Search

The death of a child may be the most traumatic event a family can experience. Bereavement care for parents is essential for their physical and mental well-being and is a psychosocial standard of care. Childhood mortality is higher in low- or middle-income countries (LMICs); however, little is known regarding bereavement support or interventions for parents in LMICs. To identify programs, services, initiatives, or interventions offered to bereaved parents in LMICs in hospital settings. A systematic search was executed following the Preferred Reported Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Articles from LMICs describing interventions, programs, or resources provided to parents after the death of a child (0–18 years old) from any cause were included. Extracted data was categorized by demographics, study design, outcomes, and quality assessment using the McGill Mixed Methods Appraisal Tool (MMAT). We retrieved 4428 papers and screened their titles and abstracts, 36 articles were selected for full-text assessment, resulting in nine articles included in the final analysis. Most interventions described support for parents whose child died during the prenatal or neonatal period. The primary interventions included psychological counseling, creating mementos (such as photographs or footprints), and bereavement workshops. Only one paper described a fully established bereavement program for parents. Eight of the papers met high-quality criteria. Although bereavement care is crucial for parents whose child has died, only a few studies have documented bereavement interventions in LMICs. More research may help with bereavement program implementation and improved care for bereaved parents in LMICs. [ABSTRACT FROM AUTHOR]

Affect recognition is currently an active research area for machine learning researchers. Researchers are paying more and more attention to the assessment and the classification of emotions in people with mental disorders in order to propose monitoring healthcare systems and then to better assist patients. In this paper, a supervised learning method to classify Autism Spectrum Disorder (ASD) and to evaluate affect levels among autistic children is proposed. The use of methodologies for clinical patient monitoring and management is the focus of our research. YouTube video frames acquired in unconstrained environments and conditions of autistic children demonstrating typical autistic behaviors, as well as images of neurotypical people are used to evaluate the performance of the proposed approach. This paper also proposes an extended version of a dataset, including the additional affect labels corresponding to the affect levels of autistic children. Finally, experiments using different models were conducted to determine which architecture performed best. These experiments have shown very promising results for continuous affect recognition of children with ASD. Results show also that using a model that has only been trained on neurotypical subjects does not perform as great when the subjects are ASD children. • A video-based approach for continuous affect recognition of children with Autism. • A new transformer-based deep learning model for affect recognition from images. • Arousal and Valence annotation of the SSBD dataset. • Data concerning neurotypical people are not relevant to studying autistic children. • Stimming behavior and face analysis can help in autism assessment. [ABSTRACT FROM AUTHOR]

Mental health is a basic need for a sustainable and developing society. The prevalence and financial burden of mental illness have increased globally, and especially in response to community and worldwide pandemic events. Children suffering from such mental disorders find it difficult to cope with educational, occupational, personal, and societal developments, and treatments are not accessible to all. Advancements in technology have resulted in much research examining the use of artificial intelligence to detect or identify characteristics of mental illness. Therefore, this paper presents a systematic review of nine developmental and mental disorders (Autism spectrum disorder, Attention deficit hyperactivity disorder, Schizophrenia, Anxiety, Depression, Dyslexia, Post-traumatic stress disorder, Tourette syndrome, and Obsessive–compulsive disorder) prominent in children and adolescents. Our paper focuses on the automated detection of these developmental and mental disorders using physiological signals. This paper also presents a detailed discussion on signal analysis, feature engineering, and decision-making with their advantages, future directions and challenges on the papers published on mental disorders of children. We have presented the details of the dataset description, validation techniques, features extracted and decision-making models. The challenges and future directions present open research questions on signal or availability, uncertainty, explainability, and hardware implementation resources for signal analysis and machine or deep learning models. Finally, the main findings of this study are presented in the conclusion section. • First study to present systematic review of children mental and learning disorders. • We covered popular physiological signals for mental and learning disorder detection. • Explored major challenges and research gaps in current automated detection systems. • We recommended concept of data fusion for future research directions. [ABSTRACT FROM AUTHOR]

This paper describes the INSIDE system, a networked robot system designed to allow the use of mobile robots as active players in the therapy of children with autism spectrum disorders (ASD). While a significant volume of work has explored the impact of robots in ASD therapy, most such work comprises remotely operated robots and/or well-structured interaction dynamics. In contrast, the INSIDE system allows for complex, semi-unstructured interaction in ASD therapy while featuring a fully autonomous robot. In this paper we describe the hardware and software infrastructure that supports such rich form of interaction, as well as the design methodology that guided the development of the INSIDE system. We also present some results on the use of our system both in pilot and in a long-term study comprising multiple therapy sessions with children at Hospital Garcia de Orta, in Portugal, highlighting the robustness and autonomy of the system as a whole. [ABSTRACT FROM AUTHOR]

