Aug 2026· International Journal for Global Academic & Scientific Research· Vol 5, pp. 28-65· 0 citations· 103 references
TL;DR
The results suggest that the use of AI to detect ASD is not yet ready for clinical use, and transparent reporting of validation, independent external cohorts, diverse datasets, and prospective testing of positive predictive value in realistic population prevalence should be the focus of future research.
Abstract
Autism spectrum disorder (ASD) is a developmental disorder that must be identified early but traditional diagnosis can be examiner-dependent, time-consuming and not accessible. This study included a dual bibliometric and systematic review on the evidence supporting the application of artificial intelligence (AI) tools in the detection of ASD according to PRISMA 2020 and SWiM guideline. A total of 41 empirical studies were identified after a search in the Scopus database. The studies were conducted between 2011 and 2026, in 11 data modalities, 7 algorithm families and 28 countries. The accuracy of the reports was between 68.18% and 100% with a median of 91%. Facial image research was the biggest modality, but all nine studies used the same public Kaggle dataset. Unstated validation designs occurred in 46% of studies, and 93% were at high risk of bias in the areas of patient selection and reference standards, and unclear flow and timing. Very high accuracy scores were massed in small, one cohort datasets, with population level studies obtaining significantly lower accuracy scores. But in general, there was only a small difference in median accuracy between the externally validated studies and the single-cohort studies (1.5 percentage points). The results suggest that the use of AI to detect ASD is not yet ready for clinical use. Transparent reporting of validation, independent external cohorts, diverse datasets, and prospective testing of positive predictive value in realistic population prevalence should be the focus of future research.
Artificial intelligence shows promise as a supportive tool for early screening, but current evidence supports its use as a complement to, rather than replacement for, clinical assessment.
Andrea Catalina Mahecha Ballesteros, Juanita Valeria García Bello, Eleaine Scarlet González Zuñiga et al.· Current Psychiatry Reports· 0 citations
It is argued that future early ASD detection systems should be developed as clinician-supervised decision-support tools rather than autonomous diagnostic instruments.
Wenhao Luo, Z. Yin, Jianbiao Dai· Diagnostics· 0 citations
A comprehensive review of recent advancements in ASD research, with particular emphasis on neuroimaging, artificial intelligence (AI), and machine learning (ML)-based diagnostic approaches, highlights the growing potential of AI-driven tools for supporting early ASD diagnosis and emphasizes the need for standardized protocols, external validation, explainable AI, and clinically translatable frameworks.
Kuljeet Singh, Khushi Mogha, S. Moctar· Neurological Sciences· 0 citations
The need to develop large, well‐balanced datasets, the application of explainable AI techniques, standardization and regulatory guidelines for facilitating the clinical translation of ASD detection systems are suggested.
Anupama N, Chandrashekar M. Patil· International Journal of Dev...· 0 citations
Purpose: The aim of this study is to critically examine and synthesise existing evidence on the application of Artificial Intelligence (AI) and Internet of Things (IoT) technologies for the early detection of autism spectrum disorder (ASD) in young children, with particular attention to their relevance, feasibility, and potential adaptation within the Rwandan context.
Design/Methodology/Approach: A comprehensive literature search was conducted across major electronic databases, including PubMed/MEDLINE, Scopus, IEEE Xplore, Web of Science, ACM Digital Library, and Google Scholar. The search combined controlled vocabulary (e.g., MeSH terms) and free-text keywords related to Artificial Intelligence (AI), Machine Learning (ML), Internet of Things (IoT), wearable sensors, computer vision, eye tracking, electroencephalography (EEG), physiological monitoring, developmental screening, and multimodal ASD detection. 185 publications were used. Systematic reviews were appraised with AMSTAR-2. Quality ratings informed the interpretation of findings but did not form the basis for exclusion.
Research Limitation: Restricting the search to peer-reviewed English-language publications may have excluded relevant non-English studies or grey literature, introducing potential language and publication bias. Marked heterogeneity in study designs, populations, sensor modalities, AI methods, and outcome definitions precluded formal meta-analysis and limited direct comparability of predictive performance across studies. Consequently, reported model performance may not generalise to diverse populations or healthcare environments, including Rwanda.
Findings: AI and IoT technologies show considerable potential for supporting early identification of ASD‑related developmental differences. Physiological and sensor‑derived indicators include EEG patterns, heart‑rate variability, electrodermal activity, sleep characteristics, movement, and other autonomic measures. Computer vision, eye tracking, wearable sensors, smartphones, and digital questionnaires provide increasingly accessible data-collection mechanisms. Multimodal approaches that integrate behavioural, physiological, developmental, and visual information appear particularly promising, as they capture complementary characteristics associated with ASD.
Practical Implication: Rwanda could explore AI‑ and IoT‑supported developmental screening to complement conventional child‑development surveillance. Nevertheless, systems developed in other countries should undergo local adaptation, clinical evaluation, and external validation using Rwandan data before implementation.
Social Implication: A locally validated and culturally appropriate system could facilitate earlier referral, expand opportunities for early intervention, and improve access to developmental services for children and families across Rwanda. Implementation must include safeguards for privacy, informed parental consent, data security, equity, and responsible AI use.
Originality/Value: It highlights the need for a Rwanda‑specific multimodal dataset and an explainable, affordable, privacy‑preserving, and externally validated AI‑IoT framework that complements rather than replaces professional developmental assessment and clinical diagnosis.
G. Twesigye, E. Masabo, P. Bamurigire· African Journal Of Applied R...· 0 citations
ABSTRACT Autism spectrum disorder (ASD) is a complex neurodevelopmental condition characterized by persistent difficulties in social communication, social interaction, and repetitive behaviors. Early and accurate diagnosis is essential but is often hindered by subjective clinical assessments, limited data availability, and inconsistencies in existing diagnostic tools. This review evaluates the role of machine learning and deep learning approaches in improving ASD prediction, with a particular focus on two important yet relatively underexplored methodological components: data augmentation and feature selection. A structured literature search was conducted across major scientific databases, including IEEE Xplore, PubMed, Scopus, and Google Scholar, to identify studies published between 2021 and 2024. The methodological quality and risk of bias of the included studies were assessed using the Prediction Model Risk of Bias Assessment Tool. A total of 26 peer‐reviewed studies were included based on their relevance to machine learning/deep learning‐based ASD prediction and their explicit application of data augmentation or feature selection techniques. Data augmentation methods were categorized into conventional approaches, such as geometric and color‐space transformations, and advanced techniques, including generative adversarial network‐based synthetic data generation. Although augmentation techniques may improve model robustness and help address dataset scarcity, relatively few studies conducted ablation analyses to isolate the contribution of individual augmentation strategies. Feature selection approaches were classified into filter, wrapper, and embedded methods. Commonly used techniques included information gain, chi‐square tests, recursive feature elimination, and elastic net regularization. While these methods may improve predictive performance and model interpretability, they are frequently applied without sufficient empirical justification or biological interpretation. Overall, this review highlights important methodological limitations, including limited external validation, insufficient ablation analyses, and inadequate evaluation frameworks, which reduce confidence in reported performance improvements and model generalizability. Future research should emphasize methodological transparency, robust validation strategies, multimodal data integration, and clinically interpretable modeling approaches to improve the reliability and clinical applicability of ASD prediction systems.
Sahar Alkhaibari, Feng Dong· Health Care Science· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
