Multivariate classification of earthquake survivors with post-traumatic stress disorder based on large-scale brain networks

Deep learning based diagnosis of PTSD using 3D-CNN and resting-state fMRI data

BACKGROUND

The incidence rate of Posttraumatic stress disorder (PTSD) is currently increasing due to wars, terrorism, and pandemic disease situations. Therefore, accurate detection of PTSD is crucial for the treatment of the patients, for this purpose, the present study aims to classify individuals with PTSD versus healthy control.

METHODS

The resting-state functional MRI (rs-fMRI) scans of 19 PTSD and 24 healthy control male subjects have been used to identify the activation pattern in most affected brain regions using group-level independent component analysis (ICA) and t-test. To classify PTSD-affected subjects from healthy control six machine learning techniques including random forest, Naive Bayes, support vector machine, decision tree, K-nearest neighbor, linear discriminant analysis, and deep learning three-dimensional 3D-CNN have been performed on the data and compared.

RESULTS

The rs-fMRI scans of the most commonly investigated 11 regions of trauma-exposed and healthy brains are analyzed to observe their level of activation. Amygdala and insula regions are determined as the most activated regions from the regions-of-interest in the brain of PTSD subjects. In addition, machine learning techniques have been applied to the components extracted from ICA but the models provided low classification accuracy. The ICA components are also fed into the 3D-CNN model, which is trained with a 5-fold cross-validation method. The 3D-CNN model demonstrated high accuracies, such as 98.12%, 98.25 %, and 98.00 % on average with training, validation, and testing datasets, respectively.

CONCLUSION

The findings indicate that 3D-CNN is a surpassing method than the other six considered techniques and it helps to recognize PTSD patients accurately.

Application of machine learning techniques in the diagnostic approach of PTSD using MRI neuroimaging data: A systematic review

Background

At present, the diagnosis of post-traumatic stress disorder（PTSD） mainly relies on clinical symptoms and psychological scales, and finding objective indicators that are helpful for diagnosis has always been a challenge in clinical practice and academic research. Neuroimaging is a useful and powerful tool for discovering the biomarkers of PTSD,especially functional MRI (fMRI), structural MRI (sMRI) and Diffusion Weighted Imaging（DTI）are the most commonly used technologies, which can provide multiple perspectives on brain function, structure and its connectivity. Machine learning (ML) is an emerging and potentially powerful method, which has aroused people's interest because it is used together with neuroimaging data to define brain structural and functional abnormalities related to diseases, and identify phenotypes, such as helping physicians make early diagnosis.

Objectives

According to the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) declaration, a systematic review was conducted to assess its accuracy in distinguishing between PTSD patients, TEHC(Trauma-Exposed Healthy Controls), and HC(healthy controls).

Methods

We searched PubMed, Embase, and Web of Science using common words for ML methods and PTSD until June 2023, with no language or time limits. This review includes 13 studies, with sensitivity, specificity, and accuracy taken from each publication or acquired directly from the authors.

Results

All ML techniques have an diagnostic accuracy rate above 70%，and support vector machine（SVM） are the most commonly used techniques. This series of studies has revealed significant neurobiological differences in key brain regions among individuals with PTSD, TEHC, and HC. The connectivity patterns of regions such as the Insula and Amygdala hold particular significance in distinguishing these groups. TEHC exhibits more normal connectivity patterns compared to PTSD, providing valuable insights for the application of machine learning in PTSD diagnosis.

Conclusion

In contrast to any currently available assessment and clinical diagnosis, ML techniques can be used as an effective and non-invasive support for early identification and detection of patients as well as for early screening of high-risk populations.

Neural correlates of PTSD in women with childhood sexual abuse with and without PTSD and response to paroxetine treatment: A placebo-controlled, double-blind trial

Objective

Childhood sexual abuse is the leading cause of posttraumatic stress disorder (PTSD) in women, and is a prominent cause of morbidity and loss of function for which limited treatments are available. Understanding the neurobiology of treatment response is important for developing new treatments. The purpose of this study was to assess neural correlates of personalized traumatic memories in women with childhood sexual abuse with and without PTSD, and to assess response to treatment.

Methods

Women with childhood sexual abuse with (N = 28) and without (N = 17) PTSD underwent brain imaging with High-Resolution Positron Emission Tomography scanning with radiolabeled water for brain blood flow measurements during exposure to personalized traumatic scripts and memory encoding tasks. Women with PTSD were randomized to paroxetine or placebo followed by three months of double-blind treatment and repeat imaging with the same protocol.

