Cognitive constraints and lexicogrammatical variability in ASD: from diagnostic discriminators to intervention strategies
IntroductionThis study examines whether specific lexicogrammatical features can reliably differentiate individuals with autism spectrum disorder (ASD) from non-ASD individuals. Classification models using logistic regression and deep neural networks (DNN) demonstrated high performance—80% accuracy,...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Human Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2025.1606701/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849337008497885184 |
|---|---|
| author | Sumi Kato Sumi Kato Kazuaki Hanawa |
| author_facet | Sumi Kato Sumi Kato Kazuaki Hanawa |
| author_sort | Sumi Kato |
| collection | DOAJ |
| description | IntroductionThis study examines whether specific lexicogrammatical features can reliably differentiate individuals with autism spectrum disorder (ASD) from non-ASD individuals. Classification models using logistic regression and deep neural networks (DNN) demonstrated high performance—80% accuracy, 82% precision, 73% sensitivity, and 87% specificity. To clarify which linguistic variables contribute to this differentiation, the analysis focused on identifying key syntactic features associated with ASD-specific patterns of lexicogrammatical choices.MethodsThis study used the Tag Linear Model, developed in prior work, which enables identification of specific lexicogrammatical discriminators. Although DNN models achieved higher predictive accuracy, their internal processes were not interpretable. To identify statistically significant features, we applied a logistic regression with 10,000 bootstrap iterations; p-values derived from this procedure indicated the statistical significance of each feature. The linear model thus provided transparent evidence of differences in lexicogrammatical features between ASD and non-ASD individuals.ResultsOf the 135 lexicogrammatical items analyzed, 46 were identified asstatistically significant discriminators (p < 0.05) between ASD and non-ASD speakers. From these 46 discriminators, 20 showing variation at the clause and phrase level were selected for detailed analysis. These were grouped into seven cognitive-functional domains implicated in ASD, including working memory, inferencing, joint attention, and mental space construction.DiscussionThese findings suggest that syntactic variation in ASD reflects underlying domain-specific cognitive constraints. Linking lexicogrammatical features to cognitive-functional domains provides a linguistically grounded perspective on the neurocognitive profiles of ASD and informs future diagnostic and intervention approaches. |
| format | Article |
| id | doaj-art-66876e243c7343bebb31fc92982b980e |
| institution | Kabale University |
| issn | 1662-5161 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Human Neuroscience |
| spelling | doaj-art-66876e243c7343bebb31fc92982b980e2025-08-20T03:44:50ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612025-08-011910.3389/fnhum.2025.16067011606701Cognitive constraints and lexicogrammatical variability in ASD: from diagnostic discriminators to intervention strategiesSumi Kato0Sumi Kato1Kazuaki Hanawa2Department of Neuropsychiatry, Graduate School of Medicine, Hirosaki University, Hirosaki, JapanFaculty of Management and Law, Aomori Chuo Gakuin University, Aomori, JapanNatural Language Processing Lab, Graduate School of Information Sciences, Tohoku University, Sendai, JapanIntroductionThis study examines whether specific lexicogrammatical features can reliably differentiate individuals with autism spectrum disorder (ASD) from non-ASD individuals. Classification models using logistic regression and deep neural networks (DNN) demonstrated high performance—80% accuracy, 82% precision, 73% sensitivity, and 87% specificity. To clarify which linguistic variables contribute to this differentiation, the analysis focused on identifying key syntactic features associated with ASD-specific patterns of lexicogrammatical choices.MethodsThis study used the Tag Linear Model, developed in prior work, which enables identification of specific lexicogrammatical discriminators. Although DNN models achieved higher predictive accuracy, their internal processes were not interpretable. To identify statistically significant features, we applied a logistic regression with 10,000 bootstrap iterations; p-values derived from this procedure indicated the statistical significance of each feature. The linear model thus provided transparent evidence of differences in lexicogrammatical features between ASD and non-ASD individuals.ResultsOf the 135 lexicogrammatical items analyzed, 46 were identified asstatistically significant discriminators (p < 0.05) between ASD and non-ASD speakers. From these 46 discriminators, 20 showing variation at the clause and phrase level were selected for detailed analysis. These were grouped into seven cognitive-functional domains implicated in ASD, including working memory, inferencing, joint attention, and mental space construction.DiscussionThese findings suggest that syntactic variation in ASD reflects underlying domain-specific cognitive constraints. Linking lexicogrammatical features to cognitive-functional domains provides a linguistically grounded perspective on the neurocognitive profiles of ASD and informs future diagnostic and intervention approaches.https://www.frontiersin.org/articles/10.3389/fnhum.2025.1606701/fullautism spectrum disorder (ASD)natural language processing (NLP)machine learningdiagnostic assessmentcorpuslexicogrammatical discriminator |
| spellingShingle | Sumi Kato Sumi Kato Kazuaki Hanawa Cognitive constraints and lexicogrammatical variability in ASD: from diagnostic discriminators to intervention strategies Frontiers in Human Neuroscience autism spectrum disorder (ASD) natural language processing (NLP) machine learning diagnostic assessment corpus lexicogrammatical discriminator |
| title | Cognitive constraints and lexicogrammatical variability in ASD: from diagnostic discriminators to intervention strategies |
| title_full | Cognitive constraints and lexicogrammatical variability in ASD: from diagnostic discriminators to intervention strategies |
| title_fullStr | Cognitive constraints and lexicogrammatical variability in ASD: from diagnostic discriminators to intervention strategies |
| title_full_unstemmed | Cognitive constraints and lexicogrammatical variability in ASD: from diagnostic discriminators to intervention strategies |
| title_short | Cognitive constraints and lexicogrammatical variability in ASD: from diagnostic discriminators to intervention strategies |
| title_sort | cognitive constraints and lexicogrammatical variability in asd from diagnostic discriminators to intervention strategies |
| topic | autism spectrum disorder (ASD) natural language processing (NLP) machine learning diagnostic assessment corpus lexicogrammatical discriminator |
| url | https://www.frontiersin.org/articles/10.3389/fnhum.2025.1606701/full |
| work_keys_str_mv | AT sumikato cognitiveconstraintsandlexicogrammaticalvariabilityinasdfromdiagnosticdiscriminatorstointerventionstrategies AT sumikato cognitiveconstraintsandlexicogrammaticalvariabilityinasdfromdiagnosticdiscriminatorstointerventionstrategies AT kazuakihanawa cognitiveconstraintsandlexicogrammaticalvariabilityinasdfromdiagnosticdiscriminatorstointerventionstrategies |