Facial Image-Based Autism Detection:A Comparative Study of Deep Neural Network Classifiers

Autism Spectrum Disorder(ASD)is a neurodevelopmental condition characterized by significant challenges in social interaction,communication,and repetitive behaviors.Timely and precise ASD detection is crucial,particularly in regions with limited diagnostic resources like Pakistan.This study aims to conduct an extensive comparative analysis of various machine learning classifiers for ASD detection using facial images to identify an accurate and cost-effective solution tailored to the local context.The research involves experimentation with VGG16 and MobileNet models,exploring different batch sizes,optimizers,and learning rate schedulers.In addition,the“Orange”machine learning tool is employed to evaluate classifier performance and automated image processing capabilities are utilized within the tool.The findings unequivocally establish VGG16 as the most effective classifier with a 5-fold cross-validation approach.Specifically,VGG16,with a batch size of 2 and the Adam optimizer,trained for 100 epochs,achieves a remarkable validation accuracy of 99% and a testing accuracy of 87%.Furthermore,the model achieves an F1 score of 88%,precision of 85%,and recall of 90% on test images.To validate the practical applicability of the VGG16 model with 5-fold cross-validation,the study conducts further testing on a dataset sourced fromautism centers in Pakistan,resulting in an accuracy rate of 85%.This reaffirms the model’s suitability for real-world ASD detection.This research offers valuable insights into classifier performance,emphasizing the potential of machine learning to deliver precise and accessible ASD diagnoses via facial image analysis.

Melatonin improves synapse development by PI3K/Akt signaling in a mouse model of autism spectrum disorder

Autism spectrum disorders are a group of neurodevelopmental disorders involving more than 1100 genes,including Ctnnd2 as a candidate gene.Ctnnd2knockout mice,serving as an animal model of autis m,have been demonstrated to exhibit decreased density of dendritic spines.The role of melatonin,as a neuro hormone capable of effectively alleviating social interaction deficits and regulating the development of dendritic spines,in Ctnnd2 deletion-induced nerve injury remains unclea r.In the present study,we discove red that the deletion of exon 2 of the Ctnnd2 gene was linked to social interaction deficits,spine loss,impaired inhibitory neurons,and suppressed phosphatidylinositol-3-kinase(PI3K)/protein kinase B(Akt) signal pathway in the prefrontal cortex.Our findings demonstrated that the long-term oral administration of melatonin for 28 days effectively alleviated the aforementioned abnormalities in Ctnnd2 gene-knockout mice.Furthermore,the administration of melatonin in the prefro ntal cortex was found to improve synaptic function and activate the PI3K/Akt signal pathway in this region.The pharmacological blockade of the PI3K/Akt signal pathway with a PI3K/Akt inhibitor,wo rtmannin,and melatonin receptor antagonists,luzindole and 4-phenyl-2-propionamidotetralin,prevented the melatonin-induced enhancement of GABAergic synaptic function.These findings suggest that melatonin treatment can ameliorate GABAe rgic synaptic function by activating the PI3K/Akt signal pathway,which may contribute to the improvement of dendritic spine abnormalities in autism spectrum disorders.

Research on the Effect of Dance Therapy on Improving Social Communication Ability of Children with Autism

Research motivation:Through the 12 weeks dance therapy intervention for children with autism,the purpose is to explore the intervention model of dance therapy for children with autism and the changes in motor ability,social ability,and communication ability of children with autism after dance therapy intervention.The results of the research are expected to expand the intervention mode of dance therapy in my country and provide practical reference for rehabilitation intervention of children with autism.Research methods:24 autistic boys aged 6 to 12 with mild to moderate symptoms were recruited and screened through the Internet as the subjects of this study.We randomly divided them into experimental group(N=12)and control group(N=12).All children with autism have an autism diagnosis certificate issued by Children’s Hospital or a tertiary hospital,excluding other mental diseases(such as epilepsy,major physical disability,mental illness,no history of drugs and other interventions,etc.).We used the paired sample t-test to compare the score difference between the dance treatment group and the control group before and after the two groups,and used the observation method to record the basic communication behavior and the number of active communication behaviors in the experimental group during the intervention process.All data analysis is used in SPSS 20.0.Research results:After 12 weeks of dance therapy intervention,there were statistically significant differences in the gross movement,balance,and coordination abilities of the children in the experimental group compared with those before the intervention(p<0.01).There was no significant difference between the children in the control group(p>0.05).After 12 weeks of dance therapy intervention,there were statistically significant differences in the scores of the social response scale for children with autism in the experimental group(p<0.05).There was no significant change in the scores of each item of the SRS scale before and after intervention in the control group and the dance treatment group(p>0.05).

