• International Journal of Computer Science & Network Security
• /
• 제23권4호
• /
• pp.179-186
• /
• 2023

For the future prosperity of any society, the sound growth of children is essential. Autism Spectrum Disorder (ASD) is a neurobehavioral disorder which has an impact on social interaction of autistic child and has an undesirable effect on his learning, speaking, and responding skills. These children have over or under sensitivity issues of touching, smelling, and hearing. Its symptoms usually appear in the child of 4- to 11-year-old but parents did not pay attention to it and could not detect it at early stages. The process to diagnose in recent time is clinical sessions that are very time consuming and expensive. To complement the conventional method, machine learning techniques are being used. In this way, it improves the required time and precision for diagnosis. We have applied TFLite model on image based dataset to predict the autism based on facial features of child. Afterwards, various machine learning techniques were trained that includes Logistic Regression, KNN, Gaussian Naïve Bayes, Random Forest and Multi-Layer Perceptron using Autism Spectrum Quotient (AQ) dataset to improve the accuracy of the ASD detection. On image based dataset, TFLite model shows 80% accuracy and based on AQ dataset, we have achieved 100% accuracy from Logistic Regression and MLP models.

• 말소리와 음성과학
• /
• 제15권2호
• /
• pp.53-59
• /
• 2023

Detection of children with autism spectrum disorder (ASD) based on speech has relied on predefined feature sets due to their ease of use and the capabilities of speech analysis. However, clinical impressions may not be adequately captured due to the broad range and the large number of features included. This paper demonstrates that the knowledge-driven speech features (KDSFs) specifically tailored to the speech traits of ASD are more effective and efficient for detecting speech of ASD children from that of children with typical development (TD) than a predefined feature set, extended Geneva Minimalistic Acoustic Standard Parameter Set (eGeMAPS). The KDSFs encompass various speech characteristics related to frequency, voice quality, speech rate, and spectral features, that have been identified as corresponding to certain of their distinctive attributes of them. The speech dataset used for the experiments consists of 63 ASD children and 9 TD children. To alleviate the imbalance in the number of training utterances, a data augmentation technique was applied to TD children's utterances. The support vector machine (SVM) classifier trained with the KDSFs achieved an accuracy of 91.25%, surpassing the 88.08% obtained using the predefined set. This result underscores the importance of incorporating domain knowledge in the development of speech technologies for individuals with disorders.

• ETRI Journal
• /
• 제44권4호
• /
• pp.613-623
• /
• 2022

Autism spectrum disorder (ASD) is a developmental disorder associated with cognitive and neurobehavioral disorders. It affects the person's behavior and performance. Autism affects verbal and non-verbal communication in social interactions. Early screening and diagnosis of ASD are essential and helpful for early educational planning and treatment, the provision of family support, and for providing appropriate medical support for the child on time. Thus, developing automated methods for diagnosing ASD is becoming an essential need. Herein, we investigate using various machine learning methods to build predictive models for diagnosing ASD in children using facial images. To achieve this, we used an autistic children dataset containing 2936 facial images of children with autism and typical children. In application, we used classical machine learning methods, such as support vector machine and random forest. In addition to using deep-learning methods, we used a state-of-the-art method, that is, automated machine learning (AutoML). We compared the results obtained from the existing techniques. Consequently, we obtained that AutoML achieved the highest performance of approximately 96% accuracy via the Hyperpot and tree-based pipeline optimization tool optimization. Furthermore, AutoML methods enabled us to easily find the best parameter settings without any human efforts for feature engineering.

• Clinical and Experimental Pediatrics
• /
• 제64권7호
• /
• pp.339-340
• /
• 2021

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• 제31권3호
• /
• pp.105-120
• /
• 2020

Although autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by social impairments, patients with ASD frequently manifest atypical sensory behaviors. Recently, atypical sensory perception in ASD has received much attention, yet little is known about its cause or neurobiology. Herein, we review the findings from neuroimaging studies related to visual perception in ASD. Specifically, we examined the neural underpinnings of visual detection, motion perception, and face processing in ASD. Results from neuroimaging studies indicate that atypical visual perception in ASD may be influenced by attention or higher order cognitive mechanisms, and atypical face perception may be affected by disrupted social brain network. However, there is considerable evidence for atypical early visual processing in ASD. It is likely that visual perceptual abnormalities are independent of deficits of social functions or cognition. Importantly, atypical visual perception in ASD may enhance difficulties in dealing with complex and subtle social stimuli, or improve outstanding abilities in certain fields in individuals with Savant syndrome. Thus, future research is required to elucidate the characteristics and neurobiology of autistic visual perception to effectively apply these findings in the interventions of ASD.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• 제30권4호
• /
• pp.145-152
• /
• 2019

