scispace - formally typeset
Book ChapterDOI

A Meta-Heuristic Model Based Computational Intelligence in Exploration and Classification of Autism in Children

01 Jan 2020-pp 61-77
TL;DR: The novelty of the paper lies in the fact of extracting important features for modeling so as to make a prior analysis by any parents at home before approaching clinicians which supports the early intervention of autism.
Abstract: Autism spectrum disorder (ASD) is one of the most notable neurodevelopmental disorders that gained major notification among parents, clinicians and even in researchers in the current era. The early identification of autism is a much needed support for parents and clinicians. The proposed methodology aims in building a computational model for such easy and early diagnosis by analyzing and finding the correlations between features-to-class and feature-to-feature so as to maximize the former and minimize the latter. The correlation between features is analyzed using (i) chi square computation technique in filter method and (ii) information gain. On analyzing the correlations, the resultant attributes of every technique are trained separately under the standard linear SVM classifier and then tested for the models performance and accuracy. There are two major contributions of the proposed work; Method 1: to build a model that takes optimized features extracted from the chi square and information gain analysis from questionnaires on the application of genetic algorithm (GA). The optimized features are then trained and tested to classify autism in support of SVM linear classifier. Method 2: to build a model based on the application of back-propagation feed forward neural network to classify the presence of autism. The paper ensures better and faster convergence of the positive class label of autism with maximized accuracy, specificity, performance and minimized error. The novelty of the paper lies in the fact of extracting important features for modeling so as to make a prior analysis by any parents at home before approaching clinicians which supports the early intervention of autism.
Topics: Autism (57%), Linear classifier (52%), Support vector machine (51%)
References
More filters

Journal ArticleDOI
TL;DR: The Autism-Spectrum Quotient is a valuable instrument for rapidly quantifying where any given individual is situated on the continuum from autism to normality, and its potential for screening for autism spectrum conditions in adults of normal intelligence remains to be fully explored.
Abstract: Currently there are no brief, self-administered instruments for measuring the degree to which an adult with normal intelligence has the traits associated with the autistic spectrum. In this paper, we report on a new instrument to assess this: the Autism-Spectrum Quotient (AQ). Individuals score in the range 0-50. Four groups of subjects were assessed: Group 1: 58 adults with Asperger syndrome (AS) or high-functioning autism (HFA); Group 2: 174 randomly selected controls. Group 3: 840 students in Cambridge University; and Group 4: 16 winners of the UK Mathematics Olympiad. The adults with AS/HFA had a mean AQ score of 35.8 (SD = 6.5), significantly higher than Group 2 controls (M = 16.4, SD = 6.3). 80% of the adults with AS/HFA scored 32+, versus 2% of controls. Among the controls, men scored slightly but significantly higher than women. No women scored extremely highly (AQ score 34+) whereas 4% of men did so. Twice as many men (40%) as women (21%) scored at intermediate levels (AQ score 20+). Among the AS/HFA group, male and female scores did not differ significantly. The students in Cambridge University did not differ from the randomly selected control group, but scientists (including mathematicians) scored significantly higher than both humanities and social sciences students, confirming an earlier study that autistic conditions are associated with scientific skills. Within the sciences, mathematicians scored highest. This was replicated in Group 4, the Mathematics Olympiad winners scoring significantly higher than the male Cambridge humanities students. 6% of the student sample scored 32+ on the AQ. On interview, 11 out of 11 of these met three or more DSM-IV criteria for AS/HFA, and all were studying sciences/mathematics, and 7 of the 11 met threshold on these criteria. Test-retest and interrater reliability of the AQ was good. The AQ is thus a valuable instrument for rapidly quantifying where any given individual is situated on the continuum from autism to normality. Its potential for screening for autism spectrum conditions in adults of normal intelligence remains to be fully explored.

4,270 citations


Journal ArticleDOI
01 Jul 2006-Pediatrics
TL;DR: The authors recommend that developmental surveillance be incorporated at every well-child preventive care visit, and children diagnosed with developmental disorders should be identified as children with special health care needs, and chronic-condition management should be initiated.
Abstract: Early identification of developmental disorders is critical to the well-being of children and their families. It is an integral function of the primary care medical home and an appropriate responsibility of all pediatric health care professionals. This statement provides an algorithm as a strategy to support health care professionals in developing a pattern and practice for addressing developmental concerns in children from birth through 3 years of age. The authors recommend that developmental surveillance be incorporated at every well-child preventive care visit. Any concerns raised during surveillance should be promptly addressed with standardized developmental screening tests. In addition, screening tests should be administered regularly at the 9-, 18-, and 30-month visits. (Because the 30-month visit is not yet a part of the preventive care system and is often not reimbursable by third-party payers at this time, developmental screening can be performed at 24 months of age. In addition, because the frequency of regular pediatric visits decreases after 24 months of age, a pediatrician who expects that his or her patients will have difficulty attending a 30-month visit should conduct screening during the 24-month visit.) The early identification of developmental problems should lead to further developmental and medical evaluation, diagnosis, and treatment, including early developmental intervention. Children diagnosed with developmental disorders should be identified as children with special health care needs, and chronic-condition management should be initiated. Identification of a developmental disorder and its underlying etiology may also drive a range of treatment planning, from medical treatment of the child to family planning for his or her parents.

