Informing Developmental Milestone Achievement for Children With Autism: Machine Learning Approach

Systematic bibliometric and visualized analysis of research hotspots and trends in artificial intelligence in autism spectrum disorder

Background

Artificial intelligence (AI) has been the subject of studies in autism spectrum disorder (ASD) and may affect its identification, diagnosis, intervention, and other medical practices in the future. Although previous studies have used bibliometric techniques to analyze and investigate AI, there has been little research on the adoption of AI in ASD. This study aimed to explore the broad applications and research frontiers of AI used in ASD.

Methods

Citation data were retrieved from the Web of Science Core Collection (WoSCC) database to assess the extent to which AI is used in ASD. CiteSpace.5.8. R3 and VOSviewer, two online tools for literature metrology analysis, were used to analyze the data.

Results

A total of 776 publications from 291 countries and regions were analyzed; of these, 256 publications were from the United States and 173 publications were from China, and England had the largest centrality of 0.33; Stanford University had the highest H-index of 17; and the largest cluster label of co-cited references was machine learning. In addition, keywords with a high number of occurrences in this field were autism spectrum disorder (295), children (255), classification (156) and diagnosis (77). The burst keywords from 2021 to 2023 were infants and feature selection, and from 2022 to 2023, the burst keyword was corpus callosum.

Conclusion

This research provides a systematic analysis of the literature concerning AI used in ASD, presenting an overall demonstration in this field. In this area, the United States and China have the largest number of publications, England has the greatest influence, and Stanford University is the most influential. In addition, the research on AI used in ASD mostly focuses on classification and diagnosis, and "infants, feature selection, and corpus callosum are at the forefront, providing directions for future research. However, the use of AI technologies to identify ASD will require further research.

Influence of User Profile Attributes on e-Cigarette-Related Searches on YouTube: Machine Learning Clustering and Classification

Background

The proliferation of e-cigarette content on YouTube is concerning because of its possible effect on youth use behaviors. YouTube has a personalized search and recommendation algorithm that derives attributes from a user's profile, such as age and sex. However, little is known about whether e-cigarette content is shown differently based on user characteristics.

Objective

The aim of this study was to understand the influence of age and sex attributes of user profiles on e-cigarette-related YouTube search results.

Methods

We created 16 fictitious YouTube profiles with ages of 16 and 24 years, sex (female and male), and ethnicity/race to search for 18 e-cigarette-related search terms. We used unsupervised (k-means clustering and classification) and supervised (graph convolutional network) machine learning and network analysis to characterize the variation in the search results of each profile. We further examined whether user attributes may play a role in e-cigarette-related content exposure by using networks and degree centrality.

Results

We analyzed 4201 nonduplicate videos. Our k-means clustering suggested that the videos could be clustered into 3 categories. The graph convolutional network achieved high accuracy (0.72). Videos were classified based on content into 4 categories: product review (49.3%), health information (15.1%), instruction (26.9%), and other (8.5%). Underage users were exposed mostly to instructional videos (37.5%), with some indication that more female 16-year-old profiles were exposed to this content, while young adult age groups (24 years) were exposed mostly to product review videos (39.2%).

Conclusions

Our results indicate that demographic attributes factor into YouTube's algorithmic systems in the context of e-cigarette-related queries on YouTube. Specifically, differences in the age and sex attributes of user profiles do result in variance in both the videos presented in YouTube search results as well as in the types of these videos. We find that underage profiles were exposed to e-cigarette content despite YouTube's age-restriction policy that ostensibly prohibits certain e-cigarette content. Greater enforcement of policies to restrict youth access to e-cigarette content is needed.

Individual and cumulative risk factors in developmental language disorder: A case-control study

Many mental disorders (MD) share common etiology, fuelling debates about the specificity of clinical categories and whether the presence of specific risk factors (RF) can distinguish among them. The study of developmental language disorder (DLD), more specifically, has been further hindered by a lack of consensus regarding its definition. These limitations increase the risk of under-detection and lifelong consequences for affected children. This paper aims (1) to document which individual RF allow differentiating DLD from other MD and (2) to compare the cumulative RF between children with DLD versus other MD. This case-control design study used medical records of a psychiatric sample of 795 preschoolers (mean age 4:11, 75% boys). A logistic regression measured the predictive value of potential RF on DLD. Later first sentences, maternal immigration and family history of language delay were identified as significant in explaining 30% of the variance for DLD diagnosis. An ANCOVA revealed that children with DLD were exposed to a significantly higher number of RF than were children with other MD. Public health policies informed with the knowledge of specific RF associated with DLD, and their cumulative impact, could improve early detection and reduce the cascade of negative consequences associated with DLD.

Sleep in Children with Autism Spectrum Disorder: A Narrative Review and Systematic Update

Purpose of Review

Sleep problems are a common comorbidity for children with autism spectrum disorder (ASD), and research in this area has a relatively long history. Within this review, we first outline historic patterns in the field of sleep and ASD. Second, we conducted a systematic update and coded these studies based on their alignment with historic patterns. Research on ASD and sleep over the past two decades has primarily focused on four principal areas: (1) documenting the prevalence and types of sleep problems; (2) sleep problem treatment options and efficacy; (3) how sleep problems are associated with other behavioral, contextual, or biological elements; and (4) the impact of child sleep problems on families and care providers. The systematic update in this paper includes empirical studies published between 2018 and 2021 with terms for sleep and ASD within the title, keywords, or abstract.

Recent Findings

In sum, 60 studies fit the inclusion/exclusion criteria and most fit within the historic patterns noted above. Notable differences included more global representation in study samples, studies on the impacts of COVID-19, and a growing body of work on sleep problems as an early marker of ASD. The majority of studies focus on correlates of sleep problems noting less optimal behavioral, contextual, and biological elements are associated with sleep problems across development for children with ASD.

Summary

Recommendations for future directions include continued expansion of global and age representation across samples, a shift toward more treatment and implementation science, and studies that inform our mechanistic understanding of how sleep and ASD are connected.

Supplementary Information

The online version contains supplementary material available at 10.1007/s40675-022-00234-5.