Individual classification of ADHD patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniques

Structural or/and functional MRI-based machine learning techniques for attention-deficit/hyperactivity disorder diagnosis: A systematic review and meta-analysis

BACKGROUND

The aim of this study was to investigate the diagnostic value of ML techniques based on sMRI or/and fMRI for ADHD.

METHODS

We conducted a comprehensive search (from database creation date to March 2024) for relevant English articles on sMRI or/and fMRI-based ML techniques for diagnosing ADHD. The pooled sensitivity, specificity, positive likelihood ratio (LR+), negative likelihood ratio (LR-), summary receiver operating characteristic (SROC) curve and area under the curve (AUC) were calculated to assess the diagnostic value of sMRI or/and fMRI-based ML techniques. The I2 test was used to assess heterogeneity and the source of heterogeneity was investigated by performing a meta-regression analysis. Publication bias was assessed using the Deeks funnel plot asymmetry test.

RESULTS

Forty-three studies were included in the systematic review, 27 of which were included in our meta-analysis. The pooled sensitivity and specificity of sMRI or/and fMRI-based ML techniques for the diagnosis of ADHD were 0.74 (95 % CI 0.65-0.81) and 0.75 (95 % CI 0.67-0.81), respectively. SROC curve showed that AUC was 0.81 (95 % CI 0.77-0.84). Based on these findings, the sMRI or/and fMRI-based ML techniques have relatively good diagnostic value for ADHD.

LIMITATIONS

Our meta-analysis specifically focused on ML techniques based on sMRI or/and fMRI studies. Since EEG-based ML techniques are also used for diagnosing ADHD, further systematic analyses are necessary to explore ML methods based on multimodal medical data.

CONCLUSION

sMRI or/and fMRI-based ML technique is a promising objective diagnostic method for ADHD.

Individualized prediction models in ADHD: a systematic review and meta-regression

There have been increasing efforts to develop prediction models supporting personalised detection, prediction, or treatment of ADHD. We overviewed the current status of prediction science in ADHD by: (1) systematically reviewing and appraising available prediction models; (2) quantitatively assessing factors impacting the performance of published models. We did a PRISMA/CHARMS/TRIPOD-compliant systematic review (PROSPERO: CRD42023387502), searching, until 20/12/2023, studies reporting internally and/or externally validated diagnostic/prognostic/treatment-response prediction models in ADHD. Using meta-regressions, we explored the impact of factors affecting the area under the curve (AUC) of the models. We assessed the study risk of bias with the Prediction Model Risk of Bias Assessment Tool (PROBAST). From 7764 identified records, 100 prediction models were included (88% diagnostic, 5% prognostic, and 7% treatment-response). Of these, 96% and 7% were internally and externally validated, respectively. None was implemented in clinical practice. Only 8% of the models were deemed at low risk of bias; 67% were considered at high risk of bias. Clinical, neuroimaging, and cognitive predictors were used in 35%, 31%, and 27% of the studies, respectively. The performance of ADHD prediction models was increased in those models including, compared to those models not including, clinical predictors (β = 6.54, p = 0.007). Type of validation, age range, type of model, number of predictors, study quality, and other type of predictors did not alter the AUC. Several prediction models have been developed to support the diagnosis of ADHD. However, efforts to predict outcomes or treatment response have been limited, and none of the available models is ready for implementation into clinical practice. The use of clinical predictors, which may be combined with other type of predictors, seems to improve the performance of the models. A new generation of research should address these gaps by conducting high quality, replicable, and externally validated models, followed by implementation research.

Static and dynamic fMRI-derived functional connectomes represent largely similar information

Functional connectivity (FC) of blood oxygen level-dependent (BOLD) fMRI time series can be estimated using methods that differ in sensitivity to the temporal order of time points (static vs. dynamic) and the number of regions considered in estimating a single edge (bivariate vs. multivariate). Previous research suggests that dynamic FC explains variability in FC fluctuations and behavior beyond static FC. Our aim was to systematically compare methods on both dimensions. We compared five FC methods: Pearson's/full correlation (static, bivariate), lagged correlation (dynamic, bivariate), partial correlation (static, multivariate), and multivariate AR model with and without self-connections (dynamic, multivariate). We compared these methods by (i) assessing similarities between FC matrices, (ii) by comparing node centrality measures, and (iii) by comparing the patterns of brain-behavior associations. Although FC estimates did not differ as a function of sensitivity to temporal order, we observed differences between the multivariate and bivariate FC methods. The dynamic FC estimates were highly correlated with the static FC estimates, especially when comparing group-level FC matrices. Similarly, there were high correlations between the patterns of brain-behavior associations obtained using the dynamic and static FC methods. We conclude that the dynamic FC estimates represent information largely similar to that of the static FC.

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.

Machine learning in attention-deficit/hyperactivity disorder: new approaches toward understanding the neural mechanisms

Attention-deficit/hyperactivity disorder (ADHD) is a highly prevalent and heterogeneous neurodevelopmental disorder in children and has a high chance of persisting in adulthood. The development of individualized, efficient, and reliable treatment strategies is limited by the lack of understanding of the underlying neural mechanisms. Diverging and inconsistent findings from existing studies suggest that ADHD may be simultaneously associated with multivariate factors across cognitive, genetic, and biological domains. Machine learning algorithms are more capable of detecting complex interactions between multiple variables than conventional statistical methods. Here we present a narrative review of the existing machine learning studies that have contributed to understanding mechanisms underlying ADHD with a focus on behavioral and neurocognitive problems, neurobiological measures including genetic data, structural magnetic resonance imaging (MRI), task-based and resting-state functional MRI (fMRI), electroencephalogram, and functional near-infrared spectroscopy, and prevention and treatment strategies. Implications of machine learning models in ADHD research are discussed. Although increasing evidence suggests that machine learning has potential in studying ADHD, extra precautions are still required when designing machine learning strategies considering the limitations of interpretability and generalization.

Static and dynamic functional connectomes represent largely similar information

Functional connectivity (FC) of blood-oxygen-level-dependent (BOLD) fMRI time series can be estimated using methods that differ in sensitivity to the temporal order of time points (static vs. dynamic) and the number of regions considered in estimating a single edge (bivariate vs. multivariate). Previous research suggests that dynamic FC explains variability in FC fluctuations and behavior beyond static FC. Our aim was to systematically compare methods on both dimensions. We compared five FC methods: Pearson's/full correlation (static, bivariate), lagged correlation (dynamic, bivariate), partial correlation (static, multivariate) and multivariate AR model with and without self-connections (dynamic, multivariate). We compared these methods by (i) assessing similarities between FC matrices, (ii) by comparing node centrality measures, and (iii) by comparing the patterns of brain-behavior associations. Although FC estimates did not differ as a function of sensitivity to temporal order, we observed differences between the multivariate and bivariate FC methods. The dynamic FC estimates were highly correlated with the static FC estimates, especially when comparing group-level FC matrices. Similarly, there were high correlations between the patterns of brain-behavior associations obtained using the dynamic and static FC methods. We conclude that the dynamic FC estimates represent information largely similar to that of the static FC.

