Common and different gray and white matter alterations in bipolar and borderline personality disorder: A source-based morphometry study

Neuroimaging and natural language processing-based classification of suicidal thoughts in major depressive disorder

Suicide is a growing public health problem around the world. The most important risk factor for suicide is underlying psychiatric illness, especially depression. Detailed classification of suicide in patients with depression can greatly enhance personalized suicide control efforts. This study used unstructured psychiatric charts and brain magnetic resonance imaging (MRI) records from a psychiatric outpatient clinic to develop a machine learning-based suicidal thought classification model. The study included 152 patients with new depressive episodes for development and 58 patients from a geographically different hospital for validation. We developed an eXtreme Gradient Boosting (XGBoost)-based classification models according to the combined types of data: independent components-map weightings from brain T1-weighted MRI and topic probabilities from clinical notes. Specifically, we used 5 psychiatric symptom topics and 5 brain networks for models. Anxiety and somatic symptoms topics were significantly more common in the suicidal group, and there were group differences in the default mode and cortical midline networks. The clinical symptoms plus structural brain patterns model had the highest area under the receiver operating characteristic curve (0.794) versus the clinical notes only and brain MRI only models (0.748 and 0.738, respectively). The results were consistent across performance metrics and external validation. Our findings suggest that focusing on personalized neuroimaging and natural language processing variables improves evaluation of suicidal thoughts.

Narcissus reflected: Grey and white matter features joint contribution to the default mode network in predicting narcissistic personality traits

Despite the clinical significance of narcissistic personality, its neural bases have not been clarified yet, primarily because of methodological limitations of the previous studies, such as the low sample size, the use of univariate techniques and the focus on only one brain modality. In this study, we employed for the first time a combination of unsupervised and supervised machine learning methods, to identify the joint contributions of grey matter (GM) and white matter (WM) to narcissistic personality traits (NPT). After preprocessing, the brain scans of 135 participants were decomposed into eight independent networks of covarying GM and WM via parallel ICA. Subsequently, stepwise regression and Random Forest were used to predict NPT. We hypothesized that a fronto-temporo parietal network, mainly related to the default mode network, may be involved in NPT and associated WM regions. Results demonstrated a distributed network that included GM alterations in fronto-temporal regions, the insula and the cingulate cortex, along with WM alterations in cerebellar and thalamic regions. To assess the specificity of our findings, we also examined whether the brain network predicting narcissism could also predict other personality traits (i.e., histrionic, paranoid and avoidant personalities). Notably, this network did not predict such personality traits. Additionally, a supervised machine learning model (Random Forest) was used to extract a predictive model for generalization to new cases. Results confirmed that the same network could predict new cases. These findings hold promise for advancing our understanding of personality traits and potentially uncovering brain biomarkers associated with narcissism.

Network dysfunction of sadness facial expression processing and morphometry in euthymic bipolar disorder

Facial emotion recognition (FER), including sadness, is altered in bipolar disorder (BD). However, the relationship between this impairment and the brain structure in BD is relatively unexplored. Furthermore, its association with clinical variables and with the subtypes of BD remains to be clarified. Twenty euthymic patients with BD type I (BD-I), 28 BD type II (BD-II), and 45 healthy controls completed a FER test and a 3D-T1-weighted magnetic resonance imaging. Gray matter volume (GMV) of the cortico-limbic regions implicated in emotional processing was estimated and their relationship with FER performance was investigated using network analysis. Patients with BD-I had worse total and sadness-related FER performance relative to the other groups. Total FER performance was significantly negatively associated with illness duration and positively associated with global functioning in patients with BD-I. Sadness-related FER performance was also significantly negatively associated with the number of previous manic episodes. Network analysis showed a reduced association of the GMV of the frontal-insular-occipital areas in patients with BD-I, with a greater edge strength between sadness-related FER performance and amygdala GMV relative to controls. Our results suggest that FER performance, particularly for facial sadness, may be distinctively impaired in patients with BD-I. The pattern of reduced interrelationship in the frontal-insular-occipital regions and a stronger positive relationship between facial sadness recognition and the amygdala GMV in BD may reflect altered cortical modulation of limbic structures that ultimately predisposes to emotional dysregulation. Future longitudinal studies investigating the effect of mood state on FER performance in BD are warranted.

