Research on Pattern Classification of Autism Spectrum Disorder Related to the Diagnosis of Attention Deficit Hyperactivity Disorder
1. Children Health Department, Women and Children Hospital of Hubei Province, Nanjing Medical University, Wuhan 430070, China
2. Children Psychiatry Department, Nanjing Brain Hospital Affiliated Nanjing Medical University, Nanjing 210000, China
| Abstract: | Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD) are common neurodevelopmental disorders. Clinically, there is extensive overlap between the symptoms of both disorders, which poses a major diagnostic challenge. This study examined the heterogeneity of ASD and ADHD by selecting indicators derived from neuropsychological and/or neuroimaging tests, and using the Support Vector Machine (SVM) algorithm to conduct research on high-functioning ASD and ADHD, so as to further elucidate the significance of different indicators in the differentiation of these two disorders. From January 2018 to June 2019, 33 children with high-functioning ASD, 35 with high-functioning ADHD and 30 typically developing (TD) children were recruited in the community during the same period and enrolled in the study. All participants were required to avoid taking neuropsychiatric drugs for 1 week before functional magnetic resonance imaging was conducted, and to stay awake and to minimize head motion during scans. Then, the collected brain image data were preprocessed to ReHo index on the dparsfa (http://www.restfmri.net/forum/DPARSF) platform, and differences in the regional homogeneity (ReHo) value of the three groups of subjects were compared and analyzed using Statistical Parametric Matching software, which took into account ReHo classification characteristics. Spearman’s correlation analysis was carried out to analyze the voxel values of the extracted difference masses correlated with the category labels, and the support vector machine method was employed to respectively test the classification accuracy of the single ReHo index for the three groups of participants and the accuracy of constructing model discrimination type in joint behavioral indexes. A comparative analysis of differences in ReHo characteristics among the three groups showed differences in SupraMarginal_R, Parietal_Sup_L, Parietal_Inf_R and Cerebelum_Crus2_L (P < 0.05). The distribution of relative ReHo values in this mass region was TD>ASD>ADHD, and the difference was statistically significant (P < 0.05). Further extracting voxel values of the three groups, using the participants' differential masses as characteristics, it was found that the maximum classification Accuracy (ACC) and Area Under Curve (AUC) of the brain resting-state local consistency index (ReHo) were 60.74% and 0.6671, respectively. Compared with the classification using resting-state local consistency (ReHo) features alone, the maximum ACC and AUC in combination with ReHo index and specific scale features were 73.53% and 0.7943, respectively. Classification accuracy was improved when combining a specific scale with the ReHo index, and this may prove more helpful for clinical auxiliary diagnosis. |
| Keywords: | Autism Spectrum Disorder; Attention Deficit Hyperactivity Disorder; Local Consistency; Support Vector Machine |
| DOI: | 10.57237/j.mrf.2023.02.003 |
View:
Downloads:
收稿日期: 2023-02-28
接受日期: 2023-05-12
在线出版日期: 2023-05-25
参考文献
| [1] | American Psychiatric Organization. Diagnostic and statistical manual of mental disorders (5th ed.) [M]. American Psychiatric Association; 2013. |
| [2] | Rao Patricia A, Landa Rebecca J. Association between severity of behavioral phenotype and comorbid attention deficit hyperactivity disorder symptoms in children with autism spectrum disorders [J]. Autism. 2014; 18: 272-280. |
| [3] | Leitner Y. The Co-Occurrence of Autism and Attention Deficit Hyperactivity Disorder in Children “What Do We Know? [J]. Frontiers in Human Neuroscience. 2014; 8: 268. |
| [4] | Miodovnik A, Harstad E, Sideridis G, et al. Timing of the Diagnosis of Attention-Deficit/Hyperactivity Disorder and Autism Spectrum Disorder. Pediatrics [J]. 2015; 136 (4): 830-837. |
| [5] | Uddin LQ, Dajani DR, Voorhies W, et al. Progress and roadblocks in the search for brain-based biomarkers of autism and attention-deficit/hyperactivity disorder [J]. Translational Psychiatry. 2017; 7 (8): 1218. |
