Surface-based shared and distinct resting functional connectivity in attention-deficit hyperactivity disorder and autism spectrum disorder

Family Environment Modulates Linkage of Transdiagnostic Psychiatric Phenotypes and Dissociable Brain Features in the Developing Brain

BACKGROUND

Family environment has long been known for shaping brain function and psychiatric phenotypes, especially during childhood and adolescence. Accumulating neuroimaging evidence suggests that across different psychiatric disorders, common phenotypes may share common neural bases, indicating latent brain-behavior relationships beyond diagnostic categories. However, the influence of family environment on the brain-behavior relationship from a transdiagnostic perspective remains unknown.

METHODS

We included a community-based sample of 699 participants (ages 5-22 years) and applied partial least squares regression analysis to determine latent brain-behavior relationships from whole-brain functional connectivity and comprehensive phenotypic measures. Comparisons were made between diagnostic and nondiagnostic groups to help interpret the latent brain-behavior relationships. A moderation model was introduced to examine the potential moderating role of family factors in the estimated brain-behavior associations.

RESULTS

Four significant latent brain-behavior pairs were identified that reflected the relationship of dissociable brain network and general behavioral problems, cognitive and language skills, externalizing problems, and social dysfunction, respectively. The group comparisons exhibited interpretable variations across different diagnostic groups. A warm family environment was found to moderate the brain-behavior relationship of core symptoms in internalizing disorders. However, in neurodevelopmental disorders, family factors were not found to moderate the brain-behavior relationship of core symptoms, but they were found to affect the brain-behavior relationship in other domains.

CONCLUSIONS

Our findings leveraged a transdiagnostic analysis to investigate the moderating effects of family factors on brain-behavior associations, emphasizing the different roles that family factors play during this developmental period across distinct diagnostic groups.

Common and distinct cortical thickness alterations in youth with autism spectrum disorder and attention-deficit/hyperactivity disorder

BACKGROUND

Autism spectrum disorder (ASD) and attention-deficit/hyperactivity disorder (ADHD) are neurodevelopmental disorders with overlapping behavioral features and genetic etiology. While brain cortical thickness (CTh) alterations have been reported in ASD and ADHD separately, the degree to which ASD and ADHD are associated with common and distinct patterns of CTh changes is unclear.

METHODS

We searched PubMed, Web of Science, Embase, and Science Direct from inception to 8 December 2023 and included studies of cortical thickness comparing youth (age less than 18) with ASD or ADHD with typically developing controls (TDC). We conducted a comparative meta-analysis of vertex-based studies to identify common and distinct CTh alterations in ASD and ADHD.

RESULTS

Twelve ASD datasets involving 458 individuals with ASD and 10 ADHD datasets involving 383 individuals with ADHD were included in the analysis. Compared to TDC, ASD showed increased CTh in bilateral superior frontal gyrus, left middle temporal gyrus, and right superior parietal lobule (SPL) and decreased CTh in right temporoparietal junction (TPJ). ADHD showed decreased CTh in bilateral precentral gyri, right postcentral gyrus, and right TPJ relative to TDC. Conjunction analysis showed both disorders shared reduced TPJ CTh located in default mode network (DMN). Comparative analyses indicated ASD had greater CTh in right SPL and TPJ located in dorsal attention network and thinner CTh in right TPJ located in ventral attention network than ADHD.

CONCLUSIONS

These results suggest shared thinner TPJ located in DMN is an overlapping neurobiological feature of ASD and ADHD. This alteration together with SPL alterations might be related to altered biological motion processing in ASD, while abnormalities in sensorimotor systems may contribute to behavioral control problems in ADHD. The disorder-specific thinner TPJ located in disparate attention networks provides novel insight into distinct symptoms of attentional deficits associated with the two neurodevelopmental disorders.

TRIAL REGISTRATION

PROSPERO CRD42022370620. Registered on November 9, 2022.

Delineating Transdiagnostic Subtypes in Neurodevelopmental Disorders via Contrastive Graph Machine Learning of Brain Connectivity Patterns

Neurodevelopmental disorders, such as Attention Deficit/Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD), are characterized by comorbidity and heterogeneity. Identifying distinct subtypes within these disorders can illuminate the underlying neurobiological and clinical characteristics, paving the way for more tailored treatments. We adopted a novel transdiagnostic approach across ADHD and ASD, using cutting-edge contrastive graph machine learning to determine subtypes based on brain network connectivity as revealed by resting-state functional magnetic resonance imaging. Our approach identified two generalizable subtypes characterized by robust and distinct functional connectivity patterns, prominently within the frontoparietal control network and the somatomotor network. These subtypes exhibited pronounced differences in major cognitive and behavioural measures. We further demonstrated the generalizability of these subtypes using data collected from independent study sites. Our data-driven approach provides a novel solution for parsing biological heterogeneity in neurodevelopmental disorders.