Identifying individuals with attention‐deficit/hyperactivity disorder based on multisite resting‐state functional magnetic resonance imaging: A radiomics analysis

Attention-deficit/hyperactivity disorder (ADHD) is one of the most common neurodevelopmental disorders, characterized by symptoms of age-inappropriate inattention, hyperactivity, and impulsivity. Apart from behavioral symptoms investigated by psychiatric methods, there is no standard biological test to diagnose ADHD. This study aimed to explore whether the radiomics features based on resting-state functional magnetic resonance (rs-fMRI) have more discriminative power for the diagnosis of ADHD. The rs-fMRI of 187 subjects with ADHD and 187 healthy controls were collected from 5 sites of ADHD-200 Consortium. A total of four preprocessed rs-fMRI images including regional homogeneity (ReHo), amplitude of low-frequency fluctuation (ALFF), voxel-mirrored homotopic connectivity (VMHC) and network degree centrality (DC) were used in this study. From each of the four images, we extracted 93 radiomics features within each of 116 automated anatomical labeling brain areas, resulting in a total of 43,152 features for each subject. After dimension reduction and feature selection, 19 radiomics features were retained (5 from ALFF, 9 from ReHo, 3 from VMHC and 2 from DC). By training and optimizing a support vector machine model using the retained features of training dataset, we achieved the accuracy of 76.3% and 77.0% (areas under curve = 0.811 and 0.797) in the training and testing datasets, respectively. Our findings demonstrate that radiomics can be a novel strategy for fully utilizing rs-fMRI information to distinguish ADHD from healthy controls. The rs-fMRI-based radiomics features have the potential to be neuroimaging biomarkers for ADHD.

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.

Machine Learning and MRI-based Diagnostic Models for ADHD: Are We There Yet?

OBJECTIVE

Machine learning (ML) has been applied to develop magnetic resonance imaging (MRI)-based diagnostic classifiers for attention-deficit/hyperactivity disorder (ADHD). This systematic review examines this literature to clarify its clinical significance and to assess the implications of the various analytic methods applied.

METHODS

A comprehensive literature search on MRI-based diagnostic classifiers for ADHD was performed and data regarding the utilized models and samples were gathered.

RESULTS

We found that, although most studies reported the classification accuracies, they varied in choice of MRI modalities, ML models, cross-validation and testing methods, and sample sizes. We found that the accuracies of cross-validation methods inflated the performance estimation compared with those of a held-out test, compromising the model generalizability. Test accuracies have increased with publication year but were not associated with training sample sizes. Improved test accuracy over time was likely due to the use of better ML methods along with strategies to deal with data imbalances.

CONCLUSION

Ultimately, large multi-modal imaging datasets, and potentially the combination with other types of data, like cognitive data and/or genetics, will be essential to achieve the goal of developing clinically useful imaging classification tools for ADHD in the future.

Frequency-dependent genetic modulation of neuronal oscillations: a combined transcriptome and resting-state functional MRI study

Neuronal oscillations within certain frequency bands are assumed to associate with specific neural processes and cognitive functions. To examine this hypothesis, transcriptome-neuroimaging spatial correlation analysis was applied to resting-state functional magnetic resonance imaging data from 793 healthy individuals and gene expression data from the Allen Human Brain Atlas. We found that expression measures of 336 genes were correlated with fractional amplitude of low-frequency fluctuations (fALFF) in the slow-4 band (0.027-0.073 Hz), whereas there were no expression-fALFF correlations for the other frequency bands. Furthermore, functional enrichment analyses showed that these slow-4 fALFF-related genes were mainly enriched for ion channel, synaptic function, and neuronal system as well as many neuropsychiatric disorders. Specific expression analyses demonstrated that these genes were specifically expressed in brain tissue, in neurons, and during the late stage of cortical development. Concurrently, the fALFF-related genes were linked to multiple behavioral domains, including dementia, attention, and emotion. In addition, these genes could construct a protein-protein interaction network supported by 30 hub genes. Our findings of a frequency-dependent genetic modulation of spontaneous neuronal activity may support the concept that neuronal oscillations within different frequency bands capture distinct neurobiological processes from the perspective of underlying molecular mechanisms.

Altered neural flexibility in children with attention-deficit/hyperactivity disorder

Attention-deficit/hyperactivity disorder (ADHD) is one of the most common neurodevelopmental disorders of childhood, and is often characterized by altered executive functioning. Executive function has been found to be supported by flexibility in dynamic brain reconfiguration. Thus, we applied multilayer community detection to resting-state fMRI data in 180 children with ADHD and 180 typically developing children (TDC) to identify alterations in dynamic brain reconfiguration in children with ADHD. We specifically evaluated MR derived neural flexibility, which is thought to underlie cognitive flexibility, or the ability to selectively switch between mental processes. Significantly decreased neural flexibility was observed in the ADHD group at both the whole brain (raw p = 0.0005) and sub-network levels (p < 0.05, FDR corrected), particularly for the default mode network, attention-related networks, executive function-related networks, and primary networks. Furthermore, the subjects with ADHD who received medication exhibited significantly increased neural flexibility (p = 0.025, FDR corrected) when compared to subjects with ADHD who were medication naïve, and their neural flexibility was not statistically different from the TDC group (p = 0.74, FDR corrected). Finally, regional neural flexibility was capable of differentiating ADHD from TDC (Accuracy: 77% for tenfold cross-validation, 74.46% for independent test) and of predicting ADHD severity using clinical measures of symptom severity (R2: 0.2794 for tenfold cross-validation, 0.156 for independent test). In conclusion, the present study found that neural flexibility is altered in children with ADHD and demonstrated the potential clinical utility of neural flexibility to identify children with ADHD, as well as to monitor treatment responses and disease severity.

Toward Precision Medicine in ADHD

Attention-Deficit Hyperactivity Disorder (ADHD) is a complex and heterogeneous neurodevelopmental condition for which curative treatments are lacking. Whilst pharmacological treatments are generally effective and safe, there is considerable inter-individual variability among patients regarding treatment response, required dose, and tolerability. Many of the non-pharmacological treatments, which are preferred to drug-treatment by some patients, either lack efficacy for core symptoms or are associated with small effect sizes. No evidence-based decision tools are currently available to allocate pharmacological or psychosocial treatments based on the patient's clinical, environmental, cognitive, genetic, or biological characteristics. We systematically reviewed potential biomarkers that may help in diagnosing ADHD and/or stratifying ADHD into more homogeneous subgroups and/or predict clinical course, treatment response, and long-term outcome across the lifespan. Most work involved exploratory studies with cognitive, actigraphic and EEG diagnostic markers to predict ADHD, along with relatively few studies exploring markers to subtype ADHD and predict response to treatment. There is a critical need for multisite prospective carefully designed experimentally controlled or observational studies to identify biomarkers that index inter-individual variability and/or predict treatment response.

Stability Analysis of fMRI BOLD Signals for Disease Diagnosis

Previous studies have demonstrated that the stability changes in physiological signals can reflect individuals' pathological conditions. Apart from this, according to system science theory, a large-scale system can generally be divided into many subsystems whose stability level govern its overall performance. Therefore, this study attempts to investigate the possibility of analyzing the stability of decomposed subsystems of resting-state fMRI (rs-fMRI) BOLD signals in order to assess the overall characteristic of the human brain and individuals' health conditions. We used attention deficit/hyperactive disorder (ADHD) as an example to illustrate our method. Rs-fMRI BOLD signals were first decomposed into dynamic modes (DMs) which can illuminate the patterns of brain subsystems. Each DM is associated with one eigenvalue that determines its stability as well as oscillation frequency. Accordingly, we divided the DMs within common BOLD frequency bands into stable and unstable DMs. Then, the features related to the stability of those DMs were extracted, and nine common classifiers were used to differentiate healthy controls from ADHD patients taken from ADHD-200, a well-known dataset. The results showed that almost all features were statistically significant. Additionally, our proposed approach outperforms all existing methods with the highest possible precision, recall, and area under the receiver operating characteristic curve of 100%. In sum, we are the first to evaluate the stability of BOLD signals and demonstrate its possibility for disease diagnosis. This method can unveil new mechanisms of brain function, and could be widely used in medicine and engineering.