Nutritional epigenetics education improves diet and attitude of parents of children with autism or attention deficit/hyperactivity disorder

BACKGROUND Unhealthy maternal diet leads to heavy metal exposures from the consumption of ultra-processed foods that may impact gene behavior across generations,creating conditions for the neurodevelopmental disorders known as autism and attention deficit/hyperactivity disorder(ADHD).Children with these disorders have difficulty metabolizing and excreting heavy metals from their bloodstream,and the severity of their symptoms correlates with the heavy metal levels measured in their blood.Psychiatrists may play a key role in helping parents reduce their ultra-processed food and dietary heavy metal intake by providing access to effective nutritional epigenetics education.AIM To test the efficacy of nutritional epigenetics instruction in reducing parental ultra-processed food intake.METHODS The study utilized a semi-randomized test and control group pretest-posttest pilot study design with participants recruited from parents having a learning-disabled child with autism or ADHD.Twenty-two parents who met the inclusion criteria were randomly selected to serve in the test(n=11)or control(n=11)group.The test group participated in the six-week online nutritional epigenetics tutorial,while the control group did not.The efficacy of the nutritional epigenetics instruction was determined by measuring changes in parent diet and attitude using data derived from an online diet survey administered to the participants during the pre and post intervention periods.Diet intake scores were derived for both ultra-processed and whole/organic foods.Paired sample t-tests were conducted to determine any differences in mean diet scores within each group.RESULTS There was a significant difference in the diet scores of the test group between the pre-and post-intervention periods.The parents in the test group significantly reduced their intake of ultra-processed foods with a preintervention diet score of 70(mean=5.385,SD=2.534)and a post-intervention diet score of 113(mean=8.692,SD=1.750)and the paired t-test analysis showing a significance of P<0.001.The test group also significantly increased their consumption of whole and/or organic foods with a pre-intervention diet score of 100(mean=5.882,SD=2.472)and post-intervention diet score of 121(mean=7.118,SD=2.390)and the paired t-test analysis showing a significance of P<0.05.CONCLUSION Here we show nutritional epigenetics education can be used to reduce ultra-processed food intake and improve attitude among parents having learning-disabled children with autism or ADHD.

Des-Arg(9)bradykinin as a causal metabolite for autism spectrum disorder

BACKGROUND Early diagnosis and therapeutic interventions can greatly enhance the developmental trajectory of children with autism spectrum disorder(ASD).However,the etiology of ASD is not completely understood.The presence of confounding factors from environment and genetics has increased the difficulty of the identification of diagnostic biomarkers for ASD.AIM To estimate and interpret the causal relationship between ASD and metabolite profile,taking into consideration both genetic and environmental influences.METHODS A two-sample Mendelian randomization(MR)analysis was conducted using summarized data from large-scale genome-wide association studies(GWAS)including a metabolite GWAS dataset covering 453 metabolites from 7824 European and an ASD GWAS dataset comprising 18381 ASD cases and 27969 healthy controls.Metabolites in plasma were set as exposures with ASD as the main outcome.The causal relationships were estimated using the inverse variant weight(IVW)algorithm.We also performed leave-one-out sensitivity tests to validate the robustness of the results.Based on the drafted metabolites,enrichment analysis was conducted to interpret the association via constructing a protein-protein interaction network with multi-scale evidence from databases including Infinome,SwissTargetPrediction,STRING,and Metascape.RESULTS Des-Arg(9)-bradykinin was identified as a causal metabolite that increases the risk of ASD(β=0.262,SE=0.064,P_(IVW)=4.64×10^(-5)).The association was robust,with no significant heterogeneity among instrument variables(P_(MR Egger)=0.663,P_(IVW)=0.906)and no evidence of pleiotropy(P=0.949).Neuroinflammation and the response to stimulus were suggested as potential biological processes mediating the association between Des-Arg(9)bradykinin and ASD.CONCLUSION Through the application of MR,this study provides practical insights into the potential causal association between plasma metabolites and ASD.These findings offer perspectives for the discovery of diagnostic or predictive biomarkers to support clinical practice in treating ASD.