1,108 citations


Journal ArticleDOI
TL;DR: Training would improve teachers’ and clinicians’ recognition of ASC in females, so that timely identification can mitigate risks and promote wellbeing of girls and women on the autism spectrum.
Abstract: We used Framework Analysis to investigate the female autism phenotype and its impact upon the under-recognition of autism spectrum conditions (ASC) in girls and women. Fourteen women with ASC (aged 22-30 years) diagnosed in late adolescence or adulthood gave in-depth accounts of: 'pretending to be normal'; of how their gender led various professionals to miss their ASC; and of conflicts between ASC and a traditional feminine identity. Experiences of sexual abuse were widespread in this sample, partially reflecting specific vulnerabilities from being a female with undiagnosed ASC. Training would improve teachers' and clinicians' recognition of ASC in females, so that timely identification can mitigate risks and promote wellbeing of girls and women on the autism spectrum.

324 citations


Journal ArticleDOI
14 Jan 2015-Molecular Autism
TL;DR: A comprehensive systematic review of the literature was performed to estimate a reliable mean AQ score in individuals without a diagnosis of an autism spectrum condition (ASC) and establish average AQ scores based on a systematic review, for populations of adult males and females with and without ASC.
Abstract: The Autism-Spectrum Quotient (AQ) is a self-report measure of autistic traits. It is frequently cited in diverse fields and has been administered to adults of at least average intelligence with autism and to nonclinical controls, as well as to clinical control groups such as those with schizophrenia, prosopagnosia, anorexia, and depression. However, there has been no empirical systematic review of the AQ since its inception in 2001. The present study reports a comprehensive systematic review of the literature to estimate a reliable mean AQ score in individuals without a diagnosis of an autism spectrum condition (ASC), in order to establish a reference norm for future studies. A systematic search of computerized databases was performed to identify studies that administered the AQ to nonclinical participant samples representing the adult male and female general population. Inclusion was based on a set of formalized criteria that evaluated the quality of the study, the usage of the AQ, and the population being assessed. After selection, 73 articles, detailing 6,934 nonclinical participants, as well as 1,963 matched clinical cases of ASC (from available cohorts within each individual study), were analyzed. Mean AQ score for the nonclinical population was 16.94 (95% CI 11.6, 20.0), while mean AQ score for the clinical population with ASC was found to be 35.19 (95% CI 27.6, 41.1). In addition, in the nonclinical population, a sex difference in autistic traits was found, although no sex difference in AQ score was seen in the clinical ASC population. These findings have implications for the study of autistic traits in the general population. Here, we confirm previous norms with more rigorous data and for the first time establish average AQ scores based on a systematic review, for populations of adult males and females with and without ASC. Finally, we advise future researchers to avoid risk of bias by carefully considering the recruitment strategy for both clinical and nonclinical groups and to demonstrate transparency by reporting recruitment methods for all participants.

322 citations


Journal ArticleDOI
TL;DR: Results from this study may prove valuable in the development of mobile tools for preliminary evaluation and clinical prioritization—in particular those focused on assessment of short home videos of children—that speed the pace of initial evaluation and broaden the reach to a significantly larger percentage of the population at risk.
Abstract: The Autism Diagnostic Observation Schedule-Generic (ADOS) is one of the most widely used instruments for behavioral evaluation of autism spectrum disorders. It is composed of four modules, each tailored for a specific group of individuals based on their language and developmental level. On average, a module takes between 30 and 60 min to deliver. We used a series of machine-learning algorithms to study the complete set of scores from Module 1 of the ADOS available at the Autism Genetic Resource Exchange (AGRE) for 612 individuals with a classification of autism and 15 non-spectrum individuals from both AGRE and the Boston Autism Consortium (AC). Our analysis indicated that 8 of the 29 items contained in Module 1 of the ADOS were sufficient to classify autism with 100% accuracy. We further validated the accuracy of this eight-item classifier against complete sets of scores from two independent sources, a collection of 110 individuals with autism from AC and a collection of 336 individuals with autism from the Simons Foundation. In both cases, our classifier performed with nearly 100% sensitivity, correctly classifying all but two of the individuals from these two resources with a diagnosis of autism, and with 94% specificity on a collection of observed and simulated non-spectrum controls. The classifier contained several elements found in the ADOS algorithm, demonstrating high test validity, and also resulted in a quantitative score that measures classification confidence and extremeness of the phenotype. With incidence rates rising, the ability to classify autism effectively and quickly requires careful design of assessment and diagnostic tools. Given the brevity, accuracy and quantitative nature of the classifier, results from this study may prove valuable in the development of mobile tools for preliminary evaluation and clinical prioritization—in particular those focused on assessment of short home videos of children—that speed the pace of initial evaluation and broaden the reach to a significantly larger percentage of the population at risk.

165 citations


Network Information
Related Papers (5)