Siblings represent an important influence on children's development. It is possible that sibling influence on developmental outcomes differs in sibling pairs when one of the children has a disability. Previous research has tended to focus on outcomes for typically developing siblings when they have a brother/sister with a disability. The purpose of this scoping review was to explore empirical studies reporting on the impact of siblings on the developmental outcomes of children with disability to better understand the areas that are influenced by siblings and the factors that contribute to this influence. To identify relevant studies, the electronic databases of EBSCO, ERIC, Informit, Ovid, ProQuest and Scopus were searched. These searches were supplemented by direction from the authors on relevant literature and citation searches of papers identified for inclusion. Descriptive details were extracted, followed by details related to research design and findings of the studies. Twenty-two papers were determined to meet inclusion criteria. Investigations of sibling influence have concentrated on children with ASD; other groups are not well represented. There is some evidence that having older siblings may be protective for children with ASD; however, this was not an invariable finding. There is too little consistency across studies to determine whether and how siblings influence development of children with disability. Further work is required to understand the potentially crucial influence that siblings may have on developmental outcomes of children with disability. • Siblings are overlooked as a source of influence on the development of their brothers/sisters with a disability. • Having an older sibling may be a positive influence for children with autism spectrum disorder. • There are a number of methodological decisions that researchers can take that will move the field forward. [ABSTRACT FROM AUTHOR]

Early diagnosis of Autism Spectrum Disorder (ASD) plays a crucial role in the intervention of ASD. Traditionally, an ASD child needs to be diagnosed by a psychiatrist in the hospital, which is expensive, time-consuming, and influenced by expertise. In this paper, we present an objective, convenient, and effective method for classifying ASD children from raw video sequences by integrating the appearance-based features from facial expressions, head pose, and head trajectory. To better extract facial expression features, we propose a novel attention-based facial expression recognition algorithm to focus on key face areas like eyebrows, mouth, etc. Moreover, we use accumulative histogram to individually extract temporal and spatial information from facial expression, head pose and head trajectory of the video sequence. After fusing these three kinds of features, we feed them to Long Short-Term Memory (LSTM) and achieve a classification accuracy of 96.7% on our self-collected ASD video dataset. [ABSTRACT FROM AUTHOR]

• New ASDD strategy is provided to give fast diagnosis for autism patients. • ASDD composes of two main layers; Pre-processing Layer and Autism Discovery Layer. • In PL, feature selection and outlier rejection are used to filter the used data. • Hybrid Rejection Technique as rejection method is main contribution of this paper. • Experimental results proven that ASDD strategy outperforms the other strategies. Autism Spectrum Disorder (ASD) represents a heterogeneous developmental disability characterized by impairments in social communication and behavioral challenges. The problem of ASD begins with childhood and continues into adolescence as well as adulthood. The number of children suffering from ASD is constantly increasing, so a modern method must be found to make a quick and early diagnosis or discovery of ASD patients with high accuracy. Early discovery of ASD patients aims to quickly take the necessary measures with patients and take care of them until their speedy recovery. During this paper, a new Autism Spectrum Disorder Discovery (ASDD) strategy is provided to give a fast and delicate diagnosis for autism patients. The ASDD composes of two main layers, which are; (i) Pre-processing Layer (PL) and (ii) Autism Discovery Layer (ADL). In the PL, two approaches called feature selection and outlier rejection are used to filter the used data from any non-informative data before starting to train the diagnostic model in the ADL for providing delicate diagnosis. Hybrid Rejection Technique (HRT) as a new outlier rejection method is the main contribution of this paper. HRT includes two main stages called Quick Rejection Stage (QRS) as a fast stage and Precise Rejection Stage (PRS) as a delicate stage. QRS uses a standard deviation to quickly remove outliers and then PRS uses a Hybrid Bio-inspired Optimization Method (HBOM) that combines Binary Genetic Algorithm (BGA) and Binary Gray Wolf Optimizer (BGWO) to delicately eliminate the rest of outliers. According to PL in ASDD strategy, Fisher Score (FS) is applied to select the best subset of features and then HRT is used to reject bad training data. Finally, an Ensemble Technique (ET)that includes three classifiers called Naïve Bayes (NB), K-Nearest Neighbors (KNN), and Deep Learning (DL) is used in ADL to diagnose ASD patients based on the filtered data from PL. The ASDD strategy has been compared to many modern strategies using ASD dataset that includes blood tests from children [1]. Experimental results proven that the ASDD strategy outperforms the other strategies in terms of many metrics called accuracy, error, sensitivity, precision, and execution-time with values 0.92, 0.08, 0.85, 0.80, and 2 s. [ABSTRACT FROM AUTHOR]

