Regional-Asymmetric Adaptive Graph Convolutional Neural Network for Diagnosis of Autism in Children With Resting-State EEG.

Currently, resting-state electroencephalography (rs-EEG) has become an effective and low-cost evaluation way to identify autism spectrum disorders (ASD) in children. However, it is of great challenge to extract useful features from raw rs-EEG data to improve diagnosis performance. Traditional methods mainly rely on the design of manual feature extractors and classifiers, which are separately performed and cannot be optimized simultaneously. To this end, this paper proposes a new end-to-end diagnostic method based on a recently emerged graph convolutional neural network for the diagnosis of ASD in children. Inspired by related neuroscience findings on the abnormal brain functional connectivity and hemispheric asymmetry characteristics observed in autism patients, we design a new Regional-asymmetric Adaptive Graph Convolutional Neural Network (RAGNN). It utilizes a hierarchical feature extraction and fusion process to learn separable spatiotemporal EEG features from different brain regions, two hemispheres, and a global brain. In the temporal feature extraction section, we utilize a convolutional layer that spans from the brain area to the hemisphere. This allows for effectively capturing temporal features both within and between brain areas. To better capture spatial characteristics of multi-channel EEG signals, we employ adaptive graph convolutional learning to capture non-Euclidean features within the brain's hemispheres. Additionally, an attention layer is introduced to highlight different contributions of the left and right hemispheres, and the fused features are used for classification. We conducted a subject-independent cross-validation experiment on rs-EEG data from 45 children with ASD and 45 typically developing (TD) children. Experimental results have shown that our proposed RAGNN model outperformed several existing deep learning-based methods (ShaollowNet, EEGNet, TSception, ST-GCN, and CGRU-MDGN).

The applied principles of EEG analysis methods in neuroscience and clinical neurology.

Electroencephalography (EEG) is a non-invasive measurement method for brain activity. Due to its safety, high resolution, and hypersensitivity to dynamic changes in brain neural signals, EEG has aroused much interest in scientific research and medical fields. This article reviews the types of EEG signals, multiple EEG signal analysis methods, and the application of relevant methods in the neuroscience field and for diagnosing neurological diseases. First, three types of EEG signals, including time-invariant EEG, accurate event-related EEG, and random event-related EEG, are introduced. Second, five main directions for the methods of EEG analysis, including power spectrum analysis, time-frequency analysis, connectivity analysis, source localization methods, and machine learning methods, are described in the main section, along with different sub-methods and effect evaluations for solving the same problem. Finally, the application scenarios of different EEG analysis methods are emphasized, and the advantages and disadvantages of similar methods are distinguished. This article is expected to assist researchers in selecting suitable EEG analysis methods based on their research objectives, provide references for subsequent research, and summarize current issues and prospects for the future.

Serum C1q/TNF-Related Protein 4 Levels are Associated with Nonalcoholic Fatty Liver Disease in Type 2 Diabetic Patients.

Introduction: There is a strong bidirectional relationship between nonalcoholic fatty liver disease (NAFLD) and type 2 diabetes mellitus (T2DM), both of which can lead to an increase in harmful metabolism and cardiovascular risk. It was discovered that C1q/TNF-related protein 4 (CTRP4) regulates glucolipid metabolism and feeding behavior. However, the correlation between serum CTRP4 and NAFLD in T2DM patients is not yet fully understood. Methods: This study enrolled 188 T2DM participants who were separated into 2 distinct groups (NAFLD and non-NAFLD) according to abdominal ultrasound imaging results. The enzyme-linked immunosorbent assay was utilized to evaluate the levels of serum CTRP4. Clinical data and CTRP4 concentration were compared between the two groups. Linear and logistic regression analyses were performed to evaluate the correlation of serum CTRP4 levels with NAFLD risk in T2DM patients. Results: Compared with non-NAFLD, the concentration of CTRP4 was lower in NAFLD group (median 2.46 vs. 2.89, P < 0.001). The log(CTRP4) value was found to be negatively correlated with alanine aminotransferase, aspartate aminotransferase, body mass index (BMI), and waist circumference in a Pearson correlation analyses (r = -0.159, -0.156, -0.224, -0.268, all P < 0.05); besides, the trend χ2 test demonstrated that the prevalence of NAFLD rose as CTRP4 concentration decreased (P < 0.001). Regression analysis suggested that NAFLD served as an independent factor influencing log(CTRP4) independently (ß-coefficient = -0.12, P = 0.011), even after adjusting for high-sensitivity C-reactive protein and white blood cells. Finally, the results of the logistic regression analysis demonstrated that BMI [odds ratio (OR) = 1.196, P = 0.028], triglyceride (OR = 2.744, P < 0.001), and CTRP4 (OR = 0.615, P = 0.032) were independently associated with NAFLD in T2DM. Conclusions: T2DM patients with NAFLD have lower CTRP4 serum concentrations than those without NAFLD. The risk of NAFLD in patients with T2DM is inversely correlated with serum CTRP4 levels.

