planning, and prognosis, in part due to difficulties studying the brain in vivo, and diagnoses are based on self-reported symptoms and observation of patient behavior and cognition. Rapid advances in brain imaging techniques allow clinical investigators to noninvasively quantify brain features at the structural, functional, and molecular levels. Psychoradiology is an emerging discipline at the intersection of psychiatry and radiology. Psychoradiology applies medical imaging technologies to psychiatry and promises not only to improve insight into structural and functional brain abnormalities in patients with psychiatric disorders but also to have potential clinical utility. We searched for representative studies related to recent advances in psychoradiology through May 1, 2022, and conducted a selective review of 165 references, including 75 research articles. We summarize the novel dynamic imaging processing methods to model brain networks and present imaging genetics studies that reveal the relationship between various neuroimaging endophenotypes and genetic markers in psychiatric disorders. Furthermore, we survey recent advances in psychoradiology, with a focus on future psychiatric diagnostic approaches with dimensional analysis and a shift from group-level to individualized analysis. Finally, we examine the application of machine learning in psychoradiology studies and the potential of a novel option for brain stimulation treatment based on psychoradiological findings in precision medicine. Here, we provide a summary of recent advances in psychoradiology research, and we hope this review will help guide the practice of psychoradiology in the scientific and clinical fields.

ERPs in Children and Adolescents with Generalized Anxiety Disorder: Before and after an Intervention Program

According to DSM 5, generalized anxiety disorder (GAD) is characterized by excessive, uncontrollable worry about various topics that occupies the majority of the subject’s time for a period of at least six months. The aforementioned state causes distress and/or functional impairments. This paper presents the outcomes of a pilot study that evaluated the implementation of cognitive behavioral therapy (CBT) and CBT with an SSRIs intervention program. The participants comprised 16 children and adolescents with GAD (8 males and 8 females) matched with 16 typically developing peers (8 males and 8 females) aged from 10 to 16 years old (M = 12.56 SD = 2.18). Baseline assessment consisted of event related potentials (ERPs), which indicated that participants with GAD presented cognitive deficits in attention and memory, as they exhibited longer P300 latencies. Following treatment with the CBT program and/or medication, children and adolescents with GAD did not present statistically significantly longer P300 latencies and reaction times in comparison to the control group. Lastly, children and adolescents who followed the CBT program or the CBT program with psychopharmacological assistance did not reveal statistically significant differences in 13 out of 15 topographic brain areas and in reaction time.

A Machine Learning Approach for Predicting Non-Suicidal Self-Injury in Young Adults

Artificial intelligence techniques were explored to assess the ability to anticipate self-harming behaviour in the mental health context using a database collected by an app previously designed to record the emotional states and activities of a group of subjects exhibiting self-harm. Specifically, the Leave-One-Subject-Out technique was used to train classification trees with a maximum of five splits. The results show an accuracy of 84.78%, a sensitivity of 64.64% and a specificity of 85.53%. In addition, positive and negative predictive values were also obtained, with results of 14.48% and 98.47%, respectively. These results are in line with those reported in previous work using a multilevel mixed-effect regression analysis. The combination of apps and AI techniques is a powerful way to improve the tools to accompany and support the care and treatment of patients with this type of behaviour. These studies also guide the improvement of apps on the user side, simplifying and collecting more meaningful data, and on the therapist side, progressing in pathology treatments. Traditional therapy involves observing and reconstructing what had happened before episodes once they have occurred. This new generation of tools will make it possible to monitor the pathology more closely and to act preventively.

Neurocircuitry of Treatment in Anxiety Disorders

Background:

Methods:

Results:

Conclusions:

Predicting the naturalistic course in anxiety disorders using clinical and biological markers: a machine learning approach

BACKGROUND

Disease trajectories of patients with anxiety disorders are highly diverse and approximately 60% remain chronically ill. The ability to predict disease course in individual patients would enable personalized management of these patients. This study aimed to predict recovery from anxiety disorders within 2 years applying a machine learning approach.

METHODS

In total, 887 patients with anxiety disorders (panic disorder, generalized anxiety disorder, agoraphobia, or social phobia) were selected from a naturalistic cohort study. A wide array of baseline predictors (N = 569) from five domains (clinical, psychological, sociodemographic, biological, lifestyle) were used to predict recovery from anxiety disorders and recovery from all common mental disorders (CMDs: anxiety disorders, major depressive disorder, dysthymia, or alcohol dependency) at 2-year follow-up using random forest classifiers (RFCs).

RESULTS

At follow-up, 484 patients (54.6%) had recovered from anxiety disorders. RFCs achieved a cross-validated area-under-the-receiving-operator-characteristic-curve (AUC) of 0.67 when using the combination of all predictor domains (sensitivity: 62.0%, specificity 62.8%) for predicting recovery from anxiety disorders. Classification of recovery from CMDs yielded an AUC of 0.70 (sensitivity: 64.6%, specificity: 62.3%) when using all domains. In both cases, the clinical domain alone provided comparable performances. Feature analysis showed that prediction of recovery from anxiety disorders was primarily driven by anxiety features, whereas recovery from CMDs was primarily driven by depression features.

CONCLUSIONS

The current study showed moderate performance in predicting recovery from anxiety disorders over a 2-year follow-up for individual patients and indicates that anxiety features are most indicative for anxiety improvement and depression features for improvement in general.