• A video dataset of Autism Spectrum Disorders (ASD) is collected. • Possibility of diagnosis of ASD is analyzed by developed action recognition methods. • The evaluations emphasize the effectiveness of appearance-based local descriptors. • According to the clinicians, our method can help them in the early diagnosis of ASD. Medical diagnosis supported by computer-assisted technologies is getting more popularity and acceptance among medical society. In this paper, we propose a non-intrusive vision-assisted method based on human action recognition to facilitate the diagnosis of Autism Spectrum Disorder (ASD). We collected a novel and comprehensive video dataset f the most distinctive Stereotype actions of this disorder with the assistance of professional clinicians. Several frameworks as a function of different input modalities were developed and used to produce extensive baseline results. Various local descriptors, which are commonly used within the Bag-of-Visual-Words approach, were tested with Multi-layer Perceptron (MLP), Gaussian Naive Bayes (GNB), and Support Vector Machines (SVM) classifiers for recognizing ASD associated behaviors. Additionally, we developed a framework that first receives articulated pose-based skeleton sequences as input and follows an LSTM network to learn the temporal evolution of the poses. Finally, obtained results were compared with two fine-tuned deep neural networks: ConvLSTM and 3DCNN. The results revealed that the Histogram of Optical Flow (HOF) descriptor achieves the best results when used with MLP classifier. The promising baseline results also confirmed that an action-recognition-based system can be potentially used to assist clinicians to provide a reliable, accurate, and timely diagnosis of ASD disorder. [ABSTRACT FROM AUTHOR]

Background: Coloured overlays have often been used to improve reading performance in preschool children with an autism spectrum disorder (ASD), however, previous evidence shows conflicts in its application.Aims: To investigate the immediate effects of coloured overlays on reading performance using eye tracking in preschool children with ASD and their typical development (TD) counterparts closely matched by chronological age.Methods: Forty participants with ASD (n = 20) or TD (n = 20) were recruited by convenience sampling and asked to read aloud numbers randomly arranged on paper. Participants' ocular performance (fixation duration, fixation count, total visit duration), reading speed and number of errors were recorded by eye tracker and digital stopwatch respectively throughout testing with and without coloured overlays.Results: The findings show that coloured overlays had no significant immediate effect in improving ocular performance and reading speed of children with ASD or TD, although individual improvements were identified in some children with ASD.Conclusions: Use of coloured overlays may not be useful to improve reading and ocular performance in children with ASD in one single occasion. The potential effect on reading ability of using coloured overlays repetitively for a longer period needs further investigation. [ABSTRACT FROM AUTHOR]

Abstract The reason of many symptoms of autistic children is sensory integration, it is the power to understand, organize and feel sensory data from the environment and body. The issues surrounding sensory integration are presented in hyposensitive and hypersensitive a reaction by children with autism to the vestibular, proprioception, tactile, audio, visual, and olfactory senses. The aim of this paper is establishing a group of guidelines for designing a therapeutic garden for children with Autism Spectrum Disorder to treat the sensory integration problems of children with ASD by designing a sensory garden which should focus on therapeutic interference. By using the elements and principles of design, guidelines for this garden focused on producing calming effects for hyper reactive children with ASD and stimulating effects for hypo reactions. [ABSTRACT FROM AUTHOR]

