Multivoxel pattern analysis of structural MRI in children and adolescents with conduct disorder

Age-related, multivariate associations between white matter microstructure and behavioral performance in three executive function domains

The executive function (EF) domains of working memory (WM), response inhibition (RI), and set shifting (SS) show maturational gains and are linked to neuroimaging-measured brain changes. This study explored ways in which maturation-linked differences in EF abilities are systematically associated with white matter microstructural differences from adolescence into young adulthood. Diffusion tensor imaging (DTI) and nine neurocognitive tests were collected from 120 healthy subjects ages 12-24. Analyses across the white matter skeleton were performed, focusing on fractional anisotropy (FA). Data were 'fused' using a multivariate technique (CCA+jICA), producing four independent components (ICs) depicting white matter FA values that covaried with test performance. Correlations between age and IC loading coefficients identified three EF-DTI profiles that may change developmentally. In one, SS performance was linked to greater reliance on the FA of ventral brain tracts, and less on dorsal tracts with age. In another, white matter microstructure was related to a pattern of strong WM and weak SS that became more pronounced with age. A final IC revealed that younger individuals with low RI and high WM/SS skills typically matured out of this cognitive imbalance, underscored by white matter changes with age. These novel multivariate results begin to emphasize the complexity of brain structure-cognition relationships in adolescents and young adults.

Identification and effective connections of core networks in patients with temporal lobe epilepsy and cognitive impairment: Granger causality analysis and multivariate pattern analysis

OBJECTIVE

This study aimed to explore effective connectivity (EC) of the core networks in cognition impairment associated with temporal lobe epilepsy (CI-TLE) by applying resting state and Granger causality analysis (REST-GCA). The specific brain regions that played a critical role in classification were assessed using multivariate pattern analysis (MVPA).

METHODS

Thirty-two patients with CI-TLE and 29 healthy controls who were matched based on age and gender underwent functional magnetic resonance imaging (fMRI).

RESULTS

REST-GCA revealed that patients with CI-TLE displayed decreased GC values in the following brain areas: from the posterior cingulate cortex (PCC) to the left fusiform gyrus (lFFG) and the right parahippocampal gyrus (rPPG); from the right dorsal prefrontal cortex (rDPFC) to the left superior parietal lobule (lSPL); from the left amygdala (lAG) to the PCC. Inhibitory EC was observed from the rDPFC to the PCC compared to HCs. The GC values increased from the right dorsal prefrontal cingulate cortex (rdACC) to the PCC and from the right dorsal forebrain insula (rDAI) to the right middle temporal gyrus (rMTG) in the CI-TLE patients. MVPA showed that the classification yielded an accuracy of 81.91% (78.12%, specificity =85.71%).

CONCLUSION

Our observations indicated that the abnormal EC between the frontal and parietal regions might be associated with the pathophysiological mechanism of CI-TLE. These results also indicated that EC might be play a role as a potential discriminative pattern to detect CI-TLE in patients.

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.

Classifying Conduct Disorder Using a Biopsychosocial Model and Machine Learning Method

BACKGROUND

Conduct disorder (CD) is a common syndrome with far-reaching effects. Risk factors for the development of CD span social, psychological, and biological domains. Researchers note that predictive models of CD are limited if the focus is on a single risk factor or even a single domain. Machine learning methods are optimized for the extraction of trends across multidomain data but have yet to be implemented in predicting the development of CD.

METHODS

Social (e.g., family, income), psychological (e.g., psychiatric, neuropsychological), and biological (e.g., resting-state graph metrics) risk factors were measured using data from the baseline visit of the Adolescent Brain Cognitive Development Study when youth were 9 to 10 years old (N = 2368). Applying a feed-forward neural network machine learning method, risk factors were used to predict CD diagnoses 2 years later.

