Computational Assessment of Facial Expression Production in ASD Children.

In this paper, a computational approach is proposed and put into practice to assess the capability of children having had diagnosed Autism Spectrum Disorders (ASD) to produce facial expressions. The proposed approach is based on computer vision components working on sequence of images acquired by an off-the-shelf camera in unconstrained conditions. Action unit intensities are estimated by analyzing local appearance and then both temporal and geometrical relationships, learned by Convolutional Neural Networks, are exploited to regularize gathered estimates. To cope with stereotyped movements and to highlight even subtle voluntary movements of facial muscles, a personalized and contextual statistical modeling of non-emotional face is formulated and used as a reference. Experimental results demonstrate how the proposed pipeline can improve the analysis of facial expressions produced by ASD children. A comparison of system's outputs with the evaluations performed by psychologists, on the same group of ASD children, makes evident how the performed quantitative analysis of children's abilities helps to go beyond the traditional qualitative ASD assessment/diagnosis protocols, whose outcomes are affected by human limitations in observing and understanding multi-cues behaviors such as facial expressions.

ASD Diagnosis and Treatment Experiences Among Mexican Heritage Families.

To understand the ASD diagnosis and treatment pathways for US families, N = 38 Mexican-heritage mothers were interviewed about how and when they obtained an ASD diagnosis for their children. Most children (84%) were diagnosed between two and three years old. One-third of mothers reported receiving four to seven referrals before diagnosis. Mothers identified multiple diagnosis circumstances including two diagnoses and services offered before diagnosis. A multiple case study design documented the diagnosis and treatment experiences of four representative participants. As compared to previous studies that utilized a deficit lens to rationalize barriers to diagnosis and treatment (e.g., parents not knowledgeable about ASD), these findings revealed a complex understanding of how structural barriers (e.g., immigration status), initial diagnosis rejection among caregivers, and abrupt service cancellation complicated the diagnosis and treatment process. Implications identified suggestions to optimize and streamline ASD diagnosis and treatment pathways for Mexican heritage families.

Pragmatic language and associations with externalizing behaviors in autistic individuals and those who have lost the autism diagnosis.

Background: Pragmatic language weaknesses, a core feature of autism spectrum disorder (ASD), are implicated in externalizing behavior disorders (Gremillion & Martel, 2014). Particularly in a clinical setting, these co-occurring externalizing disorders are very common in autism; rates of Attentional Deficit-Hyperactive Disorder (ADHD) and Oppositional Defiant Disorder (ODD) are as high as 83% (ADHD) and 73% (ODD; Joshi et al., 2010). It is possible that pragmatic language weaknesses impact the ability to effectively communicate one's needs, which may lead autistic children to utilize externalizing behaviors in order to achieve a desired outcome (Ketelaars et al., 2010; Rodas et al., 2017). Methods: The aim of the current study is to investigate the relationship between pragmatic language, assessed via multiple modalities, and externalizing behaviors, assessed by parent interview, in youth with autistic (n=33) or neurotypical (NT; n=34) developmental histories, along with youth diagnosed with autism, who lost the diagnosis (LAD) by adolescence (n=31). Results: The autism group had significantly more pragmatic language difficulties, and more externalizing behaviors and disorders; ADHD symptoms were particularly more prevalent, while LAD and NT groups did not differ. Challenges in pragmatic language abilities were associated with more externalizing symptoms when controlling for other facts that typically influence such symptoms, including nonverbal cognition, structural language, executive functioning, and autistic characteristics, but did not remain when age was included in the model. Conclusions: We discuss the mechanisms underlying difficult-to-manage externalizing behaviors and implications for interventions and long-term outcomes for youth with and without a history of autism.

Three-Dimensional Cardiac Imaging: A Necessity to the Diagnosis and Treatment of Swiss-Cheese Atrial Septal Defect.

Swiss-cheese atrial septal defect (ASD) is a malformation characterized by multi-fenestrated interatrial defects. Here, we describe a vignette of a 23-year-old man with Swiss-Cheese ASD characterized by two defects with areas of 0.74 cm2 and 0.44 cm2, complicated with an atrial septal aneurysm successfully repaired with a cribriform amplatzer septal occluder (ASO) via the percutaneous transcatheter approach. This case emphasizes the importance of attaining a clear view of three-dimensional structures for proper device selection and deployment in repair as additional structural defects such as concomitant aneurysms impose significant challenges.

