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

Diagnostic machine learning applications on clinical populations using functional near infrared spectroscopy: a review

Functional near-infrared spectroscopy (fNIRS) and its interaction with machine learning (ML) is a popular research topic for the diagnostic classification of clinical disorders due to the lack of robust and objective biomarkers. This review provides an overview of research on psychiatric diseases by using fNIRS and ML. Article search was carried out and 45 studies were evaluated by considering their sample sizes, used features, ML methodology, and reported accuracy. To our best knowledge, this is the first review that reports diagnostic ML applications using fNIRS. We found that there has been an increasing trend to perform ML applications on fNIRS-based biomarker research since 2010. The most studied populations are schizophrenia (n = 12), attention deficit and hyperactivity disorder (n = 7), and autism spectrum disorder (n = 6) are the most studied populations. There is a significant negative correlation between sample size (>21) and accuracy values. Support vector machine (SVM) and deep learning (DL) approaches were the most popular classifier approaches (SVM = 20) (DL = 10). Eight of these studies recruited a number of participants more than 100 for classification. Concentration changes in oxy-hemoglobin (ΔHbO) based features were used more than concentration changes in deoxy-hemoglobin (ΔHb) based ones and the most popular ΔHbO-based features were mean ΔHbO (n = 11) and ΔHbO-based functional connections (n = 11). Using ML on fNIRS data might be a promising approach to reveal specific biomarkers for diagnostic classification.

Multitask Learning for Joint Diagnosis of Multiple Mental Disorders in Resting-State fMRI

Facing the increasing worldwide prevalence of mental disorders, the symptom-based diagnostic criteria struggle to address the urgent public health concern due to the global shortfall in well-qualified professionals. Thanks to the recent advances in neuroimaging techniques, functional magnetic resonance imaging (fMRI) has surfaced as a new solution to characterize neuropathological biomarkers for detecting functional connectivity (FC) anomalies in mental disorders. However, the existing computer-aided diagnosis models for fMRI analysis suffer from unstable performance on large datasets. To address this issue, we propose an efficient multitask learning (MTL) framework for joint diagnosis of multiple mental disorders using resting-state fMRI data. A novel multiobjective evolutionary clustering algorithm is presented to group regions of interests (ROIs) into different clusters for FC pattern analysis. On the optimal clustering solution, the multicluster multigate mixture-of-expert model is used for the final classification by capturing the highly consistent feature patterns among related diagnostic tasks. Extensive simulation experiments demonstrate that the performance of the proposed framework is superior to that of the other state-of-the-art methods. Moreover, the potential for practical application of the framework is also validated in terms of limited computational resources, real-time analysis, and insufficient training data. The proposed model can identify the remarkable interpretative biomarkers associated with specific mental disorders for clinical interpretation analysis.

Attention-Like Multimodality Fusion With Data Augmentation for Diagnosis of Mental Disorders Using MRI

The globally rising prevalence of mental disorders leads to shortfalls in timely diagnosis and therapy to reduce patients' suffering. Facing such an urgent public health problem, professional efforts based on symptom criteria are seriously overstretched. Recently, the successful applications of computer-aided diagnosis approaches have provided timely opportunities to relieve the tension in healthcare services. Particularly, multimodal representation learning gains increasing attention thanks to the high temporal and spatial resolution information extracted from neuroimaging fusion. In this work, we propose an efficient multimodality fusion framework to identify multiple mental disorders based on the combination of functional and structural magnetic resonance imaging. A multioutput conditional generative adversarial network (GAN) is developed to address the scarcity of multimodal data for augmentation. Based on the augmented training data, the multiheaded gating fusion model is proposed for classification by extracting the complementary features across different modalities. The experiments demonstrate that the proposed model can achieve robust accuracies of 75.1 ± 1.5 %, 72.9 ± 1.1 %, and 87.2 ± 1.5 % for autism spectrum disorder (ASD), attention deficit/hyperactivity disorder, and schizophrenia, respectively. In addition, the interpretability of our model is expected to enable the identification of remarkable neuropathology diagnostic biomarkers, leading to well-informed therapeutic decisions.

