Search

ASD (autism spectrum disorder) is a complex developmental and neurological disorder that impacts the social life of the affected person by disturbing their capability for interaction and communication. As it is a behavioural disorder, early treatment will improve the quality of life of ASD patients. Traditional screening is carried out with behavioural assessment through trained physicians, which is expensive and time-consuming. To resolve the issue, several conventional methods strive to achieve an effective ASD identification system, but are limited by handling large data sets, accuracy, and speed. Therefore, the proposed identification system employed the MBA (modified bat) algorithm based on ANN (artificial neural networks), modified ANN (modified artificial neural networks), DT (decision tree), and KNN (k-nearest neighbours) for the classification of ASD in children and adolescents. A BA (bat algorithm) is utilised for the automatic zooming capability, which improves the system's efficacy by excellently finding the solutions in the identification system. Conversely, BA is effective in the identification, it still has certain drawbacks like speed, accuracy, and falls into local extremum. Therefore, the proposed identification system modifies the BA optimisation with random perturbation of trends and optimal orientation. The dataset utilised in the respective model is the Q-chat-10 dataset. This dataset contains data of four stages of age groups such as toddlers, children, adolescents, and adults. To analyse the quality of the dataset, dataset evaluation mechanism, such as the Chi-Squared Statistic and p -value, are used in the respective research. The evaluation signifies the relation of the dataset with respect to the proposed model. Further, the performance of the proposed detection system is examined with certain performance metrics to calculate its efficiency. The outcome revealed that the modified ANN classifier model attained an accuracy of 1.00, ensuring improved performance when compared with other state-of-the-art methods. Thus, the proposed model was intended to assist physicians and researchers in enhancing the diagnosis of ASD to improve the standard of life of ASD patients.

Prior studies suggest autism-specific and general developmental screens are complementary for identifying both autism and developmental delay (DD). Parents completed autism and developmental screens before 18-month visits. Children with failed screens for autism (n = 167) and age, gender, and practice-matched children passing screens (n = 241) completed diagnostic evaluations for autism and developmental delay. When referral for autism and/or DD was considered, overall false positives from the autism screens were less frequent than for referral for autism alone. Presence of a failed communication subscale in the developmental screen was a red flag for autism and/or DD. An ordinally-scored autism screen had more favorable characteristics when considering autism and/or DD, yet none of the screens achieved recommended standards at 18 months, reinforcing the need for recurrent screening as autism emerges in early development., (© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

Background: There is a lack of autism screening instruments for deaf or hard of hearing (DHH) adults with intellectual disability., Aims: This study examined the diagnostic validity of the Pervasive Developmental Disorder in Mental Retardation Scale and the Diagnostic Behavioral Assessment for autism spectrum disorder - Revised in this rare population., Methods and Participants: 56 DHH adults with intellectual disability living in three specialized therapeutic communities were examined, 9 of whom met criteria for autism., Outcomes and Results: With minimal adaptions regarding item interpretation, both tools showed good diagnostic and high convergent validity. Items probing for difficulties in reciprocal social interaction and restricted interests were discriminant between individuals with and without autism., Conclusion: These data suggest that both autism screening tools are feasible and psychometrically sound when used with appropriate adaptations for DHH adults with intellectual disability., (Copyright © 2021 Elsevier Ltd. All rights reserved.)

Early screening and diagnosis of autism spectrum disorder (ASD) primarily rely on behavioral observations by qualified clinicians whose decision process can benefit from the combination of machine learning algorithms and sensor data. We designed a computerized visual-orienting task with gaze-related or non-gaze-related directional cues, which triggered participants' gaze-following behavior. Based on their eye-movement data registered by an eye tracker, we applied the machine learning algorithms to classify high-functioning children with ASD (HFA), low-functioning children with ASD (LFA), and typically developing children (TD). We found that TD children had higher success rates in obtaining rewards than HFA children, and HFA children had higher rates than LFA children. Based on raw eye-tracking data, our machine learning algorithm could classify the three groups with an accuracy of 81.1% and relatively high sensitivity and specificity. Classification became worse if only data from the gaze or nongaze conditions were used, suggesting that "less-social" directional cues also carry useful information for distinguishing these groups. Our findings not only provide insights about visual-orienting deficits among children with ASD but also demonstrate the promise of combining classical behavioral paradigms with machine learning algorithms for aiding the screening for individuals with ASD., (© 2021 Institute of Psychology, Chinese Academy of Sciences and John Wiley & Sons Australia, Ltd.)