This paper investigates the intersections of gender, sexuality, ageing in the way autism spectrum disorder is medically described as a discrete category. On one hand, the construction of autism as a male-centric phenomenon results in a significant gender gap in autism diagnosis, with girls diagnosed with autism significantly less and later than boys. On the other hand, the focus on depicting autism as a pediatric condition exposes adult autistics to discriminatory practices such as infantilization and contributes to the disregard of their sexual desires or to the misconception of their sexual behaviors as dangerous or inappropriate. Both infantilization and the supposed inability of autistic people to "fit" into adulthood have a significant impact on both sexuality's expressions and ageing experiences. My study suggests how fostering knowledge and further learning on the infantilization of autism can bring important insight into understanding disability from a critical angle. By challenging normative notions of gender, ageing, and sexuality, autistic people's different bodily experiences question medical authority and social politics and criticize the public representation of autism in the broader social space. • Autism has a contingent historical nature, reflectingthe epistemological changes of psychiatry as a discipline. • A deficit-based understanding of autism contributed to the misleading idea about autistic people as individualsunable to express their desires and achieve autonomy. • Misconceptions about autistic bodies as child-like or disruptive and non-normative affect affected how their sexuality has been portrayed. • Fostering knowledge on the infantilization of autism can bring crucial insight into understanding disability and diversity from a critical angle. [ABSTRACT FROM AUTHOR]

The incidence rate of autism spectrum disorder (ASD) has been rising in the past decades, and has reached 1 ∼ 2%. Clinical ASD screening requires long testing time, complicated doctor training and high cost. Therefore, an objective and accurate automated method is urgently needed for large-scale early screening of autistic children. The lack of response to one's own name is one of the early warning signals of ASD. Response to name is included in various ASD early screening and diagnostic assessments. In this paper, we propose an algorithm that combines automatic name detection with human pose tracking and head pose estimation in computer vision. The final prediction is determined by the combination of shoulder rotation angle, head pose information and duration. The experimental data comes from the process of clinical screening for ASD, which has less laboratory control, more realistic child response, and a flexible number of accompanying parents. Thirty subjects including 29 children with ASD and 1 typical developing (TD) child participated in the experiment. The experimental results show that the consistency between our proposed method and clinical diagnosis achieves 93.3%, which indicates our method can play an effective auxiliary role in the early screening of ASD. • A multi perspective platform is established to capture ASD children's behavior patterns. • A "Response to name Dataset" for autism spectrum disorder is established. • Body pose and head pose are combined to judge children's RTN reaction. [ABSTRACT FROM AUTHOR]

World Health Organization reported that almost one in 100 children is diagnosed with autism spectrum disorder (ASD) worldwide. Extended Reality (XR) and Telehealth interventions are evident to be effective for ASD treatments. While there is no comprehensive systematic review to summarize and evaluate the evidence for promoting the accessibility of different technology-based treatment regiments. This paper aims to verify the efficacy and validity of XR and Telehealth interventions for children and adolescents with ASD. We reviewed 112 studies from databases of PubMed, Web of Science and Cochrane Library, published in English between January 2010 to April 1st, 2022. We found that after interventions, positive improvements for ASD participants were observed in social interaction, acceptance, and engagement, communication and speech, emotion recognition and control, daily living skill, problem behavior reduction, attention, cost reduction, anxiety symptom reduction, pretend play, contextual processing, match to sample skill, and insomnia control. Our findings provide a solid and positive evidence of XR and Telehealth interventions in improving the treatment outcomes for children and adolescents with ASD. In the future, more research with RCTs and standardized outcome measurements are required to establish the therapeutic efficiency of the two interventions independently or combined. • XR and telehealth-based interventions are effective in remodeling the basic skills of children and adolescents with ASD. • Areas such as social interaction and communication and speech were improved after XR and telehealth interventions. • The level of acceptance and engagement of both interventions is reassuring for ASD participants and their parents. [ABSTRACT FROM AUTHOR]

The purpose of this study is to explore the differences of resting EEG in children with autism spectrum disorders and then analyze the sensitive channels with significant differences, to provide support for the accurate differential diagnosis of autism spectrum disorder (ASD). Based on the weighted multi-scale sample entropy (WMSSE) algorithm and amplitude synchronization index (ASI) algorithm of EEG, this paper comprehensively evaluates the brain state of ASD children from the two aspects of brain function complexity and brain function synchronization connectivity. Further, by combining the support vector machine (SVM) classification model to explore the location of abnormal channels of ASD children and realize the diagnosis of ASD children. The WMSSE of the ASD group was lower than that of the healthy group. Furthermore, there was a significant difference in the F3/F4 channels and F7/F8 channels (P < 0.05), and the synchronization of the brain in the ASD group was also lower than that of the healthy group in Delta, Theta, Alpha, Beta band. Finally, combined with the WMSSE and ASI features of the F3/F4 channels (posterior frontal lobe) and F7/F8 channels (anterior temporal lobe), the classification accuracy and AUC value of ASD patients calculated by the SVM classification model were 82.7 ± 3.2%/ 0.795 (F3 / F4 channels), 89.8 ± 1.7%/ 0.812 (F7 / F8 channels). It avoids the one-sided problem of single analysis complexity and synchronous connectivity, and provides a research basis for the comprehensive evaluation of ASD brain function. WMSSE and ASI can be used as effective potential biomarkers for ASD diagnosis, and F7 and F8 channels can be preliminarily located as abnormal sensitive channels for ASD brain regulation. It also proves that the feature analysis of comprehensive complexity and synchronous connectivity is more conducive to the abnormal diagnosis of ASD patients. [Display omitted] • WMSSE and ASI can be used as an effective potential biomarker for ASD diagnosis. • The F7 and F8 channels can be used as abnormal channels for brain regulation in ASD patients. • Compared with MSE, WMSSE is more stable on a large time scale. [ABSTRACT FROM AUTHOR]