The norepinephrine transporter gene modulates intrinsic brain activity, visual memory, and visual attention in children with attention-deficit/hyperactivity disorder

The norepinephrine transporter gene (SLC6A2) and deficits in visual memory and attention were associated with attention-deficit/hyperactivity disorder (ADHD). The present study aimed to examine whether the SLC6A2 rs36011 (T)/rs1566652 (G) haplotype affected the intrinsic brain activity in children with ADHD and whether these gene-brain modulations were associated with visual memory and attention in this population. A total of 96 drug-naive children with ADHD and 114 typically developing children (TDC) were recruited. We analyzed intrinsic brain activity with regional homogeneity (ReHo) and degree centrality (DC). Visual memory and visual attention were assessed by the delayed matching to sample (DMS) and rapid visual information processing (RVIP) tasks, respectively. The SNP genotyping of rs36011 and rs1566652 was performed. Children with ADHD showed lower ReHo and DC in the cuneus and lingual gyri than TDC. The TG haplotype was associated with significantly increased DC in the right precentral and postcentral gyri. Significant interactions of ADHD status and the TG haplotype were found in the right postcentral gyrus and superior parietal lobule for ReHo. For the ADHD-TG group, we found significant correlations of performance on the DMS and RVIP tasks with ReHo in bilateral precentral-postcentral gyri and the right postcentral gyrus-superior parietal lobule and DC in bilateral precentral-postcentral gyri. A novel gene-brain-behavior association was identified in which the intrinsic brain activity of the sensorimotor and dorsal attention networks was related to visual memory and visual attention in ADHD children with the SLC6A2 rs36011 (T)/rs1566652 (G) haplotype.

Exposure to methylphenidate during peri-adolescence decouples the prefrontal cortex: a multimodal MRI study

This study was designed to assess the effects of daily psychostimulant exposure during juvenility and peri-adolescence on brain morphology and functional connectivity using multimodal magnetic resonance imaging. We hypothesized that long-term exposure to methylphenidate would enhance connectivity with the prefrontal cortex. Male rats were given daily injections of either methylphenidate (n=10), dextroamphetamine (n=10) or saline vehicle (n=10) from postnatal day 21 to 42. They were imaged between postnatal day 43 and 48. Voxel-based morphometry, diffusion weighted imaging, and resting state functional connectivity were used to quantify brain structure and function. Images from each modality were registered and analyzed, using a 3D MRI rat atlas providing site-specific data over 171 different brain areas. Following imaging, rats were tested for cognitive function using novel object preference. Long-lasting psychostimulant treatment was associated with only a few significant changes in brain volume and measures of anisotropy compared to vehicle. Resting state functional connectivity imaging revealed decreased coupling between the prefrontal cortex, basal ganglia and sensory motor cortices. There were no significant differences between experimental groups for cognitive behavior. In this exploratory study, we showed that chronic psychostimulant treatment throughout juvenility and preadolescence has a minimal effect on brain volume and gray matter microarchitecture, but significantly uncouples the connectivity in the cerebral/basal ganglia circuitry.

Frequency-specific alterations of the resting-state BOLD signals in nocturnal enuresis: an fMRI Study

Resting state functional magnetic resonance imaging studies of nocturnal enuresis have focused primarily on regional metrics in the blood oxygen level dependent (BOLD) signal ranging from 0.01 to 0.08 Hz. However, it remains unclear how local metrics show in sub-frequency band. 129 children with nocturnal enuresis (NE) and 37 healthy controls were included in this study. The patients were diagnosed by the pediatricians in Shanghai Children's Medical Center affiliated to Shanghai Jiao Tong University School of Medicine, according to the criteria from International Children's Continence Society (ICCS). Questionnaires were used to evaluate the symptoms of enuresis and completed by the participants. In this study, fALFF, ReHo and PerAF were calculated within five different frequency bands: typical band (0.01-0.08 Hz), slow-5 (0.01-0.027 Hz), slow-4 (0.027-0.073 Hz), slow-3 (0.073-0.198 Hz), and slow-2 (0.198-0.25 Hz). In the typical band, ReHo increased in the left insula and the right thalamus, while fALFF decreased in the right insula in children with NE. Besides, PerAF was increased in the right middle temporal gyrus in these children. The results regarding ReHo, fALFF and PerAF in the typical band was similar to those in slow-5 band, respectively. A correlation was found between the PerAF value of the right middle temporal gyrus and scores of the urinary intention-related wakefulness. Results in other bands were either negative or in white matter. NE children might have abnormal intrinsic neural oscillations mainly on slow-5 bands.

Exploring characteristic features of attention-deficit/hyperactivity disorder: findings from multi-modal MRI and candidate genetic data

The current study examined whether machine learning features best distinguishing attention-deficit/hyperactivity disorder (ADHD) from typically developing children (TDC) can explain clinical phenotypes using multi-modal neuroimaging and genetic data. Cortical morphology, diffusivity scalars, resting-state functional connectivity and polygenic risk score (PS) from norepinephrine, dopamine and glutamate genes were extracted from 47 ADHD and 47 matched TDC. Using random forests, classification accuracy was measured for each uni- and multi-modal model. The optimal model was used to explain symptom severity or task performance and its robustness was validated in the independent dataset including 18 ADHD and 18 TDC. The model consisting of cortical thickness and volume features achieved the best accuracy of 85.1%. Morphological changes across insula, sensory/motor, and inferior frontal cortex were also found as key predictors. Those explained 18.0% of ADHD rating scale, while dynamic regional homogeneity within default network explained 6.4% of the omission errors in continuous performance test. Ensemble of PS to optimal model showed minor effect on accuracy. Validation analysis achieved accuracy of 69.4%. Current findings suggest that structural deformities relevant to salience detection, sensory processing, and response inhibition may be robust classifiers and symptom predictors of ADHD. Altered local functional connectivity across default network predicted attentional lapse. However, further investigation is needed to clarify roles of genetic predisposition.

Brain dynamics: the temporal variability of connectivity, and differences in schizophrenia and ADHD

We describe advances in the understanding of brain dynamics that are important for understanding the operation of the cerebral cortex in health and disease. In data from 1017 participants from the Human Connectome Project, we show that early visual and connected areas have low temporal variability of their functional connectivity. We show that a low temporal variability of the connectivity of cortical areas is related to high mean functional connectivity between those areas, and provide an account of how these dynamics arise. We then investigate how these concepts help to understand brain dynamics in mental disorders. We find that in both first episode and long-term schizophrenia, reduced functional connectivity of early visual and related temporal cortex areas is associated with increased temporal variability of the functional connectivity, consistent with decreased stability of attractor networks related to sensory processing. In ADHD, we find these functional connectivities are increased and their temporal variability is decreased, and relate this to increased engagement with visual sensory input as manifest in high screen time usage in ADHD. We further show that these differences in the dynamics of the cortex in schizophrenia, and ADHD can be related to differences in the functional connectivity of the specific sensory vs. association thalamic nuclei. These discoveries help to advance our understanding of cortical operation in health, and in some mental disorders.

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.