Results

Women with PTSD showed decreases in areas involved in the Default Mode Network (DMN), a network of brain areas usually active when the brain is at rest, hippocampus and visual processing areas with exposure to traumatic scripts at baseline while women without PTSD showed increased activation in superior frontal gyrus and other areas (p < 0.005). Treatment of women with PTSD with paroxetine resulted in increased anterior cingulate activation and brain areas involved in the DMN and visual processing with scripts compared to placebo (p < 0.005).

Conclusion

PTSD related to childhood sexual abuse in women is associated with alterations in brain areas involved in memory and the stress response and treatment with paroxetine results in modulation of these areas.

Multivariate classification based on large-scale brain networks during early abstinence predicted lapse among male detoxified alcohol-dependent patients

Identifying biomarkers to predict lapse of alcohol-dependence (AD) is essential for treatment and prevention strategies, but remains remarkably challenging. With an aim to identify neuroimaging features for predicting AD lapse, 66 male AD patients during early-abstinence (baseline) after hospitalized detoxification underwent resting-state functional magnetic resonance imaging and were then followed-up for 6 months. The relevance-vector-machine (RVM) analysis on baseline large-scale brain networks yielded an elegant model for differentiating relapsing patients (n = 38) from abstainers, with the area under the curve of 0.912 and the accuracy by leave-one-out cross-validation of 0.833. This model captured key information about neuro-connectome biomarkers for predicting AD lapse.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Brain functional network changes associated with psychological symptoms in emergency psychological responding professionals after the first wave of COVID-19 pandemic

Background

Emergency psychological responding professionals are recruited to help deal with psychological issues as the Corona Virus Disease 2019 (COVID-19) continues. We aimed to study the neural correlates of psychological states in these emergency psychological responding professionals after exposure to COVID-19 related trauma at baseline and after 1-year self-adjustment.

Methods

Resting-state functional MRI (rs-fMRI) and multiscale network approaches were utilized to evaluate the functional brain activities in emergency psychological professionals after trauma. Temporal (baseline vs. follow-up) and cross-sectional (emergency psychological professionals vs. healthy controls) differences were studied using appropriate t-tests. The brain functional network correlates of psychological symptoms were explored.

Results

At either time-point, significant changes in the ventral attention (VEN) and the default mode network (DMN) were associated with psychological symptoms in emergency psychological professionals. In addition, the emergency psychological professionals whose mental states improved after 1 year demonstrated altered intermodular connectivity strength between several modules in the functional network, mainly linking the DMN, VEN, limbic, and frontoparietal control modules.

Conclusion

Brain functional network alterations and their longitudinal changes varied across groups of EPRT with distinctive clinical features. Exposure to emergent trauma does cause psychological professionals to produce DMN and VEN network changes related to psychological symptoms. About 65% of them will gradually adjust mental states, and the network tends to be rebalanced after a year.

Modern views of machine learning for precision psychiatry

In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

A dynamic graph convolutional neural network framework reveals new insights into connectome dysfunctions in ADHD

The pathological mechanism of attention deficit hyperactivity disorder (ADHD) is incompletely specified, which leads to difficulty in precise diagnosis. Functional magnetic resonance imaging (fMRI) has emerged as a common neuroimaging technique for studying the brain functional connectome. Most existing methods that have either ignored or simply utilized graph structure, do not fully leverage the potentially important topological information which may be useful in characterizing brain disorders. There is a crucial need for designing novel and efficient approaches which can capture such information. To this end, we propose a new dynamic graph convolutional network (dGCN), which is trained with sparse brain regional connections from dynamically calculated graph features. We also develop a novel convolutional readout layer to improve graph representation. Our extensive experimental analysis demonstrates significantly improved performance of dGCN for ADHD diagnosis compared with existing machine learning and deep learning methods. Visualizations of the salient regions of interest (ROIs) and connectivity based on informative features learned by our model show that the identified functional abnormalities mainly involve brain regions in temporal pole, gyrus rectus, and cerebellar gyri from temporal lobe, frontal lobe, and cerebellum, respectively. A positive correlation was further observed between the identified connectomic abnormalities and ADHD symptom severity. The proposed dGCN model shows great promise in providing a functional network-based precision diagnosis of ADHD and is also broadly applicable to brain connectome-based study of mental disorders.