| [6] | Clark LA, Cuthbert B, LewisFernández R, et al. Three Approaches to Understanding and Classifying Mental Disorder: ICD-11, DSM-5, and the National Institute of Mental Health's Research Domain Criteria (RDoC) [J]. Psychological Science in the Public Interest A Journal of the American Psychological Society. 2017; 18 (2): 72-145. |
| [7] | Park MTM, Raznahan A, Shaw P, et al. Neuroanatomical phenotypes in mental illness: identifying convergent and divergent cortical phenotypes across autism, ADHD and schizophrenia [J]. J Psychiatry Neurosci. 2018; 43 (3): 201-212. |
| [8] | Pacheco J, Garvey M A, Sarampote C S, et al. Annual Research Review: The contributions of the RDoC research framework on understanding the neurodevelopmental origins, progression and treatment of mental illnesses [J]. Journal of child psychology and psychiatry, 2022 (4): 63. |
| [9] | Yang H, Wu QZ, Guo LT, et al. Abnormal spontaneous brain activity in medication-naive ADHD children: A resting state fMRI study [J]. NEUROSCIENCE LETTERS. 2011; 502 (2): 89-93. |
| [10] | Li G, Rossbach K, Jiang W, et al. Resting-state brain activity in Chinese boys with low functioning autism spectrum disorder [J]. Ann Gen Psychiatry. 2018; 17: 47. |
| [11] | Guo X, Chen H, Long Z, et al. Atypical developmental trajectory of local spontaneous brain activity in autism spectrum disorder [J]. Scientific Reports. 2017; 7: 39822. |
| [12] | Lu Bin, Xiao Chen, Li Le, et al. The dynamics of spontaneous brain activity in autism and the abnormal mechanism of its integration [J]. Chinese Science Bulletin. 2018; 63 (15). |
| [13] | Cauda F, Geda E, Sacco K, et al. Grey matter abnormality in autism spectrum disorder: an activation likelihood estimation meta-analysis study [J]. Journal of Neurology Neurosurgery & Psychiatry. 2011; 82 (12): 1304-1313. |
| [14] | Di Martino A, Zuo XN, Kelly C, et al. Shared and distinct intrinsic functional network centrality in autism and attention-deficit/hyperactivity disorder. Biol Psychiatry. 2013; 74 (8): 623-632. |
| [15] | Kernbach JM, Satterthwaite TD, Bassett DS, et al. Shared endo-phenotypes of default mode dsfunction in attention deficit/hyperactivity disorder and autism spectrum disorder [J]. Transl Psychiatry. 2018; 8 (1): 133. |
| [16] | Zhao X, Rangaprakash D, Yuan B, et al. Investigating the Correspondence of Clinical Diagnostic Grouping With Underlying Neurobiological and Phenotypic Clusters Using Unsupervised Machine Learning [J]. Front Appl Math Stat. 2018; 4: 25. |
| [17] | Jung M, Tu Y, Park J, et al. Surface-based shared and distinct resting functional connectivity in attention-deficit hyperactivity disorder and autism spectrum disorder [J]. British Journal of Psychiatry. 2018; 214 (6): 1-6. |
| [18] | Studer Bettina, Cen Danlu, Walsh Vincent. The angular gyrus and visuospatial attention in decision-making under risk [J]. Neuroimage. 2014; 103: 75-80. |
| [19] | Xiao Yunhua, Cao Yuan, Zhu Di, etc. Study on the reliability and validity of the Chinese version of Griffith empathy test for parents [J]. Chinese Journal of Behavioral Medicine and Brain Science. 2016; 25 (6): 561-564. |
| [20] | Qian Ying, Wang Yufeng. Reliability and validity of the parent version of the school-age children's executive function behavior rating scale [J]. Peking University Journal: Medical Edition, 2007; (3): 277-283. |
| [21] | Guo Yanqing, Yang Xiaoling, Jing Liu, et al. Study on the diagnostic validity and reliability of autism diagnostic interview scale (revised) [J]. Chinese Journal of Psychiatry. 2002; 1: 45-48. |
| [22] | Zhou Jinbo, Guo Lanting, Chen Ying. Reliability and validity of the Chinese version of Swanson, Nolan, And pelham version iv rating scale-parent form for attention-deficit/hyperactivity disorder. Reliability and validity of Chinese version of Snap-iv rating scale for attention deficit hyperactivity disorder-parent version [J]. chinese mental health journal. 2013; 027 (006): 424-428. |
| [23] | Zhang Houcan. Revision of the Chinese version of Wechsler Intelligence Scale for Children, Fourth Edition (WISC-IV) [J]. Psychological Science. 2009; 32 (05): 155-157. |
| [24] | Lukito S, Jones CRG, Pickles A, et al. Specificity of executive function and theory of mind performance in relation to attention-deficit/hyperactivity symptoms in autism spectrum disorders [J]. Molecular Autism. 2017; 8 (1): 60. |
| [25] | Wang Yao. A study on the sense of justice and the local consistency of brain rest state in children and adolescents with high-functioning ASD [D]. Nanjing Medical University. 2018. |
| [26] | Seghier ML. The Angular Gyrus: Multiple Functions and Multiple Subdivisions [J]. The Neuroscientist. 2013; 19 (1): 43-61. |