Altered Intrinsic Brain Spontaneous Activities in Children With Autism Spectrum Disorder Comorbid ADHD

OBJECTIVE

The study involved 17 children with Autism Spectrum Disorder (ASD), 21 with ADHD, 30 with both (ASD + ADHD), and 28 typically developing children (TD).

METHODS

The amplitude of low-frequency fluctuations (ALFF) was measured as a regional brain function index. Intrinsic functional connectivity (iFC) was also analyzed using the region of interest (ROI) identified in ALFF analysis. Statistical analysis was done via one-way ANCOVA, Gaussian random field (GRF) theory, and post-hoc pair-wise comparisons.

RESULTS

The ASD + ADHD group showed increased ALFF in the left middle frontal gyrus (MFG.L) compared to the TD group. In terms of global brain function, the ASD group displayed underconnectivity in specific regions compared to the ASD + ADHD and TD groups.

CONCLUSION

The findings contribute to understanding the neural mechanisms underlying ASD + ADHD.

Thalamic functional connectivity and sensorimotor processing in neurodevelopmental disorders

One of the earliest neurobiological findings in autism has been the differences in the thalamocortical pathway connectivity, suggesting the vital role thalamus plays in human experience. The present functional MRI study investigated resting-state functional connectivity of the thalamus in 49 (autistic, ADHD, and neurotypical) young adults. All participants underwent structural MRI and eyes-open resting state functional MRI scans. After preprocessing the imaging data using Conn's connectivity toolbox, a seed-based functional connectivity analysis was conducted using bilateral thalamus as primary seeds. Autistic participants showed stronger thalamic connectivity, relative to ADHD and neurotypical participants, between the right thalamus and right precentral gyrus, right pars opercularis-BA44, right postcentral gyrus, and the right superior parietal lobule (RSPL). Autistic participants also showed significantly increased connectivity between the left thalamus and the right precentral gyrus. Furthermore, regression analyses revealed a significant relationship between autistic traits and left thalamic-precentral connectivity (R2 = 0.1113), as well as between autistic traits and right postcentral gyrus and RSPL connectivity (R2 = 0.1204) in autistic participants compared to ADHD. These findings provide significant insights into the role of thalamus in coordinating neural information processing and its alterations in neurodevelopmental disorders.

Diagnosis of Autism Spectrum Disorder (ASD) Using Recursive Feature Elimination-Graph Neural Network (RFE-GNN) and Phenotypic Feature Extractor (PFE)

Autism spectrum disorder (ASD) poses as a multifaceted neurodevelopmental condition, significantly impacting children's social, behavioral, and communicative capacities. Despite extensive research, the precise etiological origins of ASD remain elusive, with observable connections to brain activity. In this study, we propose a novel framework for ASD detection, extracting the characteristics of functional magnetic resonance imaging (fMRI) data and phenotypic data, respectively. Specifically, we employ recursive feature elimination (RFE) for feature selection of fMRI data and subsequently apply graph neural networks (GNN) to extract informative features from the chosen data. Moreover, we devise a phenotypic feature extractor (PFE) to extract phenotypic features effectively. We then, synergistically fuse the features and validate them on the ABIDE dataset, achieving 78.7% and 80.6% accuracy, respectively, thereby showcasing competitive performance compared to state-of-the-art methods. The proposed framework provides a promising direction for the development of effective diagnostic tools for ASD.

Early detection of paediatric and adolescent obsessive-compulsive, separation anxiety and attention deficit hyperactivity disorder using machine learning algorithms

Purpose

Mental health issues of young minds are at the threshold of all development and possibilities. Obsessive-compulsive disorder (OCD), separation anxiety disorder (SAD), and attention deficit hyperactivity disorder (ADHD) are three of the most common mental illness affecting children and adolescents. Several studies have been conducted on approaches for recognising OCD, SAD and ADHD, but their accuracy is inadequate due to limited features and participants. Therefore, the purpose of this study is to investigate the approach using machine learning (ML) algorithms with 1474 features from Australia's nationally representative mental health survey of children and adolescents.

Methods

Based on the internal cross-validation (CV) score of the Tree-based Pipeline Optimization Tool (TPOTClassifier), the dataset has been examined using three of the most optimal algorithms, including Random Forest (RF), Decision Tree (DT), and Gaussian Naïve Bayes (GaussianNB).

