ABSTRACT
Objective: Common methods for clinical diagnosis include clinical interview, behavioral questionnaires, and neuropsychological assessment. These methods rely on clinical interpretation and have variable reliability, sensitivity, and specificity. The goal of this study was to evaluate the utility of machine learning in the prediction and classification of children with ADHD-Combined presentation (ADHD-C) using brief neuropsychological measures (d2 Test of Attention, Children with ADHD-C and typically developing control children completed semi-structured clinical interviews and measures of attention/concentration and parents completed symptom severity questionnaires. Method: We used a forward feature selection method to identify the most informative neuropsychological features for support vector machine (SVM) classification and a decision tree model to derive a rule-based model. Results: The SVM model yielded excellent classification accuracy (100%) of individual children with and without ADHD (1.0). Decision tree algorithms identified individuals with and without ADHD-C with 100% sensitivity and specificity. Conclusion:This study observed highly accurate statistical diagnostic classification, at the individual level, in a sample of children with ADHD-C. The findings suggest data-driven behavioral algorithms based on brief neuropsychological data may present an efficient and accurate diagnostic tool for clinicians.
Subject(s)
Attention Deficit Disorder with Hyperactivity , Support Vector Machine , Attention Deficit Disorder with Hyperactivity/diagnosis , Child , Humans , Machine Learning , Neuropsychological Tests , Reproducibility of ResultsABSTRACT
BACKGROUND: Female and male trajectories of cerebellar and lobar brain structures are sexually dimorphic, making sex a potential candidate moderator of neurocognitive late effects from radiation treatment. We sought to evaluate longitudinal neurocognitive functioning in male versus female children treated for posterior fossa brain tumors. METHODS: Fifty-one female and 63 male survivors of posterior fossa tumors completed neuropsychological testing at 2 timepoints. We included patients treated with surgical resection, chemotherapy, and radiation therapy. Multilevel mixed modeling was used to predict IQ score as a function of patient sex following treatment (~2 or ~4 years post treatment). Effect sizes were used as a measure of clinical significance. RESULTS: Multilevel models resulted in a significant sex by time interaction (F = 6.69, P = 0.011). Females' cognitive scores were considerably higher compared with males at 4 years posttreatment. Females demonstrated an average improvement of 7.61 standard score IQ points compared with a decline of 2.97 points for males at 4 years follow-up. Effect sizes for female IQ compared with male IQ at 4 years posttreatment were between 0.8 and 0.9. CONCLUSION: Trajectories of neurocognitive functioning following posterior fossa tumor treatment differed between female and male children. Sexual dimorphism in radiation late effects may alter treatment decisions in children. Research into sex-specific neuroprotective mechanisms underlying neurocognitive development following pediatric brain tumor treatments is warranted.
Subject(s)
Brain/radiation effects , Infratentorial Neoplasms/radiotherapy , Intelligence/radiation effects , Radiation Injuries/complications , Sex Characteristics , Child , Cognition Disorders/etiology , Cranial Irradiation/adverse effects , Female , Humans , Male , Retrospective Studies , Wechsler ScalesABSTRACT
The cause of attention-deficit/hyperactivity disorder (ADHD) has been linked to abnormalities in prefrontal-striatal-cerebellar networks, but the brain-behavioral correlates are relatively equivocal. Children with ADHD and healthy controls underwent MRI and neuropsychological testing. Brain cortical thickness was analyzed for the bilateral rostral and caudal anterior cingulate cortex (ACC). Inhibitory control was assessed with the Stroop Inhibition test, and ADHD symptom severity was assessed with parent and teacher behavioral questionnaires. Brain-behavior relationships were calculated between cortical thickness and behavioral measures with regression models. Children with ADHD had significant cortical thinning in the right rostral ACC but nonsignificant thinning in right caudal, left caudal, or left rostral ACC compared with healthy control children after statistical correction for multiple comparisons. Further, right rostral ACC thickness predicted a significant amount of the variance in parent- and teacher-reported symptoms of ADHD. Exploratory analysis showed that cortical thickness was not related to psychostimulant medication history. Symptoms of ADHD may be related to reductions in cortical thickness in the right anterior attention network, a region implicated in behavioral error detection, impulsivity, and inhibitory control.