| [27] | Lu Xun. The comprehensive language function of the left angular gyrus of the brain [J]. Science and Education Literature. 2009; 16: 282-283. |
| [28] | Liu Jieke, Yao Li, Zhang Wenjing, et al. Gray matter abnormalities in pediatric autism spectrum disorder: a meta-analysis with signed differential mapping [J]. Eur Child Adolesc Psychiatry. 2017; 26: 933-945. |
| [29] | Wang Jia, Fu Kuang, Chen Lei, et al. Increased Gray Matter Volume and Resting-State Functional Connectivity in Somatosensory Cortex and their Relationship with Autistic Symptoms in Young Boys with Autism Spectrum Disorder [J]. Front Physiol. 2017; 8: 588. |
| [30] | Velasquez Francisco, Qin Xiaoyan Angela, Reilly Melissa A, et al. Neural correlates of emotional inhibitory control in autism spectrum disorders [J]. Res Dev Disabil. 2017; 64: 64-77. |
| [31] | Turner JWA. Parietal lobes. BMJ. 1953; 2 (4851): 1416-1416. |
| [32] | Wang Longlun. Study on local consistency of resting brain function of preschool children autism spectrum disorder [D] Chongqing Medical University. 2016. |
| [33] | Xin Wang. Correlation between resting brain functional magnetic resonance imaging and dopamine D4 receptor gene in children with attention deficit hyperactivity disorder [D]. Wenzhou Medical University. 2015. |
| [34] | Cao Xiaohua, Zhang Aixia, Liu Zhifen, et al. Resting brain functional magnetic resonance imaging study of adolescent patients with autism spectrum disorder [J]. Chinese Journal of Clinicians (electronic version) (3): 325-330. |
| [35] | Verly Marjolein, Verhoeven Judith, Zink Inge, et al. Altered functional connectivity of the language network in ASD: role of classical language areas and cerebellum [J]. Neuroimage Clin. 2014; 4: 374-382. |
| [36] | Isabelle Rapin, Michelle Dunn. Language disorders in children with autism [J]. Seminars in pediatric neurology. 1997; 4 (2): 86-92. |
| [37] | Grassi M, Perin C, Borella M. The cerebellar cognitive-affective syndrome [J]. archivos argentinos de pediatría. 2004; 113 (5): e268. |
| [38] | Hodge SM, Makris N, Kennedy DN, et al. Cerebellum, Language and Cognition in Autism and Specific Language Impairment [J]. journal of autism & developmental disorders. 2010; 40 (3): 300-316. |
| [39] | Zhao D, Zheng S, Yang L, et al. Causal connectivity abnormalities of regional homogeneity in children with attention deficit hyperactivity disorder: A rest-state fMRI study [J]. ADMET & DMPK. 2017; 5 (4): 242-252. |
| [40] | Frings Markus, Dimitrova Albena, Schorn Christoph F, et al. Cerebellar involvement in verb generation: an fMRI study [J]. Neurosci. Lett. 2006; 409 (1): 19-23. |
| [41] | Wang Lu, Fan Guoguang, Yu Bing et al. Functional magnetic resonance imaging of cerebellar dysfunction in children with attention deficit hyperactivity disorder [J]. China Medical Imaging Technology. 2009; 25 (9): 1560-1563. |
| [42] | Jiang Kaihua, Dong Xuan, Zhou Jinjin, et al. Characteristics of cerebellar functional connection in children with attention deficit hyperactivity disorder at rest [J]. Chinese journal of applied clinical pediatrics Journal. 2018; 33 (24): 1855-1858. |
| [43] | Wang JB, Zheng LJ, Cao QJ, et al. Inconsistency in Abnormal Brain Activity across Cohorts of ADHD-200 in Children with Attention Deficit Hyperactivity Disorder [J]. Front Neurosci. 2017; 11: 320. |
| [44] | Alonso Bde C, Hidalgo Tobón S, Dies Suarez P, et al. A multi-methodological MR resting state network analysis to assess the changes in brain physiology of children with ADHD [published correction appears in PLoS One. 2015; 10 (11): e0143785. PLoS One. 2014; 9 (6): e99119. |
| [45] | Duda M, Ma R, Haber N, et al. Use of machine learning for behavioral distinction of autism and ADHD [J]. Translational Psychiatry. 2016; 6 (2): e732. |
| [46] | Rommelse Nanda, Buitelaar Jan K, Hartman Catharina A. Structural brain imaging correlates of ASD and ADHD across the lifespan: a hypothesis-generating review on developmental ASD-ADHD subtypes [J]. J Neural Transm (Vienna). 2017; 124: 259-271. |
| [47] | Seernani D, Damania K, Ioannou C, et al. Visual search in ADHD, ASD and ASD+ADHD: overlapping or dissociating disorders? [J] Eur Child Adolesc Psychiatry. 2020; 20: 1235. |
| [48] | Shephard Elizabeth, Tye Charlotte, Ashwood Karen L, et al. Oscillatory neural networks underlying resting-state, attentional control and social cognition task conditions in children with ASD, ADHD and ASD+ADHD [J]. Cortex. 2019; 117: 96-110. |