Predicting Delayed Neurocognitive Recovery After Non-cardiac Surgery Using Resting-State Brain Network Patterns Combined With Machine Learning

Delayed neurocognitive recovery (DNR) is a common subtype of postoperative neurocognitive disorders. An objective approach for identifying subjects at high risk of DNR is yet lacking. The present study aimed to predict DNR using the machine learning method based on multiple cognitive-related brain network features. A total of 74 elderly patients (≥ 60-years-old) undergoing non-cardiac surgery were subjected to resting-state functional magnetic resonance imaging (rs-fMRI) before the surgery. Seed-based whole-brain functional connectivity (FC) was analyzed with 18 regions of interest (ROIs) located in the default mode network (DMN), limbic network, salience network (SN), and central executive network (CEN). Multiple machine learning models (support vector machine, decision tree, and random forest) were constructed to recognize the DNR based on FC network features. The experiment has three parts, including performance comparison, feature screening, and parameter adjustment. Then, the model with the best predictive efficacy for DNR was identified. Finally, independent testing was conducted to validate the established predictive model. Compared to the non-DNR group, the DNR group exhibited aberrant whole-brain FC in seven ROIs, including the right posterior cingulate cortex, right medial prefrontal cortex, and left lateral parietal cortex in the DMN, the right insula in the SN, the left anterior prefrontal cortex in the CEN, and the left ventral hippocampus and left amygdala in the limbic network. The machine learning experimental results identified a random forest model combined with FC features of DMN and CEN as the best prediction model. The area under the curve was 0.958 (accuracy = 0.935, precision = 0.899, recall = 0.900, F1 = 0.890) on the test set. Thus, the current study indicated that the random forest machine learning model based on rs-FC features of DMN and CEN predicts the DNR following non-cardiac surgery, which could be beneficial to the early prevention of DNR. Clinical Trial Registration: The study was registered at the Chinese Clinical Trial Registry (Identification number: ChiCTR-DCD-15006096).

Impact of exogenous estradiol on task-based and resting-state neural signature during and after fear extinction in healthy women

Fluctuations of endogenous estrogen modulates fear extinction, but the influence of exogenous estradiol is less studied. Moreover, little focus has been placed on the impact of estradiol on broad network connectivity beyond the fear extinction circuit. Here, we examined the effect of acute exogenous estradiol administration on fear extinction-induced brain activation, whole-brain functional connectivity (FC) during the fear extinction task and post-extinction resting-state. Ninety healthy women (57 using oral contraceptives [OC], 33 naturally cycling [NC]) were fear conditioned on day 1. They ingested an estradiol or placebo pill prior to extinction learning on day 2 (double-blind design). Extinction memory was assessed on day 3. Task-based functional MRI data were ascertained on days 2 and 3 and resting-state data were collected post-extinction on day 2 and pre-recall on day 3. Estradiol administration significantly modulated the neural signature associated with fear extinction learning and memory, consistent with prior studies. Importantly, estradiol administration induced significant changes in FC within multiple networks, including the default mode and somatomotor networks during extinction learning, post-extinction, and during extinction memory recall. Exploratory analyses revealed that estradiol impacted ventromedial prefrontal cortex (vmPFC) activation and FC differently in the NC and OC women. The data implicate a more diffused and significant effect of acute estradiol administration on multiple networks. Such an effect might be beneficial to modulating attention and conscious processes in addition to engaging neural processes associated with emotional learning and memory consolidation.

Dorsal attention network centrality increases during recovery from acute stress exposure

Stress is a major risk factor for the development of almost all psychiatric disorders. In addition to the acute stress response, an efficient recovery in the aftermath of stress is important for optimal resilience. Increased stress vulnerability across psychiatric disorders may therefore be related to altered trajectories during the recovery phase following stress. Such recovery trajectories can be quantified by changes in functional brain networks. This study therefore evaluated longitudinal functional network changes related to stress in healthy individuals (N = 80), individuals at risk for psychiatric disorders (healthy siblings of schizophrenia patients) (N = 39), and euthymic bipolar I disorder (BD) patients (N = 36). Network changes were evaluated before and at 20 and 90 min after onset of an experimental acute stress task (Trier Social Stress Test) or a control condition. Whole-brain functional networks were analyzed using eigenvector centrality as a proxy for network importance, centrality change over time was related to the acute stress response and recovery for each group. In healthy individuals, centrality of the dorsal attention network (DAN; p = 0.007) changed over time in relation to stress. More specifically, DAN centrality increased during the recovery phase after acute stress exposure (p = 0.020), while no DAN centrality change was observed during the initial stress response (p = 0.626). Such increasing DAN centrality during stress recovery was also found in healthy siblings (p = 0.016), but not in BD patients (p = 0.554). This study highlights that temporally complex and precise changes in network configuration are vital to understand the response to and recovery from stress.