RESULTS

A model with factors that included social, psychological, and biological domains outperformed models representing factors within any single domain, predicting the presence of a CD diagnosis with 91.18% accuracy. Within each domain, certain factors stood out in terms of their relationship to CD (social: lower parental monitoring, more aggression in the household, lower income; psychological: greater attention-deficit/hyperactivity disorder and oppositional defiant disorder symptoms, worse crystallized cognition and card sorting performance; biological: disruptions in the topology of subcortical and frontoparietal networks).

CONCLUSIONS

The development of an accurate, sensitive, and specific predictive model of CD has the potential to aid in prevention and intervention efforts. Key risk factors for CD appear best characterized as reflecting unpredictable, impulsive, deprived, and emotional external and internal contexts.

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.

The computational psychiatry of antisocial behaviour and psychopathy

Antisocial behaviours such as disobedience, lying, stealing, destruction of property, and aggression towards others are common to multiple disorders of childhood and adulthood, including conduct disorder, oppositional defiant disorder, psychopathy, and antisocial personality disorder. These disorders have a significant negative impact for individuals and for society, but whether they represent clinically different phenomena, or simply different approaches to diagnosing the same underlying psychopathology is highly debated. Computational psychiatry, with its dual focus on identifying different classes of disorder and health (data-driven) and latent cognitive and neurobiological mechanisms (theory-driven), is well placed to address these questions. The elucidation of mechanisms that might characterise latent processes across different disorders of antisocial behaviour can also provide important advances. In this review, we critically discuss the contribution of computational research to our understanding of various antisocial behaviour disorders, and highlight suggestions for how computational psychiatry can address important clinical and scientific questions about these disorders in the future.

Identifying and distinguishing of essential tremor and Parkinson's disease with grouped stability analysis based on searchlight-based MVPA

BACKGROUND

Since both essential tremor (ET) and Parkinson's disease (PD) are movement disorders and share similar clinical symptoms, it is very difficult to recognize the differences in the presentation, course, and treatment of ET and PD, which leads to misdiagnosed commonly.

PURPOSE

Although neuroimaging biomarker of ET and PD has been investigated based on statistical analysis, it is unable to assist the clinical diagnosis of ET and PD and ensure the efficiency of these biomarkers. The aim of the study was to identify the neuroimaging biomarkers of ET and PD based on structural magnetic resonance imaging (MRI). Moreover, the study also distinguished ET from PD via these biomarkers to validate their classification performance.

METHODS

This study has developed and implemented a three-level machine learning framework to identify and distinguish ET and PD. First of all, at the model-level assessment, the searchlight-based machine learning method has been used to identify the group differences of patients (ET/PD) with normal controls (NCs). And then, at the feature-level assessment, the stability of group differences has been tested based on structural brain atlas separately using the permutation test to identify the robust neuroimaging biomarkers. Furthermore, the identified biomarkers of ET and PD have been applied to classify ET from PD based on machine learning techniques. Finally, the identified biomarkers have been compared with the previous findings of the biology-level assessment.

RESULTS

According to the biomarkers identified by machine learning, this study has found widespread alterations of gray matter (GM) for ET and large overlap between ET and PD and achieved superior classification performance (PCA + SVM, accuracy = 100%).

CONCLUSIONS

This study has demonstrated the significance of a machine learning framework to identify and distinguish ET and PD. Future studies using a large data set are needed to confirm the potential clinical application of machine learning techniques to discern between PD and ET.

Machine learning approaches for parsing comorbidity/heterogeneity in antisociality and substance use disorders: A primer