Clinical predictors of treatment response towards exposure therapy in virtuo in spider phobia: A machine learning and external cross-validation approach

While being highly effective on average, exposure-based treatments are not equally effective in all patients. The a priori identification of patients with a poor prognosis may enable the application of more personalized psychotherapeutic interventions. We aimed at identifying sociodemographic and clinical pre-treatment predictors for treatment response in spider phobia (SP). N = 174 patients with SP underwent a highly standardized virtual reality exposure therapy (VRET) at two independent sites. Analyses on group-level were used to test the efficacy. We applied a state-of-the-art machine learning protocol (Random Forests) to evaluate the predictive utility of clinical and sociodemographic predictors for a priori identification of individual treatment response assessed directly after treatment and at 6-month follow-up. The reliability and generalizability of predictive models was tested via external cross-validation. Our study shows that one session of VRET is highly effective on a group-level and is among the first to reveal long-term stability of this treatment effect. Individual short-term symptom reductions could be predicted above chance, but accuracies dropped to non-significance in our between-site prediction and for predictions of long-term outcomes. With performance metrics hardly exceeding chance level and the lack of generalizability in the employed between-site replication approach, our study suggests limited clinical utility of clinical and sociodemographic predictors. Predictive models including multimodal predictors may be more promising.

Reappraisal-related neural predictors of treatment response to cognitive behavior therapy for post-traumatic stress disorder

BACKGROUND

Although trauma-focused cognitive behavior therapy (TF-CBT) is the frontline treatment for post-traumatic stress disorder (PTSD), one-third of patients are treatment non-responders. To identify neural markers of treatment response to TF-CBT when participants are reappraising aversive material.

METHODS

This study assessed PTSD patients (n = 37) prior to TF-CBT during functional magnetic brain resonance imaging (fMRI) when they reappraised or watched traumatic images. Patients then underwent nine sessions of TF-CBT, and were then assessed for symptom severity on the Clinician-Administered PTSD Scale. FMRI responses for cognitive reappraisal and emotional reactivity contrasts of traumatic images were correlated with the reduction of PTSD severity from pretreatment to post-treatment.

RESULTS

Symptom improvement was associated with decreased activation of the left amygdala during reappraisal, but increased activation of bilateral amygdala and hippocampus during emotional reactivity prior to treatment. Lower connectivity of the left amygdala to the subgenual anterior cingulate cortex, pregenual anterior cingulate cortex, and right insula, and that between the left hippocampus and right amygdala were also associated with symptom improvement.

CONCLUSIONS

These findings provide evidence that optimal treatment response to TF-CBT involves the capacity to engage emotional networks during emotional processing, and also to reduce the engagement of these networks when down-regulating emotions.

Neural processing of emotional facial stimuli in specific phobia: An fMRI study

BACKGROUND

Patients with specific phobia (SP) show altered brain activation when confronted with phobia-specific stimuli. It is unclear whether this pathogenic activation pattern generalizes to other emotional stimuli. This study addresses this question by employing a well-powered sample while implementing an established paradigm using nonspecific aversive facial stimuli.

METHODS

N = 111 patients with SP, spider subtype, and N = 111 healthy controls (HCs) performed a supraliminal emotional face-matching paradigm contrasting aversive faces versus shapes in a 3-T magnetic resonance imaging scanner. We performed region of interest (ROI) analyses for the amygdala, the insula, and the anterior cingulate cortex using univariate as well as machine-learning-based multivariate statistics based on this data. Additionally, we investigated functional connectivity by means of psychophysiological interaction (PPI).

RESULTS

Although the presentation of emotional faces showed significant activation in all three ROIs across both groups, no group differences emerged in all ROIs. Across both groups and in the HC > SP contrast, PPI analyses showed significant task-related connectivity of brain areas typically linked to higher-order emotion processing with the amygdala. The machine learning approach based on whole-brain activity patterns could significantly differentiate the groups with 73% balanced accuracy.

CONCLUSIONS

Patients suffering from SP are characterized by differences in the connectivity of the amygdala and areas typically linked to emotional processing in response to aversive facial stimuli (inferior parietal cortex, fusiform gyrus, middle cingulate, postcentral cortex, and insula). This might implicate a subtle difference in the processing of nonspecific emotional stimuli and warrants more research furthering our understanding of neurofunctional alteration in patients with SP.

The promise of machine learning in predicting treatment outcomes in psychiatry

For many years, psychiatrists have tried to understand factors involved in response to medications or psychotherapies, in order to personalize their treatment choices. There is now a broad and growing interest in the idea that we can develop models to personalize treatment decisions using new statistical approaches from the field of machine learning and applying them to larger volumes of data. In this pursuit, there has been a paradigm shift away from experimental studies to confirm or refute specific hypotheses towards a focus on the overall explanatory power of a predictive model when tested on new, unseen datasets. In this paper, we review key studies using machine learning to predict treatment outcomes in psychiatry, ranging from medications and psychotherapies to digital interventions and neurobiological treatments. Next, we focus on some new sources of data that are being used for the development of predictive models based on machine learning, such as electronic health records, smartphone and social media data, and on the potential utility of data from genetics, electrophysiology, neuroimaging and cognitive testing. Finally, we discuss how far the field has come towards implementing prediction tools in real-world clinical practice. Relatively few retrospective studies to-date include appropriate external validation procedures, and there are even fewer prospective studies testing the clinical feasibility and effectiveness of predictive models. Applications of machine learning in psychiatry face some of the same ethical challenges posed by these techniques in other areas of medicine or computer science, which we discuss here. In short, machine learning is a nascent but important approach to improve the effectiveness of mental health care, and several prospective clinical studies suggest that it may be working already.

Artificial Intelligence for Mental Health Care: Clinical Applications, Barriers, Facilitators, and Artificial Wisdom

Artificial intelligence (AI) is increasingly employed in health care fields such as oncology, radiology, and dermatology. However, the use of AI in mental health care and neurobiological research has been modest. Given the high morbidity and mortality in people with psychiatric disorders, coupled with a worsening shortage of mental health care providers, there is an urgent need for AI to help identify high-risk individuals and provide interventions to prevent and treat mental illnesses. While published research on AI in neuropsychiatry is rather limited, there is a growing number of successful examples of AI's use with electronic health records, brain imaging, sensor-based monitoring systems, and social media platforms to predict, classify, or subgroup mental illnesses as well as problems such as suicidality. This article is the product of a study group held at the American College of Neuropsychopharmacology conference in 2019. It provides an overview of AI approaches in mental health care, seeking to help with clinical diagnosis, prognosis, and treatment, as well as clinical and technological challenges, focusing on multiple illustrative publications. Although AI could help redefine mental illnesses more objectively, identify them at a prodromal stage, personalize treatments, and empower patients in their own care, it must address issues of bias, privacy, transparency, and other ethical concerns. These aspirations reflect human wisdom, which is more strongly associated than intelligence with individual and societal well-being. Thus, the future AI or artificial wisdom could provide technology that enables more compassionate and ethically sound care to diverse groups of people.