Multimodal neuroimaging-based prediction of adult outcomes in childhood-onset ADHD using ensemble learning techniques

Attention-deficit/hyperactivity disorder (ADHD) is a highly prevalent and heterogeneous neurodevelopmental disorder, which is diagnosed using subjective symptom reports. Machine learning classifiers have been utilized to assist in the development of neuroimaging-based biomarkers for objective diagnosis of ADHD. However, existing basic model-based studies in ADHD report suboptimal classification performances and inconclusive results, mainly due to the limited flexibility for each type of basic classifier to appropriately handle multi-dimensional source features with varying properties. This study applied ensemble learning techniques (ELTs), a meta-algorithm that combine several basic machine learning models into one predictive model in order to decrease variance, bias, or improve predictions, in multimodal neuroimaging data collected from 72 young adults, including 36 probands (18 remitters and 18 persisters of childhood ADHD) and 36 group-matched controls. All currently available optimization strategies for ELTs (i.e., voting, bagging, boosting and stacking techniques) were tested in a pool of semifinal classification results generated by seven basic classifiers. The high-dimensional neuroimaging features for classification included regional cortical gray matter (GM) thickness and surface area, GM volume of subcortical structures, volume and fractional anisotropy of major white matter fiber tracts, pair-wise regional connectivity and global/nodal topological properties of the functional brain network for cue-evoked attention process. As a result, the bagging-based ELT with the base model of support vector machine achieved the best results, with significant improvement of the area under the receiver of operating characteristic curve (0.89 for ADHD vs. controls and 0.9 for ADHD persisters vs. remitters). Features of nodal efficiency in right inferior frontal gyrus, right middle frontal (MFG)-inferior parietal (IPL) functional connectivity, and right amygdala volume significantly contributed to accurate discrimination between ADHD probands and controls; higher nodal efficiency of right MFG greatly contributed to inattentive and hyperactive/impulsive symptom remission, while higher right MFG-IPL functional connectivity strongly linked to symptom persistence in adults with childhood ADHD. Considering their improved robustness than the commonly implemented basic classifiers, findings suggest that ELTs may have the potential to identify more reliable neurobiological markers for neurodevelopmental disorders.

Comparison of Behavioral Changes and Brain Activity between Adolescents with Internet Gaming Disorder and Student Pro-Gamers

While pro-gamers play according to defined living habits and planned schedules, adolescents with internet gaming disorder (IGD) exhibit irregular lifestyles and unregulated impulsive gaming behavior. Fourteen IGD adolescents and 12 pro-gaming students participated in this study. At baseline and after one year, demographic data, the Child Behavior Check List (CBCL), depressed mood, anxiety, and resting-state functional magnetic resonance imaging were assessed. Over the year, IGD adolescents played games as per their usual schedule, while pro-gamer students played according to their school’s team schedule. After one year, the pro-gamers’ scores had decreased in the CBCL-total (total problematic behaviors), CBCL-externalizing (under-controlled behavior, like impulsivity and aggression), and CBCL-internalizing (over-controlled behavior like depression and anxiety) compared to those of the IGD adolescents. Both groups displayed increased brain activity in the parietal lobe (a component of the attention network) over the years. Compared to pro-gamers, IGD adolescents showed higher brain activity within the left orbitofrontal cortex. Brain activity within the orbitofrontal cortex was associated with CBCL-externalizing scores. These results suggest that gaming had increased the attention network’s brain activity, but a well-organized support system could lead to different results, in terms of improved behaviors and suppressing brain activity within the orbitofrontal cortex.

Exploring attentive task-based connectivity for screening attention deficit/hyperactivity disorder children: a functional near-infrared spectroscopy study

Connectivity impairment has frequently been associated with the pathophysiology of attention-deficit/hyperactivity disorder (ADHD). Although the connectivity of the resting state has mainly been studied, we expect the transition between baseline and task may also be impaired in ADHD children. Twenty-three typically developing (i.e., control) and 36 disordered (ADHD and autism-comorbid ADHD) children were subjected to connectivity analysis. Specifically, they performed an attention task, visual oddball, while their brains were measured by functional near-infrared spectroscopy. The results of the measurements revealed three key findings. First, the control group maintained attentive connectivity, even in the baseline interval. Meanwhile, the disordered group showed enhanced bilateral intra- and interhemispheric connectivities while performing the task. However, right intrahemispheric connectivity was found to be weaker than those for the control group. Second, connectivity and activation characteristics might not be positively correlated with each other. In our previous results, disordered children lacked activation in the right middle frontal gyrus. However, within region connectivity of the right middle frontal gyrus was relatively strong in the baseline interval and significantly increased in the task interval. Third, the connectivity-based biomarker performed better than the activation-based biomarker in terms of screening. Activation and connectivity features were independently optimized and cross validated to obtain the best performing threshold-based classifier. The effectiveness of connectivity features, which brought significantly higher training accuracy than the optimum activation features, was confirmed (88% versus 76%). The optimum screening features were characterized by two trends: (1) strong connectivities of right frontal, left frontal, and left parietal lobes and (2) weak connectivities of left frontal, left parietal, and right parietal lobes in the control group. We conclude that the attentive task-based connectivity effectively shows the difference between control and disordered children and may represent pathological characteristics to be feasibly implemented as a supporting tool for clinical screening.

Neuroimaging in Psychiatry and Neurodevelopment: why the emperor has no clothes

Neuroimaging has been a dominant force in guiding research into psychiatric and neurodevelopmental disorders for decades, yet researchers have been unable to formulate sensitive or specific imaging tests for these conditions. The search for neuroimaging biomarkers has been constrained by limited reproducibility of imaging techniques, limited tools for evaluating neurochemistry, heterogeneity of patient populations not defined by brain-based phenotypes, limited exploration of temporal components of brain function, and relatively few studies evaluating developmental and longitudinal trajectories of brain function. Opportunities for development of clinically impactful imaging metrics include longer duration functional imaging data sets, new engineering approaches to mitigate suboptimal spatiotemporal resolution, improvements in image post-processing and analysis strategies, big data approaches combined with data sharing of multisite imaging samples, and new techniques that allow dynamical exploration of brain function across multiple timescales. Despite narrow clinical impact of neuroimaging methods, there is reason for optimism that imaging will contribute to diagnosis, prognosis, and treatment monitoring for psychiatric and neurodevelopmental disorders in the near future.

Benchmarking functional connectome-based predictive models for resting-state fMRI

Functional connectomes reveal biomarkers of individual psychological or clinical traits. However, there is great variability in the analytic pipelines typically used to derive them from rest-fMRI cohorts. Here, we consider a specific type of studies, using predictive models on the edge weights of functional connectomes, for which we highlight the best modeling choices. We systematically study the prediction performances of models in 6 different cohorts and a total of 2000 individuals, encompassing neuro-degenerative (Alzheimer's, Post-traumatic stress disorder), neuro-psychiatric (Schizophrenia, Autism), drug impact (Cannabis use) clinical settings and psychological trait (fluid intelligence). The typical prediction procedure from rest-fMRI consists of three main steps: defining brain regions, representing the interactions, and supervised learning. For each step we benchmark typical choices: 8 different ways of defining regions -either pre-defined or generated from the rest-fMRI data- 3 measures to build functional connectomes from the extracted time-series, and 10 classification models to compare functional interactions across subjects. Our benchmarks summarize more than 240 different pipelines and outline modeling choices that show consistent prediction performances in spite of variations in the populations and sites. We find that regions defined from functional data work best; that it is beneficial to capture between-region interactions with tangent-based parametrization of covariances, a midway between correlations and partial correlation; and that simple linear predictors such as a logistic regression give the best predictions. Our work is a step forward to establishing reproducible imaging-based biomarkers for clinical settings.

Classification Accuracy of Neuroimaging Biomarkers in Attention-Deficit/Hyperactivity Disorder: Effects of Sample Size and Circular Analysis

BACKGROUND

Motivated by an inconsistency between reports of high diagnosis-classification accuracies and known heterogeneity in attention-deficit/hyperactivity disorder (ADHD), this study assessed classification accuracy in studies of ADHD as a function of methodological factors that can bias results. We hypothesized that high classification results in ADHD diagnosis are inflated by methodological factors.