Results

GaussianNB performs well in classifying OCD with 91% accuracy, 76% precision, and 96% specificity as well as in detecting SAD with 79% accuracy, 62% precision, 91% specificity. RF outperformed all other methods in identifying ADHD with 91% accuracy, 94% precision, and 99% specificity.

Conclusion

Using Streamlit and Python a web application was developed based on the findings of the analysis. The application will assist parents/guardians and school officials in detecting mental illnesses early in their children and adolescents using signs and symptoms to start the treatment at the earliest convenience.

Acupuncture modulates the functional connectivity among the subcortical nucleus and fronto-parietal network in adolescents with internet addiction

BACKGROUND

Internet addiction (IA), recognized as a behavioral addiction, is emerging as a global public health problem. Acupuncture has been demonstrated to be effective in alleviating IA; however, the mechanism is not yet clear. To fill this knowledge gap, our study aimed to investigate the modulatory effects of acupuncture on the functional interactions among the addiction-related networks in adolescents with IA.

METHODS

Thirty individuals with IA and thirty age- and sex-matched healthy control subjects (HCs) were recruited. Subjects with IA were given a 40-day acupuncture treatment, and resting-state functional magnetic resonance imaging (fMRI) data were collected before and after acupuncture sessions. HCs received no treatment and underwent one fMRI scan after enrollment. The intergroup differences in functional connectivity (FC) among the subcortical nucleus (SN) and fronto-parietal network (FPN) were compared between HCs and subjects with IA at baseline. Then, the intragroup FC differences between the pre- and post-treatment were analyzed in the IA group. A multiple linear regression model was further employed to fit the FC changes to symptom relief in the IA group.

RESULTS

In comparison to HCs, subjects with IA exhibited significantly heightened FC within and between the SN and FPN at baseline. After 40 days of acupuncture treatment, the FC within the FPN and between the SN and FPN were significantly decreased in individuals with IA. Symptom improvement in subjects with IA was well fitted by the decrease in FC between the left midbrain and ventral prefrontal cortex and between the left thalamus and ventral anterior prefrontal cortex.

CONCLUSION

These findings confirmed the modulatory effects of acupuncture on the aberrant functional interactions among the SN and FPN, which may partly reflect the neurophysiological mechanism of acupuncture for IA.

Alterations of Functional Connectivity in Autism and Attention-Deficit/Hyperactivity Disorder Revealed by Multi-Voxel Pattern Analysis

Background: Autism and attention-deficit/hyperactivity disorder (ADHD) are comorbid neurodevelopmental disorders that share common and distinct neurobiological mechanisms, with disrupted brain connectivity patterns being a hallmark feature of both conditions. It is challenging to gain a mechanistic understanding of the underlying disorder, because brain connectivity changes in autism and ADHD are heterogeneous. Objectives: The present resting state functional MRI (rs-fMRI) study focuses on investigating the shared and distinct resting state-fMRI connectivity (rsFC) patterns in autistic and ADHD adults using multi-voxel pattern analysis (MVPA). By identifying spatial patterns of fMRI activity across a given time course, MVPA is an innovative and powerful method for generating seed regions of interest (ROIs) without a priori hypotheses. Methods: We performed a data-driven, whole-brain, connectome-wide MVPA on rs-fMRI data collected from 15 autistic, 19 ADHD, and 15 neurotypical (NT) young adults. Results: MVPA identified cerebellar vermis 9, precuneus, and the right cerebellum VI for autistic versus NT, right inferior frontal gyrus and vermis 9 for ADHD versus NT, and right dorsolateral prefrontal cortex for autistic versus ADHD as significant clusters. Post hoc seed-to-voxel analyses using these clusters as seed ROIs were performed for further characterization of group differences. The cerebellum VI, vermis, and precuneus in autistic adults, and the vermis and frontal regions in ADHD showed different connectivity patterns in comparison with NT. Conclusions: The study characterizes the rsFC profile of cerebellum with key cortical areas in autism and ADHD, and it emphasizes the importance of studying the role of the functional connectivity of the cerebellum in neurodevelopmental disorders.

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.