Altered resting-state functional connectivity of the default mode and central executive networks following cognitive processing therapy for PTSD

Psychotherapy research is increasingly targeting both psychological and neurobiological mechanisms of therapeutic change. This trend is evident in and applicable to post-traumatic stress disorder (PTSD) treatment research given the high nonresponse rate of individuals with PTSD who undergo cognitive-behavioral therapy (CBT). Functional connectivity analyses investigating disrupted brain networks across mental disorders have been employed to understand both mental disorder symptoms and therapeutic mechanisms. However, few studies have examined pre-post CBT brain changes in PTSD using functional connectivity analyses. The current study investigated a) whether brain networks commonly implicated in psychopathology (e.g., default mode network [DMN], central executive network [CEN], and salience network [SN]) changed following Cognitive Processing Therapy (CPT) for PTSD and b) whether change in these networks was associated with PTSD and/or transdiagnostic symptom change. Independent components analysis was implemented to investigate resting-state functional connectivity in DMN, CEN, and SN in 42 women with PTSD and 18 trauma-exposed controls (TEC). Results indicated decreased CEN-cerebellum connectivity in PTSD participants versus TEC prior to CPT and decreased DMN connectivity in PTSD participants after CPT. Additionally, DMN and SN connectivity was related to change in positive and negative affectivity, while exploratory analyses at a cluster threshold of pFDR < .10 indicated DMN and SN connectivity was also related to change in PTSD symptoms and rumination. These findings provide evidence for normalization of CEN connectivity with treatment and implicate the DMN and SN in clinical symptom change following CPT.

Identification of psychiatric disorder subtypes from functional connectivity patterns in resting-state electroencephalography

The understanding and treatment of psychiatric disorders, which are known to be neurobiologically and clinically heterogeneous, could benefit from the data-driven identification of disease subtypes. Here, we report the identification of two clinically relevant subtypes of post-traumatic stress disorder (PTSD) and major depressive disorder (MDD) on the basis of robust and distinct functional connectivity patterns, prominently within the frontoparietal control network and the default mode network. We identified the disease subtypes by analysing, via unsupervised and supervised machine learning, the power-envelope-based connectivity of signals reconstructed from high-density resting-state electroencephalography in four datasets of patients with PTSD and MDD, and show that the subtypes are transferable across independent datasets recorded under different conditions. The subtype whose functional connectivity differed most from those of healthy controls was less responsive to psychotherapy treatment for PTSD and failed to respond to an antidepressant medication for MDD. By contrast, both subtypes responded equally well to two different forms of repetitive transcranial magnetic stimulation therapy for MDD. Our data-driven approach may constitute a generalizable solution for connectome-based diagnosis.

Hippocampal subfield alterations in pediatric patients with post-traumatic stress disorder

The hippocampus, a key structure with distinct subfield functions, is strongly implicated in the pathophysiology of post-traumatic stress disorder (PTSD); however, few studies of hippocampus subfields in PTSD have focused on pediatric patients. We therefore investigated the hippocampal subfield volume using an automated segmentation method and explored the subfield-centered functional connectivity aberrations related to the anatomical changes, in a homogenous population of traumatized children with and without PTSD. To investigate the potential diagnostic value in individual patients, we used a machine learning approach to identify features with significant discriminative power for diagnosis of PTSD using random forest classifiers. Compared to controls, we found significant mean volume reductions of 8.4% and 9.7% in the right presubiculum and hippocampal tail in patients, respectively. These two subfields' volumes were the most significant contributors to group discrimination, with a mean classification accuracy of 69% and a specificity of 81%. These anatomical alterations, along with the altered functional connectivity between (pre)subiculum and inferior frontal gyrus, may underlie deficits in fear circuitry leading to dysfunction of fear extinction and episodic memory, causally important in post-traumatic symptoms such as hypervigilance and re-experience. For the first time, we suggest that hippocampal subfield volumes might be useful in discriminating traumatized children with and without PTSD.