Migrated Inferior Vena Cava (IVC) Filter Presenting as Tricuspid Valve Mass, Right-Sided Heart Failure, and Parodoxical Emboli.

A 58-year-old male with an unknown medical history presented with acute encephalopathy, receptive aphasia, and hypertensive emergency. The patient did not have any family members from whom a collateral history could be obtained. He underwent X-rays of the abdomen and bilateral humeri/femurs to check for foreign bodies. He was found to have right femoral open reduction and internal fixation with retained screw fragments. He was diagnosed with ischemic stroke on MRI. Transthoracic echocardiogram (TTE) revealed right-sided heart failure and a tricuspid valve mass as well as right to left shunting. This raised concern for large atrial septal defect (ASD) with paradoxical embolization from tricuspid valve mass. Transesophageal echocardiogram (TEE) redemonstrated large ASD. Concern was raised for the ASD closure device as the cause of this "tricuspid mass." Due to history of orthopedic procedure, it was hypothesized that the patient had an IVC filter placed in the setting of pulmonary embolism (PE) prior to an orthopedic procedure. The tricuspid valve was visualized under fluoroscopy and was confirmed to be a migrated IVC filter. He was taken to the operating room (OR) for cardiac surgery for the removal of the IVC filter and repair of ASD. Surprisingly, no ASD was found.

Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review.

Autism spectrum disorder (ASD) is a brain condition characterized by diverse signs and symptoms that appear in early childhood. ASD is also associated with communication deficits and repetitive behavior in affected individuals. Various ASD detection methods have been developed, including neuroimaging modalities and psychological tests. Among these methods, magnetic resonance imaging (MRI) imaging modalities are of paramount importance to physicians. Clinicians rely on MRI modalities to diagnose ASD accurately. The MRI modalities are non-invasive methods that include functional (fMRI) and structural (sMRI) neuroimaging methods. However, diagnosing ASD with fMRI and sMRI for specialists is often laborious and time-consuming; therefore, several computer-aided design systems (CADS) based on artificial intelligence (AI) have been developed to assist specialist physicians. Conventional machine learning (ML) and deep learning (DL) are the most popular schemes of AI used for diagnosing ASD. This study aims to review the automated detection of ASD using AI. We review several CADS that have been developed using ML techniques for the automated diagnosis of ASD using MRI modalities. There has been very limited work on the use of DL techniques to develop automated diagnostic models for ASD. A summary of the studies developed using DL is provided in the Supplementary Appendix. Then, the challenges encountered during the automated diagnosis of ASD using MRI and AI techniques are described in detail. Additionally, a graphical comparison of studies using ML and DL to diagnose ASD automatically is discussed. We suggest future approaches to detecting ASDs using AI techniques and MRI neuroimaging.

Empirical Study of Autism Spectrum Disorder Diagnosis Using Facial Images by Improved Transfer Learning Approach.

Autism spectrum disorder (ASD) is a neurological illness characterized by deficits in cognition, physical activities, and social skills. There is no specific medication to treat this illness; only early intervention can improve brain functionality. Since there is no medical test to identify ASD, a diagnosis might be challenging. In order to determine a diagnosis, doctors consider the child's behavior and developmental history. The human face can be used as a biomarker as it is one of the potential reflections of the brain and thus can be used as a simple and handy tool for early diagnosis. This study uses several deep convolutional neural network (CNN)-based transfer learning approaches to detect autistic children using the facial image. An empirical study is conducted to select the best optimizer and set of hyperparameters to achieve better prediction accuracy using the CNN model. After training and validating with the optimized setting, the modified Xception model demonstrates the best performance by achieving an accuracy of 95% on the test set, whereas the VGG19, ResNet50V2, MobileNetV2, and EfficientNetB0 achieved 86.5%, 94%, 92%, and 85.8%, accuracy, respectively. Our preliminary computational results demonstrate that our transfer learning approaches outperformed existing methods. Our modified model can be employed to assist doctors and practitioners in validating their initial screening to detect children with ASD disease.

The diagnosis of ASD using multiple machine learning techniques.