Subject(s)
Attention Deficit Disorder with Hyperactivity/pathology , Brain Mapping , Gyrus Cinguli/abnormalities , Prefrontal Cortex/abnormalities , Adolescent , Analysis of Variance , Attention Deficit Disorder with Hyperactivity/physiopathology , Attention Deficit Disorder with Hyperactivity/psychology , Case-Control Studies , Child , Executive Function/physiology , Female , Humans , Inhibition, Psychological , Magnetic Resonance Imaging , Male , Neuropsychological Tests , Severity of Illness IndexABSTRACT
The extant research on nonverbal learning disability (NLD) was analyzed in this review. Studies were defined for use in the review as those that appeared in a peer-reviewed journal and included participants characterized as having NLD. Each study also needed to provide a statistical analysis of dependent variables. An a priori system was used to evaluate the quality of the research. Of the 88 publications found, 32 met criteria for inclusion in the review, with 6 meeting full criteria as strong studies. The diagnostic criteria used and the research findings are briefly discussed, as are proposed guidelines for future research.
Subject(s)
Developmental Disabilities/physiopathology , Learning Disabilities/physiopathology , Child , Developmental Disabilities/classification , Developmental Disabilities/diagnosis , Humans , Learning Disabilities/classification , Learning Disabilities/diagnosis , Practice Guidelines as Topic/standardsABSTRACT
OBJECTIVE: Studies of healthy individuals and those with cerebellar damage have implicated the cerebellum in a variety of cognitive and behavioral processes. Decreased cerebellar volume has been found in children with attention-deficit/hyperactivity disorder (ADHD) and differentially related to behavioral outcomes. The present study investigated whether smaller cerebellar vermis volume was present in children with ADHD-combined type (ADHD-C) compared with controls and whether volume related to parent- and teacher-reported levels of ADHD symptomatology. METHOD: T1-weighted magnetic resonance images and parent- and teacher-reported ADHD symptoms were acquired for 32 children diagnosed with ADHD-C and 15 typically developing controls. Participants were right-handed, had no comorbid diagnoses of learning disabilities, conduct disorder, or affective/mood disorder, and were 9 to 15 years of age. RESULTS: Participants with ADHD-C showed significantly smaller volume in the posterior inferior vermis compared with controls. No statistically significant differences were observed for cerebral volume, anterior vermis volume, posterior superior volume, or total cerebellar volume. Regression analyses indicated that a significant amount of the variance in parent-reported Behavior Assessment System for Children, Second Edition, Hyperactivity and Attention and Conners Restless/Impulsive ratings was explained by volume of the posterior inferior vermis. CONCLUSIONS: Consistent with previous studies, children with ADHD had smaller volume in the posterior inferior vermis. New findings emerged with smaller volume of the posterior inferior vermis predicting a significant amount of the variance in parent-reported hyperactivity, attention, and restlessness/impulsivity. Thus, symptoms of hyperactivity and inattention in ADHD may be partly explained by smaller volume of the cerebellar vermis and its connections within the cerebrum.
Subject(s)
Attention Deficit Disorder with Hyperactivity/diagnosis , Cerebellum/pathology , Image Processing, Computer-Assisted , Imaging, Three-Dimensional , Magnetic Resonance Imaging , Neuropsychological Tests/statistics & numerical data , Attention Deficit Disorder with Hyperactivity/pathology , Attention Deficit Disorder with Hyperactivity/psychology , Child , Female , Humans , Internal-External Control , Male , Organ Size/physiology , Personality Assessment , Psychometrics , Reference ValuesABSTRACT
Research in Attention-Deficit/Hyperactivity Disorder (ADHD) generally utilizes clinical samples or children with comorbid psychiatric diagnoses. Findings indicated that children with ADHD experience academic underachievement and poor performance on measures of response inhibition (RI). Less is known, about the neuropsychological profile of typically developing children with ADHD. The aim of the current study was twofold: (1) determine if academic skills and RI were impaired in typically developing children with ADHD-combined subtype (ADHD-C) and (2) determine to what extent RI may predict academic abilities. Children with ADHD-C did not differ on any academic domain from controls. Children with ADHD-C performed more poorly than controls on RI measures. Regression analyses suggest that Written Expression ability was significantly influenced by RI. No other academic domain was related to RI. Results suggest that children with ADHD-C may experience impairments in RI despite adequate academic functioning. Impaired RI is not solely responsible for difficulties found in academic skills in ADHD-C.