Multi-View Multi-Scale Optimization of Feature Representation for EEG Classification Improvement

Effectively extracting common space pattern (CSP) features from motor imagery (MI) EEG signals is often highly dependent on the filter band selection. At the same time, optimizing the EEG channel combinations is another key issue that substantially affects the SMR feature representations. Although numerous algorithms have been developed to find channels that record important characteristics of MI, most of them select channels in a cumbersome way with low computational efficiency, thereby limiting the practicality of MI-based BCI systems. In this study, we propose the multi-scale optimization (MSO) of spatial patterns, optimizing filter bands over multiple channel sets within CSPs to further improve the performance of MI-based BCI. Specifically, several channel subsets are first heuristically predefined, and then raw EEG data specific to each of these subsets bandpass-filtered at the overlap between a set of filter bands. Further, instead of solving learning problems for each channel subset independently, we propose a multi-view learning based sparse optimization to jointly extract robust CSP features with L_2,1 -norm regularization, aiming to capture the shared salient information across multiple related spatial patterns for enhanced classification performance. A support vector machine (SVM) classifier is then trained on these optimized EEG features for accurate recognition of MI tasks. Experimental results on three public EEG datasets validate the effectiveness of MSO compared to several other competing methods and their variants. These superior experimental results demonstrate that the proposed MSO method has promising potential in MI-based BCIs.

Individualized Prediction of PTSD Symptom Severity in Trauma Survivors From Whole-Brain Resting-State Functional Connectivity

Previous studies have demonstrated relations between spontaneous neural activity evaluated by resting-state functional magnetic resonance imaging (fMRI) and symptom severity in post-traumatic stress disorder. However, few studies have used brain-based measures to identify imaging associations with illness severity at the level of individual patients. This study applied connectome-based predictive modeling (CPM), a recently developed data-driven and subject-level method, to identify brain function features that are related to symptom severity of trauma survivors. Resting-state fMRI scans and clinical ratings were obtained 10-15 months after the earthquake from 122 earthquake survivors. Symptom severity of post-traumatic stress disorder features for each survivor was evaluated using the Clinician Administered Post-traumatic Stress Disorder Scale (CAPS-IV). A functionally pre-defined atlas was applied to divide the human brain into 268 regions. Each individual's functional connectivity 268 × 268 matrix was created to reflect correlations of functional time series data across each pair of nodes. The relationship between CAPS-IV scores and brain functional connectivity was explored in a CPM linear model. Using a leave-one-out cross-validation (LOOCV) procedure, findings showed that the positive network model predicted the left-out individual's CAPS-IV scores from resting-state functional connectivity. CPM predicted CAPS-IV scores, as indicated by a significant correspondence between predicted and actual values (r = 0.30, P = 0.001) utilizing primarily functional connectivity between visual cortex, subcortical-cerebellum, limbic, and motor systems. The current study provides data-driven evidence regarding the functional brain features that predict symptom severity based on the organization of intrinsic brain networks and highlights its potential application in making clinical evaluation of symptom severity at the individual level.

Mechanisms Underlying Unconscious Processing and Their Alterations in Post-traumatic Stress Disorder: Neuroimaging of Zero Monetary Outcomes Contextually Framed as "No Losses" vs. "No Gains"

Although unconscious processing is a key element of mental operation, its neural correlates have not been established. Also, clinical observations suggest that unconscious processing may be involved in the pathophysiology of post-traumatic stress disorder (PTSD), but the neurobiological mechanisms underlying such impairments remain unknown. The purpose of the present study was to examine putative mechanisms underlying unconscious processing by healthy participants and to determine whether these mechanisms may be altered in PTSD patients. Twenty patients with PTSD and 27 healthy individuals were administered a validated wheel of fortune-type gambling task during functional magnetic resonance imaging (fMRI). Unconscious processing was elicited using unconscious contextual framing of the zero monetary outcomes as "no loss," "no gain" or as "neutral." Brief passive visual processing of the "no loss" vs. "no gain" contrast by healthy participants yielded bilateral frontal-, temporal- and insular cortices and striatal activations. Between-group comparison revealed smaller activity in the left anterior prefrontal-, left dorsolateral prefrontal-, right temporal- and right insular cortices and in bilateral striatum in PTSD patients with the left dorsolateral prefrontal cortex activity been more pronounced in those with greater PTSD severity. These observations implicate frontal-, temporal-, and insular cortices along with the striatum in the putative mechanisms underlying unconscious processing of the monetary outcomes. Additionally, our results support the hypothesis that PTSD is associated with primary cortical and subcortical alterations involved in the above processes and that these alterations may be related to some aspects of PTSD symptomatology.