Evidence from "big data" for the default-mode hypothesis of ADHD: a mega-analysis of multiple large samples

We sought to identify resting-state characteristics related to attention deficit/hyperactivity disorder, both as a categorical diagnosis and as a trait feature, using large-scale samples which were processed according to a standardized pipeline. In categorical analyses, we considered 1301 subjects with diagnosed ADHD, contrasted against 1301 unaffected controls (total N = 2602; 1710 males (65.72%); mean age = 10.86 years, sd = 2.05). Cases and controls were 1:1 nearest neighbor matched on in-scanner motion and key demographic variables and drawn from multiple large cohorts. Associations between ADHD-traits and resting-state connectivity were also assessed in a large multi-cohort sample (N = 10,113). ADHD diagnosis was associated with less anticorrelation between the default mode and salience/ventral attention (B = 0.009, t = 3.45, p-FDR = 0.004, d = 0.14, 95% CI = 0.004, 0.014), somatomotor (B = 0.008, t = 3.49, p-FDR = 0.004, d = 0.14, 95% CI = 0.004, 0.013), and dorsal attention networks (B = 0.01, t = 4.28, p-FDR < 0.001, d = 0.17, 95% CI = 0.006, 0.015). These results were robust to sensitivity analyses considering comorbid internalizing problems, externalizing problems and psychostimulant medication. Similar findings were observed when examining ADHD traits, with the largest effect size observed for connectivity between the default mode network and the dorsal attention network (B = 0.0006, t = 5.57, p-FDR < 0.001, partial-r = 0.06, 95% CI = 0.0004, 0.0008). We report significant ADHD-related differences in interactions between the default mode network and task-positive networks, in line with default mode interference models of ADHD. Effect sizes (Cohen's d and partial-r, estimated from the mega-analytic models) were small, indicating subtle group differences. The overlap between the affected brain networks in the clinical and general population samples supports the notion of brain phenotypes operating along an ADHD continuum.

Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review

Autism spectrum disorder (ASD) is a brain condition characterized by diverse signs and symptoms that appear in early childhood. ASD is also associated with communication deficits and repetitive behavior in affected individuals. Various ASD detection methods have been developed, including neuroimaging modalities and psychological tests. Among these methods, magnetic resonance imaging (MRI) imaging modalities are of paramount importance to physicians. Clinicians rely on MRI modalities to diagnose ASD accurately. The MRI modalities are non-invasive methods that include functional (fMRI) and structural (sMRI) neuroimaging methods. However, diagnosing ASD with fMRI and sMRI for specialists is often laborious and time-consuming; therefore, several computer-aided design systems (CADS) based on artificial intelligence (AI) have been developed to assist specialist physicians. Conventional machine learning (ML) and deep learning (DL) are the most popular schemes of AI used for diagnosing ASD. This study aims to review the automated detection of ASD using AI. We review several CADS that have been developed using ML techniques for the automated diagnosis of ASD using MRI modalities. There has been very limited work on the use of DL techniques to develop automated diagnostic models for ASD. A summary of the studies developed using DL is provided in the Supplementary Appendix. Then, the challenges encountered during the automated diagnosis of ASD using MRI and AI techniques are described in detail. Additionally, a graphical comparison of studies using ML and DL to diagnose ASD automatically is discussed. We suggest future approaches to detecting ASDs using AI techniques and MRI neuroimaging.

How does brain structure and function on MRI differ in children with autism spectrum disorder, developmental coordination disorder, and/or attention deficit hyperactivity disorder?

AIM

The purpose of this study was to systematically review the neural similarities and differences in brain structure and function, measured by magnetic resonance imaging (MRI), in children with neurodevelopmental disorders that commonly co-occur to understand if and how they have shared neuronal characteristics.

METHOD

Using systematic review methodology, the following databases were comprehensively searched: MEDLINE, EMBASE, CINAHL, CENTRAL, PsycINFO, and ProQuest from the earliest record up to December 2021. Inclusion criteria were: (1) peer-reviewed studies, case reports, or theses; (2) children under 18 years of age with at least one of the following neurodevelopmental disorders: autism spectrum disorder (ASD), attention hyperactivity deficit disorder (ADHD), developmental coordination disorder (DCD), and their co-occurrence; (3) studies based on MRI modalities (i.e., structural MRI, diffusion tensor imaging (DTI), and resting-state fMRI). Thirty-one studies that met the inclusion criteria were included for quality assessment by two independent reviewers using the Appraisal tool for Cross-Sectional Studies (AXIS).

RESULTS

Studies compared brain structure and function of children with DCD and ADHD (n=6), DCD and ASD (n=1), ASD and ADHD (n=17), and various combinations of these co-occurring conditions (n=7). Structural neuroimaging (n=15) was the most commonly reported modality, followed by resting-state (n=8), DTI (n=5), and multi-modalities (n=3).

INTERPRETATION

Evidence indicated that the neural correlates of the co-occurring conditions were more widespread and distinct compared to a single diagnosis. The majority of findings (77%) suggested that each neurodevelopmental disorder had more distinct neural correlates than shared neural features, suggesting that each disorder is distinct despite commonly co-occurring with each other. As the number of papers examining the co-occurrence of ASD, DCD, and/or ADHD was limited and most findings were not corrected for multiple comparisons, these results must be interpreted with caution.