Autism Spectrum Disorder (ASD) is a highly heterogeneous set of neurodevelopmental disorders with the global prevalence estimates of 2.20%, according to DSM5 criteria. With the advancements of technology and availability of huge amount of data, assistive tools for diagnosis of ASD are being developed using machine learning techniques. The present study examines the possibility of automating the Autism diagnostic tool using various machine learning techniques on a dataset of 701 samples that contains 10 fields from AQ-10-Adult and 10 from individual characteristics. It takes two scenarios into consideration. First one is ideal case, where there are no missing values in the test cases. In this case Artificial Neural Network (ANN), Support Vector Machine (SVM) and Random Forest (RF) classifiers are trained and tested on the pre-processed dataset. To reduce computational complexity Recursive Feature Elimination (RFE) based feature selection algorithm is applied. To deal with the real-world data, in the second case missing values are introduced in the test dataset for the fields' 'age', 'gender', 'jaundice', 'autism', 'used_app_before' and their three combinations. Support Vector Machine, Random Forest, Decision Tree and Logistic Regression based RFE algorithm is introduced to handle this scenario. ANN, SVM and RF classifier based learning models are trained with all the cases. Twelve classification models were generated with RFE, out of which best performing models specific to missing value were evaluated using test cases and suggested for ASD Diagnosis.

Plasma metabolomics of autism spectrum disorder and influence of shared components in proband families.

Prevalence of autism spectrum disorder (ASD) has been increasing in the United States in the past decades. The exact mechanisms remain enigmatic, and diagnosis of the disease still relies primarily on assessment of behavior. We first used a case-control design (75 idiopathic cases and 29 controls, enrolled at Boston Children's Hospital from 2007-2012) to identify plasma biomarkers of ASD through a metabolome-wide association study approach. Then we leveraged a family-based design (31 families) to investigate the influence of shared genetic and environmental components on the autism-associated features. Using untargeted high-resolution mass spectrometry metabolomics platforms, we detected 19 184 features. Of these, 191 were associated with ASD (false discovery rate < 0.05). We putatively annotated 30 features that had an odds ratio (OR) between <0.01 and 5.84. An identified endogenous metabolite, O-phosphotyrosine, was associated with an extremely low autism odds (OR 0.17; 95% confidence interval 0.06-0.39). We also found that glutathione metabolism was associated with ASD (P = 0.048). Correlations of the significant features between proband and parents were low (median = 0.09). Of the 30 annotated features, the median correlations within families (proband-parents) were -0.15 and 0.24 for the endogenous and exogenous metabolites, respectively. We hypothesize that, without feature identification, family-based correlation analysis of autism-associated features can be an alternative way to assist the prioritization of potentially diagnostic features. A panel of ASD diagnostic metabolic markers with high specificity could be derived upon further studies.

Autism Detection in Children by Combined Use of Gaze Preference and the M-CHAT-R in a Resource-Scarce Setting.

Most children with autism spectrum disorder (ASD), in resource-limited settings (RLS), are diagnosed after the age of four. Our work confirmed and extended results of Pierce that eye tracking could discriminate between typically developing (TD) children and those with ASD. We demonstrated the initial 15 s was at least as discriminating as the entire video. We evaluated the GP-MCHAT-R, which combines the first 15 s of manually-coded gaze preference (GP) video with M-CHAT-R results on 73 TD children and 28 children with ASD, 36-99 months of age. The GP-MCHAT-R (AUC = 0.89 (95%CI: 0.82-0.95)), performed significantly better than the MCHAT-R (AUC = 0.78 (95%CI: 0.71-0.85)) and gaze preference (AUC = 0.76 (95%CI: 0.64-0.88)) alone. This tool may enable early screening for ASD in RLS.

"I don't feel different. But then again, I wouldn't know what it feels like to be normal": Perspectives of Adolescents with Autism Spectrum Disorder.

There is minimal research regarding the personal experiences and perceptions of youth with autism spectrum disorder (ASD). Yet, the positive and negative perceptions that youth internalize about their diagnoses are crucial, as they may have a strong impact on individuals' self-concept and well-being. This paper utilizes mixed methods to describe the perceptions of 38 adolescents with ASD about their diagnoses, as elicited via semi-structured interviews. Quantitative analyses explore links between youths' perceptions and other aspects of their social-emotional well-being. Implications are highlighted regarding the importance of shifting the narrative that individuals with ASD develop about themselves and their diagnoses.

Diagnostic Utility of the ADI-R and DSM-5 in the Assessment of Latino Children and Adolescents.

Latino children in the US are systematically underdiagnosed with Autism Spectrum Disorder (ASD); therefore, it is important that recent changes to the diagnostic process do not exacerbate this pattern of under-identification. Previous research has found that the Autism Diagnostic Interview-Revised (ADI-R) algorithm, based on the Diagnostic and Statistical Manual of Mental Disorder, Fourth Edition, Text Revision (DSM-IV-TR), has limitations with Latino children of Spanish speaking parents. We evaluated whether an ADI-R algorithm based on the new DSM-5 classification for ASD would be more sensitive in identifying Latino children of Spanish speaking parents who have a clinical diagnosis of ASD. Findings suggest that the DSM-5 algorithm shows better sensitivity than the DSM-IV-TR algorithm for Latino children.