A Multimodal Approach for Identifying Autism Spectrum Disorders in Children.

Identification of autism spectrum disorder (ASD) in children is challenging due to the complexity and heterogeneity of ASD. Currently, most existing methods mainly rely on a single modality with limited information and often cannot achieve satisfactory performance. To address this issue, this paper investigates from internal neurophysiological and external behavior perspectives simultaneously and proposes a new multimodal diagnosis framework for identifying ASD in children with fusion of electroencephalogram (EEG) and eye-tracking (ET) data. Specifically, we designed a two-step multimodal feature learning and fusion model based on a typical deep learning algorithm, stacked denoising autoencoder (SDAE). In the first step, two SDAE models are designed for feature learning for EEG and ET modality, respectively. Then, a third SDAE model in the second step is designed to perform multimodal fusion with learned EEG and ET features in a concatenated way. Our designed multimodal identification model can automatically capture correlations and complementarity from behavior modality and neurophysiological modality in a latent feature space, and generate informative feature representations with better discriminability and generalization for enhanced identification performance. We collected a multimodal dataset containing 40 ASD children and 50 typically developing (TD) children to evaluate our proposed method. Experimental results showed that our proposed method achieved superior performance compared with two unimodal methods and a simple feature-level fusion method, which has promising potential to provide an objective and accurate diagnosis to assist clinicians.

Association between plasma growth arrest-specific protein 6 and carotid atherosclerosis in type 2 diabetes mellitus.

BACKGROUND AND AIMS: Growth arrest-specific 6 protein (Gas6) has been established to play important roles in various biological processes, but little is currently known on the role of Gas6 signaling in humans. This research explored the association between Gas6 expression and carotid atherosclerosis (AS) in type 2 diabetes mellitus (T2DM). METHODS AND RESULTS: As many as 126 T2DM patients were recruited in this study and classified into two groups based on their carotid intima-media thickness (CIMT). Meanwhile, 50 healthy individuals were recruited for the normal control group (NC). The subgroups were compared in terms of clinical data and Gas6 expression levels. Gas6 levels were decreased in T2DM patients with or without AS compared to NC subjects (9.64 ± 1.41 ng/ml, 11.38 ± 2.08 ng/ml, and 13.64 ± 2.61 ng/ml, respectively) (p < 0.001). The interaction between Gas6 and AS in T2DM was analyzed by logistic regression model and receiver operating characteristic (ROC) curve analysis. Decreased Gas6 expression was an independent risk factor relevant to AS in T2DM (p = 0.027). The area under the ROC curve to estimate the diagnostic value of low Gas6 expression for AS in T2DM was 0.750. The correlation between Gas6 and other parameters was evaluated by Pearson correlation analysis and linear regression model. Body mass index (BMI), hemoglobin A1c (HbA1c) and tumor necrosis factor-α(TNF-α) were independently correlated with Gas6. CONCLUSION: Low Gas6 expression is an independent risk factor for AS in T2DM. Gas6 expression is affected by BMI, HbA1c and TNF-α levels.

Association of serum C1Q/TNF-related protein 4 levels with carotid atherosclerosis in subjects with type 2 diabetes mellitus: A cross-sectional study.