Objectives: The detection of autism spectrum disorder (ASD) is based on behavioral observations. To build a more objective datadriven method for screening and diagnosing ASD, many studies have attempted to incorporate artificial intelligence (AI) technologies. Therefore, the purpose of this literature review is to summarize the studies that used AI in the assessment process and examine whether other behavioral data could potentially be used to distinguish ASD characteristics. Methods: Based on our search and exclusion criteria, we reviewed 13 studies. Results: To improve the accuracy of outcomes, AI algorithms have been used to identify items in assessment instruments that are most predictive of ASD. Creating a smaller subset and therefore reducing the lengthy evaluation process, studies have tested the efficiency of identifying individuals with ASD from those without. Other studies have examined the feasibility of using other behavioral observational features as potential supportive data. Conclusion: While previous studies have shown high accuracy, sensitivity, and specificity in classifying ASD and non-ASD individuals, there remain many challenges regarding feasibility in the real-world that need to be resolved before AI methods can be fully integrated into the healthcare system as clinical decision support systems.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• 제18권2호
• /
• pp.123-129
• /
• 2007

Objectives: Autism is a complex neurodevelopmental spectrum disorder with a strong genetic component. Previous neurochemical and genetic studies have suggested the possible involvement of the serotonin system in autism. Tryptophan 2,3-dioxygenase(TDO2) is the rate-limiting enzyme in the catabolism of tryptophan, which is the precursor of serotonin synthesis. The aim of this study was to investigate the association between the TDO2 gene and autism spectrum disorders(ASD) in a Korean population. Methods: The patients were diagnosed with ASD on the basis of the DSM-IV diagnostic classification outlined in the Korean version of the Autism Diagnostic Interview-Revised and Autism Diagnostic Observation Schedule. The present study included the detection of four single nucleotide polymorphisms(SNPs) in the TDO2 gene(rs2292536, rs6856558, rs6830072, rs6830800) and the family-based association analysis of the single nucleotide polymorphisms in Korean ASD trios using a transmission disequilibrium test(TDT) and haplotype analysis. The family trios of 136 probands were included in analysis. 87.5% were male and 86.0% were diagnosed with autism. The mean age of the probands was $78.5{\pm}35.8$ months(range: 26-264 months). Results: Two SNPs showed no polymorphism, and there was no significant difference in transmission in the other two SNPs. We also could not find any significant transmission in the haplotype analysis(p>.05). Conclusion: We could not find any significant statistical association between the transmission of SNPs in the TDO2 gene and ASD in a Korean population. This result may not support the possible involvement of the TDO2 gene in the development of ASD, and further exploration might be needed to investigate other plausible SNP sites.

• 생물정신의학
• /
• 제13권4호
• /
• pp.289-298
• /
• 2006

목 적: 본 연구의 목적은 자폐스펙트럼장애를 가진 아동들과 그 부모로 이루어진 trio를 대상으로 이 장애와 NMDA 수용체 유전자, 그 가운데 GRIN2B 유전자와의 관련성을 규명하고자 하는 것이다. 방 법: 발달지연을 주소로 가천의대 길병원과 경상대학교병원 소아정신과 외래를 내원한 아동을 선별 대상으로 하였다. DSM-IV 진단체계를 이용하여 2명의 소아정신과 의사가 자폐 스펙트럼 장애로 진단한 아동이 일차적인 연구 대상으로 선별되었다. 선별된 아동과 부모들에게는 한국판 자폐증 진단 관찰 스케줄(Autism Diagnostic Observation Schedule, 이하 ADOS) 및 자폐증 진단 면담-개정판(Autism Diagnostic Interview-Revised, 이하 ADI-R)를 실시하였다. PCR-RFLP법을 이용, GRIN2B 유전자에서 모두 4개의 단일 염기 다형성을 분석하였다(rs7301328, rs1806201, rs1805247, rs1805502). 각각의 SNPs에 대한 allelic association 을 평가하기 위하여 TDT 방법이 시행되었으며, 이를 통해 자폐장애 아동이 부모로부터 후보유전자의 특정 alleles들을 유의하게 더 많이 전달받았는지의 여부를 관찰한 뒤 McNemar chi-square test(df=1)에 의거하여 분석하였다. 결 과: 1) 연구 대상군의 특성 : 총 126명의 자폐 스펙트럼장애 아동과 그들의 생물학적 부모가 최종 분석 대상에 포함되었다. 전체 대상자 중 109명(86.5%)이 남아였으며 여아는 17명(13.5%)으로, 남아 대 여아의 비율은 6.41:1이었다. 대상군의 진단 분포는 자폐장애 107명(85.1%), 달리 분류되지 않는 전반적 발달장애(PDD, NOS) 17명(13.5%), 아스퍼거 씨 장애(Asperger's disorder) 2명(1.6%)이었다. 대상군 아동의 평균 연령은 $71.9{\pm}31.6$개월(range : 26~185개월)이었으며 한국판 사회성숙도 검사로 측정된 평균 사회지수(Social Quotient)는 $61.2{\pm}20.6$(range : 23.1~126), 측정 가능한 아동들의 평균 지능은 $65.0{\pm}27.7$(range : 25~126)이었다. K-CARS 점수는 $31.5{\pm}5.4$(range 18.5~46)로 나타났다. 2) 유전자 분석 : 분석한 GRIN2B 유전자의 4개 SNPs 가운데 하나의 SNP(rs1805247)에서 의미 있는 allelic transmission의 차이를 보였다. 이 SNP에서 transmission ratio(transmitted alleles/non-transmitted alleles)는 A allele과 G allele에서 각각 2.03과 .49로, A allele이 G allele에 비해 부모로부터 환자군에게 더 빈번하게 전달(preferential transmission) 되었음이 확인되었다(TDT ${\chi}^2$=12.89, p=.0003). 이는 Bonferroni correction 후에도 여전히 유의미한 수준을 유지하였다(p=.0009). 기타 3개의 SNP(rs7301328, rs1806201, rs1805502) 들에서는 의미 있는 transmission의 차이가 나타나지 않았다(p<.05). 결 론: 본 연구에서 GRIN2B 유전자의 단일유전자 다형성과 자폐스펙트럼장애 사이에 유의한 연관성을 보였다. 이는 glutamate NMDA 2B수용체 유전자가 이 질환의 발생에 관여할 가능성을 시사하는 것이라 생각된다.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• 제28권2호
• /
• pp.96-105
• /
• 2017

