Development of personalized profiles of students with autism spectrum disorder for interactive interventions with robots to enhance language and social skills DOI Creative Commons
Javier Herrero, David Fonseca, Selene Caro-Via

и другие.

Frontiers in Psychiatry, Год журнала: 2024, Номер 15

Опубликована: Ноя. 13, 2024

The inclusion of students with autism spectrum disorder (ASD) in mainstream education (primary and secondary, the range 4-5 to 8-10 years old) is a complex task that has long challenged both educators health professionals. However, correct use digital technologies such as personalization settings interaction robots clearly shown how these new can benefit ASD students. it essential characterize profile, problems, needs each student, since not possible generalize an accessible approach for all users. work presented shows creation validation, through pilot tests, instrument outlines main student ASD, based on behavioral variables. In later phase, instructional sequences will be designed adapted tablets robot improve specific aspects identified initial profile. results demonstrate method’s ability assess prioritize profiles satisfactorily which helps create design adjusted student. first tests have been well received by students, who increased interest contents methods used this approach. Motivation levels engagement also increased, social interactions their peers improved.

Язык: Английский

Linguistic Markers of Autism Spectrum Disorder in Narrative Production: Evidence From the Monkey Cartoon Storytelling Task of the Autism Diagnostic Observation Schedule DOI Creative Commons
Eleni Peristeri, Katerina Drakoulaki,

Antonia Boznou

и другие.

Autism & Developmental Language Impairments, Год журнала: 2025, Номер 10

Опубликована: Март 1, 2025

Background and aims The Autism Diagnostic Observation Schedule (ADOS-2) is considered a “gold standard” diagnostic instrument in the assessment of autism spectrum disorder (ASD). Monkey Cartoon task an optional pictured storytelling ADOS-2, which has been designed to assess gestural verbal communication autistic children while telling story. It well established that challenging for children, particularly content coherent organization story, also known as narrative macrostructure. Existing evidence on efficacy pinpoint differences between neurotypical individuals macrostructure scant. In this study, we used version with modified scoring analyze macrostructural skills two groups without ASD. We investigated relations language ability each group. Methods A group 16 Greek-speaking age- IQ-matched were administered task. Children's vocabulary syntactic measured. Narratives analyzed terms features, including story completeness grammar, units denoting setting, internal responses added details. Results had lower scores communicating rather than grammar. Moreover, tended include less information story's setting more off-topic utterances their peers. Regarding ability, dissociated since rely at expense irrelevant narratives, relied both lexical skills, especially when instantiating references characters’ mental states respectively. Conclusions seems be efficient revealing pragmatic weaknesses mainly thematic level children. Also, frequent use semantically- pragmatically-irrelevant differentiated from may thus treated distinguishing feature ASD production. Implications findings demonstrate viability highlighting markers macrostructure, clinical implications enhancing practice countries like Greece face shortage tools

Язык: Английский

Процитировано

0
Metaphor comprehension and production in verbally able children with Autism Spectrum Disorder DOI Creative Commons

Stella Lampri,

Eleni Peristeri, Theodoros Marinis

и другие.

Autism Research, Год журнала: 2024, Номер 17(11), С. 2292 - 2304

Опубликована: Авг. 9, 2024

Research in the field of figurative language processing Autism Spectrum Disorders (ASD) has demonstrated that autistic individuals experience systematic difficulties comprehension different types metaphors. However, there is scarce evidence regarding metaphor production skills ASD. Importantly, exact source ASD remains largely controversial. The debate mainly focused on mediating role structural (i.e., lexical knowledge) and cognitive abilities Theory Mind executive functions) individuals' ability to comprehend generate present study examines 18 Greek-speaking verbally able children with 31 typically-developing (TD) controls. Participants completed two tasks, namely, a low-verbal multiple-choice sentence-picture matching task tested their conventional predicate metaphors, sentence continuation assessed also included measures fluid intelligence, expressive vocabulary, working memory within sample. results show group had significantly lower performance than TD both production. findings reveal vocabulary were key factor Working capacity was found correlate group. Conversely, no correlations neither above factors. Of note, generated more inappropriate responses no-responses compared control overall difficulty comprehending using metaphorical language. indicate may employ diverse strategies or rely underlying when metaphors

Язык: Английский

Процитировано

3
Reliable Autism Spectrum Disorder Diagnosis for Pediatrics Using Machine Learning and Explainable AI DOI Creative Commons
Insu Jeon, Minjoong Kim,

Dayeong So

и другие.