Frontal theta oscillations during emotion regulation in people with borderline personality disorder

BACKGROUND

Borderline personality disorder (BPD) is a severe psychiatric disorder conceptualised as a disorder of emotion regulation. Emotion regulation has been linked to a frontolimbic network comprising the dorsolateral prefrontal cortex and the amygdala, which apparently synchronises its activity via oscillatory coupling in the theta frequency range.

AIMS

To analyse whether there are distinct differences in theta oscillatory coupling in frontal brain regions between individuals with BPD and matched controls during emotion regulation by cognitive reappraisal.

METHOD

Electroencephalogram (EEG) recordings were performed in 25 women diagnosed with BPD and 25 matched controls during a cognitive reappraisal task in which participants were instructed to downregulate negative emotions evoked by aversive visual stimuli. Between- and within-group time-frequency analyses were conducted to analyse regulation-associated theta activity (3.5-8.5 Hz).

RESULTS

Oscillatory theta activity differed between the participants with BPD and matched controls during cognitive reappraisal. Regulation-associated theta increases were lower in frontal regions in the BPD cohort compared with matched controls. Functional connectivity analysis for regulation-associated changes in the theta frequency band revealed a lower multivariate interaction measure (MIM) increase in frontal brain regions in persons with BPD compared with matched controls.

CONCLUSIONS

Our findings support the notion of alterations in a frontal theta network in BPD, which may be underlying core symptoms of the disorder such as deficits in emotion regulation. The results add to the growing body of evidence for altered oscillatory brain dynamics in psychiatric populations, which might be investigated as individualised treatment targets using non-invasive stimulation methods.

dcSBM: A federated constrained source-based morphometry approach for multivariate brain structure mapping

The examination of multivariate brain morphometry patterns has gained attention in recent years, especially for their powerful exploratory capabilities in the study of differences between patients and controls. Among the many existing methods and tools for the analysis of brain anatomy based on structural magnetic resonance imaging data, data-driven source-based morphometry (SBM) focuses on the exploratory detection of such patterns. Here, we implement a semi-blind extension of SBM, called constrained source-based morphometry (constrained SBM), which enables the extraction of maximally independent reference-alike sources using the constrained independent component analysis (ICA) approach. To do this, we combine SBM with a set of reference components covering the full brain, derived from a large independent data set (UKBiobank), to provide a fully automated SBM framework. This also allows us to implement a federated version of constrained SBM (cSBM) to allow analysis of data that is not locally accessible. In our proposed decentralized constrained source-based morphometry (dcSBM), the original data never leaves the local site. Each site operates constrained ICA on its private local data using a common distributed computation platform. Next, an aggregator/master node aggregates the results estimated from each local site and applies statistical analysis to estimate the significance of the sources. Finally, we utilize two additional multisite patient data sets to validate our model by comparing the resulting group difference estimates from both cSBM and dcSBM.

Borderline shades: Morphometric features predict borderline personality traits but not histrionic traits