By some accounts, as many as 93% of individuals diagnosed with antisocial personality disorder (ASPD) or psychopathy also meet criteria for some form of substance use disorder (SUD). This high level of comorbidity, combined with an overlapping biopsychosocial profile, and potentially interacting features, has made it difficult to delineate the shared/unique characteristics of each disorder. Moreover, while rarely acknowledged, both SUD and antisociality exist as highly heterogeneous disorders in need of more targeted parcellation. While emerging data-driven nosology for psychiatric disorders (e.g., Research Domain Criteria (RDoC), Hierarchical Taxonomy of Psychopathology (HiTOP)) offers the opportunity for a more systematic delineation of the externalizing spectrum, the interrogation of large, complex neuroimaging-based datasets may require data-driven approaches that are not yet widely employed in psychiatric neuroscience. With this in mind, the proposed article sets out to provide an introduction into machine learning methods for neuroimaging that can help parse comorbid, heterogeneous externalizing samples. The modest machine learning work conducted to date within the externalizing domain demonstrates the potential utility of the approach but remains highly nascent. Within the paper, we make suggestions for how future work can make use of machine learning methods, in combination with emerging psychiatric nosology systems, to further diagnostic and etiological understandings of the externalizing spectrum. Finally, we briefly consider some challenges that will need to be overcome to encourage further progress in the field.

Large-scale network topology reveals brain functional abnormality in Chinese dyslexic children

It has been revealed that dyslexic children learning alphabetic languages are characterized by aberrant topological organization of brain networks. However, little is known about the functional organization and the reconfiguration pattern of brain networks in Chinese dyslexic children. Using graph theoretical analysis and functional magnetic resonance images (fMRI), we examined this issue specifically from the perspective of functional integration and segregation. We first compared large-scale topological organizations between dyslexic children and typically developing children during a Chinese phonological rhyming task, and found that dyslexic children showed increased local efficiency and clustering coefficient compared with typically developing children, which were negatively correlated with task performance. Furthermore, dyslexic children and typically developing children could be accurately distinguished at the individual-subject level based on the nodal local efficiency or clustering coefficient. Second, we studied the group difference of network reconfiguration and found that dyslexic children showed more difficulty when shifting from the resting state to the phonological task. Our results suggest an over-segregated brain functional organization and deficits in brain network reconfiguration in Chinese dyslexic children, which helps to advance our knowledge on the neural mechanisms underlying dyslexia.

The Spontaneous Activity Pattern of the Middle Occipital Gyrus Predicts the Clinical Efficacy of Acupuncture Treatment for Migraine Without Aura

The purpose of the present study was to explore whether and to what extent the neuroimaging markers could predict the relief of the symptoms of patients with migraine without aura (MWoA) following a 4-week acupuncture treatment period. In study 1, the advanced multivariate pattern analysis was applied to perform a classification analysis between 40 patients with MWoA and 40 healthy subjects (HS) based on the z-transformed amplitude of low-frequency fluctuation (zALFF) maps. In study 2, the meaningful classifying features were selected as predicting features and the support vector regression models were constructed to predict the clinical efficacy of acupuncture in reducing the frequency of migraine attacks and headache intensity in 40 patients with MWoA. In study 3, a region of interest-based comparison between the pre- and post-treatment zALFF maps was conducted in 33 patients with MwoA to assess the changes in predicting features after acupuncture intervention. The zALFF value of the foci in the bilateral middle occipital gyrus, right fusiform gyrus, left insula, and left superior cerebellum could discriminate patients with MWoA from HS with higher than 70% accuracy. The zALFF value of the clusters in the right and left middle occipital gyrus could effectively predict the relief of headache intensity (R ² = 0.38 ± 0.059, mean squared error = 2.626 ± 0.325) and frequency of migraine attacks (R ² = 0.284 ± 0.072, mean squared error = 20.535 ± 2.701) after the 4-week acupuncture treatment period. Moreover, the zALFF values of these two clusters were both significantly reduced after treatment. The present study demonstrated the feasibility and validity of applying machine learning technologies and individual cerebral spontaneous activity patterns to predict acupuncture treatment outcomes in patients with MWoA. The data provided a quantitative benchmark for selecting acupuncture for MWoA.