Classification of autism spectrum disorder using electroencephalography in Chinese children: a cross-sectional retrospective study

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition characterized by diverse clinical features. EEG biomarkers such as spectral power and functional connectivity have emerged as potential tools for enhancing early diagnosis and understanding of the neural processes underlying ASD. However, existing studies yield conflicting results, necessitating a comprehensive, data-driven analysis. We conducted a retrospective cross-sectional study involving 246 children with ASD and 42 control children. EEG was collected, and diverse EEG features, including spectral power and spectral coherence were extracted. Statistical inference methods, coupled with machine learning models, were employed to identify differences in EEG features between ASD and control groups and develop classification models for diagnostic purposes. Our analysis revealed statistically significant differences in spectral coherence, particularly in gamma and beta frequency bands, indicating elevated long range functional connectivity between frontal and parietal regions in the ASD group. Machine learning models achieved modest classification performance of ROC-AUC at 0.65. While machine learning approaches offer some discriminative power classifying individuals with ASD from controls, they also indicate the need for further refinement.

Classifying Children with ADHD Based on Prefrontal Functional Near-infrared Spectroscopy Using Machine Learning

Objective

: Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in children and adults characterized by cognitive and emotional self-control deficiencies. Previous functional near-infrared spectroscopy (fNIRS) studies found significant group differences between ADHD children and healthy controls during cognitive flexibility tasks in several brain regions. This study aims to apply a machine learning approach to identify medication-naive ADHD patients and healthy control (HC) groups using task-based fNIRS data.

Methods

: fNIRS signals from 33 ADHD children and 39 HC during the Stroop task were analyzed. In addition, regularized linear discriminant analysis (RLDA) was used to identify ADHD individuals from healthy controls, and classification performance was evaluated.

Results

: We found that participants can be correctly classified in RLDA leave-one-out cross validation, with a sensitivity of 0.67, specificity of 0.93, and accuracy of 0.82.

Conclusion

: RLDA using only fNIRS data can effectively discriminate children with ADHD from HC. This study suggests the potential utility of the fNIRS signal as a diagnostic biomarker for ADHD children.

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.

Rethinking Theta/Beta Ratio in ADHD through Functional Data Analysis

ADHD is a neurodevelopmental disorder largely diffused among children and adolescents. The current method of diagnosis is based on agreed clinical literature such as DSM-5, by identifying and evaluating signs of hyperactivity and inattention. Multiple reviews have assessed that EEG is not sufficiently reliable for the diagnosis of ADHD. Theta-Beta Ratio is now the sole EEG parameter considered for analysis, although it is not robust enough to be utilized as a confirmatory technique for diagnosis. In this setting, new objective approaches for reliably classifying neurotypical and ADHD subjects are required. As a result, we suggest a new methodology based on Functional Data Analysis, a statistical class of methods for dealing with curves and functions. The initial stage in our method is to separate frequency bands from the EEG signal using a wavelet decomposition. We next compute the Power Spectral Densities of each of these bands and represent them as mathematical functions via spline interpolation. Finally, the relevance of the collected features is assessed using the Permutation ANOVA test. Using this method, we can detect different patterns in the PSDs of the groups and identify statistically significant features, confirming prior findings in the literature. We validate the features using classification techniques such as Bagging trees, Random Forest, and AdaBoost. The latter reaches the highest accuracy score of 76.65%, confirming the relevance of the extracted features.