Diagnostics, Год журнала: 2024, Номер 14(22), С. 2504 - 2504

Опубликована: Ноя. 8, 2024

Background: As the demand for early and accurate diagnosis of autism spectrum disorder (ASD) increases, integration machine learning (ML) explainable artificial intelligence (XAI) is emerging as a critical advancement that promises to revolutionize intervention strategies by improving both accuracy transparency. Methods: This paper presents method combines XAI techniques with rigorous data-preprocessing pipeline improve interpretability ML-based diagnostic tools. Our preprocessing included outlier removal, missing data handling, selecting pertinent features based on clinical expert advice. Using R caret package (version 6.0.94), we developed compared several ML algorithms, validated using 10-fold cross-validation optimized grid search hyperparameter tuning. were employed model transparency, offering insights into how contribute predictions, thereby enhancing clinician trust. Results: Rigorous improved models’ generalizability real-world applicability across diverse datasets, ensuring robust performance. Neural networks extreme gradient boosting models achieved best performance in terms accuracy, precision, recall. demonstrated behavioral significantly influenced leading greater interpretability. Conclusions: study successfully highly precise interpretable ASD diagnosis, connecting advanced methods practical application supporting adoption AI-driven tools healthcare professionals. study’s findings personalized practices, ultimately outcomes quality life individuals ASD.

Язык: Английский

Процитировано

3
Early detection of mental health disorders using machine learning models using behavioral and voice data analysis DOI Creative Commons
Sunil Kumar Sharma, Ahmed I. Alutaibi, Ahmad Raza Khan

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Май 13, 2025

Язык: Английский

Процитировано

0
Speech and language patterns in autism: towards natural language processing as a research and clinical tool DOI
Jadyn Trayvick, Sarah B. Barkley, Alessia McGowan

и другие.

Psychiatry Research, Год журнала: 2024, Номер 340, С. 116109 - 116109

Опубликована: Июль 30, 2024

Язык: Английский

Процитировано

2
Data-centric automated approach to predict autism spectrum disorder based on selective features and explainable artificial intelligence DOI Creative Commons
Asma Aldrees, Stephen Ojo, J. A. Wanliss

и другие.

Frontiers in Computational Neuroscience, Год журнала: 2024, Номер 18

Опубликована: Окт. 21, 2024

Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by notable challenges in cognitive function, understanding language, recognizing objects, interacting with others, and communicating effectively. Its origins are mainly genetic, identifying it early intervening promptly can reduce the necessity for extensive medical treatments lengthy diagnostic procedures those impacted ASD. This research designed two types of experimentation ASD analysis. In first set experiments, authors utilized three feature engineering techniques (Chi-square, backward elimination, PCA) multiple machine learning models autism presence prediction toddlers. The proposed XGBoost 2.0 obtained 99% accuracy, F1 score, recall 98% precision chi-square significant features. second scenario, main focus shifts to tailored educational methods children through assessment their behavioral, verbal, physical responses. Again, approach performs well recall, precision. this research, cross-validation technique also implemented check stability model along comparison previously published works show significance model. study aims develop personalized strategies individuals using meet specific needs better.

Язык: Английский

Процитировано

2
Development of personalized profiles of students with autism spectrum disorder for interactive interventions with robots to enhance language and social skills DOI Creative Commons
Javier Herrero, David Fonseca, Selene Caro-Via

и другие.

Frontiers in Psychiatry, Год журнала: 2024, Номер 15

Опубликована: Ноя. 13, 2024

The inclusion of students with autism spectrum disorder (ASD) in mainstream education (primary and secondary, the range 4-5 to 8-10 years old) is a complex task that has long challenged both educators health professionals. However, correct use digital technologies such as personalization settings interaction robots clearly shown how these new can benefit ASD students. it essential characterize profile, problems, needs each student, since not possible generalize an accessible approach for all users. work presented shows creation validation, through pilot tests, instrument outlines main student ASD, based on behavioral variables. In later phase, instructional sequences will be designed adapted tablets robot improve specific aspects identified initial profile. results demonstrate method’s ability assess prioritize profiles satisfactorily which helps create design adjusted student. first tests have been well received by students, who increased interest contents methods used this approach. Motivation levels engagement also increased, social interactions their peers improved.

Язык: Английский

Процитировано

1