METHODS

We reviewed 69 studies (of 95 studies identified) that used neuroimaging features to predict ADHD diagnosis. Based on reported methods, we assessed the prevalence of circular analysis, which inflates classification accuracy, and evaluated the relationship between sample size and accuracy to test if small-sample models tend to report higher classification accuracy, also an indicator of bias.

RESULTS

Circular analysis was detected in 15.9% of ADHD classification studies, lack of independent test set was noted in 13%, and insufficient methodological detail to establish its presence was noted in another 11.6%. Accuracy of classification ranged from 60% to 80% in the 59.4% of reviewed studies that met criteria for independence of feature selection, model construction, and test datasets. Moreover, there was a negative relationship between accuracy and sample size, implying additional bias contributing to reported accuracies at lower sample sizes.

CONCLUSIONS

High classification accuracies in neuroimaging studies of ADHD appear to be inflated by circular analysis and small sample size. Accuracies on independent datasets were consistent with known heterogeneity of the disorder. Steps to resolve these issues, and a shift toward accounting for sample heterogeneity and prediction of future outcomes, will be crucial in future classification studies in ADHD.

The resilient brain: psychological resilience mediates the effect of amplitude of low-frequency fluctuations in orbitofrontal cortex on subjective well-being in young healthy adults

Psychological resilience reflects the capacity to bounce back from stress, which plays an important role in health and well-being. However, less is known about the neural substrate for psychological resilience and the underlying mechanism for how psychological resilience enhances subjective well-being in the healthy brain. To investigate these issues, we employed fractional amplitude of low-frequency fluctuations (fALFF) measured with resting-state fMRI in 100 young healthy adults. The correlation analysis found that higher psychological resilience was related to lower fALFF in the left orbitofrontal cortex (OFC), which is involved in reward-related processing and emotion regulation. Furthermore, the mediation analysis indicated that psychological resilience acted as a full mediator of the association between the fALFF in left OFC and subjective well-being indicators (i.e. life satisfaction and hedonic balance). Importantly, these results remained significant after controlling for the effect of gray matter volume and regional homogeneity in the region. Overall, the present study provides the further evidence for functional neural substrates of psychological resilience and reveals a potential mechanism that psychological resilience mediates the effect of spontaneous brain activity on subjective well-being.

Multimodal Neuroimaging: Basic Concepts and Classification of Neuropsychiatric Diseases

Neuroimaging techniques are widely used in neuroscience to visualize neural activity, to improve our understanding of brain mechanisms, and to identify biomarkers-especially for psychiatric diseases; however, each neuroimaging technique has several limitations. These limitations led to the development of multimodal neuroimaging (MN), which combines data obtained from multiple neuroimaging techniques, such as electroencephalography, functional magnetic resonance imaging, and yields more detailed information about brain dynamics. There are several types of MN, including visual inspection, data integration, and data fusion. This literature review aimed to provide a brief summary and basic information about MN techniques (data fusion approaches in particular) and classification approaches. Data fusion approaches are generally categorized as asymmetric and symmetric. The present review focused exclusively on studies based on symmetric data fusion methods (data-driven methods), such as independent component analysis and principal component analysis. Machine learning techniques have recently been introduced for use in identifying diseases and biomarkers of disease. The machine learning technique most widely used by neuroscientists is classification-especially support vector machine classification. Several studies differentiated patients with psychiatric diseases and healthy controls with using combined datasets. The common conclusion among these studies is that the prediction of diseases increases when combining data via MN techniques; however, there remain a few challenges associated with MN, such as sample size. Perhaps in the future N-way fusion can be used to combine multiple neuroimaging techniques or nonimaging predictors (eg, cognitive ability) to overcome the limitations of MN.

Resting-state functional magnetic resonance imaging investigation of the neural correlates of cognitive-behavioral therapy for externalizing behavior problems in adolescent bullies

The purpose of this study was to investigate the neural correlates of cognitive-behavioral therapy (CBT) for externalizing behavior problems in perpetrators of school bullying using assessments of brain activity and behavior. Twenty-five adolescent bullies participated in an 8-session intervention. Prior to and after participation, 24 adolescents were evaluated using the Child Behavior Checklist (CBCL) and 23 completed resting-state functional magnetic resonance imaging. Changes in the fractional amplitude of low-frequency fluctuations (fALFF) and scores on the CBCL were analyzed. We also compared the identified changes into 2 groups (low and high delinquency) differentiated by a cutoff of 65 points on the delinquency subscale of the CBCL. Following the intervention, participants exhibited improvement in the subscores of the CBCL and decreases in the fALFF of the inferior parietal lobule, lingual, interior frontal and middle occipital gyrus. A positive correlation was observed between changes in the CBCL externalizing behavior scores and fALFF of the inferior frontal gyrus. The high delinquency group showed a greater decrease in delinquency and externalizing CBCL subscores across time than did the low delinquency group. The high delinquency group had more areas that showed change in fALFF post-intervention than did the low delinquency group. A positive correlation was observed between changes in the CBCL delinquency scores and fALFF of the precentral gyrus in the high delinquency group. The results indicate that this CBT for externalizing behavior problems in bullies had more positive effects on delinquent behavior in adolescents with high levels of delinquency, and these changes were associated with functional changes in brain activity.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT02670876.

Identifying individuals with attention deficit hyperactivity disorder based on temporal variability of dynamic functional connectivity

Attention deficit hyperactivity disorder (ADHD) is a common disorder that emerges in school-age children. The diagnostic model based on neuroimaging features could be beneficial for ADHD in twofold: identifying individuals with ADHD and discovering the discriminative patterns for patients. The dynamic functional connectivity of ADHD remains unclear. Towards this end, 100 children with ADHD and 140 normal controls were obtained from the ADHD-200 Consortium. The raw features were derived from the temporal variability between intrinsic connectivity networks (ICNs) as well as the demographic and covariate variables. The diagnostic model was based on the support vector machines (SVMs). The performance of diagnostic model was analyzed using leave-one-out cross-validation (LOOCV) and 10-folds cross-validations (CVs). The diagnostic model based on inter-ICN variability outperformed that based on inter-ICN functional connectivity and inter-ICN phase synchrony. The LOOCV achieved total accuracy of 78.75%, the sensitivity of 76%, and the specificity of 80.71%. The 10-folds CVs achieved average prediction accuracy of 75.54% ± 1.34%, average sensitivity of 70.5% ± 2.34%, and average specificity of 77.44% ± 1.47%. In addition, the discriminative patterns for ADHD were discovered using SVMs. The discriminative patterns confirmed with previous findings. In summary, individuals with ADHD could be identified through inter-ICN variability, which could be potential biomarkers for diagnostic model of ADHD.

Diagnostic model for attention-deficit hyperactivity disorder based on interregional morphological connectivity

Previous brain morphology-related diagnostic models for attention-deficit hyperactivity disorder (ADHD) were based on regional features. However, building a model of individual interregional morphological connectivity is a challenging task. This study aimed to identify children with ADHD utilizing a novel interregional morphological connectivity model and discover the discriminative patterns in patients. Therefore, novel interregional morphological patterns rather than regional patterns were extracted via surface-based analysis. The interregional morphological features were trained and tested using a hybrid machine learning method, which was implemented using the leave-one-out cross-validation (LOOCV) method to produce the optimized discriminative model and discriminative patterns. The inclusion of interregional morphological connectivity significantly improved the performance of the diagnostic models compared to the performance of the model constructed using regional features. The optimized discriminative model exhibited a total accuracy of 74.65%, a sensitivity of 75% and a specificity of 74.29%. The brain regions displaying altered morphological connectivity included the insula, the caudal anterior cingulate cortex, the frontal pole, and the postcentral cortex, among others. In addition, the altered connections correlated with the clinical symptoms. In summary, patients with ADHD exhibited altered morphological connectivity, which might be a potential biomarker for the classification of ADHD. The discriminative features will potentially benefit studies investigating the brain network mechanisms of ADHD.