Evaluation of Clinician Training in Autism Screening, Care Management, and Patient Education

Objective: The demand for pediatric developmental evaluations has far exceeded the workforce available to perform them, which creates long significant wait times for services. A year-long clinician training using the Extension for Community Healthcare Outcomes (ECHO®) model with monthly meetings was conducted and evaluated for its impact on primary care clinicians’ self-reported self-efficacy, ability to administer autism screening and counsel families, professional fulfillment, and burnout. Methods: Participants represented six community health centers and a hospital-based practice. Data collection was informed by participant feedback and the Normalization Process Theory via online surveys and focus groups/interviews. Twelve virtual monthly trainings were delivered between November 2020 and October 2021. Results: 30 clinicians participated in data collection. Matched analyses (n = 9) indicated statistically significant increase in self-rated ability to counsel families about autism (Pre-test Mean = 3.00, Post-test Mean = 3.89, p = 0.0313), manage autistic patients’ care (Pre-test Mean = 2.56, Post-test Mean = 4.11, p = 0.0078), empathy toward patients (Pre-test Mean = 2.11, Post-test Mean = 1.22, p = 0.0156) and colleagues (Pre-test Mean = 2.33, Post-test Mean = 1.22, respectively, p = 0.0391). Unmatched analysis revealed increases in participants confident about educating patients about autism (70.59%, post-test n = 12 vs. 3.33%, pre-test n = 1, p = 0.0019). Focus groups found increased confidence in using the term “autism”. Conclusion: Participants reported increases in ability and confidence to care for autistic patients, as well as empathy toward patients and colleagues. Future research should explore long-term outcomes in participants’ knowledge retention, confidence in practice, and improvements to autism evaluations and care.

Metabolomic changes in children with autism

BACKGROUND Autism spectrum disorder(ASD)is a neurodevelopmental condition characterized by deficits in social communication and repetitive behaviors.Metabolomic profiling has emerged as a valuable tool for understanding the underlying metabolic dysregulations associated with ASD.AIM To comprehensively explore metabolomic changes in children with ASD,integrating findings from various research articles,reviews,systematic reviews,meta-analyses,case reports,editorials,and a book chapter.METHODS A systematic search was conducted in electronic databases,including PubMed,PubMed Central,Cochrane Library,Embase,Web of Science,CINAHL,Scopus,LISA,and NLM catalog up until January 2024.Inclusion criteria encompassed research articles(83),review articles(145),meta-analyses(6),systematic reviews(6),case reports(2),editorials(2),and a book chapter(1)related to metabolomic changes in children with ASD.Exclusion criteria were applied to ensure the relevance and quality of included studies.RESULTS The systematic review identified specific metabolites and metabolic pathways showing consistent differences in children with ASD compared to typically developing individuals.These metabolic biomarkers may serve as objective measures to support clinical assessments,improve diagnostic accuracy,and inform personalized treatment approaches.Metabolomic profiling also offers insights into the metabolic alterations associated with comorbid conditions commonly observed in individuals with ASD.CONCLUSION Integration of metabolomic changes in children with ASD holds promise for enhancing diagnostic accuracy,guiding personalized treatment approaches,monitoring treatment response,and improving outcomes.Further research is needed to validate findings,establish standardized protocols,and overcome technical challenges in metabolomic analysis.By advancing our understanding of metabolic dysregulations in ASD,clinicians can improve the lives of affected individuals and their families.

Faith and Belief in Autism in Cote d’Ivoire: About Judith, God’s Strange Gift

Faced with autism, motherhood and parenthood are turned upside down in many ways. Coping with stress and mental health problems, continuing to assume a rewarding parental role and finding suitable care are the trials and tribulations that mark out the journey of African parents. Faith and belief have been described as providing meaning and coping mechanisms in the frightening ordeal of disability. An encounter with a young girl and her parents provided an opportunity to analyse the mother’s experience and the impact of beliefs and discourses on her commitment to care. Based on this clinical story, we discuss the place of other-actors (parents and carers) and the Other-God in relation to the psychopathological dynamics of the mother.

