Diagnostic and Predictive Neuroimaging Biomarkers for Posttraumatic Stress Disorder

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.

Individual-Specific Animated Profiles of Mental Health

How important is the timing of the pretreatment evaluation? If we consider mental health to be a relatively fixed condition, the specific timing (e.g., day, hour) of the evaluation is immaterial and often determined on the basis of technical considerations. Indeed, the fundamental assumption underlying the vast majority of psychotherapy research and practice is that mental health is a state that can be captured in a one-dimensional snapshot. If this fundamental assumption, underlying 80 years of empirical research and practice, is incorrect, it may help explain why for decades psychotherapy failed to rise above the 50% efficacy rate in the treatment of mental-health disorders, especially depression, a heterogeneous disorder and the leading cause of disability worldwide. Based on recent studies suggesting within-individual dynamics, this article proposes that mental health and its underlying therapeutic mechanisms have underlying intrinsic dynamics that manifest across dimensions. Computational psychotherapy is needed to develop individual-specific pretreatment animated profiles of mental health. Such individual-specific animated profiles are expected to improve the ability to select the optimal treatment for each patient, devise adequate treatment plans, and adjust them on the basis of ongoing evaluations of mental-health dynamics, creating a new understanding of therapeutic change as a transition toward a more adaptive animated profile.

Systematic review of machine learning in PTSD studies for automated diagnosis evaluation

Post-traumatic stress disorder (PTSD) is frequently underdiagnosed due to its clinical and biological heterogeneity. Worldwide, many people face barriers to accessing accurate and timely diagnoses. Machine learning (ML) techniques have been utilized for early assessments and outcome prediction to address these challenges. This paper aims to conduct a systematic review to investigate if ML is a promising approach for PTSD diagnosis. In this review, statistical methods were employed to synthesize the outcomes of the included research and provide guidance on critical considerations for ML task implementation. These included (a) selection of the most appropriate ML model for the available dataset, (b) identification of optimal ML features based on the chosen diagnostic method, (c) determination of appropriate sample size based on the distribution of the data, and (d) implementation of suitable validation tools to assess the performance of the selected ML models. We screened 3186 studies and included 41 articles based on eligibility criteria in the final synthesis. Here we report that the analysis of the included studies highlights the potential of artificial intelligence (AI) in PTSD diagnosis. However, implementing AI-based diagnostic systems in real clinical settings requires addressing several limitations, including appropriate regulation, ethical considerations, and protection of patient privacy.

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.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Elucidating behavioral and functional connectivity markers of aberrant threat discrimination in PTSD

BACKGROUND

Patients with posttraumatic stress disorder (PTSD) tend to overgeneralize threat to safe stimuli, potentially reflecting aberrant stimuli discrimination. Yet, it is not clear whether threat overgeneralization reflects general discrimination deficits, or rather a specific bias related to aversive stimuli. Here we tested this question and characterized the neural correlates of threat discrimination.

METHODS

One-hundred and eight participants (33 PTSD; 43 trauma-exposed controls; 32 healthy controls) completed an emotionally neutral complex shape discrimination task involving identifying in 42 similar pairs the previously observed shape; and an emotionally aversive discrimination task, involving providing risk ratings for an aversive conditioned stimulus (CS+), and for several stimuli gradually differing in size from the original CS+. Resting state functional connectivity (rsFC) was collected before completing the tasks.

RESULTS

No group differences emerged on the emotionally neutral task. Conversely, on the emotionally aversive task, individuals with PTSD had steeper linear risk rating slopes as the stimuli more resembled the conditioned stimulus. Finally, lower rsFC of amygdala-default mode network (DMN) and DMN-salience network (SN) were associated with steeper risk slopes, while for hippocampus-SN, lower rsFC was found only among participants with PTSD.

CONCLUSIONS

Individuals with PTSD show deficits in discrimination only when presented with aversive stimuli. Dysregulated discrimination pattern may relate to a lack of input from regulatory brain areas (e.g., DMN/hippocampus) to threat-related brain areas (e.g., SN/amygdala).