Objectives: The purpose of this study is to investigate the professional knowledge and perceptions of the early screening of Autism Spectrum Disorder (ASD) in practitioners who have contact with patients with ASD. Methods: A survey was carried out among 674 practitioners in total, where practitioners are defined as those who work at primary medical centers, public institutions, educational institutions and treatment institutions. The survey was carried out both online and offline, and it mainly focused on 1) knowledge about ASD symptoms, 2) knowledge about the early screening of ASD, 3) measures taken after ASD detection, 4) thoughts on the development of early screening tools for ASD, and 5) the current status of ASD treatment. The data collected were analyzed through descriptive statistics, analysis of frequency and cross tabulation analysis using SPSS WIN 22.0. Results: The results of this study suggest that the practitioners were not aware of the exact symptoms of ASD and their professional knowledge and the environment for early screening were insufficient. Furthermore, very few and inappropriate measures were taken after the detection of ASD. In addition, there was a high demand for early ASD screening tools to be used on site and, regarding treatment, the significance of the implementation of evidence based treatments as well as the continuity of relevant research came to the fore. Conclusion: It seems that there is a lack of knowledge and perception of the early screening of ASD and that education and training among practitioners is urgently required. This issue is discussed in more detail in the paper.

• 정신신체의학
• /
• 제24권2호
• /
• pp.165-173
• /
• 2016

연구목적 자폐스펙트럼장애에 대한 인식이 높아지면서 진단을 위해 병원에 방문하는 영유아가 늘고 있고 조기 진단을 통한 조기 개입의 중요성이 부각되고 있다. 그러나, 자폐스펙트럼장애 환자가 처음 병원을 방문하게 되는 주 문제가 대부분 발달 지연이기 때문에 지적 장애와의 진단적 구별이 어렵다. 본 연구는 1) 자폐스펙트럼장애와 지적 장애 아동의 인구학적, 임상적 특성 및 산과적 합병증을 비교하고, 2) 초진 시 지적 장애로 진단을 받은 아동 중 재 방문 시 진단이 바뀐 아동과 진단이 유지된 아동의 특징을 비교하고자 한다. 방 법 2001년 5월부터 2014년 12월까지 국민건강보험 일산병원 발달지연클리닉에 내원한 아동 중 자폐스펙트럼 장애나 지적 장애로 진단된 816명의 아동을 대상으로 하였다. 부모 면담을 통해 인구학적, 산과적 합병증에 대해 조사하였다. 인지 평가를 위해 한국 베일리 영유아 발달검사와 한국 웩슬러 유아 지능검사를 시행했고 언어평가를 위해 영유아 언어 발달검사와 취학전 아동 수용언어 표현언어 발달척도I를 시행하였다. 1차 방문에서 자폐스펙트럼장애와 지적 장애로 진단된 아동의 특성을 비교하였고, 1차 방문 시 지적 장애로 진단된 아동 중 2차 방문 시 진단이 자폐스펙트럼장애로 바뀐 아동과 지적 장애로 유지된 아동의 특성을 분석 하였다. 결 과 1차 방문 시 자폐스펙트럼장애와 지적 장애로 진단 받은 아동을 비교한 결과 자폐스펙트럼장애에서 남아의 비율이 높고 산과적 합병증은 적었다. 또한, 자폐스펙트럼장애 아동이 지적 장애 아동에 비해 언어 평가상 전체 수행이 저조 하였고 특히 수용언어발달지수가 더욱 저조하였다. 1차 방문 시 지적 장애로 진단 받은 아동 중 2차 방문 시 진단이 자폐스펙트럼 장애로 바뀐 아동은 모두 남아였고, 지적 장애로 진단이 유지된 아동에 비해 발달 지연의 가족력(family history)이 많았다. 언어 평가 결과에서는 자폐스펙트럼 장애로 진단이 바뀐 아동에서 1차 내원 때 시행한 언어평가에서 수용언어지수가 더 낮은 점수를 보였다. 결 론 이러한 결과를 통해 성별, 언어평가 결과, 산과적 합병증 여부가 자폐스펙트럼장애의 조기 진단에 도움을 줄 수 있음을 알 수 있다.