BACKGROUND: Carotid atherosclerosis (CAS) is a common manifestation of macroangiopathy in type 2 diabetes mellitus (T2DM). C1Q/TNF-related protein 4 (CTRP4) was found to be involved in regulation of food intake behaviors and glucolipid metabolism, which were also key factors in the development of CAS. However, the relationship between serum CTRP4 and CAS in T2DM remains unclear. METHODS: A total of 111 participants with T2DM were enrolled in the study and were divided into 2 groups (T2DM group and T2DM + CAS group) according to the result of carotid ultrasound examinations. Serum CTRP4 levels were measured by enzyme linked immunosorbent assay (ELISA). Trend χ2 test and binary stepwise logistic regression were conducted to assess the association between serum CTRP4 and the risk of CAS in T2DM. RESULTS: Serum CTRP4 concentrations in T2DM + CAS group were significantly lower compared with those in T2DM group [7.98 (5.53) vs. 11.29 (7.36) ng/ml, P < 0.01]. The risk of CAS in T2DM decreased with the increasing of CTRP4 quartiles (P for trend < 0.01). Binary stepwise logistic regression suggested that serum CTRP4 might be an independent influence factor for CAS in patients with T2DM (P < 0.01) and high concentrations of serum CTRP4 were related to low risk of CAS in T2DM. CONCLUSIONS: The concentrations of serum CTRP4 are lower in T2DM patients with CAS compared to those without CAS. Serum CTRP4 levels are negatively related to the risk of CAS in T2DM.

Appearance-Based Gaze Estimation for ASD Diagnosis.

Biomarkers, such as magnetic resonance imaging (MRI) and electroencephalogram have been used to help diagnose autism spectrum disorder (ASD). However, the diagnosis needs the assist of specialized medical equipment in the hospital or laboratory. To diagnose ASD in a more effective and convenient way, in this article, we propose an appearance-based gaze estimation algorithm-AttentionGazeNet, to accurately estimate the subject's 3-D gaze from a raw video. The experimental results show its competitive performance on the MPIIGaze dataset and the improvement of 14.7% for static head pose and 46.7% for moving head pose on the EYEDIAP dataset compared with the state-of-the-art gaze estimation algorithms. After projecting the obtained gaze vector onto the screen coordinate, we apply accumulated histogram to taking into account both spatial and temporal information of estimated gaze-point and head-pose sequences. Finally, classification is conducted on our self-collected autistic children video dataset (ACVD), which contains 405 videos from 135 different ASD children, 135 typically developing (TD) children in a primary school, and 135 TD children in a kindergarten. The classification results on ACVD shows the effectiveness and efficiency of our proposed method, with the accuracy 94.8%, the sensitivity 91.1% and the specificity 96.7% for ASD.

Increased serum C1q/TNF-related protein 4 concentration in patients with acute coronary syndrome.

Accumulated evidence have revealed profound associations between C1q/TNF-related proteins (CTRPs) and coronary artery disease (CAD); yet, the relationship of CTRP4 to CAD has not been investigated. We examined the role of CTRP4 in CAD, and especially in acute coronary syndrome (ACS). METHODS: A total of 138 patients referred for coronary angiography were included in this study and were classified into 3 groups (ACS, CAD and control group). Comparisons regarding clinical data and CTRP4 concentration were performed among 3 groups. Weighted least-squares regression analysis was used to identify the independent predicting factors for CTRP4. RESULTS: Compared with either CAD (median 7.19 vs. 9.43, P < 0.05) or control group (median 7.22 vs. 9.43, P < 0.01), ACS group showed higher CTRP4 concentration. In addition, trend χ2 test revealed the presence of ACS increased with increased CTRP4 concentration (P = 0.010). Finally, in the weighted least-squares regression analysis, ACS was the only independent variable influencing CTRP4 concentration (ß- coefficient = 3.082, P = 0.004), even after adjusting for high-sensitivity C reactive protein (ß- coefficient = 3.050, P = 0.007). CONCLUSIONS: CTRP4 was associated with ACS; moreover, ACS was the independent factor in predicting CTRP4 concentration. The potentially important implications of CTRP4 in ACS may offer a novel insight into understanding the link between inflammation and ACS.

Electrophysiological correlates of visual attention span in Chinese adults with poor reading fluency.