Background: Group social skills interventions (GSSIs) are offered to youth with Autism Spectrum Disorder (ASD) to improve social functioning. This systematic review focused on the adolescent population, including a wider range of disabilities.Aims: To evaluate effectiveness of GSSIs at improving social functioning in adolescents with congenital, acquired or developmental disabilities.Methods and Procedures: Databases, trial registries and dissertations were systematically searched and a meta-analysis of randomized controlled trials conducted. Study screening, risk-of-bias assessment and Grading of Recommendations Assessment, Development and Evaluation were completed.Outcomes and Results: Sixteen studies (n = 1119), 15 with adolescents with ASD and one with brain tumor survivors, revealed GSSIs reduced social impairment on the Social Responsiveness Scale (mean difference (MD) 9.68, 95% CI 5.63-13.73; P < 0.001), increased social skills on the Social Skill Improvement System Rating Scales (SMD 0.38, 95% CI 0.10-0.65; P = 0.007), and improved adolescent social knowledge on the Test of Adolescent Social Skills (MD 7.43 points, 95% CI 5.36-9.50; P < 0.001).Conclusions and Implications: There is moderate certainty evidence that GSSIs improve social responsiveness, social skills and knowledge, and low certainty of evidence to improve social participation for adolescents with ASD. High quality randomized studies are required to inform clinical practice with adolescents with other disabilities.What This Paper Adds: Current evidence for group social skills interventions (GSSIs) is for adolescents with autism (ASD). GSSIs likely improve social knowledge and reduce impairments in adolescents with ASD, however the effect of GSSIs on social participation is not well understood. Only one randomized trial investigated GSSIs in another population of adolescents, highlighting the need for more high-quality studies including adolescents with other disabilities. [ABSTRACT FROM AUTHOR]

• A Residual Neural Network (ResNet) was designed to classify small/similar gestures. • The gesture recognition system was within a new robot therapy for autistic children. • The trained ResNet was exploited online for interactive feedback during therapy. • Offline classification reached 95% test accuracy in our training Dataset. • Online classification achieved 79% F1-score during clinical application. Children with Autism Spectrum Disorders (ASDs) exhibit significant impairments in gesture imitation. Newest interventions are based on Human-Robot Interaction (HRI) since children with ASD cope well with stylized, rule-based and predictable systems. These collaborative approaches encompass therapy games based on joint exercises, imitation and interaction between robots and children. This paper's aim was to implement an algorithm to automatically recognize small and similar gestures within a humanoid-robot therapy called IOGIOCO for ASD children. IOGIOCO is a multi-level HRI therapy meant to teach 19 meaningful gestures in a semantic framework based on a feedback interaction. Gestures were tracked as 3D coordinates of body keypoints captured by a Kinect. A Residual Neural Network was implemented and trained on a segmented Dataset acquired within this study to generate the offline model which was then exploited in a real-time classification using a sliding window. Feedback as sound stimuli from NAO robot was provided based on the automatic evaluation of each performance. Clinical acquisitions were carried out on 4 ASD children within the IOGIOCO therapy. Offline recognition was successful: exploiting Artificial Neural Networks we reached 95% of test accuracy for 19 gestures. A real-time recognition on healthy subjects reached 94% accuracy. Clinical applications were evaluated through the F1 score that achieved 79% value. These outcomes were encouraging considering the wide gesture set and all the challenges the therapy raises. This kind of automatic algorithm was able to decrease the therapist workload and increase the robustness of the therapy and engagement of the child. [ABSTRACT FROM AUTHOR]