Pre-autism:What a paediatrician should know about early diagnosis of autism

Autism,also known as an autism spectrum disorder,is a complex neurodevelopmental disorder usually diagnosed in the first three years of a child's life.A range of symptoms characterizes it and can be diagnosed at any age,including adolescence and adulthood.However,early diagnosis is crucial for effective management,prognosis,and care.Unfortunately,there are no established fetal,prenatal,or newborn screening programs for autism,making early detection difficult.This review aims to shed light on the early detection of autism prenatally,natally,and early in life,during a stage we call as“pre-autism”when typical symptoms are not yet apparent.Some fetal,neonatal,and infant biomarkers may predict an increased risk of autism in the coming baby.By developing a biomarker array,we can create an objective diagnostic tool to diagnose and rank the severity of autism for each patient.These biomarkers could be genetic,immunological,hormonal,metabolic,amino acids,acute phase reactants,neonatal brainstem function biophysical activity,behavioral profile,body measurements,or radiological markers.However,every biomarker has its accuracy and limitations.Several factors can make early detection of autism a real challenge.To improve early detection,we need to overcome various challenges,such as raising community awareness of early signs of autism,improving access to diagnostic tools,reducing the stigma attached to the diagnosis of autism,and addressing various culturally sensitive concepts related to the disorder.

Play therapy in children with autism:Its role,implications,and limitations

Play is a pleasurable physical or mental activity that enhances the child’s skills involving negotiation abilities,problem-solving,manual dexterity,sharing,decision-making,and working in a group.Play affects all the brain's areas,structures,and functions.Children with autism have adaptive behavior,adaptive response,and social interaction limitations.This review explores the different applications of play therapy in helping children with autism disorder.Play is usually significantly impaired in children with autism.Play therapy is mainly intended to help children to honor their unique mental abilities and developmental levels.The main aim of play therapy is to prevent or solve psychosocial difficulties and achieve optimal child-healthy growth and development.Play therapy helps children with autism to engage in play activities of their interest and choice to express themselves in the most comfortable ways.It changes their way of self-expression from unwanted behaviors to more non-injurious expressive behavior using toys or activities of their choice as their words.Play therapy also helps those children to experience feeling out various interaction styles.Every child with autism is unique and responds differently.Therefore,different types of intervention,like play therapy,could fit the differences in children with autism.Proper evaluation of the child is mandatory to evaluate which type fits the child more than the others.This narrative review revised the different types of play therapy that could fit children with autism in an evidence-based way.Despite weak evidence,play therapy still has potential benefits for patients and their families.

Autism的本质理解及翻译问题研究

心理学概念autism有两个汉语译名:孤独症与自闭症。两个译名同时并用,造成了不同程度的混乱和误解。从词源学翻译及理论史双重视角看,autism的本质及合适译名不是孤独症,而是自闭症。孤独症是错误的意译,不符合autism的原始含义,易将其本质误解为极度孤独或依恋障碍。自闭症译名更能反映autism的本义,更符合《精神障碍诊断与统计手册》诊断体系对autism的临床描述,即以自我封闭为根本特征的社交障碍。因此,学界应当放弃孤独症译名,只用自闭症来翻译和理解autism,以避免不正确的病因学解释及一词两译带来的其他问题。

Conditional Generative Adversarial Network Approach for Autism Prediction

Autism Spectrum Disorder(ASD)requires a precise diagnosis in order to be managed and rehabilitated.Non-invasive neuroimaging methods are disease markers that can be used to help diagnose ASD.The majority of available techniques in the literature use functional magnetic resonance imaging(fMRI)to detect ASD with a small dataset,resulting in high accuracy but low generality.Traditional supervised machine learning classification algorithms such as support vector machines function well with unstructured and semi structured data such as text,images,and videos,but their performance and robustness are restricted by the size of the accompanying training data.Deep learning on the other hand creates an artificial neural network that can learn and make intelligent judgments on its own by layering algorithms.It takes use of plentiful low-cost computing and many approaches are focused with very big datasets that are concerned with creating far larger and more sophisticated neural networks.Generative modelling,also known as Generative Adversarial Networks(GANs),is an unsupervised deep learning task that entails automatically discovering and learning regularities or patterns in input data in order for the model to generate or output new examples that could have been drawn from the original dataset.GANs are an exciting and rapidly changingfield that delivers on the promise of generative models in terms of their ability to generate realistic examples across a range of problem domains,most notably in image-to-image translation tasks and hasn't been explored much for Autism spectrum disorder prediction in the past.In this paper,we present a novel conditional generative adversarial network,or cGAN for short,which is a form of GAN that uses a generator model to conditionally generate images.In terms of prediction and accuracy,they outperform the standard GAN.The pro-posed model is 74%more accurate than the traditional methods and takes only around 10 min for training even with a huge dataset.