Hyper and hypo attention networks activations affect social development in children with autism spectrum disorder

Children with autism spectrum disorder (ASD) experience a range of social and non-social attention deficits. To date, most studies assessed the neurological framework or discrete behavioral traits related to one attention network, leaving a gap in the understanding of the developmental cascade affecting the inter-relations among attention networks in ASD in a pervasive manner. We propose a theoretical framework that integrates the behavioral deficits and neurological manifestations through a cohesive developmental prism of attention networks’ activations while assessing their impact on social deficits in children with ASD. Insights arising from the model suggest hyper-and-hypoactivation of posterior attention networks leads to an altered prefrontal anterior attention network weight in ways that conjointly impact social performance in ASD. This perspective on how attention networks develop and interact in ASD may inform future research directions regarding ASD and attention development.

Different Eye Tracking Patterns in Autism Spectrum Disorder in Toddler and Preschool Children

BACKGROUND

Children with autism spectrum disorder (ASD) have been observed to be associated with fixation abnormality as measured eye tracking, but the dynamics behind fixation patterns across age remain unclear.

MATERIALS AND METHODS

In this study, we investigated gaze patterns between toddlers and preschoolers with and without ASD while they viewed video clips and still images (i.e., mouth-moving face, biological motion, mouthing face vs. moving object, still face picture vs. objects, and moving toys).

RESULTS

We found that the fixation time percentage of children with ASD showed significant decrease compared with that of TD children in almost all areas of interest (AOI) except for moving toy (helicopter). We also observed a diagnostic group (ASD vs. TD) and chronological age (Toddlers vs. preschooler) interaction for the eye AOI during the mouth-moving video clip. Support vector machine analysis showed that the classifier could discriminate ASD from TD in toddlers with an accuracy of 80% and could discriminate ASD from TD in preschoolers with an accuracy of 71%.

CONCLUSION

Our results suggest that toddlers and preschoolers may be associated with both common and distinct fixation patterns. A combination of eye tracking and machine learning methods has the potential to shed light on the development of new early screening/diagnosis methods for ASD.

Brain imaging-based machine learning in autism spectrum disorder: methods and applications

Autism spectrum disorder (ASD) is a neurodevelopmental condition with early childhood onset and high heterogeneity. As the pathogenesis is still elusive, ASD diagnosis is comprised of a constellation of behavioral symptoms. Non-invasive brain imaging techniques, such as magnetic resonance imaging (MRI), provide a valuable objective measurement of the brain. Many efforts have been devoted to developing imaging-based diagnostic tools for ASD based on machine learning (ML) technologies. In this survey, we review recent advances that utilize machine learning approaches to classify individuals with and without ASD. First, we provide a brief overview of neuroimaging-based ASD classification studies, including the analysis of publications and general classification pipeline. Next, representative studies are highlighted and discussed in detail regarding different imaging modalities, methods and sample sizes. Finally, we highlight several common challenges and provide recommendations on future directions. In summary, identifying discriminative biomarkers for ASD diagnosis is challenging, and further establishing more comprehensive datasets and dissecting the individual and group heterogeneity will be critical to achieve better ADS diagnosis performance. Machine learning methods will continue to be developed and are poised to help advance the field in this regard.

Predicting disease severity in children with combined attention deficit hyperactivity disorder using quantitative features from structural MRI of amygdaloid and hippocampal subfields

OBJECTIVE

Volumetric changes in the amygdaloid and hippocampal subfields have been observed in children with combined attention deficit hyperactivity disorder (ADHD-C). The purpose of this study was to investigate whether volumetric changes in the amygdaloid and hippocampal subfields could be used to predict disease severity in children with ADHD-C.

APPROACH

The data used in this study was from ADHD-200 datasets, a total of 76 ADHD-C patients were included in this study. T1 structural MRI data were used and 64 structural features from the amygdala and hippocampus were extracted. Three ADHD rating scales were used as indicators of ADHD severity. Sequential backward elimination (SBE) algorithm was used for feature selection. A linear support vector regression (SVR) was configured to predict disease severity in children with ADHD-C.

MAIN RESULTS

The three ADHD rating scales could be accurately predicted with the use of SBE-SVR. SBE-SVR achieved the highest accuracy in predicting ADHD index with a correlation of 0.7164 (p < 0.001, tested with 1000-time permutation test). Mean squared error of the SVR was 43.6868, normalized mean squared error was 0.0086, mean absolute error was 3.2893. Several amygdaloid and hippocampal subregions were significantly related to ADHD severity, as revealed by the absolute weight from the SVR model.