Individuals with reading fluency difficulty (RFD) show an impairment in the simultaneous processing of multiple elements, which could be reflected in their visual attention span (VAS) capacity. However, the relationship between VAS impairment and RFD is still controversial. A series of processes underlie VAS, such as the early stage of visual attentional processing and the late stage of allocating and maintaining attentional resources. Therefore, the present study explored the relationships between VAS skills and RFD through the event-related potential (ERP) technique to disentangle the contributing cognitive processes regarding VAS from a temporal perspective. Eighteen Chinese adults with poor reading fluency and 18 age-matched normal readers participated. Their VAS skills were measured by a visual one-back task with symbols as nonverbal stimuli and key pressing as nonverbal responses, while relevant electrophysiological signals were recorded. The results showed that lower d' values and abnormal electrophysiological activities (especially weak amplitudes in the N1 and P3 components) in the VAS task were observed for the nonfluent readers compared with the controls. These findings suggested that the low VAS capacity in adults with poor reading fluency could be reflected by problems both in directing selective attention to visually discriminate stimuli within a multielement string at the early processing stage and in allocating attention to further encode targets at the late processing stage. Alternative explanations were further discussed. The current results provide theoretical explanations of the VAS-RFD relationship from a temporal perspective and provide insights for future remediation of reading fluency difficulty.

Long noncoding RNA MEG3 deteriorates inflammatory damage by downregulating microRNA-101a.

Valvulopathy is a familiar heart disease, which fearfully harms the health of the body. We studied the effects and mechanism of long noncoding RNA maternally expressed gene 3 (lncMEG3) on MVICs cell in inflammatory damage. Cell Counting Kit-8 and flow cytometry were respectively used to detect the effect of tumor necrosis factor α (TNF-α), MEG3 and microRNA (miR)-101a on cell viability and apoptosis. Moreover, MEG3 and miR-101a expression were changed by cell transfection and investigated by reverse transcription-quantitative polymerase chain reaction. Furthermore, Western blot was used to investigate the levels of Bax, pro-caspase-3, cleaved-caspase-3, pro-caspase-9, cleaved-caspase-9, interleukin (IL)-1ß, IL-6 and related-proteins of cell pathways. Otherwise, the levels of IL-1ß and IL-6 were also investigated by enzyme-linked immunosorbent assay kit. Reactive oxygen species (ROS) was examined by ROS assay. We found TNF-α caused inflammatory damage and upregulated MEG3. MEG3 was overexpressed and silenced in cells. Besides, MEG3 deteriorated inflammatory damage. Furthermore, MEG3 negatively regulated miR-101a and miR-101a mimic could reverse the effect of pc-MEG3. Besides, MEG3 enhanced the JNK and NF-κB pathways by downregulating miR-101a. In conclusion, MEG3 deteriorated cell inflammatory damage by downregulating miR-101a via JNK and NF-κB pathways.

[Feature exaction and classification of autism spectrum disorder children related electroencephalographic signals based on entropy].

The early diagnosis of children with autism spectrum disorders (ASD) is essential. Electroencephalography (EEG) is one of most commonly used neuroimaging techniques as the most accessible and informative method. In this study, approximate entropy (ApEn), sample entropy (SaEn), permutation entropy (PeEn) and wavelet entropy (WaEn) were extracted from EEGs of ASD child and a control group, and Student's t-test was used to analyze between-group differences. Support vector machine (SVM) algorithm was utilized to build classification models for each entropy measure derived from different regions. Permutation test was applied in search for optimize subset of features, with which the SVM model achieved best performance. The results showed that the complexity of EEGs in children with autism was lower than that of the normal control group. Among all four entropies, WaEn got a better classification performance than others. Classification results vary in different regions, and the frontal lobe showed the best performance. After feature selection, six features were filtered out and the accuracy rate was increased to 84.55%, which can be convincing for assisting early diagnosis of autism.

Retracted: Tetramethylpyrazine partially relieves hypoxia-caused damage of cardiomyocytes H9c2 by downregulation of miR-449a.

Inadequate oxygen supply is probably one of the most important pathophysiological mechanisms of cardiomyocyte damage in ischemic heart disease. Tetramethylpyrazine (TMP, also known as ligustrazine) is the main active ingredient isolated from the rhizome of Ligusticum chuanxiong Hort. A previous study reported that the TMP could exert cardioprotective activity. This study aimed to explore the molecular mechanism of the protective effects of TMP on cardiomyocyte damage caused by hypoxia. The viability and apoptosis of cardiomyocytes H9c2 were detected using cell counting kit-8 assay and annexin V-FITC/PI staining, respectively. Quantitative reverse transcription polymerase chain reaction was conducted to measure the expression level of microRNA-449a (miR-449a). Cell transfection was performed to upregulate the expression level of miR-449a or downregulate the expression level of sirtuin 1 (Sirt1). The protein expression levels of Sirt1 and key factors involved in cell apoptosis and phosphatidylinositol 3-kinase/protein kinase 3 (PI3K/AKT) pathway were evaluated using western blot analysis. We found that the hypoxia incubation inhibited H9c2 viability, induced cell apoptosis, and inactivated the PI3K/AKT pathway. TMP treatment partially relieved the hypoxia-caused H9c2 cell viability loss and apoptosis, as well as reversed the hypoxia-caused inactivation of the PI3K/AKT pathway. Moreover, TMP partially alleviated the upregulation of miR-449a in H9c2 cells caused by hypoxia. Overexpression of miR-449a weakened the effects of TMP on hypoxia-treated H9c2 cells. Furthermore, Sirt1 was a target gene of miR-449a. Knockdown of Sirt1 also weakened the effects of TMP on hypoxia-treated H9c2 cells. In conclusion, TMP partially relieved hypoxia-caused cardiomyocytes H9c2 viability loss and apoptosis at least through downregulating miR-499a, upregulating Sirt1, and then activating the PI3K/AKT pathway.