The tendency of mothers to cradle their infant on their left side was first demonstrated by Salk back in 1960, but has been the subject of renewed interest in recent years. In this paper, I examine the different aspects of this tendency, making a short detour to explore this behavioral bias in other mammals and in nonhuman primates. The left cradling bias has been investigated not only in mothers, but also in fathers, children and students, as well as in different cultures. Moreover, the origins and causes of this behavior have been explored by examining its links to hemispheric specialization and to other motor asymmetries in mothers and infants. In recent years, researchers have also explored divergent patterns of cradling in groups of mothers exhibiting stress, anxiety, or depressive symptoms during pregnancy and after delivery, as well as in children with atypical development (e.g., autism spectrum disorder). The findings reported in the past 20 years open up promising avenues for anticipating potential difficulties in the relationship between mother and child, for given that a left cradling bias has been found in about 75% of the samples tested, cradling patterns could constitute natural behavioral markers of the socio-emotional harmony between cradler and cradled. [ABSTRACT FROM AUTHOR]

B Introduction: b Autism Spectrum Disorder (ASD) is a lifelong neurological and developmental disorder with highly heterogeneous clinical phenotypes. On these 71 papers, 39 reported comorbidities but only 15 provided the prevalence of comorbidities in ASD and were included in this analysis. [Extracted from the article]

Little is known about the current situation regarding Autism Spectrum Conditions in mainland China. Electronic databases and bibliographies were searched to identify literature on service provision for ASC in both English and Chinese databases. 14 studies and 6 reports were reviewed. The findings of identified papers on service provision were summarized according to four settings for ASC including healthcare, mainstream education, private special education, and state-run special education. The literature on the situation of the healthcare system and educational services for children with ASC in China was profoundly limited. There were great financial problems faced by the parents of autistic children which were partly due to the under-developed healthcare and educational system for ASC. [Copyright &y& Elsevier]

Of late there has been growing interest in the potential of technology to support children with Autistic Spectrum Disorders (ASD) with social and life skills. There has also been a burgeoning interest in the potential use of mobile technology in the classroom and in the use of such technology to support children with ASD. Building on these developments, the HANDS project has developed a mobile cognitive support application for smartphones, based on the principles of persuasive technology design, which supports children with ASD with social and life skills functioning – areas of ability which tend to be impaired in this population. The software application has been piloted in four special schools for children with ASD. This paper reports on a qualitative interpretivist evaluation, which explores which factors may mediate how the software application is incorporated in to existing practice and what influence it has on practice. Kairos is identified as a key factor, which is associated with the teachers’ view of the software application as extending their reach beyond the classroom. Design guidelines are proposed for future implementations of similarly purposed technology tools. [Copyright &y& Elsevier]

• IP webcam based repetitive behavior assessment of autistic child. • IP webcam based autistic child drug severity analysis through pre-trained CNNs. • Over-fitting problem in CNNs solve through transfer learning. • Proposed approach estimates autism drug dosage level through IP webcam images. • Thermal images validate temperature variation of autism child due drug overdosage. Autism Spectrum Disorder (ASD), in child is identified through various parameters such as social skills, repetitive behaviors, speech and nonverbal communication. Among the above parameters repetitive behavior plays a vital role for physician to prescribe dosage of drugs. The repetitive behavior and more aggressiveness in the autistic child is the symptom for growth of the disease. To control the repetitive behavior, the physician prescribe the dosage level of drug based on Aberrant Behavior Checklist (ABC). The ABC is measured only for few seconds by the physician and such measurement need continuous monitoring for proper prescription of drugs and also to avoid adverse drug effect. The above problem solve through IP Webcam app based ASD recognition for continuous monitoring and replaces the empirical method of ABC measurement. In this paper, the proposed method recognizes behavior and changes in autistic child through activity detection and repetitive behaviour, due to overdosage of drugs. In proposed method, hybrid framework incorporates training of deep CNN model for the monitoring of ASD children in natural environment through Autismdata.Net. Moreover, Transfer learning avoids the over-fitting problem in small size Autismdata.Net dataset through CNN in severity analysis of child. The behavior of ASD children is evaluated through Autismdata.Net dataset and validated through drug thermo regulation of autistic child. Action recognition accuracy of the proposed method is much better than the clinical literate/therapist analysis/observation. The proposed system helps physician for regulation of dosage level to ASD children. [ABSTRACT FROM AUTHOR]