Shared Numerosity Representations Across Formats and Tasks Revealed with 7 Tesla fMRI: Decoding, Generalization, and Individual Differences in Behavior

Debate continues on whether encoding of symbolic number is grounded in nonsymbolic numerical magnitudes. Nevertheless, fluency of perceiving both number formats, and translating between them, predicts math skills across the life span. Therefore, this study asked if numbers share cortical activation patterns across formats and tasks, and whether neural response to number predicts math-related behaviors. We analyzed patterns of neural activation using 7 Tesla functional magnetic resonance imaging in a sample of 39 healthy adults. Discrimination was successful between numerosities 2, 4, 6, and 8 dots and generalized to activation patterns of the same numerosities represented as Arabic digits in the bilateral parietal lobes and left inferior frontal gyrus (IFG) (and vice versa). This indicates that numerosity-specific neural resources are shared between formats. Generalization was also successful across tasks where participants either identified or compared numerosities in bilateral parietal lobes and IFG. Individual differences in decoding did not relate to performance on a number comparison task completed outside of the scanner, but generalization between formats and across tasks negatively related to math achievement in the parietal lobes. Together, these findings suggest that individual differences in representational specificity within format and task contexts relate to mathematical expertise.

Characterizing the Structural Pattern of Heavy Smokers Using Multivoxel Pattern Analysis

Background: Smoking addiction is a major public health issue which causes a series of chronic diseases and mortalities worldwide. We aimed to explore the most discriminative gray matter regions between heavy smokers and healthy controls with a data-driven multivoxel pattern analysis technique, and to explore the methodological differences between multivoxel pattern analysis and voxel-based morphometry. Methods: Traditional voxel-based morphometry has continuously contributed to finding smoking addiction-related regions on structural magnetic resonance imaging. However, voxel-based morphometry has its inherent limitations. In this study, a multivoxel pattern analysis using a searchlight algorithm and support vector machine was applied on structural magnetic resonance imaging to identify the spatial pattern of gray matter volume in heavy smokers. Results: Our proposed method yielded a voxel-wise accuracy of at least 81% for classifying heavy smokers from healthy controls. The identified regions were primarily located at the temporal cortex and prefrontal cortex, occipital cortex, thalamus (bilateral), insula (left), anterior and median cingulate gyri, and precuneus (left). Conclusions: Our results suggested that several regions, which were seldomly reported in voxel-based morphometry analysis, might be latently correlated with smoking addiction. Such findings might provide insights for understanding the mechanism of chronic smoking and the creation of effective cessation treatment. Multivoxel pattern analysis can be efficient in locating brain discriminative regions which were neglected by voxel-based morphometry.

Characterizing the Structural Pattern Predicting Medication Response in Herpes Zoster Patients Using Multivoxel Pattern Analysis

Herpes zoster (HZ) can cause a blistering skin rash with severe neuropathic pain. Pharmacotherapy is the most common treatment for HZ patients. However, most patients are usually the elderly or those that are immunocompromised, and thus often suffer from side effects or easily get intractable post-herpetic neuralgia (PHN) if medication fails. It is challenging for clinicians to tailor treatment to patients, due to the lack of prognosis information on the neurological pathogenesis that underlies HZ. In the current study, we aimed at characterizing the brain structural pattern of HZ before treatment with medication that could help predict medication responses. High-resolution structural magnetic resonance imaging (MRI) scans of 14 right-handed HZ patients (aged 61.0 ± 7.0, 8 males) with poor response and 15 (aged 62.6 ± 8.3, 5 males) age- (p = 0.58), gender-matched (p = 0.20) patients responding well, were acquired and analyzed. Multivoxel pattern analysis (MVPA) with a searchlight algorithm and support vector machine (SVM), was applied to identify the spatial pattern of the gray matter (GM) volume, with high predicting accuracy. The predictive regions, with an accuracy higher than 79%, were located within the cerebellum, posterior insular cortex (pIC), middle and orbital frontal lobes (mFC and OFC), anterior and middle cingulum (ACC and MCC), precuneus (PCu) and cuneus. Among these regions, mFC, pIC and MCC displayed significant increases of GM volumes in patients with poor response, compared to those with a good response. The combination of sMRI and MVPA might be a useful tool to explore the neuroanatomical imaging biomarkers of HZ-related pain associated with medication responses.