Functional MRI signal fluctuations highlight altered resting brain activity in Huntington's disease

The fractional Amplitude of Low Frequency Fluctuations (fALFF) and the degree of local synchronization (Regional Homogeneity - ReHo) of resting-state BOLD signal have been suggested to map spontaneous neuronal activity and local functional connectivity, respectively. We compared voxelwise, independent of atrophy, the fALFF and ReHo patterns of 11 presymptomatic (ps-HD) and 28 symptomatic (sHD) Huntington's disease mutation carriers, with those of 40 normal volunteers, and tested their possible correlations with the motor and cognitive subscores of the Unified Huntington's Disease Rating Scale. In sHD patients, fALFF was mainly reduced bilaterally in parietal lobes (right precuneus being already affected in psHD), and in superior frontal gyri, and increased bilaterally in cerebellar lobules VI, VIII and IX, as well as in the right inferior temporal gyrus. In sHD, and to a lesser extent in psHD, ReHo was bilaterally reduced in putamina, cerebellar lobules III to VI, and superior medial frontal gyri, and increased in both psHD and sHD in fronto-basal cortices, and in the right temporal lobe. fALFF correlated inversely with cognitive scores in lobule IX of the cerebellum (mainly with total Stroop score, p < 0.0001), and in the medial portions of both thalami. These results are consistent with a reduced neuronal activity in the cortical components of the executive networks, known to be affected in Huntington's Disease, and with reduced local functional integration in subcortical and cerebellar components of the sensori-motor network. Cerebellar clusters of significant correlation of fALFF with executive function scores may be related to compensatory mechanisms.

Resting-State Brain Signal Variability in Prefrontal Cortex Is Associated With ADHD Symptom Severity in Children

Atypical brain function in attention-deficit/hyperactivity disorder (ADHD) has been identified using both task-activation and functional connectivity fMRI approaches. Recent work highlights the potential for another measure derived from functional neuroimaging data, brain signal variability, to reveal insights into clinical conditions. Higher brain signal variability has previously been linked with optimal behavioral performance. At present, little is known regarding the relationship between resting-state brain signal variability and ADHD symptom severity. The current study examined the relationship between a measure of moment-to-moment brain signal variability called mean-square successive difference (MSSD) and ADHD symptomatology in a group of children (7–12 years old) with (n = 40) and without (n = 30) a formal diagnosis of ADHD. A categorical analysis comparing subjects with and without a clinical diagnosis of ADHD showed no differences in MSSD between groups. A dimensional analysis revealed a positive relationship between MSSD and overall ADHD symptom severity and inattention across children with and without an ADHD diagnosis. Specifically, this positive relationship was found in medial prefrontal areas comprising the default mode network. These results demonstrate a link between intrinsic brain signal variability and ADHD symptom severity that cuts across diagnostic categories, and point to a locus of dysfunction consistent with previous neuroimaging literature.

Fusion of fMRI and non-imaging data for ADHD classification

Resting state fMRI has emerged as a popular neuroimaging method for automated recognition and classification of different brain disorders. Attention Deficit Hyperactivity Disorder (ADHD) is one of the most common brain disorders affecting young children, yet its underlying mechanism is not completely understood and its diagnosis is mainly dependent on behavior analysis. This paper addresses the problem of classification of ADHD based on resting state fMRI and proposes a machine learning framework with integration of non-imaging data with imaging data to investigate functional connectivity alterations between ADHD and control subjects (not diagnosed with ADHD). Our aim is to apply computational techniques to (1) automatically classify a subject as ADHD or control, (2) identify differences in functional connectivity of these two groups and (3) evaluate the importance of fusing non-imaging with imaging data for classification. In the first stage of our framework, we determine the functional connectivity of brain regions by grouping brain activity using clustering algorithms. Next, we employ Elastic Net based feature selection to select the most discriminant features from the dense functional brain network and integrate non-imaging data. Finally, a Support Vector Machine classifier is trained to classify ADHD subjects vs. control. The proposed framework was evaluated on a public ADHD-200 dataset, and our results suggest that fusion of non-imaging data improves the performance of the framework. Classification results outperform the state-of-the-art on some subsets of the data.

A Computational Model for the Automatic Diagnosis of Attention Deficit Hyperactivity Disorder Based on Functional Brain Volume

In this paper, we investigated the problem of computer-aided diagnosis of Attention Deficit Hyperactivity Disorder (ADHD) using machine learning techniques. With the ADHD-200 dataset, we developed a Support Vector Machine (SVM) model to classify ADHD patients from typically developing controls (TDCs), using the regional brain volumes as predictors. Conventionally, the volume of a brain region was considered to be an anatomical feature and quantified using structural magnetic resonance images. One major contribution of the present study was that we had initially proposed to measure the regional brain volumes using fMRI images. Brain volumes measured from fMRI images were denoted as functional volumes, which quantified the volumes of brain regions that were actually functioning during fMRI imaging. We compared the predictive power of functional volumes with that of regional brain volumes measured from anatomical images, which were denoted as anatomical volumes. The former demonstrated higher discriminative power than the latter for the classification of ADHD patients vs. TDCs. Combined with our two-step feature selection approach which integrated prior knowledge with the recursive feature elimination (RFE) algorithm, our SVM classification model combining functional volumes and demographic characteristics achieved a balanced accuracy of 67.7%, which was 16.1% higher than that of a relevant model published previously in the work of Sato et al. Furthermore, our classifier highlighted 10 brain regions that were most discriminative in distinguishing between ADHD patients and TDCs. These 10 regions were mainly located in occipital lobe, cerebellum posterior lobe, parietal lobe, frontal lobe, and temporal lobe. Our present study using functional images will likely provide new perspectives about the brain regions affected by ADHD.

Individual variation in functional brain connectivity: implications for personalized approaches to psychiatric disease

Functional brain connectivity measured with functional magnetic resonance imaging (fMRI) is a popular technique for investigating neural organization in both healthy subjects and patients with mental illness. Despite a rapidly growing body of literature, however, functional connectivity research has yet to deliver biomarkers that can aid psychiatric diagnosis or prognosis at the single-subject level. One impediment to developing such practical tools has been uncertainty regarding the ratio of intra- to interindividual variability in functional connectivity; in other words, how much variance is state- versus trait-related. Here, we review recent evidence that functional connectivity profiles are both reliable within subjects and unique across subjects, and that features of these profiles relate to behavioral phenotypes. Together, these results suggest the potential to discover reliable correlates of present and future illness and/or response to treatment in the strength of an individual's functional brain connections. Ultimately, this work could help develop personalized approaches to psychiatric illness.

Progress and roadblocks in the search for brain-based biomarkers of autism and attention-deficit/hyperactivity disorder

Children with neurodevelopmental disorders benefit most from early interventions and treatments. The development and validation of brain-based biomarkers to aid in objective diagnosis can facilitate this important clinical aim. The objective of this review is to provide an overview of current progress in the use of neuroimaging to identify brain-based biomarkers for autism spectrum disorder (ASD) and attention-deficit/hyperactivity disorder (ADHD), two prevalent neurodevelopmental disorders. We summarize empirical work that has laid the foundation for using neuroimaging to objectively quantify brain structure and function in ways that are beginning to be used in biomarker development, noting limitations of the data currently available. The most successful machine learning methods that have been developed and applied to date are discussed. Overall, there is increasing evidence that specific features (for example, functional connectivity, gray matter volume) of brain regions comprising the salience and default mode networks can be used to discriminate ASD from typical development. Brain regions contributing to successful discrimination of ADHD from typical development appear to be more widespread, however there is initial evidence that features derived from frontal and cerebellar regions are most informative for classification. The identification of brain-based biomarkers for ASD and ADHD could potentially assist in objective diagnosis, monitoring of treatment response and prediction of outcomes for children with these neurodevelopmental disorders. At present, however, the field has yet to identify reliable and reproducible biomarkers for these disorders, and must address issues related to clinical heterogeneity, methodological standardization and cross-site validation before further progress can be achieved.