Borderline personality disorder (BPD) is one of the most diagnosed disorders in clinical settings. Besides the fully diagnosed disorder, borderline personality traits (BPT) are quite common in the general population. Prior studies have investigated the neural correlates of BPD but not of BPT. This paper investigates the neural correlates of BPT in a subclinical population using a supervised machine learning method known as Kernel Ridge Regression (KRR) to build predictive models. Additionally, we want to determine whether the same brain areas involved in BPD are also involved in subclinical BPT. Recent attempts to characterize the specific role of resting state-derived macro networks in BPD have highlighted the role of the default mode network. However, it is not known if this extends to the subclinical population. Finally, we wanted to test the hypothesis that the same circuitry that predicts BPT can also predict histrionic personality traits. Histrionic personality is sometimes considered a milder form of BPD, and making a differential diagnosis between the two may be difficult. For the first time KRR was applied to structural images of 135 individuals to predict BPT, based on the whole brain, on a circuit previously found to correctly classify BPD, and on the five macro-networks. At a whole brain level, results show that frontal and parietal regions, as well as the Heschl's area, the thalamus, the cingulum, and the insula, are able to predict borderline traits. BPT predictions increase when considering only the regions limited to the brain circuit derived from a study on BPD, confirming a certain overlap in brain structure between subclinical and clinical samples. Of all the five macro networks, only the DMN successfully predicts BPD, confirming previous observations on its role in the BPD. Histrionic traits could not be predicted by the BPT circuit. The results have implications for the diagnosis of BPD and a dimensional model of personality.

Decoding reappraisal and suppression from neural circuits: A combined supervised and unsupervised machine learning approach

Emotion regulation is a core construct of mental health and deficits in emotion regulation abilities lead to psychological disorders. Reappraisal and suppression are two widely studied emotion regulation strategies but, possibly due to methodological limitations in previous studies, a consistent picture of the neural correlates related to the individual differences in their habitual use remains elusive. To address these issues, the present study applied a combination of unsupervised and supervised machine learning algorithms to the structural MRI scans of 128 individuals. First, unsupervised machine learning was used to separate the brain into naturally grouping grey matter circuits. Then, supervised machine learning was applied to predict individual differences in the use of different strategies of emotion regulation. Two predictive models, including structural brain features and psychological ones, were tested. Results showed that a temporo-parahippocampal-orbitofrontal network successfully predicted the individual differences in the use of reappraisal. Differently, insular and fronto-temporo-cerebellar networks successfully predicted suppression. In both predictive models, anxiety, the opposite strategy, and specific emotional intelligence factors played a role in predicting the use of reappraisal and suppression. This work provides new insights regarding the decoding of individual differences from structural features and other psychologically relevant variables while extending previous observations on the neural bases of emotion regulation strategies.

"Holding in Anger" as a Mediator in the Relationship between Attachment Orientations and Borderline Personality Features

Insecure attachment and difficulties in regulating anger have both been put forward as possible explanations for emotional dysfunction in borderline personality (BP). This study aimed to test a model according to which the influence of attachment on BP features in a subclinical population is mediated by anger regulation. In a sample of 302 participants, BP features were assessed with the Borderline features scale of the Personality Assessment Inventory (PAI-BOR), attachment was measured with the Experiences in Close Relationships-12 (ECR-12), and trait anger and anger regulation were assessed with the State and Trait Anger Expression Inventory-2 (STAXI-2). The results indicated that anger suppression emerged as a significant mediator of the associations between both anxious and avoidant attachment and BP traits, while anger control resulted as a marginal mediator in the association between attachment avoidance and BP. Suppressing anger may reflect different forms of cognitive or behavioural avoidance of anger, which may differ on the basis of attachment orientations. We argue that these results may have important clinical implications: the promotion of anger regulation in BP should be considered a critical treatment goal.

Abnormal Brain Circuits Characterize Borderline Personality and Mediate the Relationship between Childhood Traumas and Symptoms: A mCCA+jICA and Random Forest Approach

