RESUMEN
BACKGROUND: Autism Spectrum Disorder (ASD) diagnosis can be aided by approaches based on eye-tracking signals. Recently, the feasibility of building Visual Attention Models (VAMs) from features extracted from visual stimuli and their use for classifying cases and controls has been demonstrated using Neural Networks and Support Vector Machines. The present work has three aims: 1) to evaluate whether the trained classifier from the previous study was generalist enough to classify new samples with a new stimulus; 2) to replicate the previously approach to train a new classifier with a new dataset; 3) to evaluate the performance of classifiers obtained by a new classification algorithm (Random Forest) using the previous and the current datasets. METHODS: The previously approach was replicated with a new stimulus and new sample, 44 from the Typical Development group and 33 from the ASD group. After the replication, Random Forest classifier was tested to substitute Neural Networks algorithm. RESULTS: The test with the trained classifier reached an AUC of 0.56, suggesting that the trained classifier requires retraining of the VAMs when changing the stimulus. The replication results reached an AUC of 0.71, indicating the potential of generalization of the approach for aiding ASD diagnosis, as long as the stimulus is similar to the originally proposed. The results achieved with Random Forest were superior to those achieved with the original approach, with an average AUC of 0.95 for the previous dataset and 0.74 for the new dataset. CONCLUSION: In summary, the results of the replication experiment were satisfactory, which suggests the robustness of the approach and the VAM-based approaches feasibility to aid in ASD diagnosis. The proposed method change improved the classification performance. Some limitations are discussed and additional studies are encouraged to test other conditions and scenarios.
Asunto(s)
Trastorno del Espectro Autista , Trastorno Autístico , Humanos , Trastorno del Espectro Autista/diagnóstico , Tecnología de Seguimiento Ocular , Diagnóstico por Computador , ComputadoresRESUMEN
Although Autism Spectrum Disorders (ASD) is recognized as being heavily influenced by genetic factors, the role of epigenetic and environmental factors is still being established. This study aimed to identify ASD vulnerability components based on familial history and intrauterine environmental stress exposure, explore possible vulnerability subgroups, access DNA methylation age acceleration (AA) as a proxy of stress exposure during life, and evaluate the association of ASD vulnerability components and AA to phenotypic severity measures. Principal Component Analysis (PCA) was used to search the vulnerability components from 67 mothers of autistic children. We found that PC1 had a higher correlation with psychosocial stress (maternal stress, maternal education, and social class), and PC2 had a higher correlation with biological factors (psychiatric family history and gestational complications). Comparing the methylome between above and below PC1 average subgroups we found 11,879 statistically significant differentially methylated probes (DMPs, p < 0.05). DMPs CpG sites were enriched in variably methylated regions (VMRs), most showing environmental and genetic influences. Hypermethylated probes presented higher rates in different regulatory regions associated with functional SNPs, indicating that the subgroups may have different affected regulatory regions and their liability to disease explained by common variations. Vulnerability components score moderated by epigenetic clock AA was associated with Vineland Total score (p = 0.0036, adjR2 = 0.31), suggesting risk factors with stress burden can influence ASD phenotype.
Asunto(s)
Trastorno del Espectro Autista/epidemiología , Trastorno del Espectro Autista/genética , Relojes Circadianos/genética , Interacción Gen-Ambiente , Adolescente , Adulto , Factores de Edad , Trastorno del Espectro Autista/etiología , Trastorno del Espectro Autista/patología , Brasil/epidemiología , Niño , Preescolar , Metilación de ADN/fisiología , Susceptibilidad a Enfermedades , Ambiente , Epigénesis Genética , Femenino , Heterogeneidad Genética , Humanos , Lactante , Recién Nacido , Masculino , Persona de Mediana Edad , Parto , Embarazo , Factores de Riesgo , Poblaciones Vulnerables/estadística & datos numéricos , Adulto JovenRESUMEN
An advantage of using eye tracking for diagnosis is that it is non-invasive and can be performed in individuals with different functional levels and ages. Computer/aided diagnosis using eye tracking data is commonly based on eye fixation points in some regions of interest (ROI) in an image. However, besides the need for every ROI demarcation in each image or video frame used in the experiment, the diversity of visual features contained in each ROI may compromise the characterization of visual attention in each group (case or control) and consequent diagnosis accuracy. Although some approaches use eye tracking signals for aiding diagnosis, it is still a challenge to identify frames of interest when videos are used as stimuli and to select relevant characteristics extracted from the videos. This is mainly observed in applications for autism spectrum disorder (ASD) diagnosis. To address these issues, the present paper proposes: (1) a computational method, integrating concepts of Visual Attention Model, Image Processing and Artificial Intelligence techniques for learning a model for each group (case and control) using eye tracking data, and (2) a supervised classifier that, using the learned models, performs the diagnosis. Although this approach is not disorder-specific, it was tested in the context of ASD diagnosis, obtaining an average of precision, recall and specificity of 90%, 69% and 93%, respectively.
Asunto(s)
Atención , Trastorno del Espectro Autista/diagnóstico , Trastorno del Espectro Autista/fisiopatología , Diagnóstico por Computador , Tecnología de Seguimiento Ocular , Fijación Ocular , Algoritmos , Diagnóstico por Computador/métodos , Movimientos Oculares , Humanos , Curva ROCRESUMEN
Pervasive developmental disorders are now commonly referred to as autism spectrum disorders (ASDs). ASDs present with a range of severity and impairments, and often are a cause of severe disability, representing a major public health concern. The diagnostic criteria require delays or abnormal functioning in social interaction, language, and/or imaginative play within the first 3 years of life, resulting in a deviation from the developmental pattern expected for the age. Because establishing a diagnosis of ASD is possible as early as 18-24 months of age, clinicians should strive to identify and begin intervention in children with ASD as soon as signs are manifest. Increasing efforts are underway to make ASD screening universal in pediatric healthcare. Given the crucial importance of early identification and multiple modalities of treatment for ASD, this review will summarize the diagnostic criteria, key areas for assessment by clinicians, specific scales and instruments for assessment, and discussion of evidence-based treatment programs and the role of specific drug therapies for symptom management.
Asunto(s)
Trastornos Generalizados del Desarrollo Infantil/diagnóstico , Trastornos Generalizados del Desarrollo Infantil/terapia , Factores de Edad , Niño , Preescolar , Manual Diagnóstico y Estadístico de los Trastornos Mentales , Medicina Basada en la Evidencia , Humanos , Tamizaje MasivoRESUMEN
Pervasive developmental disorders are now commonly referred to as autism spectrum disorders (ASDs). ASDs present with a range of severity and impairments, and often are a cause of severe disability, representing a major public health concern. The diagnostic criteria require delays or abnormal functioning in social interaction, language, and/or imaginative play within the first 3 years of life, resulting in a deviation from the developmental pattern expected for the age. Because establishing a diagnosis of ASD is possible as early as 18-24 months of age, clinicians should strive to identify and begin intervention in children with ASD as soon as signs are manifest. Increasing efforts are underway to make ASD screening universal in pediatric healthcare. Given the crucial importance of early identification and multiple modalities of treatment for ASD, this review will summarize the diagnostic criteria, key areas for assessment by clinicians, specific scales and instruments for assessment, and discussion of evidence-based treatment programs and the role of specific drug therapies for symptom management.