EEG-based multi-feature fusion assessment for autism.

Autism spectrum disorder (ASD) is a heterogeneous neurodevelopmental disorder which affects the developmental trajectory in several behavioral domains, including impairments of social communication, cognitive and language abilities. In this paper, multi-feature fusion method based on EEG signal is used to extract as many as possible features including power spectrum analysis, bicoherence, entropy and coherence methods, then we use minimum redundancy maximum correlation (mRMR) algorithm to choose the features, which are applied to input to three classifiers to obtain accuracy classification results. We try to find some key biomarkers of ASD by examining the accuracy of classifier, using different models which use the combination of multiplex features. The results show when nine features are selected by SVM-linear classifier, the accuracy is up to 91.38%. This method might provide objective basis for clinical diagnosis of autism.

Transcranial Direct Current Stimulation (tDCS) Can Modulate EEG Complexity of Children With Autism Spectrum Disorder.

Autism spectrum disorder (ASD) is a heterogeneous neurodevelopmental disorder which affects the developmental trajectory in several behavioral domains, including impairments of social communication, cognitive and language abilities. Transcranial direct current stimulation (tDCS) is a non-invasive brain stimulation technique, and it was used for modulating the brain disorders. In this paper, we enrolled 13 ASD children (11 males and 2 females; mean ± SD age: 6.5 ± 1.7 years) to participate in our trial. Each patient received 10 treatments over the dorsolateral prefrontal cortex (DLPFC) once every 2 days. Also, we enrolled 13 ASD children (11 males and 2 females; mean ± SD age: 6.3 ± 1.7 years) waiting to receive therapy as controls. A maximum entropy ratio (MER) method was adapted to measure the change of complexity of EEG series. It was found that the MER value significantly increased after tDCS. This study suggests that tDCS may be a helpful tool for the rehabilitation of children with ASD.

Identifying ADHD children using hemodynamic responses during a working memory task measured by functional near-infrared spectroscopy.

OBJECTIVE: Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder affecting children and adults. Previous studies found that functional near-infrared spectroscopy (fNIRS) can reveal significant group differences in several brain regions between ADHD children and healthy controls during working memory tasks. This study aimed to use fNIRS activation patterns to identify ADHD children from healthy controls. APPROACH: FNIRS signals from 25 ADHD children and 25 healthy controls performing the n-back task were recorded; then, multivariate pattern analysis was used to discriminate ADHD individuals from healthy controls, and classification performance was evaluated for significance by the permutation test. MAIN RESULTS: The results showed that 86.0% ([Formula: see text]) of participants can be correctly classified in leave-one-out cross-validation. The most discriminative brain regions included the bilateral dorsolateral prefrontal cortex, inferior medial prefrontal cortex, right posterior prefrontal cortex, and right temporal cortex. SIGNIFICANCE: This study demonstrated that, in a small sample, multivariate pattern analysis can effectively identify ADHD children from healthy controls based on fNIRS signals, which argues for the potential utility of fNIRS in future assessments.

Disrupted Brain Network in Children with Autism Spectrum Disorder.