SIGNIFICANCE

The proposed SBE-SVR could accurately predict the severity of patients with ADHD-C based on quantitative features extracted from the amygdaloid and hippocampal structures. The results also demonstrated that the two subcortical nuclei could be used as potential biomarkers in the progression and evaluation of ADHD.

Linking ADHD and Behavioral Assessment Through Identification of Shared Diagnostic Task-Based Functional Connections

A mixed literature implicates atypical connectivity involving attentional, reward and task inhibition networks in ADHD. The neural mechanisms underlying the utility of behavioral tasks in ADHD diagnosis are likewise underexplored. We hypothesized that a machine-learning classifier may use task-based functional connectivity to compute a joint probability function that identifies connectivity signatures that accurately predict ADHD diagnosis and performance on a clinically-relevant behavioral task, providing an explicit neural mechanism linking behavioral phenotype to diagnosis. We analyzed archival MRI and behavioral data of 80 participants (64 male) who had completed the go/no-go task from the longitudinal follow-up of the Multimodal Treatment Study of ADHD (MTA 168) (mean age = 24 years). Cross-mutual information within a functionally-defined mask measured functional connectivity for each task run. Multilayer feedforward classifier models identified the subset of functional connections that predicted clinical diagnosis (ADHD vs. Control) and split-half performance on the Iowa Gambling Task (IGT). A sample of random models trained on functional connectivity profiles predicted validation set clinical diagnosis and IGT performance with 0.91 accuracy and d' > 2.9, indicating very high sensitivity and specificity. We identified the most diagnostic functional connections between visual and ventral attentional networks and the anterior default mode network. Our results show that task-based functional connectivity is a biomarker of ADHD. Our analytic framework provides a template approach that explicitly ties behavioral assessment measures to both clinical diagnosis, and functional connectivity. This may differentiate otherwise similar diagnoses, and promote more efficacious intervention strategies.

Beyond diagnosis: Cross-diagnostic features in canonical resting-state networks in children with neurodevelopmental disorders

•

Resting-state connectivity did not differ across neurodevelopmental disorders.

•

General adaptive function across all participants related to subcortical connectivity.

•

Participants in the same data-driven clusters were highly heterogeneous in diagnosis.

•

Neurobiological similarity and dissimilarity may be seen in beyond-diagnosis categories.

Children with neurodevelopmental disorders (NDDs) share common behavioural manifestations despite distinct categorical diagnostic criteria. Here, we examined canonical resting-state network connectivity in three diagnostic groups (autism spectrum disorder, attention-deficit/hyperactivity disorder and paediatric obsessive–compulsive disorder) and typically developing controls (TD) in a large single-site sample (N = 407), applying diagnosis-based and dimensional approaches to understand underlying neurobiology across NDDs. Each participant’s functional network graphs were computed using five graph metrics. In diagnosis-based comparisons, an analysis of covariance was performed to compare all NDDs to TD, followed by pairwise comparisons between NDDs. In the dimensional approach, participants’ functional network graphs were correlated with continuous behavioural measures, and a data-driven k-means clustering analysis was applied to determine if subgroups of participants were seen, without diagnostic information having been included. In the diagnosis-based comparisons, children with NDDs did not differ significantly from the TD group and the NDD categorical groups also did not differ significantly from each other, across all graph metrics. In the dimensional, diagnostic-independent approach, however, subcortical functional connectivity was significantly correlated with participants’ general adaptive functioning across all participants. The clustering analysis identified an optimal solution of two clusters, and participants assigned in the same data-driven cluster were highly heterogeneous in diagnosis. Neither cluster exclusively contained a specific diagnostic group, nor did NDDs separate cleanly from TDs. Each participant’s distance ratio between the two clusters was significantly correlated with general adaptive functioning, social deficits and attentional problems. Our results suggest the neurobiological similarity and dissimilarity between NDDs need to be investigated beyond DSM/ICD-based, behaviourally-defined diagnostic categories.

Neuroimaging-Based Deep Learning in Autism Spectrum Disorder and Attention-Deficit/Hyperactivity Disorder

Deep learning (DL) is a kind of machine learning technique that uses artificial intelligence to identify the characteristics of given data and efficiently analyze large amounts of information to perform tasks such as classification and prediction. In the field of neuroimaging of neurodevelopmental disorders, various biomarkers for diagnosis, classification, prognosis prediction, and treatment response prediction have been examined; however, they have not been efficiently combined to produce meaningful results. DL can be applied to overcome these limitations and produce clinically helpful results. Here, we review studies that combine neurodevelopmental disorder neuroimaging and DL techniques to explore the strengths, limitations, and future directions of this research area.