Cannabidiol normalizes resting-state functional connectivity in treatment-resistant epilepsy

OBJECTIVE

Resting-state (rs) network dysfunction is a contributing factor to treatment resistance in epilepsy. In treatment-resistant epilepsy (TRE), pharmacological and nonpharmacological therapies have been shown to improve such dysfunction. In this study, our goal was to prospectively evaluate the effect of highly purified plant-derived cannabidiol (CBD; Epidiolex®) on rs functional magnetic resonance imaging (fMRI) functional connectivity (rs-FC). We hypothesized that CBD would change and potentially normalize the rs-FC in TRE.

METHODS

Twenty-two of 27 participants with TRE completed all study procedures including longitudinal pre-/on-CBD rs-fMRI (8M/14F, mean age = 36.2 ± 15.9 years, TRE duration = 18.3 ± 12.6 years); there were no differences in age (p = 0.99) or sex (p = 0.15) between groups. Assessments collected included seizure frequency (SF), Chalfont Seizure Severity Scale (CSSS), Columbia Suicide Severity Rating Scale (C-SSRS), Adverse Events Profile (AEP), and Profile of Mood States (POMS). Twenty-three healthy controls (HCs) received rs-fMRI and POMS once.

RESULTS

Participants with TRE showed average decrease of 71.7% in SF (p < 0.0001) and improved CSSS, AEP, and POMS confusion, depression, and fatigue subscores (all p < 0.05) on-CBD with POMS scores becoming similar to those of HCs. Paired t-tests showed significant pre-/on-CBD changes in rs-FC in cerebellum, frontal areas, temporal areas, hippocampus, and amygdala with some of them correlating with improvement in behavioral measures. Significant differences in rs-FC between pre-CBD and HCs were found in cerebellum, frontal, and occipital regions. After controlling for changes in SF with CBD, these differences were no longer present when comparing on-CBD to HCs.

SIGNIFICANCE

This study indicates that highly purified CBD modulates and potentially normalizes rs-FC in the epileptic brain. This effect may underlie its efficacy. This study provides Class III evidence for CBD's normalizing effect on rs-FC in TRE.

A scoping review of machine learning in psychotherapy research

Machine learning (ML) offers robust statistical and probabilistic techniques that can help to make sense of large amounts of data. This scoping review paper aims to broadly explore the nature of research activity using ML in the context of psychological talk therapies, highlighting the scope of current methods and considerations for clinical practice and directions for future research. Using a systematic search methodology, fifty-one studies were identified. A narrative synthesis indicates two types of studies, those who developed and tested an ML model (k=44), and those who reported on the feasibility of a particular treatment tool that uses an ML algorithm (k=7). Most model development studies used supervised learning techniques to classify or predict labeled treatment process or outcome data, whereas others used unsupervised techniques to identify clusters in the unlabeled patient or treatment data. Overall, the current applications of ML in psychotherapy research demonstrated a range of possible benefits for indications of treatment process, adherence, therapist skills and treatment response prediction, as well as ways to accelerate research through automated behavioral or linguistic process coding. Given the novelty and potential of this research field, these proof-of-concept studies are encouraging, however, do not necessarily translate to improved clinical practice (yet).

Theranostic markers for personalized therapy of spider phobia: Methods of a bicentric external cross-validation machine learning approach

OBJECTIVES

Embedded in the Collaborative Research Center "Fear, Anxiety, Anxiety Disorders" (CRC-TRR58), this bicentric clinical study aims at identifying biobehavioral markers of treatment (non-)response by applying machine learning methodology with an external cross-validation protocol. We hypothesize that a priori prediction of treatment (non-)response is possible in a second, independent sample based on multimodal markers.

METHODS

One-session virtual reality exposure treatment (VRET) with patients with spider phobia was conducted on two sites. Clinical, neuroimaging, and genetic data were assessed at baseline, post-treatment and after 6 months. The primary and secondary outcomes defining treatment response are as follows: 30% reduction regarding the individual score in the Spider Phobia Questionnaire and 50% reduction regarding the individual distance in the behavioral avoidance test.

RESULTS

N = 204 patients have been included (n = 100 in Würzburg, n = 104 in Münster). Sample characteristics for both sites are comparable.

DISCUSSION

This study will offer cross-validated theranostic markers for predicting the individual success of exposure-based therapy. Findings will support clinical decision-making on personalized therapy, bridge the gap between basic and clinical research, and bring stratified therapy into reach. The study is registered at ClinicalTrials.gov (ID: NCT03208400).