Alterations in brain connectivity have been extensively reported in autism spectrum disorder (ASD), while their effects on the topology of brain network are still unclear. This study investigated whether and how the brain networks in children with ASD were abnormally organized with resting state EEG. Temporal synchronization analysis was first applied to capture the aberrant brain connectivity. Then brain network topology was characterized by three graph analysis methods including the commonly-used weighted and binary graph, as well as minimum spanning tree (MST). Whole brain connectivity in ASD group was found to be significantly reduced in theta and alpha band compared to typically development children (TD). Weighted graph found significantly decreased path length together with marginally significantly decreased clustering coefficient in ASD in alpha band, indicating a loss of small-world architecture to a random network. Such abnormal network topology was also demonstrated in the binary graph. In MST analysis, children with ASD showed a significant lower leaf fractions with a decrease trend of tree hierarchy in the alpha band, suggesting a shift towards line-like decentralized organization in ASD. The altered brain network may offer an insight into the underlying pathology of ASD and possibly serve as a biomarker that may aid in diagnosis of ASD.

Development of Brain Network in Children with Autism from Early Childhood to Late Childhood.

Extensive studies have indicated brain function connectivity abnormalities in autism spectrum disorder (ASD). However, there is a lack of longitudinal or cross-sectional research focused on tracking age-related developmental trends of autistic children at an early stage of brain development or based on a relatively large sample. The present study examined brain network changes in a total of 186 children both with and without ASD from 3 to 11 years, an early and key development period when significant changes are expected. The study aimed to investigate possible abnormal connectivity patterns and topological properties of children with ASD from early childhood to late childhood by using resting-state electroencephalographic (EEG) data. The main findings of the study were as follows: (1) From the connectivity analysis, several inter-regional synchronizations with reduction were identified in the younger and older ASD groups, and several intra-regional synchronization increases were observed in the older ASD group. (2) From the graph analysis, a reduced clustering coefficient and enhanced mean shortest path length in specific frequencies was observed in children with ASD. (3) Results suggested an age-related decrease of the mean shortest path length in the delta and theta bands in TD children, whereas atypical age-related alteration was observed in the ASD group. In addition, graph measures were correlated with ASD symptom severity in the alpha band. These results demonstrate that abnormal neural communication is already present at the early stages of brain development in autistic children and this may be involved in the behavioral deficits associated with ASD.

Reduced Prefrontal Cortex Activation in Children with Attention-Deficit/Hyperactivity Disorder during Go/No-Go Task: A Functional Near-Infrared Spectroscopy Study.

Objective: Attention-deficit/hyperactivity disorder (ADHD) is one of the most common neuropsychiatric disorders in children and affects 3 to 5% of school-aged children. This study is to demonstrate whether functional near-infrared spectroscopy (fNIRS) can detect the changes in the concentration of oxygenated hemoglobin (oxy-HB) in children with ADHD and typically developing children (TD children). Method: In this study, 14 children with ADHD and 15 TD children were studied. Metabolic signals of functional blood oxygen were recorded by using fNIRS during go/no-go task. A statistic method is used to compare the fNIRS between the ADHD children and controls. Results: A significant oxy-HB increase in the left frontopolar cortex (FPC) in control subjects but not in children with ADHD during inhibitory tasks. Moreover, ADHD children showed reduced activation in left FPC relative to TD children. Conclusion: Functional brain imaging using fNIRS showed reduced activation in the left prefrontal cortex (PFC) of children with ADHD during the inhibition task. The fNIRS could be a promising tool for differentiating children with ADHD and TD children.

Complexity analysis of fNIRS signals in ADHD children during working memory task.

Attention-deficit/hyperactivity disorder (ADHD) is a prevalent neurodevelopmental disorder in children. Neuroimaging studies have revealed abnormalities of neural activities in some brain regions, including the frontal cortex, striatum, cerebellum, and occipital cortex. Recently, some investigators have demonstrated that nonlinear complexity analysis of neural activity may provide a new index to indicate ADHD. In the present study, we used the permutation entropy (PE) to measure the complexity of functional near-infrared spectroscopy (fNIRS) signals in children with and without ADHD during a working memory task, it was aimed to investigate the relationship between the PE values and the cortical activations, and the different PE values between the children with and without ADHD. We found that PE values exhibited significantly negative correlation with the cortical activations (r = -0.515, p = 0.003), and the PE values of right dorsolateral prefrontal cortex in ADHD children were significantly larger than those in normal controls (p = 0.027). In addition, the PE values of right dorsolateral prefrontal cortex were positively correlated to the ADHD index (r = 0.448, p = 0.012). These results suggest that complexity analysis of fNIRS signals could be a promising tool in diagnosing children with ADHD.