Guidance for identification and treatment of individuals with attention deficit/hyperactivity disorder and autism spectrum disorder based upon expert consensus

BACKGROUND

Individuals with co-occurring hyperactivity disorder/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) can have complex presentations that may complicate diagnosis and treatment. There are established guidelines with regard to the identification and treatment of ADHD and ASD as independent conditions. However, ADHD and ASD were not formally recognised diagnostically as co-occurring conditions until the Diagnostic and Statistical Manual of Mental Disorders 5 (DSM-5) was published in 2013. Hence, awareness and understanding of both conditions when they co-occur is less established and there is little guidance in the clinical literature. This has led to uncertainty among healthcare practitioners when working with children, young people and adults who present with co-existing ADHD and ASD. The United Kingdom ADHD Partnership (UKAP) therefore convened a meeting of professional experts that aimed to address this gap and reach expert consensus on the topic that will aid healthcare practitioners and allied professionals when working with this complex and vulnerable population.

METHOD

UK experts from multiple disciplines in the fields of ADHD and ASD convened in London in December 2017. The meeting provided the opportunity to address the complexities of ADHD and ASD as a co-occurring presentation from different perspectives and included presentations, discussion and group work. The authors considered the clinical challenges of working with this complex group of individuals, producing a consensus for a unified approach when working with male and female, children, adolescents and adults with co-occurring ADHD and ASD. This was written up, circulated and endorsed by all authors.

RESULTS

The authors reached a consensus of practical recommendations for working across the lifespan with males and females with ADHD and ASD. Consensus was reached on topics of (1) identification and assessment using rating scales, clinical diagnostic interviews and objective supporting assessments; outcomes of assessment, including standards of clinical reporting; (2) non-pharmacological interventions and care management, including psychoeducation, carer interventions/carer training, behavioural/environmental and Cognitive Behavioural Therapy (CBT) approaches; and multi-agency liaison, including educational interventions, career advice, occupational skills and training, and (3) pharmacological treatments.

CONCLUSIONS

The guidance and practice recommendations (Tables 1, 4, 5, 7, 8 and 10) will support healthcare practitioners and allied professionals to meet the needs of this complex group from a multidisciplinary perspective. Further research is needed to enhance our understanding of the diagnosis, treatment and management of individuals presenting with comorbid ADHD and ASD.

Potential Locations for Noninvasive Brain Stimulation in Treating Autism Spectrum Disorders-A Functional Connectivity Study

OBJECTIVES

Noninvasive brain stimulation (NIBS) is an emerging tool for treating autism spectrum disorder (ASD). Exploring new stimulation targets may improve the efficacy of NIBS for ASD.

MATERIALS AND METHODS

We first conducted a meta-analysis on 170 functional magnetic resonance imaging studies to identify ASD-associated brain regions. We then performed resting state functional connectivity analysis on 70 individuals with ASD to investigate brain surface regions correlated with these ASD-associated regions and identify potential NIBS targets for ASD.

RESULTS

We found that the medial prefrontal cortex, angular gyrus, dorsal lateral prefrontal cortex, inferior frontal gyrus, superior parietal lobe, postcentral gyrus, precentral gyrus, middle temporal gyrus, superior temporal sulcus, lateral occipital cortex, and supplementary motor area/paracentral gyrus are potential locations for NIBS in ASD.

CONCLUSION

Our findings may shed light on the development of new NIBS targets for ASD.

Developmental nicotine exposure engenders intergenerational downregulation and aberrant posttranslational modification of cardinal epigenetic factors in the frontal cortices, striata, and hippocampi of adolescent mice

BACKGROUND

Maternal smoking of traditional or electronic cigarettes during pregnancy, which constitutes developmental nicotine exposure (DNE), heightens the risk of neurodevelopmental disorders including ADHD, autism, and schizophrenia in children. Modeling the intergenerationally transmissible impacts of smoking during pregnancy, we previously demonstrated that both the first- and second-generation adolescent offspring of nicotine-exposed female mice exhibit enhanced nicotine preference, hyperactivity and risk-taking behaviors, aberrant rhythmicity of home cage activity, nicotinic acetylcholine receptor and dopamine transporter dysfunction, impaired furin-mediated proBDNF proteolysis, hypocorticosteronemia-related glucocorticoid receptor hypoactivity, and global DNA hypomethylation in the frontal cortices and striata. This ensemble of multigenerational DNE-induced behavioral, neuropharmacological, neurotrophic, neuroendocrine, and DNA methylomic anomalies recapitulates the pathosymptomatology of neurodevelopmental disorders such as ADHD, autism, and schizophrenia. Further probing the epigenetic bases of DNE-induced multigenerational phenotypic aberrations, the present study examined the expression and phosphorylation of key epigenetic factors via an array of immunoblot experiments.