Candidate diagnostic biomarkers for neurodevelopmental disorders in children and adolescents: a systematic review

Neurodevelopmental disorders - including attention-deficit/hyperactivity disorder (ADHD), autism spectrum disorder, communication disorders, intellectual disability, motor disorders, specific learning disorders, and tic disorders - manifest themselves early in development. Valid, reliable and broadly usable biomarkers supporting a timely diagnosis of these disorders would be highly relevant from a clinical and public health standpoint. We conducted the first systematic review of studies on candidate diagnostic biomarkers for these disorders in children and adolescents. We searched Medline and Embase + Embase Classic with terms relating to biomarkers until April 6, 2022, and conducted additional targeted searches for genome-wide association studies (GWAS) and neuroimaging or neurophysiological studies carried out by international consortia. We considered a candidate biomarker as promising if it was reported in at least two independent studies providing evidence of sensitivity and specificity of at least 80%. After screening 10,625 references, we retained 780 studies (374 biochemical, 203 neuroimaging, 133 neurophysiological and 65 neuropsychological studies, and five GWAS), including a total of approximately 120,000 cases and 176,000 controls. While the majority of the studies focused simply on associations, we could not find any biomarker for which there was evidence - from two or more studies from independent research groups, with results going into the same direction - of specificity and sensitivity of at least 80%. Other important metrics to assess the validity of a candidate biomarker, such as positive predictive value and negative predictive value, were infrequently reported. Limitations of the currently available studies include mostly small sample size, heterogeneous approaches and candidate biomarker targets, undue focus on single instead of joint biomarker signatures, and incomplete accounting for potential confounding factors. Future multivariable and multi-level approaches may be best suited to find valid candidate biomarkers, which will then need to be validated in external, independent samples and then, importantly, tested in terms of feasibility and cost-effectiveness, before they can be implemented in daily clinical practice.

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.

Classification of Functional Movement Disorders with Resting-State Functional Magnetic Resonance Imaging

Introduction: Functional movement disorder (FMD) is a type of functional neurological disorder characterized by abnormal movements that patients do not perceive as self-generated. Prior imaging studies show a complex pattern of altered activity, linking regions of the brain involved in emotional responses, motor control, and agency. This study aimed to better characterize these relationships by building a classifier using a support vector machine to accurately distinguish between 61 FMD patients and 59 healthy controls using features derived from resting-state functional magnetic resonance imaging. Materials and Methods: First, we selected 66 seed regions based on prior related studies, then we calculated the full correlation matrix between them before performing recursive feature elimination to winnow the feature set to the most predictive features and building the classifier. Results: We identified 29 features of interest that were highly predictive of the FMD condition, classifying patients and controls with 80% accuracy. Several key features included regions in the right sensorimotor cortex, left dorsolateral prefrontal cortex, left cerebellum, and left posterior insula. Conclusions: The features selected by the model highlight the importance of the interconnected relationship between areas associated with emotion, reward, and sensorimotor integration, potentially mediating communication between regions associated with motor function, attention, and executive function. Exploratory machine learning was able to identify this distinctive abnormal pattern, suggesting that alterations in functional linkages between these regions may be a consistent feature of the condition in many FMD patients. Clinical-Trials.gov ID: NCT00500994 Impact statement Our research presents novel results that further elucidate the pathophysiology of functional movement disorder (FMD) with a machine learning model that classifies FMD and healthy controls correctly 80% of the time. Herein, we demonstrate how known differences in resting-state functional magnetic resonance imaging connectivity in FMD patients can be leveraged to better understand the complex pattern of neural changes in these patients. Knowing that there are measurable predictable differences in brain activity in patients with FMD may help both clinicians and patients conceptualize and better understand the illness at the point of diagnosis and during treatment. Our methods demonstrate how an effective combination of machine learning and qualitative approaches to analyzing functional brain connectivity can enhance our understanding of abnormal patterns of brain activity in FMD patients.

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.

Classification of drug-naive children with attention-deficit/hyperactivity disorder from typical development controls using resting-state fMRI and graph theoretical approach

Background and objectives

The study of brain functional connectivity alterations in children with Attention-Deficit/Hyperactivity Disorder (ADHD) has been the subject of considerable investigation, but the biological mechanisms underlying these changes remain poorly understood. Here, we aim to investigate the brain alterations in patients with ADHD and Typical Development (TD) children and accurately classify ADHD children from TD controls using the graph-theoretical measures obtained from resting-state fMRI (rs-fMRI).