Levers and barriers to success in the use of translational neuroscience for the prevention and treatment of mental health and promotion of well-being across the lifespan

Neuroscientific tools and approaches such as neuroimaging, measures of neuroendocrine and psychoneuroimmune activity, and peripheral physiology are increasingly used in clinical science and health psychology research. We define translational neuroscience (TN) as a systematic, theory-driven approach that aims to develop and leverage basic and clinical neuroscientific knowledge to aid the development and optimization of clinical and public health interventions. There is considerable potential across basic and clinical science fields for this approach to provide insights into mental and physical health pathology that had previously been inaccessible. For example, TN might hold the potential to enhance diagnostic specificity, better recognize increased vulnerability in at-risk populations, and augment intervention efficacy. Despite this potential, there has been limited consideration of the advantages and limitations of such an approach. In this article, we articulate extant challenges in defining TN and propose a unifying conceptualization. We illustrate how TN can inform the application of neuroscientific tools to realistically guide clinical research and inform intervention design. We outline specific leverage points of the TN approach and barriers to progress. Ten principles of TN are presented to guide and shape the emerging field. We close by articulating ongoing issues facing TN research. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

Nucleus accumbens volume as a predictor of anxiety symptom improvement following CBT and SSRI treatment in two independent samples

Structural variations of neural regions implicated in fear responses have been well documented in the pathophysiology of anxiety and may play an important role in treatment response. We examined whether gray matter volume of three neural regions supporting fear and avoidance responses [bilateral amygdala, nucleus accumbens (NAcc), and ventromedial prefrontal cortex (PFC)] predicted cognitive-behavioral therapy (CBT) and selective serotonin reuptake inhibitor (SSRI) treatment outcome in two independent samples of patients with anxiety disorders. Study 1 consisted of 81 adults with anxiety disorders and Study 2 included 55 children and adolescents with anxiety disorders. In both studies, patients completed baseline structural MRI scans and received either CBT or SSRI treatment. Clinician-rated interviews of anxiety symptoms were assessed at baseline and posttreatment. Among the adult sample, greater pre-treatment bilateral NAcc volume was associated with a greater reduction in clinician-rated anxiety symptoms pre-to-post CBT and SSRI treatment. Greater left NAcc volume also predicted greater decreases in clinician-rated anxiety symptoms pre-to-post CBT and SSRI treatment among youth with current anxiety. Across studies, results were similar across treatments, and findings were maintained when adjusting for patient's age, sex, and total intracranial brain volume. We found no evidence for baseline amygdala or ventromedial PFC volume serving as treatment predictors across the two samples. Together, these findings provide promising support for the role of NAcc volume as an objective marker of anxiety treatment improvement that spans across development. Future studies should clarify the specific mechanisms through which NAcc volume exerts its therapeutic effects.

Neuroimaging, genetic, clinical, and demographic predictors of treatment response in patients with social anxiety disorder

BACKGROUND

Correct prediction of treatment response is a central goal of precision psychiatry. Here, we tested the predictive accuracy of a variety of pre-treatment patient characteristics, including clinical, demographic, molecular genetic, and neuroimaging markers, for treatment response in patients with social anxiety disorder (SAD).

METHODS

Forty-seven SAD patients (mean±SD age 33.9 ± 9.4 years, 24 women) were randomized and commenced 9 weeks' Internet-delivered cognitive behavior therapy (CBT) combined either with the selective serotonin reuptake inhibitor (SSRI) escitalopram (20 mg daily [10 mg first week], SSRI+CBT, n = 24) or placebo (placebo+CBT, n = 23). Treatment responders were defined from the Clinical Global Impression-Improvement scale (CGI-I ≤ 2). Before treatment, patients underwent functional magnetic resonance imaging and the Multi-Source Interference Task taxing cognitive interference. Support vector machines (SVMs) were trained to separate responders from nonresponders based on pre-treatment neural reactivity in the dorsal anterior cingulate cortex (dACC), amygdala, and occipital cortex, as well as molecular genetic, demographic, and clinical data. SVM models were tested using leave-one-subject-out cross-validation.

RESULTS

The best model separated treatment responders (n = 24) from nonresponders based on pre-treatment dACC reactivity (83% accuracy, P = 0.001). Responders had greater pre-treatment dACC reactivity than nonresponders especially in the SSRI+CBT group. No other variable was associated with clinical response or added predictive accuracy to the dACC SVM model.

LIMITATIONS

Small sample size, especially for genetic analyses. No replication or validation samples were available.

CONCLUSIONS

The findings demonstrate that treatment outcome predictions based on neural cingulate activity, at the individual level, outperform genetic, demographic, and clinical variables for medication-assisted Internet-delivered CBT, supporting the use of neuroimaging in precision psychiatry.

Protocol for a randomized controlled trial examining multilevel prediction of response to behavioral activation and exposure-based therapy for generalized anxiety disorder

BACKGROUND

Only 40-60% of patients with generalized anxiety disorder experience long-lasting improvement with gold standard psychosocial interventions. Identifying neurobehavioral factors that predict treatment success might provide specific targets for more individualized interventions, fostering more optimal outcomes and bringing us closer to the goal of "personalized medicine." Research suggests that reward and threat processing (approach/avoidance behavior) and cognitive control may be important for understanding anxiety and comorbid depressive disorders and may have relevance to treatment outcomes. This study was designed to determine whether approach-avoidance behaviors and associated neural responses moderate treatment response to exposure-based versus behavioral activation therapy for generalized anxiety disorder.

METHODS/DESIGN

We are conducting a randomized controlled trial involving two 10-week group-based interventions: exposure-based therapy or behavioral activation therapy. These interventions focus on specific and unique aspects of threat and reward processing, respectively. Prior to and after treatment, participants are interviewed and undergo behavioral, biomarker, and neuroimaging assessments, with a focus on approach and avoidance processing and decision-making. Primary analyses will use mixed models to examine whether hypothesized approach, avoidance, and conflict arbitration behaviors and associated neural responses at baseline moderate symptom change with treatment, as assessed using the Generalized Anxiety Disorder-7 item scale. Exploratory analyses will examine additional potential treatment moderators and use data reduction and machine learning methods.

DISCUSSION

This protocol provides a framework for how studies may be designed to move the field toward neuroscience-informed and personalized psychosocial treatments. The results of this trial will have implications for approach-avoidance processing in generalized anxiety disorder, relationships between levels of analysis (i.e., behavioral, neural), and predictors of behavioral therapy outcome.

TRIAL REGISTRATION

The study was retrospectively registered within 21 days of first participant enrollment in accordance with FDAAA 801 with ClinicalTrials.gov, NCT02807480. Registered on June 21, 2016, before results.

