Implementation of generative AI for the assessment and treatment of autism spectrum disorders: a scoping review

IntroductionAutism spectrum disorder (ASD) is characterized by persistent deficits in social communication and restrictive, repetitive behaviors. Current diagnostic and intervention pathways rely heavily on clinician expertise, leading to delays and limited scalability. Generative artificial intelli...

Full description

Saved in:
Bibliographic Details
Main Authors: Jun-Seok Sohn, Eojin Lee, Jae-Jin Kim, Hyang-Kyeong Oh, Eunjoo Kim
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Psychiatry
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1628216/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387650259091456
author Jun-Seok Sohn
Eojin Lee
Jae-Jin Kim
Jae-Jin Kim
Hyang-Kyeong Oh
Eunjoo Kim
Eunjoo Kim
author_facet Jun-Seok Sohn
Eojin Lee
Jae-Jin Kim
Jae-Jin Kim
Hyang-Kyeong Oh
Eunjoo Kim
Eunjoo Kim
author_sort Jun-Seok Sohn
collection DOAJ
description IntroductionAutism spectrum disorder (ASD) is characterized by persistent deficits in social communication and restrictive, repetitive behaviors. Current diagnostic and intervention pathways rely heavily on clinician expertise, leading to delays and limited scalability. Generative artificial intelligence (GenAI) offers emerging opportunities for automatically assisting and personalizing ASD care, though technical and ethical concerns persist.MethodsWe conducted systematic searches in Embase, PsycINFO, PubMed, Scopus, and Web of Science (January 2014 to February 2025). Two reviewers independently screened and extracted eligible studies reporting empirical applications of GenAI in ASD screening, diagnosis, or intervention. Data were charted across GenAI architectures, application domains, evaluation metrics, and validation strategies. Comparative performance against baseline methods was synthesized where available.ResultsFrom 553 records, 10 studies met the inclusion criteria across three domains: (1) screening and diagnosis (e.g., transformer-based classifiers and GAN-based data augmentation), (2) assessment and intervention, (e.g., multimodal emotion recognition and feedback systems), and (3) caregiver education and support (e.g., LLM-based chatbots). While most studies reported potential performance improvements, they also highlighted limitations such as small sample sizes, data biases, limited validation, and model hallucinations. Comparative analyses were sparse and lacked standardized metrics.DiscussionThis review (i) maps GenAI applications in ASD care, (ii) compares GenAI and traditional approaches, (iii) highlights methodological and ethical challenges, and (iv) proposes future research directions. Our findings underscore GenAI’s emerging potential in autism care and the prerequisites for its ethical, transparent, and clinically validated implementation.Systematic review registrationhttps://osf.io/4gsyj/, identifier DOI: 10.17605/OSF.IO/4GSYJ.
format Article
id doaj-art-a5ccf09fb6b24397b133c258e2d78dbe
institution Kabale University
issn 1664-0640
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Psychiatry
spelling doaj-art-a5ccf09fb6b24397b133c258e2d78dbe2025-08-20T03:51:30ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402025-07-011610.3389/fpsyt.2025.16282161628216Implementation of generative AI for the assessment and treatment of autism spectrum disorders: a scoping reviewJun-Seok Sohn0Eojin Lee1Jae-Jin Kim2Jae-Jin Kim3Hyang-Kyeong Oh4Eunjoo Kim5Eunjoo Kim6Department of Medicine, Yonsei University College of Medicine, Seoul, Republic of KoreaInstitute of Behavioral Sciences in Medicine, Yonsei University College of Medicine, Seoul, Republic of KoreaInstitute of Behavioral Sciences in Medicine, Yonsei University College of Medicine, Seoul, Republic of KoreaDepartment of Psychiatry, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul, Republic of KoreaInstitute of Behavioral Sciences in Medicine, Yonsei University College of Medicine, Seoul, Republic of KoreaInstitute of Behavioral Sciences in Medicine, Yonsei University College of Medicine, Seoul, Republic of KoreaDepartment of Psychiatry, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul, Republic of KoreaIntroductionAutism