Spontaneous brain activity, graph metrics, and head motion related to prospective post-traumatic stress disorder trauma-focused therapy response

Introduction

Trauma-focused psychotherapy for post-traumatic stress disorder (PTSD) is effective in about half of all patients. Investigating biological systems related to prospective treatment response is important to gain insight in mechanisms predisposing patients for successful intervention. We studied if spontaneous brain activity, brain network characteristics and head motion during the resting state are associated with future treatment success.

Methods

Functional magnetic resonance imaging scans were acquired from 46 veterans with PTSD around the start of treatment. Psychotherapy consisted of trauma-focused cognitive behavioral therapy (tf-CBT), eye movement desensitization and reprocessing (EMDR), or a combination thereof. After intervention, 24 patients were classified as treatment responders and 22 as treatment resistant. Differences between groups in spontaneous brain activity were evaluated using amplitude of low-frequency fluctuations (ALFF), while global and regional brain network characteristics were assessed using a minimum spanning tree (MST) approach. In addition, in-scanner head motion was assessed.

Results

No differences in spontaneous brain activity and global network characteristics were observed between the responder and non-responder group. The right inferior parietal lobule, right putamen and left superior parietal lobule had a more central position in the network in the responder group compared to the non-responder group, while the right dorsolateral prefrontal cortex (DLPFC), right inferior frontal gyrus and left inferior temporal gyrus had a less central position. In addition, responders showed less head motion.

Discussion

These results show that areas involved in executive functioning, attentional and action processes, learning, and visual-object processing, are related to prospective PTSD treatment response in veterans. In addition, these findings suggest that involuntary micromovements may be related to future treatment success.

Cortico-Striatal Activity Characterizes Human Safety Learning via Pavlovian Conditioned Inhibition

Safety learning generates associative links between neutral stimuli and the absence of threat, promoting the inhibition of fear and security-seeking behaviors. Precisely how safety learning is mediated at the level of underlying brain systems, particularly in humans, remains unclear. Here, we integrated a novel Pavlovian conditioned inhibition task with ultra-high field (7 Tesla) fMRI to examine the neural basis of safety learning in 49 healthy participants. In our task, participants were conditioned to two safety signals: a conditioned inhibitor that predicted threat omission when paired with a known threat signal (A+/AX-), and a standard safety signal that generally predicted threat omission (BC-). Both safety signals evoked equivalent autonomic and subjective learning responses but diverged strongly in terms of underlying brain activation (PFDR whole-brain corrected). The conditioned inhibitor was characterized by more prominent activation of the dorsal striatum, anterior insular, and dorsolateral PFC compared with the standard safety signal, whereas the latter evoked greater activation of the ventromedial PFC, posterior cingulate, and hippocampus, among other regions. Further analyses of the conditioned inhibitor indicated that its initial learning was characterized by consistent engagement of dorsal striatal, midbrain, thalamic, premotor, and prefrontal subregions. These findings suggest that safety learning via conditioned inhibition involves a distributed cortico-striatal circuitry, separable from broader cortical regions involved with processing standard safety signals (e.g., CS-). This cortico-striatal system could represent a novel neural substrate of safety learning, underlying the initial generation of "stimulus-safety" associations, distinct from wider cortical correlates of safety processing, which facilitate the behavioral outcomes of learning.SIGNIFICANCE STATEMENT Identifying safety is critical for maintaining adaptive levels of anxiety, but the neural mechanisms of human safety learning remain unclear. Using 7 Tesla fMRI, we compared learning-related brain activity for a conditioned inhibitor, which actively predicted threat omission, and a standard safety signal (CS-), which was passively unpaired with threat. The inhibitor engaged an extended circuitry primarily featuring the dorsal striatum, along with thalamic, midbrain, and premotor/PFC regions. The CS- exclusively involved cortical safety-related regions observed in basic safety conditioning, such as the vmPFC. These findings extend current models to include learning-specific mechanisms for encoding stimulus-safety associations, which might be distinguished from expression-related cortical mechanisms. These insights may suggest novel avenues for targeting dysfunctional safety learning in psychopathology.

Using deep learning to classify pediatric posttraumatic stress disorder at the individual level

BACKGROUND

Children exposed to natural disasters are vulnerable to developing posttraumatic stress disorder (PTSD). Previous studies using resting-state functional neuroimaging have revealed alterations in graph-based brain topological network metrics in pediatric PTSD patients relative to healthy controls (HC). Here we aimed to apply deep learning (DL) models to neuroimaging markers of classification which may be of assistance in diagnosis of pediatric PTSD.