Principal component analysis and brain-based predictors of emotion regulation in anxiety and depression

BACKGROUND

Reappraisal, an adaptive emotion regulation strategy, is associated with frontal engagement. In internalizing psychopathologies (IPs) such as anxiety and depression frontal activity is atypically reduced suggesting impaired regulation capacity. Yet, successful reappraisal is often demonstrated at the behavioral level. A data-driven approach was used to clarify brain and behavioral relationships in IPs.

METHODS

During functional magnetic resonance imaging, anxious [general anxiety disorder (n = 43), social anxiety disorder (n = 72)] and depressed (n = 47) patients reappraised negative images to reduce negative affect ('ReappNeg') and viewed negative images ('LookNeg'). After each trial, the affective state was reported. A cut-point (i.e. values <0 based on ΔReappNeg-LookNeg) demarcated successful reappraisers. Neural activity for ReappNeg-LookNeg, derived from 37 regions of interest, was submitted to Principal Component Analysis (PCA) to identify unique components of reappraisal-related brain response. PCA factors, symptom severity, and self-reported habitual reappraisal were submitted to discriminant function analysis and linear regression to examine whether these data predicted successful reappraisal (yes/no) and variance in reappraisal ability.

RESULTS

Most patients (63%) were successful reappraisers according to the behavioral criterion (values<0; ΔReappNeg-LookNeg). Discriminant function analysis was not significant for PCA factors, symptoms, or habitual reappraisal. For regression, more activation in a factor with high loadings for frontal regions predicted better reappraisal facility. Results were not significant for other variables.

CONCLUSIONS

At the individual level, more activation in a 'frontal' factor corresponded with better reappraisal facility. However, neither brain nor behavioral variables classified successful reappraisal (yes/no). Findings suggest individual differences in regions strongly implicated in reappraisal play a role in on-line reappraisal capability.

Individualized treatment response prediction of dialectical behavior therapy for borderline personality disorder using multimodal magnetic resonance imaging

INTRODUCTION

Individualized treatment prediction is crucial for the development and selection of personalized psychiatric interventions. Here, we use random forest classification via pretreatment clinical and demographical (CD), functional, and structural magnetic resonance imaging (MRI) data from patients with borderline personality disorder (BPD) to predict individual treatment response.

METHODS

Before dialectical behavior therapy (DBT), 31 female patients underwent functional (three different emotion regulation tasks) and structural MRI. DBT response was predicted using CD and MRI data in previously identified anatomical regions, which have been reported to be multimodally affected in BPD.

RESULTS

Amygdala and parahippocampus activation during a cognitive reappraisal task (in contrasts displaying neural activation for emotional challenge and for regulation), along with severity measures of BPD psychopathology and gray matter volume of the amygdala, provided best predictive power with neuronal hyperractivities in nonresponders. All models, except one model using CD data solely, achieved significantly better accuracy (>70.25%) than a simple all-respond model, with sensitivity and specificity of >0.7 and >0.7, as well as positive and negative likelihood ratios of >2.74 and <0.36 each. Surprisingly, a model combining all data modalities only reached rank five of seven. Among the functional tasks, only the activation elicited by a cognitive reappraisal paradigm yielded sufficient predictive power to enter the final models.

CONCLUSION

This proof of principle study shows that it is possible to achieve good predictions of psychotherapy outcome to find the most valid predictors among numerous variables via using a random forest classification approach.

Pragmatic neuroscience for clinical psychiatry

Mental health and substance use disorders are the leading cause of long-term disability and a cause of significant mortality, worldwide. However, it is widely recognised that clinical practice in psychiatry has not fundamentally changed for over half a century. The Royal College of Psychiatrists is reviewing its trainee curriculum to identify neuroscience that relates to psychiatric practice. To date though, neuroscience has had very little impact on routine clinical practice. We discuss how a pragmatic approach to neuroscience can address this problem together with a route to implementation in National Health Service care. This has implications for altered funding priorities and training future psychiatrists. Five training recommendations for psychiatrists are identified.Declaration of interestJ.D.S. receives direct funding from MRC Program Grant MR/S010351/1 aimed at developing machine learning-based methods for routinely acquired NHS data and indirect funding from the Wellcome Trust STRADL study. M.P.P. receives payments for an UpToDate chapter on methamphetamine and is principal investigator on the following grants: NIGMS P20GM121312 and NIDA U01 DA041089 and receives support from the William K. Warren Foundation.

A review of neuroimaging studies in generalized anxiety disorder: "So where do we stand?"

Generalized anxiety disorder (GAD) is a prevalent anxiety disorder, but is still poorly recognized in clinical practice. The aim of this review is to provide a coherent understanding of the functional neuroanatomy of GAD; second, to discuss the current theoretical cognitive models surrounding GAD; and finally to discuss the discrepancy between fundamental research and clinical practice and highlight several potential directions for future research in this domain. A systematic review of original papers investigating the neural correlates of DSM-IV and DSM-5 defined GAD samples was undertaken in Ovid literature search, PubMed, Medline, EMbase, PsycINFO, Google Scholar, and TRIP databases. Articles published between 2007 and 2018 were included. First, GAD seems to be characterized by limbic and (pre)frontal abnormalities. More specifically, GAD patients show difficulties in engaging the prefrontal cortex (PFC) and anterior cingulate cortex (ACC) during emotional regulation tasks. Second, the involved brain areas appear to be characterized by heterogeneity possibly due to a variety of experimental designs and test subjects. Third, regarding the discrimination between GAD and other anxiety disorders via fMRI, results appear to be mixed. Studies report both GAD-specific activity and an inability to differentiate between GAD and other anxiety or mood disorders. The usage of different experimental tasks, test subjects, outcome measures and experimental designs limits the possibilities of generalizing results as well as conducting meta-analytical research. Certain theoretical models of GAD describe our understanding of this disorder and form the basis for treatment interventions. However, fMRI research thus far has failed to validate these models. To bridge the gap between fundamental research and clinical practice in GAD, we propose that fMRI researchers make an effort to validate the existing cognitive model of GAD. An alternative approach could be that new models would be based on current neuroimaging research as well as convergent research methods such as Heart Rate Variability (a bottom up approach).