Early intervention and treatment are crucial for individuals with autism spectrum disorder (ASD). However, it is challenging to identify individuals with ASD at an early age, i.e. under 3 years old, due to the lack of an effective and objective identification method. The mainstream clinical diagnosis relies on long-term observation of children's behaviors, which is time-consuming and expensive, and thus how to accurately and quickly distinguish children with ASD in early childhood has become a critical issue. In this paper, we propose an eye movement based model to identify children with ASD. Specifically, children are required to freely observe some images. At the same time, their eye movements are recorded to analyze. Both the observed image and eye movements are input into our model. The input data are processed by the embedding layer, dynamic filters and LSTM block, respectively. Eventually, the spatiotemporal features are extracted to identify the eye movements belonging to a child with ASD or a typically developed child. Experiments on the Saliency4ASD dataset demonstrate that the proposed model achieves state-of-the-art performance in identifying children with ASD. • An effective model is proposed to identify children with autism spectrum disorder. • Dynamic filters are introduced to customize feature maps for each scanpath. • Field of view (FoV) maps are proposed to extract fixation-specific features. • A module based on scanpath and saliency prediction is proposed to generate spatiotemporal features. [ABSTRACT FROM AUTHOR]

As early intervention is highly effective for young children with autism spectrum disorder (ASD), it is imperative to make accurate diagnosis as early as possible. ASD has often been associated with atypical visual attention and eye gaze data can be collected at a very early age. An automatic screening tool based on eye gaze data that could identify ASD risk offers the opportunity for intervention before the full set of symptoms is present. In this paper, we propose two machine learning methods, synthetic saccade approach and image based approach, to automatically classify ASD given children's eye gaze data collected from free-viewing tasks of natural images. The first approach uses a generative model of synthetic saccade patterns to represent the baseline scan-path from a typical non-ASD individual and combines it with the real scan-path as well as other auxiliary data as inputs to a deep learning classifier. The second approach adopts a more holistic image-based approach by feeding the input image and a sequence of fixation maps into a convolutional or recurrent neural network. Using a publicly-accessible collection of children's gaze data, our experiments indicate that the ASD prediction accuracy reaches 67.23% accuracy on the validation dataset and 62.13% accuracy on the test dataset. • Atypical visual attention associated with autism spectrum disorders can be studied through eye gaze behavior of children at a very young age. • Autistic gaze viewing patterns in a free-viewing paradigm studied using computer vision. • Correlation between scan-path fixations and high-level image semantics extracted through deep learning result in ASD prediction accuracy up to 62% • Study finds significant class differences by applying machine learning to raw scan-path fixations and duration; verification on larger dataset needed. [ABSTRACT FROM AUTHOR]

Autism Spectrum Disorder is a developmental disorder characterized by a deficit in social behaviour and specific interactions such as reduced eye contact and body gestures. Recent advancements in software and hardware multimedia technologies provide the tools for early detecting the presence of this disorder. In this paper we present an approach based on the combined use of machine learning and eye tracking information. More specifically, features are extracted from image content and viewing behaviour, such as the presence of objects and fixations towards the centre of a scene. Those features are used to train a machine learning-based classifier. The obtained results show that the considered features allow to identify children affected by autism spectrum disorder and typically developing ones. • Autism Spectrum Disorder is characterized by a deficit in social behaviour and specific interaction. • Signal processing techniques can be used for identifying Autism Spectrum Disorder symptoms. • Features extracted from image content and viewing behaviour support an early diagnosis of Autism Spectrum Disorder. • Eye tracking and machine learning algorithms are combined to implement a fast and accurate diagnosis system. [ABSTRACT FROM AUTHOR]

In just 50 years the prevalence of autism spectrum disorder has vaulted from extremely rare to common in every community. During this time, a large body of scientific literature has been amassed regarding what environmental, genetic, maternal, or obstetric factors may be at work. The hypothesis presented here identifies two developments in today's childbirth experience that, in combination, may provide the key: 1) a significant increase in the mean duration of labor and 2) the adoption of continuous electronic fetal monitoring utilizing Doppler ultrasound as the standard of care even in low-risk pregnancies. Together, these two factors have created an unprecedented fetal environment that has the potential to affect neuronal migration and cause non-inherited genetic disruptions. This paper will briefly describe the nature and history of contributing factors, why there may be a link between evolving maternal characteristics, obstetric trends and the increase in autism, as well as the means by which the hypothesis can be tested. [ABSTRACT FROM AUTHOR]