Materials and methods

We investigated the performances of rs-fMRI data for classifying drug-naive children with ADHD from TD controls. Fifty six drug-naive ADHD children (average age 11.86 ± 2.21 years; 49 male) and 56 age matched TD controls (average age 11.51 ± 1.77 years, 44 male) were included in this study. The graph measures extracted from rs-fMRI functional connectivity were used as features. Extracted network-based features were fed to the RFE feature selection algorithm to select the most discriminating subset of features. We trained and tested Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB) using Peking center data from ADHD-200 database to classify ADHD and TD children using discriminative features. In addition to the machine learning approach, the statistical analysis was conducted on graph measures to discover the differences in the brain network of patients with ADHD.

Results

An accuracy of 78.2% was achieved for classifying drug-naive children with ADHD from TD controls employing the optimal features and the GB classifier. We also performed a hub node analysis and found that the number of hubs in TD controls and ADHD children were 8 and 5, respectively, indicating that children with ADHD have disturbance of critical communication regions in their brain network. The findings of this study provide insight into the neurophysiological mechanisms underlying ADHD.

Conclusion

Pattern recognition and graph measures of the brain networks, based on the rs-fMRI data, can efficiently assist in the classification of ADHD children from TD controls.

A framework for characterizing heterogeneity in neurodevelopmental data using latent profile analysis in a sample of children with ADHD

BACKGROUND

Heterogeneity in neurodevelopmental disorders, and attention deficit hyperactivity disorder (ADHD) in particular, is increasingly identified as a barrier to identifying biomarkers and developing standards for clinical care. Clustering analytic methods have previously been used across a variety of data types with the goal of identifying meaningful subgroups of individuals with ADHD. However, these analyses have often relied on algorithmic approaches which assume no error in group membership and have not made associations between patterns of behavioral, neurocognitive, and genetic indicators. More sophisticated latent classification models are often not utilized in neurodevelopmental research due to the difficulty of working with these models in small sample sizes.

METHODS

In the current study, we propose a framework for evaluating mixture models in sample sizes typical of neurodevelopmental research. We describe a combination of qualitative and quantitative model fit evaluation procedures. We test our framework using latent profile analysis (LPA) in a case study of 120 children with and without ADHD, starting with well-understood neuropsychological indicators, and building toward integration of electroencephalogram (EEG) measures.

RESULTS

We identified a stable five-class LPA model using seven neuropsychological indicators. Although we were not able to identify a stable multimethod indicator model, we did successfully extrapolate results of the neuropsychological model to identify distinct patterns of resting EEG power across five frequency bands.

CONCLUSIONS

Our approach, which emphasizes theoretical as well as empirical evaluation of mixture models, could make these models more accessible to clinical researchers and may be a useful approach to parsing heterogeneity in neurodevelopmental disorders.

Population heterogeneity in clinical cohorts affects the predictive accuracy of brain imaging

Brain imaging research enjoys increasing adoption of supervised machine learning for single-participant disease classification. Yet, the success of these algorithms likely depends on population diversity, including demographic differences and other factors that may be outside of primary scientific interest. Here, we capitalize on propensity scores as a composite confound index to quantify diversity due to major sources of population variation. We delineate the impact of population heterogeneity on the predictive accuracy and pattern stability in 2 separate clinical cohorts: the Autism Brain Imaging Data Exchange (ABIDE, n = 297) and the Healthy Brain Network (HBN, n = 551). Across various analysis scenarios, our results uncover the extent to which cross-validated prediction performances are interlocked with diversity. The instability of extracted brain patterns attributable to diversity is located preferentially in regions part of the default mode network. Collectively, our findings highlight the limitations of prevailing deconfounding practices in mitigating the full consequences of population diversity.

Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.