Autism spectrum disorders and their treatment with psychotropic medications in a nationally representative outpatient sample: 1994-2009.

PURPOSE: No prior studies have assessed change in health care provider-coded rates of Autism spectrum disorder (ASD) diagnoses over time, and few have investigated sociodemographic factors associated with having an ASD diagnosis, having behavioral conditions comorbid with ASD, or using psychotropic medications for this group. METHODS: We used data from the 1994-2009 National (Hospital) Ambulatory Medical Care Surveys for children aged 2-18 years (n = 158,488). RESULTS: Rates of visits with coded-ASD per 100 outpatient medical visits increased from 0.04% to 0.82% from 1994 to 2009. Factors associated with an ASD diagnosis included male gender, lack of private insurance, white race, and later study period. The most frequent comorbid behavioral diagnoses were ADHD, anxiety, disruptive behavior, and mood disorders. Older age was linked to an increased likelihood of having a comorbid behavioral diagnosis and using psychotropic medications. Geographic region was also associated with having a comorbid behavioral diagnosis, and psychotropic use was linked to have a behavioral comorbidity. Comorbidities with the highest rates of psychotropic use were ADHD, mood, and anxiety disorders. CONCLUSIONS: Pediatric outpatient visits with an ASD diagnosis have increased dramatically from 1994 to 2009. Further study is needed to determine the reasons for the observed sociodemographic disparities in ASD diagnosis.

Impact of Diagnostic Practices on the Self-Reported Health of Mothers of Recently Diagnosed Children with ASD.

OBJECTIVES: Obtaining a diagnosis of an Autism Spectrum Disorder (ASD) for a child is a pivotal point in developing the treatment plan for the child but can also be regarded as highly stressful by parents. The current study examined the impact of different aspects of the diagnosis process on the self-reported mental health of mothers of children undergoing a diagnosis for ASD in a cross-sectional cohort design. METHODS: One-hundred-fifty-eight mothers of consequently diagnosed children with ASD participated. The severity of the children's ASD and their intellectual functioning was assessed within twelve months of the diagnosis, and the mothers completed a psychometric assessment battery including the Hospital Anxiety and Depression Scale, General Health Questionnaire, and Questionnaire on Resources and Stress. RESULTS: The actual time from first reporting a problem to obtaining a diagnosis, and the speed of the diagnostic process from first to last appointment, were both negatively related to patenting stress. In contrast, mothers' perceptions of the speed and helpfulness of the process were negatively related to levels of anxiety and depression. The number of professionals involved in the process and the perceived coherence of the diagnosis were also negatively related to aspects of mothers' functioning. CONCLUSIONS: Care is needed to help mothers through the diagnostic process with regard to their own functioning. Providing information and help sources throughout the process, while keeping the number of professionals involved to a minimum, may improve the parent perception of the process and reduce the negative impacts of the diagnosis on the family as a whole.

Current diagnostic and treatment strategies for Lutembacher syndrome: the pivotal role of echocardiography.

Lutembacher syndrome (LS) is a rare cardiac abnormality characterized by any combination of a congenital or iatrogenic atrial septal defect (ASD) and a congenital or acquired mitral stenosis (MS). Clinical features and hemodynamic effects of LS depend on the balance of effects of the MS and the ASD. Prognosis is influenced by several factors [pulmonary vascular resistance, right ventricle (RV) compliance, size of ASD and MS severity] but the occurrence of secondary pulmonary hypertension and congestive heart failure is commonly associated with poor outcome. Echocardiography remains the gold standard for diagnosis and evaluation of LS. Timely diagnosis is critical for modifying the natural course, by allowing patients to benefit from currently available percutaneous trans-catheter therapies with favorable effects on the outcomes. This article is a review of published literature on the current diagnostic and therapeutic modalities for LS, focusing on the pivotal role of echocardiography as the key diagnostic tool. Clinical suspicion of LS should prompt extensive investigation with non-invasive and where possible, invasive technics. Multicenter registers have a potential to assist the evaluation of long term outcomes of percutaneous trans-catheter therapies in patients with LS.