Analyzing on the time-varying behavior of spontaneous hemodynamic fluctuations from fNIRS was performed to investigate the possible functional patterns associated with autism spectrum disorder (ASD) and potential contribution of optical channels to ASD/TD classification; Then a deep learning model combining the long-short term memory (LSTM) and convolutional neural network (CNN) was conducted to represent the temporal variation of brain activity for accurate identification of ASD. • Monitoring brain activity of bilateral TL by functional near-infrared spectroscopy. • Temporal variation in hemodynamic fluctuations of ASD children differs from TD. • Weaker internal logic but stronger memory to random shocks in ASD children. • Identifying ASD with long-short term memory and convolutional neural network. • Hemodynamic signals of Hb demonstrated classification accuracy of 95.7 %. Functional near-infrared spectroscopy (fNIRS) was used to investigate spontaneous hemodynamic fluctuations in the bilateral temporal cortices for typically developing (TD) children and children with autism spectrum disorder (ASD). This paper proposed an approach to estimate the global time-varying behavior of brain activity through the measurement on change in first-order statistical properties directly from fNIRS time series. Then, a deep learning model combining the long-short term memory (LSTM) and convolutional neural network (CNN) was constructed based on the integration strategy with improved bagging algorithm, with the purpose to explore the potential patterns of temporal variation for ASD identification. Based on the theory of stationarity, analysis on the global time-varying behavior of hemodynamic fluctuations in oxy-hemoglobin (HbO 2) and deoxy-hemoglobin (Hb) demonstrated that children with ASD showed weaker internal logic, but stronger memory and persistence to random shocks than TD children. Differentiating between ASD and TD with the proposed deep learning approach resulted in high accurate classification with sensitivity of 97.1 % and specificity of 94.3 %. Using fNIRS time series of Hb from single optical channel, we achieved a better classification accuracy of 95.7 % that was about 8 % higher than previous methods with similar data. The characterization on time-varying behavior of brain activity holds promise for better understanding the underlying causes to ASD. And the deployed deep learning framework with an integration manner has the potential for screening children with risk of ASD. [ABSTRACT FROM AUTHOR]

The number of children diagnosed with autism spectrum disorder (ASD) has been increasing. Previous studies suggested potential association between pregnancy air pollution exposure and ASD. This systematic review and meta-analysis is intended to summarize the association between maternal exposure to outdoor air pollution and ASD in children by trimester based on recent studies. A systematic literature search in 3 databases (Medline, Embase, and Web of Science) was performed using subject headings related to ASD and air pollution since 2007. Eligible studies were screened and evaluated based on predetermined criteria. For meta-analyses, the studies were grouped by air pollutant and exposure time (prenatal period and trimesters). Within-group studies were standardized by log odds ratio (OR) and then combined by three meta-analysis methods: frequentist fixed and random effects models, and Bayesian random effects model. Initial search identified 1564 papers, of which 25 studies remained for final analysis after duplicates and ineligible studies were removed. Of the 25 studies, 13, 14, 12, and 7 studies investigated ASD in children associated with PM 2.5 , PM 10 , NO 2 , and ozone, respectively. The frequentist and Bayesian random effects models resulted in different statistical significance. For prenatal period, frequentist meta-analysis returned significant pooled ORs with 95% confidence intervals, 1.06(1.01,1.11) for PM 2.5 and 1.02(1.01,1.04) for NO 2 , whereas Bayesian meta-analysis showed similar ORs with wider 95% posterior intervals, 1.06(1.00,1.13) for PM 2.5 and 1.02(1.00,1.05) for NO 2. Third trimester appeared to have higher pooled ORs for PM 2.5 , PM 10 , and ozone, but patterns in the time-varying associations over the trimester were inconsistent. For positive association between maternal exposure to ambient air pollution and ASD in children, there is some evidence for PM 2.5 , weak evidence for NO 2 and little evidence for PM 10 and ozone. However, patterns in associations over trimesters were inconsistent among studies and among air pollutants. Image 1 • Some evidence for positive association between maternal exposure to PM 2.5 and ASD. • Weak evidence for positive association between maternal exposure to NO 2 and ASD. • Little evidence for association between maternal exposure to PM 10 and O 3 and ASD. • Inconsistent time-varying associations over trimesters between studies. • Inconsistent time-varying associations over trimesters between air pollutants. A meta-analysis on autism spectrum disorder(ASD) in children and maternal exposure to ambient air pollution found some evidence for PM 2.5 , weak evidence for NO 2 and little evidence for PM 10 and ozone. [ABSTRACT FROM AUTHOR]