Borderline personality disorder (BPD) is a severe personality disorder whose neural bases are still unclear. Indeed, previous studies reported inconsistent findings concerning alterations in cortical and subcortical areas. In the present study, we applied for the first time a combination of an unsupervised machine learning approach known as multimodal canonical correlation analysis plus joint independent component analysis (mCCA+jICA), in combination with a supervised machine learning approach known as random forest, to possibly find covarying gray matter and white matter (GM-WM) circuits that separate BPD from controls and that are also predictive of this diagnosis. The first analysis was used to decompose the brain into independent circuits of covarying grey and white matter concentrations. The second method was used to develop a predictive model able to correctly classify new unobserved BPD cases based on one or more circuits derived from the first analysis. To this aim, we analyzed the structural images of patients with BPD and matched healthy controls (HCs). The results showed that two GM-WM covarying circuits, including basal ganglia, amygdala, and portions of the temporal lobes and of the orbitofrontal cortex, correctly classified BPD against HC. Notably, these circuits are affected by specific child traumatic experiences (emotional and physical neglect, and physical abuse) and predict symptoms severity in the interpersonal and impulsivity domains. These results support that BPD is characterized by anomalies in both GM and WM circuits related to early traumatic experiences and specific symptoms.

Decoding individual differences in expressing and suppressing anger from structural brain networks: A supervised machine learning approach

Anger can be broken down into different elements: a transitory state (state anger), a stable personality feature (trait anger), a tendency to express it (anger-out), or to suppress it (anger-in), and the ability to regulate it (anger control). These elements are characterized by individual differences that vary across a continuum. Among them, the abilities to express and suppress anger are of particular relevance as they determine outcomes and enable successful anger management in daily situations. The aim of this study was to demonstrate that anger suppression and expression can be decoded by patterns of grey matter of specific well-known brain networks. To this aim, a supervised machine learning technique, known as Kernel Ridge Regression, was used to predict anger expression and suppression scores of 212 healthy subjects from the grey matter concentration. Results show that individual differences in anger suppression were predicted by two grey matter patterns associated with the Default-Mode Network and the Salience Network. Additionally, individual differences in anger expression were predicted by a circuit mainly involving subcortical and fronto-temporal regions when considering whole brain grey matter features. These results expand previous findings regarding the neural bases of anger by showing that individual differences in specific anger-related components can be predicted by the grey matter features of specific networks.

Anxious Brains: A Combined Data Fusion Machine Learning Approach to Predict Trait Anxiety from Morphometric Features

Trait anxiety relates to the steady propensity to experience and report negative emotions and thoughts such as fear and worries across different situations, along with a stable perception of the environment as characterized by threatening stimuli. Previous studies have tried to investigate neuroanatomical features related to anxiety mostly using univariate analyses and thus giving rise to contrasting results. The aim of this study is to build a predictive model of individual differences in trait anxiety from brain morphometric features, by taking advantage of a combined data fusion machine learning approach to allow generalization to new cases. Additionally, we aimed to perform a network analysis to test the hypothesis that anxiety-related networks have a central role in modulating other networks not strictly associated with anxiety. Finally, we wanted to test the hypothesis that trait anxiety was associated with specific cognitive emotion regulation strategies, and whether anxiety may decrease with ageing. Structural brain images of 158 participants were first decomposed into independent covarying gray and white matter networks with a data fusion unsupervised machine learning approach (Parallel ICA). Then, supervised machine learning (decision tree) and backward regression were used to extract and test the generalizability of a predictive model of trait anxiety. Two covarying gray and white matter independent networks successfully predicted trait anxiety. The first network included mainly parietal and temporal regions such as the postcentral gyrus, the precuneus, and the middle and superior temporal gyrus, while the second network included frontal and parietal regions such as the superior and middle temporal gyrus, the anterior cingulate, and the precuneus. We also found that trait anxiety was positively associated with catastrophizing, rumination, other- and self-blame, and negatively associated with positive refocusing and reappraisal. Moreover, trait anxiety was negatively associated with age. This paper provides new insights regarding the prediction of individual differences in trait anxiety from brain and psychological features and can pave the way for future diagnostic predictive models of anxiety.