When the Whole Is Less Than the Sum of Its Parts: Maximum Object Category Information and Behavioral Prediction in Multiscale Activation Patterns

Neural codes are reflected in complex neural activation patterns. Conventional electroencephalography (EEG) decoding analyses summarize activations by averaging/down-sampling signals within the analysis window. This diminishes informative fine-grained patterns. While previous studies have proposed distinct statistical features capable of capturing variability-dependent neural codes, it has been suggested that the brain could use a combination of encoding protocols not reflected in any one mathematical feature alone. To check, we combined 30 features using state-of-the-art supervised and unsupervised feature selection procedures (n = 17). Across three datasets, we compared decoding of visual object category between these 17 sets of combined features, and between combined and individual features. Object category could be robustly decoded using the combined features from all of the 17 algorithms. However, the combination of features, which were equalized in dimension to the individual features, were outperformed across most of the time points by the multiscale feature of Wavelet coefficients. Moreover, the Wavelet coefficients also explained the behavioral performance more accurately than the combined features. These results suggest that a single but multiscale encoding protocol may capture the EEG neural codes better than any combination of protocols. Our findings put new constraints on the models of neural information encoding in EEG.

Navigating the pitfalls of applying machine learning in genomics

The scale of genetic, epigenomic, transcriptomic, cheminformatic and proteomic data available today, coupled with easy-to-use machine learning (ML) toolkits, has propelled the application of supervised learning in genomics research. However, the assumptions behind the statistical models and performance evaluations in ML software frequently are not met in biological systems. In this Review, we illustrate the impact of several common pitfalls encountered when applying supervised ML in genomics. We explore how the structure of genomics data can bias performance evaluations and predictions. To address the challenges associated with applying cutting-edge ML methods to genomics, we describe solutions and appropriate use cases where ML modelling shows great potential.

What Has Been Learned from Using EEG Methods in Research of ADHD?

Electrophysiological recording methods, including electroencephalography (EEG) and magnetoencephalography (MEG), have an unparalleled capacity to provide insights into the timing and frequency (spectral) composition of rapidly changing neural activity associated with various cognitive processes. The current chapter provides an overview of EEG studies examining alterations in brain activity in ADHD, measured both at rest and during cognitive tasks. While EEG resting state studies of ADHD indicate no universal alterations in the disorder, event-related studies reveal consistent deficits in attentional and inhibitory control and consequently inform the proposed cognitive models of ADHD. Similar to other neuroimaging measures, EEG research indicates alterations in multiple neural circuits and cognitive functions. EEG methods - supported by the constant refinement of analytic strategies - have the potential to contribute to improved diagnostics and interventions for ADHD, underlining their clinical utility.

Multimodal Ensemble Deep Learning to Predict Disruptive Behavior Disorders in Children

Oppositional defiant disorder and conduct disorder, collectively referred to as disruptive behavior disorders (DBDs), are prevalent psychiatric disorders in children. Early diagnosis of DBDs is crucial because they can increase the risks of other mental health and substance use disorders without appropriate psychosocial interventions and treatment. However, diagnosing DBDs is challenging as they are often comorbid with other disorders, such as attention-deficit/hyperactivity disorder, anxiety, and depression. In this study, a multimodal ensemble three-dimensional convolutional neural network (3D CNN) deep learning model was used to classify children with DBDs and typically developing children. The study participants included 419 females and 681 males, aged 108–131 months who were enrolled in the Adolescent Brain Cognitive Development Study. Children were grouped based on the presence of DBDs (n = 550) and typically developing (n = 550); assessments were based on the scores from the Child Behavior Checklist and on the Schedule for Affective Disorders and Schizophrenia for School-age Children-Present and Lifetime version for DSM-5. The diffusion, structural, and resting-state functional magnetic resonance imaging (rs-fMRI) data were used as input data to the 3D CNN. The model achieved 72% accuracy in classifying children with DBDs with 70% sensitivity, 72% specificity, and an F1-score of 70. In addition, the discriminative power of the classifier was investigated by identifying the cortical and subcortical regions primarily involved in the prediction of DBDs using a gradient-weighted class activation mapping method. The classification results were compared with those obtained using the three neuroimaging modalities individually, and a connectome-based graph CNN and a multi-scale recurrent neural network using only the rs-fMRI data.

Ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features

Background

Autism spectrum disorder (ASD) is characterized by a spectrum of social and communication impairments and rigid and stereotyped behaviors that have a neurodevelopmental origin. Although many imaging studies have reported structural and functional alterations in multiple brain regions, clinically useful diagnostic imaging biomarkers for ASD remain unavailable.

Methods

In this study, we applied machine learning (ML) models to regional volumetric and cortical thickness data from the largest structural magnetic resonance imaging (sMRI) dataset available from the Enhancing Neuro Imaging Genetics Through Meta-Analysis (ENIGMA) consortium (1833 subjects with ASD and 1838 without ASD; age range: 1.5-64; average age: 15.6; male/female ratio: 4.2:1).

Results

The highest classification accuracy on a hold-out test set was achieved using a stacked Extra Tree Classifier. The area under the receiver operating characteristic (ROC) curve (AUC) was 0.62 (95% confidence interval [CI]: 0.57, 0.68) and the area under the precision-recall curve was 0.58. Learning curve analysis showed the good fit of the model and suggests that more training examples will not likely benefit model performance.

Conclusions

Our results suggest that sMRI volumetric and cortical thickness data alone may not provide clinically sufficient useful diagnostic biomarkers for ASD. Developing clinically useful imaging classifiers for ASD will benefit from combining other data modalities or feature types, such as functional MRI data and raw images that can leverage other machine learning (ML) techniques such as convolutional neural networks.

Trends, Limits, and Challenges of Computer Technologies in Attention Deficit Hyperactivity Disorder Diagnosis and Treatment

Attention deficit hyperactivity disorder (ADHD) is a neurobiological condition that appears during an individual's childhood and may follow her/him for life. The research objective was to understand better how and which computer technologies have been applied to support ADHD diagnosis and treatment. The research used the systematic literature review method: a rigorous, verifiable, and repeatable approach that follows well-defined steps. Six well-known academic data sources have been consulted, including search engines and bibliographic databases, from technology and health care areas. After a rigorous research protocol, 1,239 articles were analyzed. For the diagnosis, the use of machine learning techniques was verified in 61 percent of the articles. Neurofeedback was ranked second with 9.3 percent participation, followed by serious games and eye tracking with 5.6 percent each. For the treatment, neurofeedback was present in 50 percent of the articles, whereas some studies combined both approaches, accounting for 31 percent of the total. Nine percent of the articles reported remote assistance technology, whereas another 9 percent have used virtual reality. By highlighting the leading computer technologies used, their applications, results, and challenges, this literature review breaks ground for further investigations. Moreover, the study highlighted the lack of consensus on ADHD biomarkers. The approaches using machine learning call attention to the probable occurrence of overfitting in several studies, thus demonstrating limitations of this technology on small-sized bases. This research also presented the convergence of evidence from different studies on the persistence of long-term effects of using neurofeedback in treating ADHD.

Estimating Gender and Age from Brain Structural MRI of Children and Adolescents: A 3D Convolutional Neural Network Multitask Learning Model

Despite recent advances, assessing biological measurements for neuropsychiatric disorders is still a challenge, where confounding variables such as gender and age (as a proxy for neurodevelopment) play an important role. This study explores brain structural magnetic resonance imaging (sMRI) from two public data sets (ABIDE-II and ADHD-200) with healthy control (HC, N = 894), autism spectrum disorder (ASD, N = 251), and attention deficit hyperactivity disorder (ADHD, N = 357) individuals. We used gray and white matter preprocessed via voxel-based morphometry (VBM) to train a 3D convolutional neural network with a multitask learning strategy to estimate gender, age, and mental health status from structural brain differences. Gradient-based methods were employed to generate attention maps, providing clinically relevant identification of most representative brain regions for models' decision-making. This approach resulted in satisfactory predictions for gender and age. ADHD-200-trained models, evaluated in 10-fold cross-validation procedures on test set, obtained a mean absolute error (MAE) of 1.43 years (±0.22 SD) for age prediction and an area under the curve (AUC) of 0.85 (±0.04 SD) for gender classification. In out-of-sample validation, the best-performing ADHD-200 models satisfactorily predicted age (MAE = 1.57 years) and gender (AUC = 0.89) in the ABIDE-II data set. The models' accuracy was in line with the current state-of-the-art machine learning applications in neuroimaging. Key regions for models' accuracy were presented as a meaningful graphical output. New implementations, such as the use of VBM along with a 3D convolutional neural network multitask learning model and a brain imaging graphical output, reinforce the relevance of the proposed workflow.