Pharmacotherapy in autism spectrum disorders,including promising older drugs warranting trials

Available pharmacotherapies for autism spectrum disorders(ASD)are reviewed based on clinical and research experience,highlighting some older drugs with emerging evidence.Several medications show efficacy in ASD,though controlled studies in ASD are largely lacking.Only risperidone and aripiprazole have Federal Drug Administration approval in the United States.Methylphenidate(MPH)studies showed lower efficacy and tolerability for attention deficit hyperactivity disorder(ADHD)than in the typically developing(TD)population;atomoxetine demonstrated lower efficacy but comparable tolerability to TD outcomes.Guanfacine improved hyperactivity in ASD comparably to TD.Dextroamphetamine promises greater efficacy than MPH in ASD.ADHD medications reduce impulsive aggression in youth,and may also be key for this in adults.Controlled trials of the selective serotonin reuptake inhibitors citalopram and fluoxetine demonstrated poor tolerability and lack of efficacy for repetitive behaviors.Trials of antiseizure medications in ASD remain inconclusive,however clinical trials may be warranted in severely disabled individuals showing bizarre behaviors.No identified drugs treat ASD core symptoms;oxytocin lacked efficacy.Amitriptyline and loxapine however,show promise.Loxapine at 5-10 mg daily resembled an atypical antipsychotic in positron emission tomography studies,but may be weight-sparing.Amitriptyline at approximately 1 mg/kg/day used cautiously,shows efficacy for sleep,anxiety,impulsivity and ADHD,repetitive behaviors,and enuresis.Both drugs have promising neurotrophic properties.

Higher rates of autism and attention deficit/hyperactivity disorder in American children:Are food quality issues impacting epigenetic inheritance?

In the United States,schools offer special education services to children who are diagnosed with a learning or neurodevelopmental disorder and have difficulty meeting their learning goals.Pediatricians may play a key role in helping children access special education services.The number of children ages 6-21 in the United States receiving special education services increased 10.4%from 2006 to 2021.Children receiving special education services under the autism category increased 242%during the same period.The demand for special education services for children under the developmental delay and other health impaired categories increased by 184%and 83%respectively.Although student enrollment in American schools has remained stable since 2006,the percentage distribution of children receiving special education services nearly tripled for the autism category and quadrupled for the developmental delay category by 2021.Allowable heavy metal residues remain persistent in the American food supply due to food ingredient manufacturing processes.Numerous clinical trial data indicate heavy metal exposures and poor diet are the primary epigenetic factors responsible for the autism and attention deficit hyperactivity disorder epidemics.Dietary heavy metal exposures,especially inorganic mercury and lead may impact gene behavior across generations.In 2021,the United States Congress found heavy metal residues problematic in the American food supply but took no legislative action.Mandatory health warning labels on select foods may be the only way to reduce dietary heavy metal exposures and improve child learning across generations.

Role of gastrointestinal health in managing children with autism spectrum disorder

Children with autism spectrum disorders(ASD)or autism are more prone to gastrointestinal(GI)disorders than the general population.These disorders can significantly affect their health,learning,and development due to various factors such as genetics,environment,and behavior.The causes of GI disorders in children with ASD can include gut dysbiosis,immune dysfunction,food sensitivities,digestive enzyme deficiencies,and sensory processing differences.Many studies suggest that numerous children with ASD experience GI problems,and effective management is crucial.Diagnosing autism is typically done through genetic,neurological,functional,and behavioral assessments and observations,while GI tests are not consistently reliable.Some GI tests may increase the risk of developing ASD or exacerbating symptoms.Addressing GI issues in individuals with ASD can improve their overall well-being,leading to better behavior,cognitive function,and educational abilities.Proper management can improve digestion,nutrient absorption,and appetite by relieving physical discomfort and pain.Alleviating GI symptoms can improve sleep patterns,increase energy levels,and contribute to a general sense of well-being,ultimately leading to a better quality of life for the individual and improved family dynamics.The primary goal of GI interventions is to improve nutritional status,reduce symptom severity,promote a balanced mood,and increase patient independence.