Structural Features Related to Affective Instability Correctly Classify Patients With Borderline Personality Disorder. A Supervised Machine Learning Approach

Previous morphometric studies of Borderline Personality Disorder (BPD) reported inconsistent alterations in cortical and subcortical areas. However, these studies have investigated the brain at the voxel level using mass univariate methods or region of interest approaches, which are subject to several artifacts and do not enable detection of more complex patterns of structural alterations that may separate BPD from other clinical populations and healthy controls (HC). Multiple Kernel Learning (MKL) is a whole-brain multivariate supervised machine learning method able to classify individuals and predict an objective diagnosis based on structural features. As such, this method can help identifying objective biomarkers related to BPD pathophysiology and predict new cases. To this aim, we applied MKL to structural images of patients with BPD and matched HCs. Moreover, to ensure that results are specific for BPD and not for general psychological disorders, we also applied MKL to BPD against a group of patients with bipolar disorder, for their similarities in affective instability. Results showed that a circuit, including basal ganglia, amygdala, and portions of the temporal lobes and of the orbitofrontal cortex, correctly classified BPD against HC (80%). Notably, this circuit positively correlates with the affective sector of the Zanarini questionnaire, thus indicating an involvement of this circuit with affective disturbances. Moreover, by contrasting BPD with BD, the spurious regions were excluded, and a specific circuit for BPD was outlined. These results support that BPD is characterized by anomalies in a cortico-subcortical circuit related to affective instability and that this circuit discriminates BPD from controls and from other clinical populations.

Structural Features Predict Sexual Trauma and Interpersonal Problems in Borderline Personality Disorder but Not in Controls: A Multi-Voxel Pattern Analysis

Child trauma plays an important role in the etiology of Bordeline Personality Disorder (BPD). Of all traumas, sexual trauma is the most common, severe and most associated with receiving a BPD diagnosis when adult. Etiologic models posit sexual abuse as a prognostic factor in BPD. Here we apply machine learning using Multiple Kernel Regression to the Magnetic Resonance Structural Images of 20 BPD and 13 healthy control (HC) to see whether their brain predicts five sources of traumas: sex abuse, emotion neglect, emotional abuse, physical neglect, physical abuse (Child Trauma Questionnaire; CTQ). We also applied the same analysis to predict symptom severity in five domains: affective, cognitive, impulsivity, interpersonal (Zanarini Rating Scale for Borderline Personality Disorder; Zan-BPD) for BPD patients only. Results indicate that CTQ sexual trauma is predicted by a set of areas including the amygdala, the Heschl area, the Caudate, the Putamen, and portions of the Cerebellum in BPD patients only. Importantly, interpersonal problems only in BPD patients were predicted by a set of areas including temporal lobe and cerebellar regions. Notably, sexual trauma and interpersonal problems were not predicted by structural features in matched healthy controls. This finding may help elucidate the brain circuit affected by traumatic experiences and connected with interpersonal problems BPD suffer from.

Structural and functional brain networks of individual differences in trait anger and anger control: An unsupervised machine learning study

The ability to experience, use and eventually control anger is crucial to maintain well-being and build healthy relationships. Despite its relevance, the neural mechanisms behind individual differences in experiencing and controlling anger are poorly understood. To elucidate these points, we employed an unsupervised machine learning approach based on independent component analysis to test the hypothesis that specific functional and structural networks are associated with individual differences in trait anger and anger control. Structural and functional resting state images of 71 subjects as well as their scores from the State-Trait Anger Expression Inventory entered the analyses. At a structural level, the concentration of grey matter in a network including ventromedial temporal areas, posterior cingulate, fusiform gyrus and cerebellum was associated with trait anger. The higher the concentration, the higher the proneness to experience anger in daily life due to the greater tendency to orient attention towards aversive events and interpret them with higher hostility. At a functional level, the activity of the default mode network (DMN) was associated with anger control. The higher the DMN temporal frequency, the stronger the exerted control over anger, thus extending previous evidence on the role of the DMN in regulating cognitive and emotional functions in the domain of anger. Taken together, these results show, for the first time, two specialized brain networks for encoding individual differences in trait anger and anger control.