Abnormal Functional Resting-State Networks in ADHD: Graph Theory and Pattern Recognition Analysis of fMRI Data

Abstract

The framework of graph theory provides useful tools for investigating the neural substrates of neuropsychiatric disorders. Graph description measures may be useful as predictor variables in classification procedures. Here, we consider several centrality measures as predictor features in a classification algorithm to identify nodes of resting-state networks containing predictive information that can discriminate between typical developing children and patients with attention-deficit/hyperactivity disorder (ADHD). The prediction was based on a support vector machines classifier. The analyses were performed in a multisite and publicly available resting-state fMRI dataset of healthy children and ADHD patients: the ADHD-200 database. Network centrality measures contained little predictive information for the discrimination between ADHD patients and healthy subjects. However, the classification between inattentive and combined ADHD subtypes was more promising, achieving accuracies higher than 65% (balance between sensitivity and specificity) in some sites. Finally, brain regions were ranked according to the amount of discriminant information and the most relevant were mapped. As hypothesized, we found that brain regions in motor, frontoparietal, and default mode networks contained the most predictive information. We concluded that the functional connectivity estimations are strongly dependent on the sample characteristics. Thus different acquisition protocols and clinical heterogeneity decrease the predictive values of the graph descriptors.

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

“…Fortunately, the availability of open datasets is facilitating efforts to perform head-to-head comparisons of analytical strategies (148;149). Explicit replication of published results (e.g., 107) remains the exception (54;111); across-site comparisons have ranged from encouraging (47) to cautionary (49). As funding agencies increasingly require fast and open access to large-scale research data and emphasize reproducibility (150), the field has the opportunity to extend the metaphor of brain mapping into analytical topography .…”

Phenotypic Integrated Framework for Classification of ADHD Using fMRI

“…Functional connectivity: Functional connectivity can be estimated by correlation of time-domain signals [1], [4], as well as clustering [2], [15]. We propose a hybrid framework which employs Affinity Propagation (AP) clustering [8] and the Density Peaks (DP) algorithm [9] for functional connectivity estimation.…”

“…While coordinating bodily function, the brain regions continuously share information, and regions exhibiting temporal correlation are said to be functionally connected. Research studies have shown that neurological disorders such as Alzheimer's disease, epilepsy, ADHD can alter the functional connectivity of the brain network [1], [2]. Accurate identification of altered functional connectivity induced by a neurological disorder is thus an important task and may highlight the underlying mechanism of the disorder.…”

“…ADHD has received significant research focus, including studies employing fMRI to investigate functional connectivity alterations in ADHD: [5] proposed a functional-anatomical discriminative region model for the identification of discriminant features and pattern classification of ADHD, and evaluated Elastic Net [6] based feature selection. Dey et al [4] employed attributed graph distance measures for classification of ADHD, and similarly [1] investigated different graph based measures to assess their discriminative power. Tabas et al [7] proposed a variant of Independent Component Analysis (ICA) to characterize the differences between control and patients, employing fMRI data.…”

Breaking down the genetics of depression using brain endophenotypes

“…These may explain attentional lapses in ADHD, where mind wandering controlled by the DMN might interfere with sustained attention [324,325]. However, many other findings have not been replicated, for example the reduced connectivity between DMN and putamen [324,327], reduced regional homogeneity in the DMN [328], inferior frontal gyrus and dorsal caudate [324,329], together with aberrant brain activation or network properties [324,330,331]. Investigating the relationship between HM and ADHD symptoms such as inattention or hyperactivityimpulsivity might indicate whether inconsistent findings from prior resting-state studies could reflect a potential confound.…”