African American families on autism diagnosis and treatment: the influence of culture.

Cultural factors such as health care access and autism spectrum disorder (ASD) symptom interpretations have been proposed as impacting delayed diagnosis and treatment for African American children with ASD. A qualitative study of urban African American families caring for their child with autism was conducted with 24 family members and 28 ASD professionals. Cultural caring meant families protected their child from harm including potential or actual distrustful encounters, and took action for their child and community to optimize their child's health and address the knowledge deficits of ASD within their community. Families and professionals believed cultural influences delayed families' receiving and seeking appropriate health care for the African American child with ASD affecting timely autism diagnosis and treatment.

Consideraciones sobre algunas consecuencias del diagnóstico de trastorno del espectro autista: el desplazamiento de las categorías diagnósticas del DSM-IV al DSM-V / Considérations sur certaines conséquences du diagnostic du trouble du spectre autistique: le déplacement des catégories diagnostiques du DSM-IV au DSM-V / Considerations on certain consequences of autistic spectrum disorder: the shifting of diagnosis categories from DSM-IV to DSM-V / Considerações sobre algumas consequências do diagnóstico do transtorno do espectro autista: o deslocamento das categorias de diagnóstico DSM-IV para DSM-V

El artículo se propone analizar las consecuencias que el diagnóstico de Trastorno del espectro autista (TEA), acarrea sobre los niños y sus familias y los desplazamientos de categorías y criterios diagnósticos del DSM-4 al DSM-5, poniendo en evidencia el cambio de paradigma teórico e ideológico subyacente entre ambos. Rastrea históricamente los fundamentos de los DSM, para distinguir luego en tres niveles (el teórico, clínico y técnico), algunas consecuencias del diagnóstico de TEA(AU)

The article intends to analyze the consequences that the diagnosis of Autistic Spectrum Disorder (ASD) brings upon children and their families, as well as the shifting of diagnosis categories and criteria from DSM-4 to DSM-5, highlighting the underlying theoretical and ideological change of paradigm between the two. We track the historical foundations of the DSM, in order to identify in 3 levels (theoretical, clinical, and technical) various consequences of ASD diagnosis(AU)

L'article propose d'analyser les conséquences que le diagnostic du Trouble du spectre autistique (TSA) produit sur les enfants et leur famille, ainsi que les évolutions dans les catégories et les critères diagnostiques du DSM-4 et DSM-5, mettant en évidence le changement sous-jacent du paradigme théorique et idéologique entre ces derniers. On retrace historiquement les fondements du DSM, pour ensuite identifier certaines conséquences du diagnostic du TSA sur trois niveaux (théorique, clinique, et technique)(AU)

O artigo tem como objetivo analisar as consequências do diagnóstico do Transtorno do Espectro Autista (TEA), sobre as crianças e seus familiares e os deslocamentos de categorias e critérios diagnósticos do DSM-4 para o DSM-5, destacando a mudança no paradigma teórico e ideológico subjacente entre os dois. Ele historicamente traça os fundamentos dos DSMs, e depois distingue em três níveis (teórico, clínico e técnico), algumas consequências do diagnóstico de TEA(AU)

Are urinary porphyrins a valid diagnostic biomarker of autism spectrum disorder?

A fundamental challenge to the timely diagnosis of Autism Spectrum Disorder (ASD) is the reliance on the observation of a set of aberrant behavior. Consequently, the diagnostic process requires that the child reach an age where the behaviors would typically be exhibited. The identification of a reliable biological marker (biomarker) could be of considerable benefit to the diagnostic process. As a diagnostic biomarker, porphyrins present an attractive prospect as previous studies have reported consistent findings of children with ASD showing significant elevations in porphyrin levels in contrast to controls. Furthermore, there is some evidence that ASD severity may be associated with porphyrins, which would be a valuable characteristic of any ASD biomarker. Importantly, for practical use, porphyrins can be tested non-invasively via a sample of urine. The present study sought to investigate whether porphyrin profiles can reliably be used to (a) differentiate ASD cases from healthy controls; and (b) predict ASD severity. The study compared the porphyrin levels of three groups of children aged 2-6 years: Group 1-children diagnosed with ASD (n = 70); Group 2-healthy, normally developing siblings of children diagnosed with ASD (n = 36); and Group 3-healthy, normally developing children with no known blood relative diagnosed with ASD (n = 54). The results of logistic regression analyses failed to find support for the hypotheses that porphyrin levels could be used as a valid tool to detect ASD cases or predict severity.