Objectives: Autism Spectrum Disorder (ASD) is a complex range of neurodegenerative conditions that impact individuals' social behaviour and communication skills. However, ASD data often contains far more controls than cases. This poses a serious challenge when creating classification models due to deriving models that favour controls during the classification of individuals. This problem is known as class imbalance, and it may reduce the performance in classification models derived by machine learning (ML) techniques due to individuals may remain undetected., Methods: ML appears to help in the distressing disorder by improving outcome quality besides speeding up the access to early diagnosis and consequential treatment. A screening dataset that consists of over 1100 instances was used to perform extensive quantitative analysis using different data resampling techniques and according to specific evaluation metrics. We measure the effect of class imbalance on autism screening performance using different data resampling techniques with a ML classifier and with respect to sensitivity, specificity, and F1-measure. We would like to know which resampling methods work well in balancing autism screening data., Results: The results reveal that data resampling, and especially oversampling, improve results derived by the considered ML classifier. More importantly, there was superiority in terms of sensitivity and specificity for models derived by Naive Bayes classifier when oversampling methods have been used for data pre-processing on the autism data considered., Conclusion: The results reported encourages further improvement of the design and implementation of ASD screening systems using intelligent technology.

Autism spectrum symptoms in children with congenital blindness Abstract. Objective: Previous studies reported increased rates of autistic symptoms in children with impaired visual abilities (IV). However, the application of existing screening questionnaires for autism spectrum disorders (ASD) proved problematic, as intact visual abilities are typically required. The current study examines the general applicability of three autism-screening questionnaires in children with congenital blindness. Methods: Autistic symptoms were assessed in 15 children with congenital blindness, 15 children with ASD (without IV), and 20 typically developing controls (aged from 8 to 14 years), using the Social Communication Questionnaire, the Marburg Rating Scale for Asperger's Syndrome, and the Social Responsiveness Scale. Results: Items assessing motor, mimic/gesture-related, or joint attention deficits were identified as highly prevalent in children with congenital blindness. These children scored, in general, higher on ASD-screening questionnaires than typically developing controls but lower than sighted children with ASD. Depending on the screening questionnaire used, between 23 % and 67 % of the sample with congenital blindness reached clinical cutoff scores for ASD. SRS total score was negatively correlated to cognitive empathy and verbal IQ in those children. Conclusions: Mothers of children with congenital blindness reported increased autistic symptoms in ASD-screening questionnaires. ASD and IV might share a broad range of symptoms. Future development and validation of screening instruments specifically adapted to the needs of persons with impaired visual abilities seem necessary.

There are concerns that females with autism spectrum disorders (ASD) may be underidentified because of factors such as better camouflaging and poorer recognition of the signs of ASD in females. One stage at which females may be underidentified is during screening. In this study, we, therefore, evaluated whether the autism spectrum quotient (AQ-10), a brief recommended screening instrument for ASD in adults suspected of having ASD, showed any evidence of underestimating symptoms in females. Our results broadly replicate those of an earlier study in finding no strong evidence that the AQ-10 is biased against females. However, to achieve better performance in females, we suggest that one item be replaced with an item measuring more "female" manifestations of ASD.

Background: Autism spectrum disorder (ASD) diagnosis can be delayed due in part to the time required for administration of standard exams, such as the Autism Diagnostic Observation Schedule (ADOS). Shorter and potentially mobilized approaches would help to alleviate bottlenecks in the healthcare system. Previous work using machine learning suggested that a subset of the behaviors measured by ADOS can achieve clinically acceptable levels of accuracy. Here we expand on this initial work to build sparse models that have higher potential to generalize to the clinical population., Methods: We assembled a collection of score sheets for two ADOS modules, one for children with phrased speech (Module 2; 1319 ASD cases, 70 controls) and the other for children with verbal fluency (Module 3; 2870 ASD cases, 273 controls). We used sparsity/parsimony enforcing regularization techniques in a nested cross validation grid search to select features for 17 unique supervised learning models, encoding missing values as additional indicator features. We augmented our feature sets with gender and age to train minimal and interpretable classifiers capable of robust detection of ASD from non-ASD., Results: By applying 17 unique supervised learning methods across 5 classification families tuned for sparse use of features and to be within 1 standard error of the optimal model, we find reduced sets of 10 and 5 features used in a majority of models. We tested the performance of the most interpretable of these sparse models, including Logistic Regression with L2 regularization or Linear SVM with L1 regularization. We obtained an area under the ROC curve of 0.95 for ADOS Module 3 and 0.93 for ADOS Module 2 with less than or equal to 10 features., Conclusions: The resulting models provide improved stability over previous machine learning efforts to minimize the time complexity of autism detection due to regularization and a small parameter space. These robustness techniques yield classifiers that are sparse, interpretable and that have potential to generalize to alternative modes of autism screening, diagnosis and monitoring, possibly including analysis of short home videos., Competing Interests: Not applicable.Not applicable.Dennis P. Wall is a founder of Cognoa.com, a company focused on building digital solutions for child health.Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

