An integrated feature ranking and selection framework for ADHD characterization

Abstract

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.

Multi-modal, Multi-measure, and Multi-class Discrimination of ADHD with Hierarchical Feature Extraction and Extreme Learning Machine Using Structural and Functional Brain MRI

“…Most of these studies were binary and the classification scores were ranging from about 72 to 95% (Igual et al, 2012; Lim et al, 2013; Peng et al, 2013; Johnston et al, 2014; Deshpande et al, 2015; Hammer et al, 2015; Iannaccone et al, 2015; Wolfers et al, 2015; Qureshi and Lee, 2016; Qureshi et al, 2016; Xiao et al, 2016). Except for one study, all used feature selection methods prior to classification (Wolfers et al, 2015).…”

“…Except for one study, all used feature selection methods prior to classification (Wolfers et al, 2015). In Xiao et al (2016), a different ADHD dataset was used with only 47 subjects, compared to the current study. Although the theme of this study by Xiao et al (2016) is similar to our present work, the results are not comparable due to dataset differences and their use of only cortical thickness ROIs.…”

“…In Xiao et al (2016), a different ADHD dataset was used with only 47 subjects, compared to the current study. Although the theme of this study by Xiao et al (2016) is similar to our present work, the results are not comparable due to dataset differences and their use of only cortical thickness ROIs. In addition, our main focus was the multi-class, multi-measure, and multi-modal classification of the ADHD-200 dataset.…”

“…In addition, it averages the scaled time series over the whole brain mask and finally the length ( l 2 -norm) of this averaged series represents the GCOR. ADHD is considered as an age-related neurodevelopmental disorder and the symptoms might reflect age-related differences in the cortical and subcortical maturation that characterize ADHD (Xiao et al, 2016). Therefore, we first made a gray matter mask of 5-mm thickness created by using AFNI program 3dSeg and 3dcalc to acquire the functional connectivity maps of only the cortical regions of the brain.…”

“…These techniques hold the potential to combine complementary information across different sources in an efficient way (Wolfers et al, 2015). In addition, many previous machine learning based studies investigated these subtypes of ADHD (Solanto, 2000; Castellanos and Tannock, 2002; Colby et al, 2012; Dai et al, 2012; Fair et al, 2012; Igual et al, 2012; Willcutt et al, 2012; Lim et al, 2013; Peng et al, 2013; Johnston et al, 2014; Deshpande et al, 2015; Hammer et al, 2015; Iannaccone et al, 2015; Qureshi and Lee, 2016; Qureshi et al, 2016; Xiao et al, 2016). However, the outcomes from a small number of studies that attempted to distinguish the features of these subtypes with neuroimaging methods were inconclusive (Pineda et al, 2002; Miller et al, 2006).…”