REVIEW article
Front. Neurol.
Sec. Artificial Intelligence in Neurology
Volume 16 - 2025 | doi: 10.3389/fneur.2025.1587147
AI-Driven Digital Therapeutics in Screening, Diagnosis and Intervention of Autism Spectrum Disorder: Prospects and Challenges
Provisionally accepted
- 1Zhuhai Promotion Association of Mental Health, zhuahi, China
- 2Department of Breast Surgery, Affiliated Tumor Hospital, Xinjiang Medical University, Urumqi, China
- 3The University of Tokyo, Bunkyo, Japan
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Autism spectrum disorder (ASD) is a type of neurodevelopmental disorder characterized by social communication and behavioral impairments. Globally, the prevalence of autism has been steadily increasing, reaching 2.76% by 2023. Traditional diagnostic and intervention methods primarily rely on subjective scales and clinical observations, which face several challenges, including lengthy diagnostic processes, cultural biases, and limited sensitivity. The integration of artificial intelligence (AI) and digital therapeutics (DTx) offers revolutionary potential for the screening, diagnosis, and intervention of ASD. AI-driven digital therapeutics (AI-driven DTx) significantly enhance the precision and accessibility of diagnosis and intervention by utilizing multimodal data, such as eye-tracking, facial expression analysis, and advanced algorithms. In the screening phase, through detailed analysis of gaze patterns and micro-behavioral abnormalities, gamified tasks, virtual reality, and wearable devices enable early detection within a short time frame. During the diagnostic process, machine learning models apply neuroimaging data for classification, allowing rapid and accurate diagnoses. In terms of intervention, tools such as social robots and virtual reality scenarios powered by natural language processing technology can dynamically adjust according to the individual's needs, efficiently improving the patient's social skills. Despite the significant potential of AI-driven DTx, it still faces barriers such as data limitations in clinical applications. Currently, there is a lack of comprehensive reviews on the application of AI-driven DTx in the field of autism. This article will systematically summarize the use of AI-driven DTx in autism screening, diagnosis, and intervention, while also highlighting its current shortcomings and exploring its future application prospects.
Keywords: artificial intelligence, Autism Spectrum Disorder, digital therapeutics, screening, diagnosis, intervention
Received: 14 Mar 2025; Accepted: 20 Oct 2025.
Copyright: © 2025 Wang, Chen and Zhangben. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Hong-yi Zhangben, fantasyzbhy@gmail.com
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.