The Mobile Autism Risk Assessment (MARA) is a new, electronically administered, 7-question autism spectrum disorder (ASD) screen to triage those at highest risk for ASD. Children 16 months-17 years (N = 222) were screened during their first visit in a developmental-behavioral pediatric clinic. MARA scores were compared to diagnosis from the clinical encounter. Participant median age was 5.8 years, 76.1 % were male, and most participants had an intelligence/developmental quotient score >85; 69 of the participants (31 %) received a clinical diagnosis of ASD. The sensitivity of the MARA in detecting ASD was 89.9 % [95 % CI = 82.7-97]; the specificity was 79.7 % [95 % CI = 73.4-86.1]. In a high-risk clinical setting, the MARA shows promise as a screen to distinguish ASD from other developmental/behavioral disorders.

Increased public awareness of autism spectrum disorders (ASD) and routine screening in primary care have contributed to increased requests for diagnostic ASD evaluations. However, given the scarcity of subspecialty autism diagnostic resources, overreferral of children suspected of having ASD may be contributing to long waiting lists at tertiary care autism centers and delaying diagnosis for those children who truly have ASD. To determine whether children are being excessively referred to ASD-specific diagnostic clinics, our objective was to determine the prevalence of true ASD diagnoses in children referred for diagnostic ASD evaluation. Charts of all patients referred to a regional autism center between April 2011 and August 2012 for suspicion of a possible ASD were retrospectively reviewed and demographic and clinical diagnoses abstracted. Only 214 of 348 patients evaluated (61%) received an ASD diagnosis. Thus, concerns about autism are not confirmed by an ASD diagnosis in a significant number of children., (© The Author(s) 2015.)

ASD (autism spectrum disorder) is a complex developmental and neurological disorder that impacts the social life of the affected person by disturbing their capability for interaction and communication. As it is a behavioural disorder, early treatment will improve the quality of life of ASD patients. Traditional screening is carried out with behavioural assessment through trained physicians, which is expensive and time-consuming. To resolve the issue, several conventional methods strive to achieve an effective ASD identification system, but are limited by handling large data sets, accuracy, and speed. Therefore, the proposed identification system employed the MBA (modified bat) algorithm based on ANN (artificial neural networks), modified ANN (modified artificial neural networks), DT (decision tree), and KNN (k-nearest neighbours) for the classification of ASD in children and adolescents. A BA (bat algorithm) is utilised for the automatic zooming capability, which improves the system's efficacy by excellently finding the solutions in the identification system. Conversely, BA is effective in the identification, it still has certain drawbacks like speed, accuracy, and falls into local extremum. Therefore, the proposed identification system modifies the BA optimisation with random perturbation of trends and optimal orientation. The dataset utilised in the respective model is the Q-chat-10 dataset. This dataset contains data of four stages of age groups such as toddlers, children, adolescents, and adults. To analyse the quality of the dataset, dataset evaluation mechanism, such as the Chi-Squared Statistic and p-value, are used in the respective research. The evaluation signifies the relation of the dataset with respect to the proposed model. Further, the performance of the proposed detection system is examined with certain performance metrics to calculate its efficiency. The outcome revealed that the modified ANN classifier model attained an accuracy of 1.00, ensuring improved performance when compared with other state-of-the-art methods. Thus, the proposed model was intended to assist physicians and researchers in enhancing the diagnosis of ASD to improve the standard of life of ASD patients. [ABSTRACT FROM AUTHOR]

