Enhancing early autism diagnosis through machine learning: Exploring raw motion data for classification.

In recent years, research has been demonstrating that movement analysis, utilizing machine learning methods, can be a promising aid for clinicians in supporting autism diagnostic process. Within this field of research, we aim to explore new models and delve into the detailed observation of certain features that previous literature has identified as prominent in the classification process. Our study employs a game-based tablet application to collect motor data. We use artificial neural networks to analyze raw trajectories in a "drag and drop" task. We compare a two-features model (utilizing only raw coordinates) with a four-features model (including velocities and accelerations). The aim is to assess the effectiveness of raw data analysis and determine the impact of acceleration on autism classification. Our results revealed that both models demonstrate promising accuracy in classifying motor trajectories. The four-features model consistently outperforms the two-features model, as evidenced by accuracy values (0.90 vs. 0.76). However, our findings support the potential of raw data analysis in objectively assessing motor behaviors related to autism. While the four-features model excels, the two-features model still achieves reasonable accuracy. Addressing limitations related to sample size and noise is essential for future research. Our study emphasizes the importance of integrating intelligent solutions to enhance and assist autism traditional diagnostic process and intervention, paving the way for more effective tools in assessing motor skills.

A deep learning latent variable model to identify children with autism through motor abnormalities.

Introduction: Autism Spectrum Disorder (ASD) is a by-birth neurodevelopmental disorder difficult to diagnose owing to the lack of clinical objective and quantitative measures. Classical diagnostic processes are time-consuming and require many specialists' collaborative efforts to be properly accomplished. Most recent research has been conducted on automated ASD detection using advanced technologies. The proposed model automates ASD detection and provides a new quantitative method to assess ASD. Methods: The theoretical framework of our study assumes that motor abnormalities can be a potential hallmark of ASD, and Machine Learning may represent the method of choice to analyse them. In this study, a variational autoencoder, a particular type of Artificial Neural Network, is used to improve ASD detection by analysing the latent distribution description of motion features detected by a tablet-based psychometric scale. Results: The proposed ASD detection model revealed that the motion features of children with autism consistently differ from those of children with typical development. Discussion: Our results suggested that it could be possible to identify potential motion hallmarks typical for autism and support clinicians in their diagnostic process. Potentially, these measures could be used as additional indicators of disorder or suspected diagnosis.

Pregnancy in autistic women and social medical considerations: scoping review and meta- synthesis.

Introduction: This article addresses a topic that has been largely overlooked by scientific literature, namely pregnancy in autistic women. Generally, the issue of sexuality in disability, particularly in disabled women, autistic or otherwise, has been underexplored. However, it is necessary to scientifically investigate this topic to propose adequate social and health policies. Therefore, we chose to conduct a scoping review to answer three main questions: "What does it mean for an autistic woman to be pregnant?"; "How do these two conditions coexist?"; "Are health services prepared to receive this population adequately or does autism become a stigma for pregnant women?" Methods: We conducted a systematic review and qualitative thematic synthesis following the Preferred Reporting Guidelines for Systematic Reviews and Meta-Analyses on autistic women and pregnancy in the last 10 years. Results: The studies included in our review are 7, extremely diverse in terms of methodologies and sample sizes. Despite the heterogeneity of samples and methodologies, all research tends to highlight the following results. For autistic women during pregnancy, three areas seem to be the most difficult: sensory issues, mood disorders, and relationships with specialists. Discussion: Our study found that women with ASD face unique challenges during childbirth that differ from those of neurotypical women. Participants often felt belittled, ignored, and uninformed about the care they received, and being placed at the centre of attention was often seen as negative and hindering rather than positive. However, the research shows us how some "expected" results, such as difficulties in breastfeeding, have been disproven.

Age-Related Differences in Psychological Distress during the COVID-19 Pandemic.

While the negative impact of COVID-19 total lockdown on mental health in youth has been extensively studied, findings collected during subsequent waves of the pandemic, in which restrictive rules were more eased, are very sparse. Here, we explore perceived psychological distress during the partial lockdown of the third wave in Southern Italy in a large sample of students, focusing on age and gender differences. Also, we assessed whether attending the type of education could have a protective role on students' psychological well-being. An online survey was completed by 1064 southern Italian students (age range: 8-19 years; males = 368) from March to July 2021. The survey consists of a set of questions regarding general sociodemographic information as well as several aspects of students' psychological well-being. Psychological distress was higher in high school students compared to both elementary and middle ones. In addition, we found gender differences, but only in high school students, with females reporting higher psychological distress than males. Finally, our mediation analysis showed a mediated role of face-to-face schooling in the relationship between age and psychological distress. In conclusion, this study highlights age-related differences in psychological distress during the pandemic and the protective role of school in presence for mental health in Italian students.

Examining Predictors of Different ABA Treatments: A Systematic Review.

In the recent literature, there is a broad consensus on the effectiveness of Applied Behavior Analysis interventions for autism spectrum disorder (ASD). Despite their proven efficacy, research in clinical settings shows that these treatments are not equally effective for all children and the issue of which intervention should be chosen for an individual remains a common dilemma. The current work systematically reviewed studies on predictors and moderators of response to different types of evidence-based treatment for children with ASD. Specifically, our goal was to critically review the relationships between pre-treatment child characteristics and specific treatment outcomes, covering different aspects of functioning (i.e., social, communicative, adaptive, cognitive, motor, global functioning, play, and symptom severity). Our results questioned the binomial "better functioning-better outcome", emphasizing the complex interplay between pre-treatment child characteristics and treatment outcomes. However, some pre-treatment variables seem to act as prerequisites for a specific treatment, and the issue of "what works for whom and why" remains challenging. Future research should focus on the definition of evidence-based decision-making models that capture those individual factors through which a specific intervention will exert its effects.

Using Technology to Identify Children With Autism Through Motor Abnormalities.

Autism is a neurodevelopmental disorder typically assessed and diagnosed through observational analysis of behavior. Assessment exclusively based on behavioral observation sessions requires a lot of time for the diagnosis. In recent years, there is a growing need to make assessment processes more motivating and capable to provide objective measures of the disorder. New evidence showed that motor abnormalities may underpin the disorder and provide a computational marker to enhance assessment and diagnostic processes. Thus, a measure of motor patterns could provide a means to assess young children with autism and a new starting point for rehabilitation treatments. In this study, we propose to use a software tool that through a smart tablet device and touch screen sensor technologies could be able to capture detailed information about children's motor patterns. We compared movement trajectories of autistic children and typically developing children, with the aim to identify autism motor signatures analyzing their coordinates of movements. We used a smart tablet device to record coordinates of dragging movements carried out by 60 children (30 autistic children and 30 typically developing children) during a cognitive task. Machine learning analysis of children's motor patterns identified autism with 93% accuracy, demonstrating that autism can be computationally identified. The analysis of the features that most affect the prediction reveals and describes the differences between the groups, confirming that motor abnormalities are a core feature of autism.