Differential effects of methylphenidate and atomoxetine on intrinsic brain activity in children with attention deficit hyperactivity disorder

BACKGROUND

Methylphenidate and atomoxetine are commonly prescribed for treating attention deficit hyperactivity disorder (ADHD). However, their therapeutic neural mechanisms remain unclear.

METHOD

After baseline evaluation including cognitive testing of the Cambridge Neuropsychological Test Automated Battery (CANTAB), drug-naive children with ADHD (n = 46), aged 7-17 years, were randomly assigned to a 12-week treatment with methylphenidate (n = 22) or atomoxetine (n = 24). Intrinsic brain activity, including the fractional amplitude of low-frequency fluctuations (fALFF) and regional homogeneity (ReHo), was quantified via resting-state functional magnetic resonance imaging at baseline and week 12.

RESULTS

Reductions in inattentive symptoms were related to increased fALFF in the left superior temporal gyrus and left inferior parietal lobule for ADHD children treated with methylphenidate, and in the left lingual gyrus and left inferior occipital gyrus for ADHD children treated with atomoxetine. Hyperactivity/impulsivity symptom reductions were differentially related to increased fALFF in the methylphenidate group and to decreased fALFF in the atomoxetine group in bilateral precentral and postcentral gyri. Prediction analyses in the atomoxetine group revealed negative correlations between pre-treatment CANTAB simple reaction time and fALFF change in the left lingual gyrus and left inferior occipital gyrus, and positive correlations between pre-treatment CANTAB simple movement time and fALFF change in bilateral precentral and postcentral gyri and left precuneus, with a negative correlation between movement time and the fALFF change in the left lingual gyrus and the inferior occipital gyrus.

CONCLUSIONS

Our findings suggest differential neurophysiological mechanisms for the treatment effects of methylphenidate and atomoxetine in children with ADHD.

Individual variation in functional brain connectivity: implications for personalized approaches to psychiatric disease

Functional brain connectivity measured with functional magnetic resonance imaging (fMRI) is a popular technique for investigating neural organization in both healthy subjects and patients with mental illness. Despite a rapidly growing body of literature, however, functional connectivity research has yet to deliver biomarkers that can aid psychiatric diagnosis or prognosis at the single-subject level. One impediment to developing such practical tools has been uncertainty regarding the ratio of intra- to interindividual variability in functional connectivity; in other words, how much variance is state- versus trait-related. Here, we review recent evidence that functional connectivity profiles are both reliable within subjects and unique across subjects, and that features of these profiles relate to behavioral phenotypes. Together, these results suggest the potential to discover reliable correlates of present and future illness and/or response to treatment in the strength of an individual's functional brain connections. Ultimately, this work could help develop personalized approaches to psychiatric illness.

The Neuro Bureau ADHD-200 Preprocessed repository

In 2011, the "ADHD-200 Global Competition" was held with the aim of identifying biomarkers of attention-deficit/hyperactivity disorder from resting-state functional magnetic resonance imaging (rs-fMRI) and structural MRI (s-MRI) data collected on 973 individuals. Statisticians and computer scientists were potentially the most qualified for the machine learning aspect of the competition, but generally lacked the specialized skills to implement the necessary steps of data preparation for rs-fMRI. Realizing this barrier to entry, the Neuro Bureau prospectively collaborated with all competitors by preprocessing the data and sharing these results at the Neuroimaging Informatics Tools and Resources Clearinghouse (NITRC) (http://www.nitrc.org/frs/?group_id=383). This "ADHD-200 Preprocessed" release included multiple analytical pipelines to cater to different philosophies of data analysis. The processed derivatives included denoised and registered 4D fMRI volumes, regional time series extracted from brain parcellations, maps of 10 intrinsic connectivity networks, fractional amplitude of low frequency fluctuation, and regional homogeneity, along with grey matter density maps. The data was used by several teams who competed in the ADHD-200 Global Competition, including the winning entry by a group of biostaticians. To the best of our knowledge, the ADHD-200 Preprocessed release was the first large public resource of preprocessed resting-state fMRI and structural MRI data, and remains to this day the only resource featuring a battery of alternative processing paths.

Intrinsic Functional Connectivity in Attention-Deficit/Hyperactivity Disorder: A Science in Development

Functional magnetic resonance imaging (fMRI) without an explicit task, i.e., resting state fMRI, of individuals with Attention-Deficit/Hyperactivity Disorder (ADHD) is growing rapidly. Early studies were unaware of the vulnerability of this method to even minor degrees of head motion, a major concern in the field. Recent efforts are implementing various strategies to address this source of artifact along with a growing set of analytical tools. Availability of the ADHD-200 Consortium dataset, a large-scale multi-site repository, is facilitating increasingly sophisticated approaches. In parallel, investigators are beginning to explicitly test the replicability of published findings. In this narrative review, we sketch out broad, overarching hypotheses being entertained while noting methodological uncertainties. Current hypotheses implicate the interplay of default, cognitive control (frontoparietal) and attention (dorsal, ventral, salience) networks in ADHD; functional connectivities of reward-related and amygdala-related circuits are also supported as substrates for dimensional aspects of ADHD. Before these can be further specified and definitively tested, we assert the field must take on the challenge of mapping the "topography" of the analytical space, i.e., determining the sensitivities of results to variations in acquisition, analysis, demographic and phenotypic parameters. Doing so with openly available datasets will provide the needed foundation for delineating typical and atypical developmental trajectories of brain structure and function in neurodevelopmental disorders including ADHD when applied to large-scale multi-site prospective longitudinal studies such as the forthcoming Adolescent Brain Cognitive Development study.

Network-based classification of ADHD patients using discriminative subnetwork selection and graph kernel PCA

BACKGROUND

Attention Deficit Hyperactivity Disorder (ADHD) is one of the most prevalent behavioral disorders in childhood and adolescence. Recently, network-based diagnosis of ADHD has attracted great attentions due to the fact that ADHD disease is related to not only individual brain regions but also the connections among them, while existing methods are hard to discover disorder patterns related with several brain regions.

NEW METHOD

To overcome this drawback, a discriminative subnetwork selection method is proposed to directly mine those frequent and discriminative subnetworks from the whole brain networks of ADHD and normal control (NC) groups. Then, the graph kernel principal component (PCA) is applied to extract features from those discriminative subnetworks. Finally, support vector machine (SVM) is adopted for classification of ADHD and NC subjects.

RESULTS

We evaluate the performances of our proposed method using the ADHD200 dataset, which contains 118 ADHD patients and 98 normal controls. The experimental results show that our proposed method can achieve a very high accuracy of 94.91% for ADHD vs. NC classification. Moreover, our proposed method can also discover the discriminative subnetworks as well as the discriminative brain regions, which are helpful for enhancing our understanding of ADHD disease.

COMPARISON WITH EXISTING METHOD(S)

The accuracy of our proposed method is 9.20% higher than those of the state-of-the-art methods.

CONCLUSIONS

A lot of experiments in ADHD200 dataset show that, our proposed method can improve the performance significantly comparing to the state-of-the-art methods.