METHODS

We studied 33 pediatric PTSD and 53 matched HC. Functional connectivity between 90 brain regions from the automated anatomical labeling atlas was established using partial correlation coefficients, and the whole-brain functional connectome was constructed by applying a threshold to the resultant 90 * 90 partial correlation matrix. Graph theory analysis was used to examine the topological properties of the functional connectome. A DL algorithm then used this measure to classify pediatric PTSD vs HC.

RESULTS

Graphic topological measures using DL provide a potentially clinically useful classifier for differentiating pediatric PTSD and HC (overall accuracy 71.2%). Frontoparietal areas (central executive network), cingulate cortex, and amygdala contributed the most to the DL model's performance.

CONCLUSIONS

Graphic topological measures based on fMRI data could contribute to imaging models of clinical utility in distinguishing pediatric PTSD from HC. DL model may be a useful tool in the identification of brain mechanisms PTSD participants.

Defining focal brain stimulation targets for PTSD using neuroimaging

INTRODUCTION

Focal brain stimulation has potential as a treatment for posttraumatic stress disorder (PTSD). In this review, we aim to inform selection of focal brain stimulation targets for treating PTSD by examining studies of the functional neuroanatomy of PTSD and treatment response. We first briefly review data on brain stimulation interventions for PTSD. Although published data suggest good efficacy overall, the neurobiological rationale for each stimulation target is not always clear.

METHODS

Therefore, we assess pre- and post-treatment (predominantly psychotherapy) functional neuroimaging studies in PTSD to determine which brain changes seem critical to treatment response. Results of these studies are presented within a previously proposed functional neural systems model of PTSD.

RESULTS

While not completely consistent, research suggests that downregulating the fear learning and threat and salience detection circuits (i.e., amygdala, dorsal anterior cingulate cortex and insula) and upregulating the emotion regulation and executive function and contextual processing circuits (i.e., prefrontal cortical regions and hippocampus) may mediate PTSD treatment response.

CONCLUSION

This literature review provides some justification for current focal brain stimulation targets. However, the examination of treatment effects on neural networks is limited, and studies that include the stimulation targets are lacking. Further, additional targets, such as the cingulate, medial prefrontal cortex, and inferior parietal lobe, may also be worth investigation, especially when considering how to achieve network level changes. Additional research combining PTSD treatment with functional neuroimaging will help move the field forward by identifying and validating novel targets, providing better rationale for specific treatment parameters and personalizing treatment for PTSD.

Machine Learning Methods to Evaluate the Depression Status of Chinese Recruits: A Diagnostic Study

PURPOSE

Traditional questionnaires assessing the severity of depression are limited and might not be appropriate for military personnel. We intend to explore the diagnostic ability of three machine learning methods for evaluating the depression status of Chinese recruits, using the Chinese version of Beck Depression Inventory-II (BDI-II) as the standard.

PATIENTS AND METHODS

Our diagnostic study was carried out in Luoyang City (Henan Province, China; 10/16/2018-12/10/2018) with a sample of 1000 Chinese male recruits selected using cluster convenient sampling. All participants completed the BDI and 3 questionnaires including the data of demographics, military careers and 18 factors. The participants were randomly selected as the training set and the testing at 2:1. The machine learning methods tested for assessing the presence or absence of depression status were neural network (NN), support vector machine (SVM), and decision tree (DT).

RESULTS

A total of 1000 participants completed the questionnaires, with 223 reporting depression status and 777 not. The highest sensitivity was observed for DT (94.1%), followed by SVM (93.4%) and NN (93.1%). The highest specificity was observed for NN (60.0%), followed by SVM (58.8%) and DT (43.3%). The area under the curve (AUC) of the SVM was the largest (0.862) compared with NN (0.860) and DT (0.734). The regression prediction error and error volatility of the SVM were the smallest.

CONCLUSION

The SVM has the smallest prediction error and error volatility, as well as the largest AUC compared with NN and DT for assessing the presence or absence of depression status in Chinese recruits.