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

Abstract

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.

Early identification of Alzheimer's disease in mouse models: Application of deep neural network algorithm to cognitive behavioral parameters

“…Using all available or apparently significant parameters ( Figure 2 ) did not improve the classification performance. A similar phenomenon was previously observed ( Sutoko et al., 2019 ). Johnson et al.…”

“…Using all available or apparently significant parameters (Figure 2) did not improve the classification performance. A similar phenomenon was previously observed (Sutoko et al, 2019). Johnson et al (2014) considered the stepwise feature-selecting method to be ineffective at explaining non-independent features.…”

“…Furthermore, a k-fold (5-fold) crossvalidation was used to minimize overfitting. The feature selection was optimized by following the stepwiseforward approach (Hocking, 1976;Sutoko et al, 2019). This approach added features to be used as input nodes one-by-one on the condition that the added features provided better classification performance (Figure S4).…”

Detection of Emotional Sensitivity Using fNIRS Based Dynamic Functional Connectivity

“…A recent fNIRS study [23] investigated emotional dysregulation in children with attention-deficit/hyperactivity disorder (ADHD), and examined them using cortical activation (i.e., hemodynamic concentration changes). However, Sutoko et al [24] demonstrated that dynamic FC could provide a better performance than hemodynamic activation in screening ADHD children whom often display lack of emotion recognition [25]. Hence, we hypothesize that dynamic FC network features could provide useful biomarkers to detect emotional sensitivity among nursing students and registered nurses, where we assumed registered nurses have developed strategies to ameliorate emotional sensitivity.…”

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

“…Recent research has also employed deep learning techniques (Riaz, Asad, Alonso, & Slabaugh, 2018, 2020) with interesting studies have used data augmentation methods to overcome sample size limitations (Cicek, Ozmen, & Akan, 2019; Zhu & Chang, 2019). Early autism spectrum diagnoses from MRI in infancy has also been suggested in preliminary research (Jin, Wee, Shi, Thung, Ni, et al., 2015; Jin, Wee, Shi, Thung, Yap, et al., 2015; Shen et al., 2017, 2018) and differential diagnostic classifiers that display clinical utility by demonstrating specificity have also been developed for autism spectrum (Kushki et al., 2019; Rabany et al., 2019; Sutoko et al., 2019; Yassin et al., 2020) and ADHD (Diler et al., 2007; Duda et al., 2017; Duda, Ma, Haber, & Wall, 2016b; Faedda et al., 2016; Studerus et al., 2018).…”