RESULTS

Data indicate that DNE confers intergenerational deficits in corticostriatal DNA methyltransferase 3A (DNMT3A) expression accompanied by downregulation of methyl-CpG-binding protein 2 (MeCP2) and histone deacetylase 2 (HDAC2) in the frontal cortices and hippocampi, while the expression of ten-eleven translocase methylcytosine dioxygenase 2 (TET2) is unaltered. Moreover, DNE evokes multigenerational abnormalities in HDAC2 (Ser394) but not MeCP2 (Ser421) phosphorylation in the frontal cortices, striata, and hippocampi.

CONCLUSIONS

In light of the extensive gene regulatory roles of DNMT3A, MeCP2, and HDAC2, the findings of this study that DNE elicits downregulation and aberrant posttranslational modification of these factors in both first- and second-generation DNE mice suggest that epigenetic perturbations may constitute a mechanistic hub for the intergenerational transmission of DNE-induced neurodevelopmental disorder-like phenotypes.

An fMRI-based neural marker for migraine without aura

OBJECTIVE

To identify and validate an fMRI-based neural marker for migraine without aura (MwoA) and to examine its association with treatment response.

METHODS

We conducted cross-sectional studies with resting-state fMRI data from 230 participants and machine learning analyses. In studies 1 through 3, we identified, cross-validated, independently validated, and cross-sectionally validated an fMRI-based neural marker for MwoA. In study 4, we assessed the relationship between the neural marker and treatment responses in migraineurs who received a 4-week real or sham acupuncture treatment, or were waitlisted, in a registered clinical trial.

RESULTS

In study 1 (n = 116), we identified a neural marker with abnormal functional connectivity within the visual, default mode, sensorimotor, and frontal-parietal networks that could discriminate migraineurs from healthy controls (HCs) with 93% sensitivity and 89% specificity. In study 2 (n = 38), we investigated the generalizability of the marker by applying it to an independent cohort of migraineurs and HCs and achieved 84% sensitivity and specificity. In study 3 (n = 76), we verified the specificity of the marker with new datasets of migraineurs and patients with other chronic pain disorders (chronic low back pain and fibromyalgia) and demonstrated 78% sensitivity and 76% specificity for discriminating migraineurs from nonmigraineurs. In study 4 (n = 116), we found that the changes in the marker responses showed significant correlation with the changes in headache frequency in response to real acupuncture.

CONCLUSION

We identified an fMRI-based neural marker that captures distinct characteristics of MwoA and can link disease pattern changes to brain changes.

Developmental nicotine exposure elicits multigenerational disequilibria in proBDNF proteolysis and glucocorticoid signaling in the frontal cortices, striata, and hippocampi of adolescent mice

Maternal smoking of conventional or vapor cigarettes during pregnancy, a form of developmental nicotine exposure (DNE), enhances the risk of neurodevelopmental disorders such as ADHD, autism, and schizophrenia in children. Modeling the multigenerational effects of smoking during pregnancy and nursing in the first- (F1) and second- (F2) generation adolescent offspring of oral nicotine-treated female C57BL/6J mice, we have previously reported that DNE precipitates intergenerational transmission of nicotine preference, hyperactivity and impulsivity-like behaviors, altered rhythmicity of home cage activity, corticostriatal nicotinic acetylcholine receptor and dopamine transporter dysfunction, and corticostriatal global DNA methylome deficits. In aggregate, these DNE-evoked behavioral, neuropharmacological, and epigenomic anomalies mirror fundamental etiological aspects of neurodevelopmental disorders including ADHD, autism, and schizophrenia. Expanding this line of research, the current study profiled the multigenerational neurotrophic and neuroendocrine consequences of DNE. Results reveal impaired proBDNF proteolysis as indicated by proBDNF-BDNF imbalance, downregulation of the proBDNF processing enzyme furin, atypical glucocorticoid receptor (GR) activity as implied by decreased relative nuclear GR localization, and deficient basal plasma corticosterone (CORT) levels in adolescent DNE offspring and grandoffspring. Collectively, these data recapitulate the BDNF deficits and HPA axis dysregulation characteristic of neurodevelopmental disorders such as ADHD, autism, and schizophrenia as well as the children of maternal smokers. Notably, as BDNF is a quintessential mediator of neurodevelopment, our prior findings of multigenerational DNE-induced behavioral and neuropharmacological abnormalities may stem from neurodevelopmental insults conferred by the proBDNF-BDNF imbalance detected in DNE mice. Similarly, our findings of multigenerational GR hypoactivity may contribute to the increased risk-taking behaviors and aberrant circadian rhythmicity of home cage activity that we previously documented in first- and second-generation DNE mice.