ASD (autism spectrum disorder) is a complex developmental and neurological disorder that impacts the social life of the affected person by disturbing their capability for interaction and communication. As it is a behavioural disorder, early treatment will improve the quality of life of ASD patients. Traditional screening is carried out with behavioural assessment through trained physicians, which is expensive and time-consuming. To resolve the issue, several conventional methods strive to achieve an effective ASD identification system, but are limited by handling large data sets, accuracy, and speed. Therefore, the proposed identification system employed the MBA (modified bat) algorithm based on ANN (artificial neural networks), modified ANN (modified artificial neural networks), DT (decision tree), and KNN (k-nearest neighbours) for the classification of ASD in children and adolescents. A BA (bat algorithm) is utilised for the automatic zooming capability, which improves the system’s efficacy by excellently finding the solutions in the identification system. Conversely, BA is effective in the identification, it still has certain drawbacks like speed, accuracy, and falls into local extremum. Therefore, the proposed identification system modifies the BA optimisation with random perturbation of trends and optimal orientation. The dataset utilised in the respective model is the Q-chat-10 dataset. This dataset contains data of four stages of age groups such as toddlers, children, adolescents, and adults. To analyse the quality of the dataset, dataset evaluation mechanism, such as the Chi-Squared Statistic and p-value, are used in the respective research. The evaluation signifies the relation of the dataset with respect to the proposed model. Further, the performance of the proposed detection system is examined with certain performance metrics to calculate its efficiency. The outcome revealed that the modified ANN classifier model attained an accuracy of 1.00, ensuring improved performance when compared with other state-of-the-art methods. Thus, the proposed model was intended to assist physicians and researchers in enhancing the diagnosis of ASD to improve the standard of life of ASD patients.

Evolutionary computing algorithms are computational intelligent systems that are used in a wide range of research applications, primarily for optimization. In this paper, an artificial neural network (ANN), a machine learning technique, is used to classify the data. The weights associated with each neuron and the architecture of the neural network always bias the output of the network model. With prior knowledge or trial and error techniques, different metrics or objectives can be used to optimise these weights. The optimization of weights using multiple objectives refers to a "multi-objective optimization problem." In this paper, an evolutionary cultural algorithm is used to optimise weights in ANN, and the results are reported with improved accuracy. Three benchmark datasets for autism screening data are used, trained, and tested for model accuracy in the classification: toddlers (1054,19), children (292,21), and adults (704,21).With the support of the domain expert, real-time data were collected from parents and caregivers and totalled over 1000 records, with a moderate difference in attributes based on CARS-2 (Childhood Autism Rating Scale, 2nd Edition) for ASD screening. In this paper, the proposed model is compared using a curve-fitting mathematical technique. The proposed model is trained and tested, and the results showed that it outperformed other algorithms in terms of precision, accuracy, sensitivity, and specificity. [ABSTRACT FROM AUTHOR]

Early identification of children with autism is necessary to support their social and communicative skills and cognitive, verbal, and adaptive development. Researchers have identified several barriers to early diagnosis. Data collected in low- and middle-income contexts—where the vast majority of children in the world live—is scarce. In Ecuador, as in many other countries, estimates are lower compared to the global prevalence. Health authorities estimate a prevalence of 0.28% (0.18%–0.41%) in children aged five years old or less. Based on the hypothesis that, as in many parts of the world, children in Ecuador are not routinely screened and that this situation may result from poor recognition of this condition, our objective was to identify potential obstacles to case identification in pediatric settings. Several barriers, consistent with those identified in other countries, were reported by 153 participants on a survey, including lack of time, lack of resources to refer, fear of unnecessarily alarming families, and lack of information to guide families with concerns. The vast majority of participants are aware of the need for a screening tool for autism detection but report a lack of knowledge of its formal application. Most of the barriers reported in this study could be overcome by educational programs tailored to professional needs in order to support the well-being of children with autism and their families.

Abstract Background Autism spectrum disorder (ASD) diagnosis can be delayed due in part to the time required for administration of standard exams, such as the Autism Diagnostic Observation Schedule (ADOS). Shorter and potentially mobilized approaches would help to alleviate bottlenecks in the healthcare system. Previous work using machine learning suggested that a subset of the behaviors measured by ADOS can achieve clinically acceptable levels of accuracy. Here we expand on this initial work to build sparse models that have higher potential to generalize to the clinical population. Methods We assembled a collection of score sheets for two ADOS modules, one for children with phrased speech (Module 2; 1319 ASD cases, 70 controls) and the other for children with verbal fluency (Module 3; 2870 ASD cases, 273 controls). We used sparsity/parsimony enforcing regularization techniques in a nested cross validation grid search to select features for 17 unique supervised learning models, encoding missing values as additional indicator features. We augmented our feature sets with gender and age to train minimal and interpretable classifiers capable of robust detection of ASD from non-ASD. Results By applying 17 unique supervised learning methods across 5 classification families tuned for sparse use of features and to be within 1 standard error of the optimal model, we find reduced sets of 10 and 5 features used in a majority of models. We tested the performance of the most interpretable of these sparse models, including Logistic Regression with L2 regularization or Linear SVM with L1 regularization. We obtained an area under the ROC curve of 0.95 for ADOS Module 3 and 0.93 for ADOS Module 2 with less than or equal to 10 features. Conclusions The resulting models provide improved stability over previous machine learning efforts to minimize the time complexity of autism detection due to regularization and a small parameter space. These robustness techniques yield classifiers that are sparse, interpretable and that have potential to generalize to alternative modes of autism screening, diagnosis and monitoring, possibly including analysis of short home videos.