Quantifying performance of machine learning methods for neuroimaging data

Machine learning is increasingly being applied to neuroimaging data. However, most machine learning algorithms have not been designed to accommodate neuroimaging data, which typically has many more data points than subjects, in addition to multicollinearity and low signal-to-noise. Consequently, the relative efficacy of different machine learning regression algorithms for different types of neuroimaging data are not known. Here, we sought to quantify the performance of a variety of machine learning algorithms for use with neuroimaging data with various sample sizes, feature set sizes, and predictor effect sizes. The contribution of additional machine learning techniques - embedded feature selection and bootstrap aggregation (bagging) - to model performance was also quantified. Five machine learning regression methods - Gaussian Process Regression, Multiple Kernel Learning, Kernel Ridge Regression, the Elastic Net and Random Forest, were examined with both real and simulated MRI data, and in comparison to standard multiple regression. The different machine learning regression algorithms produced varying results, which depended on sample size, feature set size, and predictor effect size. When the effect size was large, the Elastic Net, Kernel Ridge Regression and Gaussian Process Regression performed well at most sample sizes and feature set sizes. However, when the effect size was small, only the Elastic Net made accurate predictions, but this was limited to analyses with sample sizes greater than 400. Random Forest also produced a moderate performance for small effect sizes, but could do so across all sample sizes. Machine learning techniques also improved prediction accuracy for multiple regression. These data provide empirical evidence for the differential performance of various machines on neuroimaging data, which are dependent on number of sample size, features and effect size.

Neuroimaging findings as predictors of treatment outcome of psychotherapy in anxiety disorders

Anxiety disorders are the largest group of mental disorders and a leading cause of impairment, implicating in high costs for health systems and society. Effective pharmacological and psychological treatments are available, but a significant fraction of these patients does not respond adequately to these treatments. The objective of this study is to identify neuroimaging findings that could predict response to psychotherapy in anxiety disorders.

METHODS

The authors reviewed psychotherapy clinical trials with neuroimaging conducted with patients with anxiety disorders. A systematic review was performed in MEDLINE database through PubMed, the Cochrane Collaboration's Clinical Trials Register (CENTRAL), PsycINFO and Thomson Reuters's Web of Science.

RESULTS

From the studies included in this review, 24 investigated anxiety disorder patients, and findings in the amygdala, dorsolateral prefrontal cortex (dlPFC), anterior cingulate cortex (ACC) and insula predicted response to psychotherapy in social anxiety disorder. Findings in ACC, hippocampus, insula, dlPFC, amygdala and inferior frontal gyrus (iFG) predicted response to psychotherapy in panic disorder and generalized anxiety disorder.

LIMITATIONS

There was great heterogeneity between the included studies regarding neuroimaging techniques and the tasks performed during functional neuroimaging.

CONCLUSION

Neuroimaging studies suggest that abnormalities in hippocampus, amygdala, iFG, uncus and areas linked with emotional regulation (dlPFC and ACC), predict a good outcome to psychotherapy in anxiety disorders.

Translational machine learning for psychiatric neuroimaging

Despite its initial promise, neuroimaging has not been widely translated into clinical psychiatry to assist in the prediction of diagnoses, prognoses, and optimal therapeutic strategies. Machine learning approaches may enhance the translational potential of neuroimaging because they specifically focus on overcoming biases by optimizing the generalizability of pipelines that measure complex brain patterns to predict targets at a single-subject level. This article introduces some fundamentals of a translational machine learning approach before selectively reviewing literature to-date. Promising initial results are then balanced by the description of limitations that should be considered in order to interpret existing research and maximize the possibility of future translation. Future directions are then presented in order to inspire further research and progress the field towards clinical translation.

The Electrical Aftermath: Brain Signals of Posttraumatic Stress Disorder Filtered Through a Clinical Lens

This review aims to identify patterns of electrical signals identified using electroencephalography (EEG) linked to posttraumatic stress disorder (PTSD) diagnosis and symptom dimensions. We filter EEG findings through a clinical lens, evaluating nuances in findings according to study criteria and participant characteristics. Within the EEG frequency domain, greater right than left parietal asymmetry in alpha band power is the most promising marker of PTSD symptoms and is linked to exaggerated physiological arousal that may impair filtering of environmental distractors. The most consistent findings within the EEG time domain focused on event related potentials (ERPs) include: 1) exaggerated frontocentral responses (contingent negative variation, mismatch negativity, and P3a amplitudes) to task-irrelevant distractors, and 2) attenuated parietal responses (P3b amplitudes) to task-relevant target stimuli. These findings suggest that some individuals with PTSD suffer from attention dysregulation, which could contribute to problems concentrating on daily tasks and goals in lieu of threatening distractors. Future research investigating the utility of alpha asymmetry and frontoparietal ERPs as diagnostic and predictive biomarkers or intervention targets are recommended.

Development of Neuroimaging-Based Biomarkers in Psychiatry

This chapter presents an overview of accumulating neuroimaging data with emphasis on translational potential. The subject will be described in the context of three disease states, i.e., schizophrenia, bipolar disorder, and major depressive disorder, and for three clinical goals, i.e., disease risk assessment, subtyping, and treatment decision.