Recent advancements in noninvasive brain modulation for individuals with autism spectrum disorder

Autism spectrum disorder is classified as a spectrum of neurodevelopmental disorders with an unknown definitive etiology.Individuals with autism spectrum disorder show deficits in a variety of areas including cognition,memory,attention,emotion recognition,and social skills.With no definitive treatment or cure,the main interventions for individuals with autism spectrum disorder are based on behavioral modulations.Recently,noninvasive brain modulation techniques including repetitive transcranial magnetic stimulation,intermittent theta burst stimulation,continuous theta burst stimulation,and transcranial direct current stimulation have been studied for their therapeutic properties of modifying neuroplasticity,particularly in individuals with autism spectrum disorder.Preliminary evidence from small cohort studies,pilot studies,and clinical trials suggests that the various noninvasive brain stimulation techniques have therapeutic benefits for treating both behavioral and cognitive manifestations of autism spectrum disorder.However,little data is available for quantifying the clinical significance of these findings as well as the long-term outcomes of individuals with autism spectrum disorder who underwent transcranial stimulation.The objective of this review is to highlight the most recent advancements in the application of noninvasive brain modulation technology in individuals with autism spectrum disorder.

Associations between meeting 24-hour movement guidelines and quality of life among children and adolescents with autism spectrum disorder

Background:The Canadian 24-hour movement behavior(24-HMB)guidelines suggest that a limited amount of screen time use,an adequate level of physical activity(PA),and sufficient sleep duration are beneficial for ensuring and optimizing the health and quality of life(QoL)of children and adolescents.However,this topic has yet to be examined for children and adolescents with autism spectrum disorder(ASD)specifically.The aim of this cross-sectional observational study was to examine the associations between meeting 24-HMB guidelines and several QoLrelated indicators among a national sample of American children and adolescents with ASD.Methods:Data were taken from the 2020 U.S.National Survey of Children’s Health dataset.Participants(n=956)aged 617 years and currently diagnosed with ASD were included.The exposure of interest was adherence to the 24-HMB guidelines.Outcomes were QoL indicators,including learning interest/curiosity,repeating grades,adaptive ability,victimization by bullying,and behavioral problems.Categorical variables were described with unweighted sample counts and weighted percentages.Age,sex,race,preterm birth status,medication,behavioral treatment,household poverty level,and the educational level of the primary caregivers were included as covariates.Odds ratio(OR)and 95%confidence interval(95%CI)were used to present the strength of association between adherence to 24-HMB guidelines and QoL-related indicators.Results:Overall,452 participants(45.34%)met 1 of the 3 recommendations,216(22.65%)met 2 recommendations,whereas only 39 participants(5.04%)met all 3 recommendations.Compared with meeting none of the recommendations,meeting both sleep duration and PA recommendations(OR=3.92,95%CI:1.639.48,p<0.001)or all 3 recommendations(OR=2.11,95%CI:1.034.35,p=0.04)was associated with higher odds of showing learning interest/curiosity.Meeting both screen time and PA recommendations(OR=0.15,95%CI:0.040.61,p<0.05)or both sleep duration and PA recommendations(OR=0.24,95%CI:0.070.87,p<0.05)was associated with lower odds of repeating any grades.With respect to adaptive ability,participants who met only the PA recommendation of the 24-HMB were less likely to have difficulties dressing or bathing(OR=0.11,95%CI:0.020.66,p<0.05)than those who did not.For participants who met all 3 recommendations(OR=0.38,95%CI:0.150.99,p=0.05),the odds of being victimized by bullying was lower.Participants who adhered to both sleep duration and PA recommendations were less likely to present with severe behavioral problems(OR=0.17,95%CI:0.040.71,p<0.05)than those who did not meet those guidelines.Conclusion:Significant associations were found between adhering to 24-HMB guidelines and selected QoL indicators.These findings highlight the importance of maintaining a healthy lifestyle as a key factor in promoting and preserving the QoL of children with ASD.