BackgroundBoth parent-report and clinician-administered autism spectrum disorder (ASD) screening instruments are important to accurately inform ASD risk ascertainment. The aim of this study was to adapt a clinician-administered ASD screening instrument, the Autistic Behavioural Indicators Instrument (ABII), as a parent questionnaire equivalent (ABII-PQ). Method The modification of ABII items into parent questions is described. The ABII-PQ was trialled in a sample of parents of children, aged between 12 months and 6 years, with an ASD (n = 65,Mchild age = 4.03 years) or typical development (n = 37,Mchild age = 2.09 years). ResultsInternal consistency was high,α = .92. Receiver operator curves analysis identified the optimal ABII-PQ cut-off score, which yielded high sensitivity (.97) and specificity (.95). Classification accuracy was high for children across the autism spectrum (autistic disorder:n = 35, 100%; Asperger syndrome:n = 14, 93%; pervasive developmental disorder not otherwise specified:n = 14, 93%). ConclusionThe ABII-PQ shows promise as a parent questionnaire version of the ABII. [ABSTRACT FROM PUBLISHER]

Early identification of children with autism is necessary to support their social and communicative skills and cognitive, verbal, and adaptive development. Researchers have identified several barriers to early diagnosis. Data collected in low- and middle-income contexts—where the vast majority of children in the world live—is scarce. In Ecuador, as in many other countries, estimates are lower compared to the global prevalence. Health authorities estimate a prevalence of 0.28% (0.18%–0.41%) in children aged five years old or less. Based on the hypothesis that, as in many parts of the world, children in Ecuador are not routinely screened and that this situation may result from poor recognition of this condition, our objective was to identify potential obstacles to case identification in pediatric settings. Several barriers, consistent with those identified in other countries, were reported by 153 participants on a survey, including lack of time, lack of resources to refer, fear of unnecessarily alarming families, and lack of information to guide families with concerns. The vast majority of participants are aware of the need for a screening tool for autism detection but report a lack of knowledge of its formal application. Most of the barriers reported in this study could be overcome by educational programs tailored to professional needs in order to support the well-being of children with autism and their families. [ABSTRACT FROM AUTHOR]

The GARS-2 (Gilliam ) is widely used for autism screening; however, the validity of its three conceptually-derived subscales has not been evaluated. In this study, exploratory (EFA) and confirmatory (CFA) factor analyses of data from matched subgroups of the standardization sample did not support the GARS-2 subscale structure. EFAs identified four factors in the model development subgroup ( n = 496): stereotyped/repetitive behavior, stereotyped/idiosyncratic language, word use problems, and social impairment. CFAs supported this model in the replication subgroup ( n = 494). Findings suggest that the GARS-2 subscales have limited clinical utility and that the Autism Index should be interpreted with caution. Although more research is needed, the clinical utility of the four empirically-derived scales may be limited by factors related to item content and test development procedures. [ABSTRACT FROM AUTHOR]

Despite the increment of researches related to Social Assistive Robotics (SAR), achieving a plausible Robot-Assisted Diagnosis (RAD) for Children with Autism Spectrum Disorders (CwASD) remains a considerable challenge to the clinical and robotics community. The work of specialists regarding ASD diagnosis is hard and labor-intensive due to the condition's manifestations are inherently heterogeneous and makes the process more difficult. Besides, the aforementioned complexity may be the main reason for the slow progress in the development of SAR with diagnostic purposes. Thus, this work provides a comprehensive Robot-Assisted Intervention for CwASD showing the conditions in which a Robot-based approach can be useful to assess autism risk factors for an autism diagnosis purpose. The intervention scheme consists of an improved version of a multimodal environment for Robot-based intervention proposed in our previous work. More specifically, we compared the behavior of CwASD with that of children in a control group during a human/robot-mediated intervention while Joint Attention (JA) behaviors are elicited and analyzed. Through statistical data analysis, it was possible to identify that 17 out of 23 children of the CwASD group showed a different behavior pattern related to three characteristics of autism, which suggests that this pattern can be used to identify autism risk factors through Robot-based interventions. • ASD risk factors associated with CwASD ability to manifest JA were identified in RMI. • CwASD group showed a different behavioral pattern in three autism signs. • CwASD did not perform better in the RMI; this does not mean that RMI are not suitable. • Robot was relevant, because it led to demonstrate differences between the two groups [ABSTRACT FROM AUTHOR]