Within- and Between-Session Prefrontal Cortex Response to Virtual Reality Exposure Therapy for Acrophobia

Exposure Therapy (ET) has demonstrated its efficacy in the treatment of phobias, anxiety and Post-traumatic Stress Disorder (PTSD), however, it suffers a high drop-out rate because of too low or too high patient engagement in treatment. Virtual Reality Exposure Therapy (VRET) is comparably effective regarding symptom reduction and offers an alternative tool to facilitate engagement for avoidant participants. Neuroimaging studies have demonstrated that both ET and VRET normalize brain activity within a fear circuit. However, previous studies have employed brain imaging technology which restricts people's movement and hides their body, surroundings and therapist from view. This is at odds with the way engagement is typically controlled. We used a novel combination of neural imaging and VR technology-Functional Near-Infrared Spectroscopy (fNIRS) and Immersive Projection Technology (IPT), to avoid these limitations. Although there are a few studies that have investigated the effect of VRET on a brain function after the treatment, the present study utilized technologies which promote ecological validity to measure brain changes after VRET treatment. Furthermore, there are no studies that have measured brain activity within VRET session. In this study brain activity within the prefrontal cortex (PFC) was measured during three consecutive exposure sessions. N = 13 acrophobic volunteers were asked to walk on a virtual plank with a 6 m drop below. Changes in oxygenated (HbO) hemoglobin concentrations in the PFC were measured in three blocks using fNIRS. Consistent with previous functional magnetic resonance imaging (fMRI) studies, the analysis showed decreased activity in the DLPFC and MPFC during first exposure. The activity increased toward normal across three sessions. The study demonstrates potential efficacy of a method for measuring within-session neural response to virtual stimuli that could be replicated within clinics and research institutes, with equipment better suited to an ET session and at fraction of the cost, when compared to fMRI. This has application in widening access to, and increasing ecological validity of, immersive neuroimaging across understanding, diagnosis, assessment and treatment of, a range of mental disorders such as phobia, anxiety and PTSD or addictions.

Neuroimaging Predictors and Mechanisms of Treatment Response in Social Anxiety Disorder: an Overview of the Amygdala

PURPOSE OF REVIEW

Aberrant amygdala activity is implicated in the neurobiology of social anxiety disorder (SAD) and is, therefore, a treatment target. However, the extent to which amygdala predicts clinical improvement or is impacted by treatment has not been critically examined. This review highlights recent neuroimaging findings from clinical trials and research that test links between amygdala and mechanisms of action.

RECENT FINDINGS

Neuropredictor studies largely comprised psychotherapy where improvement was foretold by amygdala activity and regions beyond amygdala such as frontal structures (e.g., anterior cingulate cortex, medial prefrontal cortex) and areas involved in visual processes (e.g., occipital regions, superior temporal gyrus). Pre-treatment functional connectivity between amygdala and frontal areas was also shown to predict improvement signifying circuits that support emotion processing and regulation interact with treatment. Pre-to-post studies revealed decreases in amygdala response and altered functional connectivity in amygdala pathways regardless of treatment modality. In analogue studies of fear exposure, greater reduction in anxiety was predicted by less amygdala response to a speech challenge and amygdala activity decreased following exposures. Yet, studies have also failed to detect amygdala effects reporting instead treatment-related changes in regions and functional systems that support sensory, emotion, and regulation processes. An array of regions in the corticolimbic subcircuits and extrastriate cortex appear to be viable sites of action. The amygdala and amygdala pathways predict treatment outcome and are altered following treatment. However, further study is needed to establish the role of the amygdala and other candidate regions and brain circuits as sites of action.

Referral paths in the U.S. physician network

In this paper, we analyze the millions of referral paths of patients' interactions with the healthcare system for each year in the 2006-2011 time period and relate them to U.S. cardiovascular treatment records. For a patient, a "referral path" records the chronological sequence of physicians encountered by a patient (subject to certain constraints on the times between encounters). It provides a basic unit of analysis in a broader referral network that encodes the flow of patients and information between physicians in a healthcare system. We consider referral networks defined over a range of interactions as well as the characteristics of referral paths, producing a characterization of the various networks as well as the physicians they comprise. We further relate these metrics and findings to outcomes in the specific area of cardiovascular care. In particular, we match a referral path to occurrences of Acute Myocardial Infarction (AMI) and use the summary measures of the referral path to predict the treatment a patient receives and medical outcomes following treatment. Some referral path features are more significant with respect to their ability to boost a tree-based predictive model, and have stronger correlations with numerical treatment outcome variables. The patterns of referral paths and the derived informative features illustrate the potential for using network science to optimize patient referrals in healthcare systems for improved treatment outcomes and more efficient utilization of medical resources.

PREDICTION OF PIVOTAL RESPONSE TREATMENT OUTCOME WITH TASK FMRI USING RANDOM FOREST AND VARIABLE SELECTION

Behavior intervention has shown promise for treatment for young children with autism spectrum disorder (ASD). However, current therapeutic decisions are based on trial and error, often leading to suboptimal outcomes. We propose an approach that employs task-based fMRI for early outcome prediction. Our strategy is based on the general linear model (GLM) and a random forest, combined with feature selection techniques. GLM analysis is performed on each voxel to get t-statistic of contrast between two tasks. Due to the high dimensionality of predictor variables, feature selection is crucial for accurate prediction. Thus we propose a two-step feature selection method: a "shadow" method to select all-relevant variables, followed by a stepwise method to select minimal-optimal set of variables for prediction. A few columns of random noise are generated and added as shadow variables. Regression based on the random forest is performed, and permutation importance of each variable is estimated. Candidate voxels with higher importance than the shadow are kept. Surviving voxels are fed into stepwise variable selection methods. We test both forward and backward stepwise selection. Our method was validated on a dataset of 20 children with ASD using leave-one-out cross-validation, and compared to other standard regression methods. The proposed pipeline generated highest accuracy.