Combining machine learning algorithms for prediction of antidepressant treatment response

OBJECTIVES

Predictors for unfavorable treatment outcome in major depressive disorder (MDD) applicable for treatment selection are still lacking. The database of a longitudinal multicenter study on 1079 acutely depressed patients, performed by the German research network on depression (GRND), allows supervised and unsupervised learning to further elucidate the interplay of clinical and psycho-sociodemographic variables and their predictive impact on treatment outcome phenotypes.

EXPERIMENTAL PROCEDURES

Treatment response was defined by a change of HAM-D 17-item baseline score ≥50% and remission by the established threshold of ≤7, respectively, after up to eight weeks of inpatient treatment. After hierarchical symptom clustering and stratification by treatment subtypes (serotonin reuptake inhibitors, tricyclic antidepressants, antipsychotic, and lithium augmentation), prediction models for different outcome phenotypes were computed with random forest in a cross-center validation design. In total, 88 predictors were implemented.

RESULTS

Clustering revealed four distinct HAM-D subscores related to emotional, anxious, sleep, and appetite symptoms, respectively. After feature selection, classification models reached moderate to high accuracies up to 0.85. Highest accuracies were observed for the SSRI and TCA subgroups and for sleep and appetite symptoms, while anxious symptoms showed poor predictability.

CONCLUSION

Our results support a decisive role for machine learning in the management of antidepressant treatment. Treatment- and symptom-specific algorithms may increase accuracies by reducing heterogeneity. Especially, predictors related to duration of illness, baseline depression severity, anxiety and somatic symptoms, and personality traits moderate treatment success. However, prospectives application of machine learning models will be necessary to prove their value for the clinic.

Objective score from initial interview identifies patients with probable dissociative seizures

OBJECTIVE

To develop a Dissociative Seizures Likelihood Score (DSLS), which is a comprehensive, evidence-based tool using information available during the first outpatient visit to identify patients with "probable" dissociative seizures (DS) to allow early triage to more extensive diagnostic assessment.

METHODS

Based on data from 1616 patients with video-electroencephalography (vEEG) confirmed diagnoses, we compared the clinical history from a single neurology interview of patients in five mutually exclusive groups: epileptic seizures (ES), DS, physiologic nonepileptic seizure-like events (PSLE), mixed DS plus ES, and inconclusive monitoring. We used data-driven methods to determine the diagnostic utility of 76 features from retrospective chart review and applied this model to prospective interviews.

RESULTS

The DSLS using recursive feature elimination (RFE) correctly identified 77% (95% confidence interval (CI), 74-80%) of prospective patients with either ES or DS, with a sensitivity of 74% and specificity of 84%. This accuracy was not significantly inferior than neurologists' impression (84%, 95% CI: 80-88%) and the kappa between neurologists' and the DSLS was 21% (95% CI: 1-41%). Only 3% of patients with DS were missed by both the fellows and our score (95% CI 0-11%).

SIGNIFICANCE

The evidence-based DSLS establishes one method to reliably identify some patients with probable DS using clinical history. The DSLS supports and does not replace clinical decision making. While not all patients with DS can be identified by clinical history alone, these methods combined with clinical judgement could be used to identify patients who warrant further diagnostic assessment at a comprehensive epilepsy center.