An integrated feature ranking and selection framework for ADHD characterization

Today, diagnosis of attention deficit hyperactivity disorder (ADHD) still primarily relies on a series of subjective evaluations that highly rely on a doctor’s experiences and intuitions from diagnostic interviews and observed behavior measures. An accurate and objective diagnosis of ADHD is still a challenge and leaves much to be desired. Many children and adults are inappropriately labeled with ADHD conditions, whereas many are left undiagnosed and untreated. Recent advances in neuroimaging studies have enabled us to search for both structural (e.g., cortical thickness, brain volume) and functional (functional connectivity) abnormalities that can potentially be used as new biomarkers of ADHD. However, structural and functional characteristics of neuroimaging data, especially magnetic resonance imaging (MRI), usually generate a large number of features. With a limited sample size, traditional machine learning techniques can be problematic to discover the true characteristic features of ADHD due to the significant issues of overfitting, computational burden, and interpretability of the model. There is an urgent need of efficient approaches to identify meaningful discriminative variables from a higher dimensional feature space when sample size is small compared with the number of features. To tackle this problem, this paper proposes a novel integrated feature ranking and selection framework that utilizes normalized brain cortical thickness features extracted from MRI data to discriminate ADHD subjects against healthy controls. The proposed framework combines information theoretic criteria and the least absolute shrinkage and selection operator (Lasso) method into a two-step feature selection process which is capable of selecting a sparse model while preserving the most informative features. The experimental results showed that the proposed framework generated the highest/comparable ADHD prediction accuracy compared with the state-of-the-art feature selection approaches with minimum number of features in the final model. The selected regions of interest in our model were consistent with recent brain–behavior studies of ADHD development, and thus confirmed the validity of the selected features by the proposed approach.

Multivariate pattern classification of pediatric Tourette syndrome using functional connectivity MRI

Tourette syndrome (TS) is a developmental neuropsychiatric disorder characterized by motor and vocal tics. Individuals with TS would benefit greatly from advances in prediction of symptom timecourse and treatment effectiveness. As a first step, we applied a multivariate method – support vector machine (SVM) classification – to test whether patterns in brain network activity, measured with resting state functional connectivity (RSFC) MRI, could predict diagnostic group membership for individuals. RSFC data from 42 children with TS (8–15 yrs) and 42 unaffected controls (age, IQ, in‐scanner movement matched) were included. While univariate tests identified no significant group differences, SVM classified group membership with ~70% accuracy (p < .001). We also report a novel adaptation of SVM binary classification that, in addition to an overall accuracy rate for the SVM, provides a confidence measure for the accurate classification of each individual. Our results support the contention that multivariate methods can better capture the complexity of some brain disorders, and hold promise for predicting prognosis and treatment outcome for individuals with TS.

Multivariate analyses applied to fetal, neonatal and pediatric MRI of neurodevelopmental disorders

Multivariate analysis (MVA) is a class of statistical and pattern recognition methods that involve the processing of data that contains multiple measurements per sample. MVA can be used to address a wide variety of medical neuroimaging-related challenges including identifying variables associated with a measure of clinical importance (i.e. patient outcome), creating diagnostic tests, assisting in characterizing developmental disorders, understanding disease etiology, development and progression, assisting in treatment monitoring and much more. Compared to adults, imaging of developing immature brains has attracted less attention from MVA researchers. However, remarkable MVA research growth has occurred in recent years. This paper presents the results of a systematic review of the literature focusing on MVA technologies applied to neurodevelopmental disorders in fetal, neonatal and pediatric magnetic resonance imaging (MRI) of the brain. The goal of this manuscript is to provide a concise review of the state of the scientific literature on studies employing brain MRI and MVA in a pre-adult population. Neurological developmental disorders addressed in the MVA research contained in this review include autism spectrum disorder, attention deficit hyperactivity disorder, epilepsy, schizophrenia and more. While the results of this review demonstrate considerable interest from the scientific community in applications of MVA technologies in pediatric/neonatal/fetal brain MRI, the field is still young and considerable research growth remains ahead of us.

Early warning for human mental sub-health based on fMRI data analysis: an example from a seafarers' resting-data study

Effective mental sub-health early warning mechanism is of great significance in the protection of individual mental health. The traditional mental health assessment method is mainly based on questionnaire surveys, which may have some uncertainties. In this study, based on the relationship between the default mode network (DMN) and the mental health status, we proposed a human mental sub-health early warning method by utilizing two-fold support vector machine (SVM) model, where seafarers' fMRI data analysis was utilized as an example. The method firstly constructed a structural-functional DMN template by combining the anatomical automatic labeling template with the functional DMN extracted by independent component analysis. Then, it put forward a two-fold SVM-based classifier, with one-class SVM utilized for the training of the initial classifier and two-class SVM utilized to refine the classification performance, to identify seafarers' mental health status by utilizing the correlation coefficients (CCs) among the areas of structural-functional DMN as the features. The experimental results showed that the proposed model could discriminate the seafarers with DMN function alteration from the healthy control (HC) effectively, and further the results demonstrated that when compared with the HC group, the brain functional disorders of the mental sub-healthy seafarers mainly manifested as follows: the functional connectivity of DMN had obvious alteration; the CCs among the different DMN regions were significant lower; the regional homogeneity decreased in parts of the prefrontal cortex and increased in multi-regions of the parietal, temporal and occipital cortices; the fractional amplitude of low-frequency fluctuation decreased in parts of the prefrontal cortex and increased in parts of the parietal cortex. All of the results showed that fMRI-based analysis of brain functional activities could be effectively used to distinguish the mental health and sub-health status.

A review of feature reduction techniques in neuroimaging

Machine learning techniques are increasingly being used in making relevant predictions and inferences on individual subjects neuroimaging scan data. Previous studies have mostly focused on categorical discrimination of patients and matched healthy controls and more recently, on prediction of individual continuous variables such as clinical scores or age. However, these studies are greatly hampered by the large number of predictor variables (voxels) and low observations (subjects) also known as the curse-of-dimensionality or small-n-large-p problem. As a result, feature reduction techniques such as feature subset selection and dimensionality reduction are used to remove redundant predictor variables and experimental noise, a process which mitigates the curse-of-dimensionality and small-n-large-p effects. Feature reduction is an essential step before training a machine learning model to avoid overfitting and therefore improving model prediction accuracy and generalization ability. In this review, we discuss feature reduction techniques used with machine learning in neuroimaging studies.

Altered functional connectivity links in neuroleptic-naïve and neuroleptic-treated patients with schizophrenia, and their relation to symptoms including volition

In order to analyze functional connectivity in untreated and treated patients with schizophrenia, resting-state fMRI data were obtained for whole-brain functional connectivity analysis from 22 first-episode neuroleptic-naïve schizophrenia (NNS), 61 first-episode neuroleptic-treated schizophrenia (NTS) patients, and 60 healthy controls (HC). Reductions were found in untreated and treated patients in the functional connectivity between the posterior cingulate gyrus and precuneus, and this was correlated with the reduction in volition from the Positive and Negative Symptoms Scale (PANSS), that is in the willful initiation, sustenance, and control of thoughts, behavior, movements, and speech, and with the general and negative symptoms. In addition in both patient groups interhemispheric functional connectivity was weaker between the orbitofrontal cortex, amygdala and temporal pole. These functional connectivity changes and the related symptoms were not treated by the neuroleptics. Differences between the patient groups were that there were more strong functional connectivity links in the NNS patients (including in hippocampal, frontal, and striatal circuits) than in the NTS patients. These findings with a whole brain analysis in untreated and treated patients with schizophrenia provide evidence on some of the brain regions implicated in the volitional, other general, and negative symptoms, of schizophrenia that are not treated by neuroleptics so have implications for the development of other treatments; and provide evidence on some brain systems in which neuroleptics do alter the functional connectivity.