Distributed Intrinsic Functional Connectivity Patterns Predict Diagnostic Status in Large Autism Cohort

Diagnosis of autism spectrum disorder (ASD) currently relies on behavioral observations because brain markers are unknown. Machine learning approaches can identify patterns in imaging data that predict diagnostic status, but most studies using functional connectivity MRI (fcMRI) data achieved only modest accuracies of 60-80%. We used conditional random forest (CRF), an ensemble learning technique protected against bias from feature correlation (which exists in fcMRI matrices). We selected 252 low-motion resting-state functional MRI scans from the Autism Brain Imaging Data Exchange, including 126 typically developing (TD) and 126 ASD participants, matched for age, nonverbal IQ, and head motion. A matrix of functional connectivities between 220 functionally defined regions of interest was used for diagnostic classification. In several runs, we achieved accuracies of 92-99% for classifiers with >300 features (most informative connections). Features, including pericentral somatosensory and motor regions, were disproportionately informative. Findings differed partially from a previous study in the same sample that used feature selection with random forest (which is biased by feature correlations). External validation in a smaller in-house data set, however, achieved only 67-71% accuracy. The large number of features in optimal models can be attributed to etiological heterogeneity under the clinical ASD umbrella. Lower accuracy in external validation is expected due to differences in unknown composition of ASD variants across samples. High accuracy in the main data set is unlikely due to noise overfitting, but rather indicates optimized characterization of a given cohort.

Roadmap for optimizing the clinical utility of emotional stress paradigms in human neuroimaging research

The emotional stress response is relevant to a number of psychiatric disorders, including posttraumatic stress disorder (PTSD) in particular. Research using neuroimaging methods such as functional magnetic resonance imaging (fMRI) to probe stress-related neural processing have provided some insights into psychiatric disorders. Treatment providers and individual patients would benefit from clinically useful fMRI paradigms that provide information about patients' current brain state and responses to stress in order to inform the treatment selection process. However, neuroimaging has not yet made a meaningful impact on real-world clinical practice. This lack of clinical utility may be related to a number of basic psychometric properties that are often overlooked during fMRI task development. The goals of the current review are to discuss important methodological considerations for current human fMRI stress-related paradigms and to provide a roadmap for developing methodologically sound and clinically useful paradigms. This would include establishing various aspects of reliability, including internal consistency, test-retest and multi-site, as well as validity, including face, content, construct, and criterion. In addition, the establishment of standardized normative data from a large sample of participants would support our understanding of how any one individual compares to the general population. Addressing these methodological gaps will likely have a powerful effect on improving the replicability of findings and optimize our chances for improving real-world clinical outcomes.

Machine Learning Approaches for Clinical Psychology and Psychiatry

Machine learning approaches for clinical psychology and psychiatry explicitly focus on learning statistical functions from multidimensional data sets to make generalizable predictions about individuals. The goal of this review is to provide an accessible understanding of why this approach is important for future practice given its potential to augment decisions associated with the diagnosis, prognosis, and treatment of people suffering from mental illness using clinical and biological data. To this end, the limitations of current statistical paradigms in mental health research are critiqued, and an introduction is provided to critical machine learning methods used in clinical studies. A selective literature review is then presented aiming to reinforce the usefulness of machine learning methods and provide evidence of their potential. In the context of promising initial results, the current limitations of machine learning approaches are addressed, and considerations for future clinical translation are outlined.

Predictive Neuroimaging Markers of Psychotherapy Response: A Systematic Review

INTRODUCTION

Predictive neuroimaging markers of treatment response are increasingly sought in order to inform the treatment of major depressive and anxiety disorders. We review the existing literature regarding candidate predictive neuroimaging markers of psychotherapy response and assess their potential clinical utility.

METHODS

We searched Embase, PsycINFO, and PubMed up to October 2014 for studies correlating pretreatment neuroimaging parameters with psychotherapy response in major depressive and anxiety disorders. Our search yielded 40 eligible studies.

RESULTS

The anterior cingulate cortex, amygdala, and anterior insula emerged as potential markers in major depressive disorder and some anxiety disorders. Results across studies displayed a large degree of variability, however, and to date the findings have not been systematically validated in independent clinical cohorts and have not been shown capable of distinguishing between medication and psychotherapy responders. Also limited is the examination of how neuroimaging compares or might add to other prognostic clinical variables.

CONCLUSION

While the extant data suggest avenues of further investigation, we are still far from being able to use these markers clinically. Future studies need to focus on longitudinal testing of potential markers, determining their prescriptive value and examining how they might be integrated with clinical factors.

Imaging and Genetic Approaches to Inform Biomarkers for Anxiety Disorders, Obsessive-Compulsive Disorders, and PSTD

Anxiety disorders are the most common mental health problem in the world and also claim the highest health care cost among various neuropsychiatric disorders. Anxiety disorders have a chronic and recurrent course and cause significantly negative impacts on patients' social, personal, and occupational functioning as well as quality of life. Despite their high prevalence rates, anxiety disorders have often been under-diagnosed or misdiagnosed, and consequently under-treated. Even with the correct diagnosis, anxiety disorders are known to be difficult to treat successfully. In order to implement better strategies in diagnosis, prognosis, treatment decision, and early prevention for anxiety disorders, tremendous efforts have been put into studies using genetic and neuroimaging techniques to advance our understandings of the underlying biological mechanisms. In addition to anxiety disorders including panic disorder, generalised anxiety disorder (GAD), specific phobias, social anxiety disorders (SAD), due to overlapping symptom dimensions, obsessive-compulsive disorder (OCD), and post-traumatic stress disorder (PTSD) (which were removed from the anxiety disorder category in DSM-5 to become separate categories) are also included for review of relevant genetic and neuroimaging findings. Although the number of genetic or neuroimaging studies focusing on anxiety disorders is relatively small compare to other psychiatric disorders such as psychotic disorders or mood disorders, various structural abnormalities in the grey or white matter, functional alterations of activity during resting-state or task conditions, molecular changes of neurotransmitter receptors or transporters, and genetic associations have all been reported. With continuing effort, further genetic and neuroimaging research may potentially lead to clinically useful biomarkers for the prevention, diagnosis, and management of these disorders.