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.

Using autoregressive-dynamic conditional correlation model with residual analysis to extract dynamic functional connectivity.

OBJECTIVE: Statistical methods that simultaneously model temporal and spatial variations of fMRI data are promising tools for dynamic functional connectivity (FC) estimation. Although different approaches are available, they need to manually set the parameters, or may disregard some important fMRI features such as the autocorrelation. In addition, no reliable method exists for the validation of dynamic FC analysis models. APPROACH: In the present study, we have proposed an autoregressive dynamic conditional correlation model to deal with the temporal autocorrelation and non-stationarity in fMRI time-series. This model assumes that the brain time courses follow a multivariate Gaussian distribution, and that the conditional mean, variance and covariances change in an autoregressive form. Also, we proposed a new measurement index for the evaluation of the statistical consistency between the inferred dynamic functional connectivity and the real fMRI data. The performance of our model was tested in both simulated and real fMRI data. MAIN RESULTS: The model was associated with independent Gaussian residuals, and identified the dynamic connectivity patterns with high precision. Applying the model to the fMRI data from typically developing and attention deficit hyperactivity disorder subjects, brain connectivities were significantly different between the two groups. SIGNIFICANCE: Prominent features of our model were the consideration of the fMRI autocorrelation, no need to adjust the window length, and also elimination of the variance changes in each brain time-course from its connectivity changes.