Diagnosis of Autism Spectrum Disorder by Imperialistic Competitive Algorithm and Logistic Regression Classifier

Autism spectrum disorder(ASD),classified as a developmental disability,is now more common in children than ever.A drastic increase in the rate of autism spectrum disorder in children worldwide demands early detection of autism in children.Parents can seek professional help for a better prognosis of the child’s therapy when ASD is diagnosed under five years.This research study aims to develop an automated tool for diagnosing autism in children.The computer-aided diagnosis tool for ASD detection is designed and developed by a novel methodology that includes data acquisition,feature selection,and classification phases.The most deterministic features are selected from the self-acquired dataset by novel feature selection methods before classification.The Imperialistic competitive algorithm(ICA)based on empires conquering colonies performs feature selection in this study.The performance of Logistic Regression(LR),Decision tree,K-Nearest Neighbor(KNN),and Random Forest(RF)classifiers are experimentally studied in this research work.The experimental results prove that the Logistic regression classifier exhibits the highest accuracy for the self-acquired dataset.The ASD detection is evaluated experimentally with the Least Absolute Shrinkage and Selection Operator(LASSO)feature selection method and different classifiers.The Exploratory Data Analysis(EDA)phase has uncovered crucial facts about the data,like the correlation of the features in the dataset with the class variable.

Jellyfish Search Optimization with Deep Learning Driven Autism Spectrum Disorder Classification

Autism spectrum disorder(ASD)is regarded as a neurological disorder well-defined by a specific set of problems associated with social skills,recurrent conduct,and communication.Identifying ASD as soon as possible is favourable due to prior identification of ASD permits prompt interferences in children with ASD.Recognition of ASD related to objective pathogenicmutation screening is the initial step against prior intervention and efficient treatment of children who were affected.Nowadays,healthcare and machine learning(ML)industries are combined for determining the existence of various diseases.This article devises a Jellyfish Search Optimization with Deep Learning Driven ASD Detection and Classification(JSODL-ASDDC)model.The goal of the JSODL-ASDDC algorithm is to identify the different stages of ASD with the help of biomedical data.The proposed JSODLASDDC model initially performs min-max data normalization approach to scale the data into uniform range.In addition,the JSODL-ASDDC model involves JSO based feature selection(JFSO-FS)process to choose optimal feature subsets.Moreover,Gated Recurrent Unit(GRU)based classification model is utilized for the recognition and classification of ASD.Furthermore,the Bacterial Foraging Optimization(BFO)assisted parameter tuning process gets executed to enhance the efficacy of the GRU system.The experimental assessment of the JSODL-ASDDC model is investigated against distinct datasets.The experimental outcomes highlighted the enhanced performances of the JSODL-ASDDC algorithm over recent approaches.

Automated Autism Spectral Disorder Classification Using Optimal Machine Learning Model

Autism Spectrum Disorder (ASD) refers to a neuro-disorder wherean individual has long-lasting effects on communication and interaction withothers.Advanced information technologywhich employs artificial intelligence(AI) model has assisted in early identify ASD by using pattern detection.Recent advances of AI models assist in the automated identification andclassification of ASD, which helps to reduce the severity of the disease.This study introduces an automated ASD classification using owl searchalgorithm with machine learning (ASDC-OSAML) model. The proposedASDC-OSAML model majorly focuses on the identification and classificationof ASD. To attain this, the presentedASDC-OSAML model follows minmaxnormalization approach as a pre-processing stage. Next, the owl searchalgorithm (OSA)-based feature selection (OSA-FS) model is used to derivefeature subsets. Then, beetle swarm antenna search (BSAS) algorithm withIterative Dichotomiser 3 (ID3) classification method was implied for ASDdetection and classification. The design of BSAS algorithm helps to determinethe parameter values of the ID3 classifier. The performance analysis of theASDC-OSAML model is performed using benchmark dataset. An extensivecomparison study highlighted the supremacy of the ASDC-OSAML modelover recent state of art approaches.