Data-Driven Approaches for Autism Detection: A Comprehensive Review of Machine Learning Algorithms and Datasets

AI Summary

ML and DL models applied to behavioural, neuroimaging, EEG, eye tracking and speech achieved 68% to 99% diagnostic accuracy.
Studies suffer from small sample sizes, demographic bias, overfitting and lack of external validation, reducing generalisability.
Hybrid multimodal fusion boosts performance; large balanced datasets, explainable AI, standardisation and regulatory frameworks are essential for clinical translation.

AI Summary

The results demonstrated that classical ML algorithms (such as logistic regression [LR], support vector machines [SVM] and random forests [RF]) and DL models (convolutional neural networks [CNN], recurrent neural networks (RNN) and transformers) were used to assess the accuracy of the diagnosis for a variety of data modalities ranging from behavioural measures to neuroimaging, electroencephalography (EEG), eye tracking and speech, with accuracy from 68% to 99%.

This review highlights four major points: (1) a critical review of dataset ethics and validity, even for non-clinical facial image datasets; (2) an architectural comparison of multimodal fusion strategies (early fusion, late fusion and hybrid fusion) focusing on computational complexity and clinical applicability; (3) a quantitative summarization of the performance trends by modalities and sample size; and (4) a structured review of indicators of reproducibility and regulatory hurdles for clinical translation.

This review suggests the need to develop large, well-balanced datasets, the application of explainable AI (XAI) techniques, standardization (e.g., brain imaging data structure [BIDS]) and regulatory guidelines for facilitating the clinical translation of ASD detection systems.

Basic summary

Int J Dev Neurosci. 2026 Aug;86(5):e70172. doi: 10.1002/jdn.70172.

ABSTRACT

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition with a broad spectrum of symptoms, which makes timely and accurate diagnosis challenging. The development of machine learning (ML) and deep learning (DL) has created opportunities for automated ASD screening and detection. This systematic review focuses on the analyses of 59 peer-reviewed studies on unimodal and multimodal approaches to ASD detection that were published between 2019 and 2025. The results demonstrated that classical ML algorithms (such as logistic regression [LR], support vector machines [SVM] and random forests [RF]) and DL models (convolutional neural networks [CNN], recurrent neural networks (RNN) and transformers) were used to assess the accuracy of the diagnosis for a variety of data modalities ranging from behavioural measures to neuroimaging, electroencephalography (EEG), eye tracking and speech, with accuracy from 68% to 99%. A careful examination of these studies, however, shows that they share certain common flaws, including small sample size, demographic bias, overfitting and absence of external validation. Hybrid multimodal frameworks have been shown to yield consistent performance improvements over unimodal frameworks, with accuracies of 95%-99% achieved through attention, graph-based learning and hybrid fusion approaches. This review highlights four major points: (1) a critical review of dataset ethics and validity, even for non-clinical facial image datasets; (2) an architectural comparison of multimodal fusion strategies (early fusion, late fusion and hybrid fusion) focusing on computational complexity and clinical applicability; (3) a quantitative summarization of the performance trends by modalities and sample size; and (4) a structured review of indicators of reproducibility and regulatory hurdles for clinical translation. This review suggests the need to develop large, well-balanced datasets, the application of explainable AI (XAI) techniques, standardization (e.g., brain imaging data structure [BIDS]) and regulatory guidelines for facilitating the clinical translation of ASD detection systems.

PMID:42601827 | PMC:PMC13476672 | DOI:10.1002/jdn.70172

Document this CPD