ADHD: Current Concepts and Treatments in Children and Adolescents

Attention deficit hyperactivity disorder (ADHD) is among the most frequent disorders within child and adolescent psychiatry, with a prevalence of over 5%. Nosological systems, such as the Diagnostic and Statistical Manual of Mental Disorders, 5th edition (DSM-5) and the International Classification of Diseases, editions 10 and 11 (ICD-10/11) continue to define ADHD according to behavioral criteria, based on observation and on informant reports. Despite an overwhelming body of research on ADHD over the last 10 to 20 years, valid neurobiological markers or other objective criteria that may lead to unequivocal diagnostic classification are still lacking. On the contrary, the concept of ADHD seems to have become broader and more heterogeneous. Thus, the diagnosis and treatment of ADHD are still challenging for clinicians, necessitating increased reliance on their expertise and experience. The first part of this review presents an overview of the current definitions of the disorder (DSM-5, ICD-10/11). Furthermore, it discusses more controversial aspects of the construct of ADHD, including the dimensional versus categorical approach, alternative ADHD constructs, and aspects pertaining to epidemiology and prevalence. The second part focuses on comorbidities, on the difficulty of distinguishing between "primary" and "secondary" ADHD for purposes of differential diagnosis, and on clinical diagnostic procedures. In the third and most prominent part, an overview of current neurobiological concepts of ADHD is given, including neuropsychological and neurophysiological researches and summaries of current neuroimaging and genetic studies. Finally, treatment options are reviewed, including a discussion of multimodal, pharmacological, and nonpharmacological interventions and their evidence base.

EEG spectral power, but not theta/beta ratio, is a neuromarker for adult ADHD

Adults with attention-deficit/hyperactivity disorder (ADHD) have been described as having altered resting-state electroencephalographic (EEG) spectral power and theta/beta ratio (TBR). However, a recent review (Pulini et al. 2018) identified methodological errors in neuroimaging, including EEG, ADHD classification studies. Therefore, the specific EEG neuromarkers of adult ADHD remain to be identified, as do the EEG characteristics that mediate between genes and behaviour (mediational endophenotypes). Resting-state eyes-open and eyes-closed EEG was measured from 38 adults with ADHD, 45 first-degree relatives of people with ADHD and 51 unrelated controls. A machine learning classification analysis using penalized logistic regression (Elastic Net) examined if EEG spectral power (1-45 Hz) and TBR could classify participants into ADHD, first-degree relatives and/or control groups. Random-label permutation was used to quantify any bias in the analysis. Eyes-open absolute and relative EEG power distinguished ADHD from control participants (area under receiver operating characteristic = 0.71-0.77). The best predictors of ADHD status were increased power in delta, theta and low-alpha over centro-parietal regions, and in frontal low-beta and parietal mid-beta. TBR did not successfully classify ADHD status. Elevated eyes-open power in delta, theta, low-alpha and low-beta distinguished first-degree relatives from controls (area under receiver operating characteristic = 0.68-0.72), suggesting that these features may be a mediational endophenotype for adult ADHD. Resting-state EEG spectral power may be a neuromarker and mediational endophenotype of adult ADHD. These results did not support TBR as a diagnostic neuromarker for ADHD. It is possible that TBR is a characteristic of childhood ADHD.

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.

The blessing of Dimensionality: Feature Selection outperforms functional connectivity-based feature transformation to classify ADHD subjects from EEG patterns of phase synchronisation

Functional connectivity (FC) characterizes brain activity from a multivariate set of N brain signals by means of an NxN matrix A, whose elements estimate the dependence within each possible pair of signals. Such matrix can be used as a feature vector for (un)supervised subject classification. Yet if N is large, A is highly dimensional. Little is known on the effect that different strategies to reduce its dimensionality may have on its classification ability. Here, we apply different machine learning algorithms to classify 33 children (age [6-14 years]) into two groups (healthy controls and Attention Deficit Hyperactivity Disorder patients) using EEG FC patterns obtained from two phase synchronisation indices. We found that the classification is highly successful (around 95%) if the whole matrix A is taken into account, and the relevant features are selected using machine learning methods. However, if FC algorithms are applied instead to transform A into a lower dimensionality matrix, the classification rate drops to less than 80%. We conclude that, for the purpose of pattern classification, the relevant features should be selected among the elements of A by using appropriate machine learning algorithms.