spectrum disorder (ASD) is characterized by persistent deficits in social communication and restrictive, repetitive behaviors. Current diagnostic and intervention pathways rely heavily on clinician expertise, leading to delays and limited scalability. Generative artificial intelligence (GenAI) offers emerging opportunities for automatically assisting and personalizing ASD care, though technical and ethical concerns persist.MethodsWe conducted systematic searches in Embase, PsycINFO, PubMed, Scopus, and Web of Science (January 2014 to February 2025). Two reviewers independently screened and extracted eligible studies reporting empirical applications of GenAI in ASD screening, diagnosis, or intervention. Data were charted across GenAI architectures, application domains, evaluation metrics, and validation strategies. Comparative performance against baseline methods was synthesized where available.ResultsFrom 553 records, 10 studies met the inclusion criteria across three domains: (1) screening and diagnosis (e.g., transformer-based classifiers and GAN-based data augmentation), (2) assessment and intervention, (e.g., multimodal emotion recognition and feedback systems), and (3) caregiver education and support (e.g., LLM-based chatbots). While most studies reported potential performance improvements, they also highlighted limitations such as small sample sizes, data biases, limited validation, and model hallucinations. Comparative analyses were sparse and lacked standardized metrics.DiscussionThis review (i) maps GenAI applications in ASD care, (ii) compares GenAI and traditional approaches, (iii) highlights methodological and ethical challenges, and (iv) proposes future research directions. Our findings underscore GenAI’s emerging potential in autism care and the prerequisites for its ethical, transparent, and clinically validated implementation.Systematic review registrationhttps://osf.io/4gsyj/, identifier DOI: 10.17605/OSF.IO/4GSYJ.https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1628216/fullautism spectrum disordergenerative artificial intelligencelarge language modelmachine learningdeep learningmental health
spellingShingle Jun-Seok Sohn
Eojin Lee
Jae-Jin Kim
Jae-Jin Kim
Hyang-Kyeong Oh
Eunjoo Kim
Eunjoo Kim
Implementation of generative AI for the assessment and treatment of autism spectrum disorders: a scoping review
Frontiers in Psychiatry
autism spectrum disorder
generative artificial intelligence
large language model
machine learning
deep learning
mental health
title Implementation of generative AI for the assessment and treatment of autism spectrum disorders: a scoping review
title_full Implementation of generative AI for the assessment and treatment of autism spectrum disorders: a scoping review
title_fullStr Implementation of generative AI for the assessment and treatment of autism spectrum disorders: a scoping review
title_full_unstemmed Implementation of generative AI for the assessment and treatment of autism spectrum disorders: a scoping review
title_short Implementation of generative AI for the assessment and treatment of autism spectrum disorders: a scoping review
title_sort implementation of generative ai for the assessment and treatment of autism spectrum disorders a scoping review
topic autism spectrum disorder
generative artificial intelligence
large language model
machine learning
deep learning
mental health
url https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1628216/full
work_keys_str_mv AT junseoksohn implementationofgenerativeaifortheassessmentandtreatmentofautismspectrumdisordersascopingreview
AT eojinlee implementationofgenerativeaifortheassessmentandtreatmentofautismspectrumdisordersascopingreview
AT jaejinkim implementationofgenerativeaifortheassessmentandtreatmentofautismspectrumdisordersascopingreview
AT jaejinkim implementationofgenerativeaifortheassessmentandtreatmentofautismspectrumdisordersascopingreview
AT hyangkyeongoh implementationofgenerativeaifortheassessmentandtreatmentofautismspectrumdisordersascopingreview
AT eunjookim implementationofgenerativeaifortheassessmentandtreatmentofautismspectrumdisordersascopingreview
AT eunjookim implementationofgenerativeaifortheassessmentandtreatmentofautismspectrumdisordersascopingreview