Aug 2026· ARID International Journal for Science and Technology· 0 citations
TL;DR
A comprehensive machine learning framework to classify ASD severity (mild, moderate, severe) is developed and validates by investigating the differential impact of feature engineering and selection, revealing a critical “evaluation paradox” where radical, unguided feature reduction improved geometric cluster cohesion but degraded clinical accuracy.
Abstract
Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by significant heterogeneity, making the accurate classification of its severity levels crucial for effective intervention. This study develops and validates a comprehensive machine learning framework to classify ASD severity (mild, moderate, severe) by investigating the differential impact of feature engineering and selection. A dataset of 340 individuals was analyzed using a dual-framework approach, integrating supervised classification (SVM, Random Forest, XGBoost) and unsupervised clustering (K-Means, Hierarchical, GMM). The methodology centered on comparing a feature-centric approach, using a hybrid selection strategy on 60 engineered and original features, against a baseline approach using only 33 original features. The feature-centric approach yielded markedly superior results; a Random Forest classifier, trained on a minimal subset of just nine engineered features, achieved a test accuracy of 76.5%, significantly outperforming all other models, including an SVM trained on 22 original features (70.6% accuracy). This highlights that feature quality is more critical than quantity. The unsupervised analysis revealed a critical “evaluation paradox,” where radical, unguided feature reduction improved geometric cluster cohesion but degraded clinical accuracy. Conversely, a guided, domain-informed selection improved both internal and external metrics.
Autism Spectrum Disorder (ASD) is a heterogeneous neurodevelopmental condition defined by differences in social communication and restricted, repetitive behaviours. As diagnostic criteria have broadened, ASD is now recognised across a wider range of individuals, raising key questions about its structure: does ASD have discrete sub-types, or is it better conceptualised as a continuous, possibly multidimensional, condition? We aim to explore whether a multidimensional continuum model more accurately captures the variability within ASD. We analysed a large SPARK phenotypic dataset of medical history and diagnostic surveys (background history, SCQ, RBS-R; n=36,710 individuals). We apply and compare two traditional statistical approaches, Factor Analysis and Gaussian Mixture Models, with a modern machine learning technique, the Variational Autoencoder (VAE). VAEs reconstructed unseen test data with ~4-fold better accuracy than Factor Analysis, and ~8-fold better accuracy than Gaussian Mixture Models. We identified four stable latent factors across 100 independently trained VAEs. These four dimensions provide an individual behavioural profile that can be visualized using radar-plots, offering a compact way to compare profiles at the person level. Through further analysis, we found evidence for 3 overlapping clusters or subtypes of ASD identified within the 4D latent space. This work aims to inform new ways of modelling ASD using a VAE that will be able to discern between a continuum or a clustered output and that go beyond binary diagnosis, instead reflecting the complex range of trait profiles, with implications for personalised diagnosis and intervention.
H. Quigley, B. Gardiner, L. McDaid et al.· medRxiv· 0 citations
Autism Spectrum Disorder (ASD) classification using machine learning has shown promising results on behavioral screening datasets, however, such performance may be influenced by embedded questionnaire scoring and threshold-based patterns. This study presents an explainable multi-model ASD classification Framework that consist of questionnaire based screening, augmentation analysis, rule based interpretation, explainable artificial intelligence, and rs-fMRI based neuroimaging classification. The proposed framework is organized into three progressive models. ASD classification on child behavioral dataset focuses on child behavioral screening data and evaluated Logistic Regression, XGBoost, Linear Support Vector Machine, and Bernoulli Naive Bayes with XAI and rule-based interpretation. Multi-cohort ASD classification framework combined child, adolescent, and and adult AQ_10 based datasets and assessed the same classifiers under real, SMOTE, ADASYN, CTGAN, and TVAE training conditions. ABIDE-1 multi-modal ASD classification extended the analysis to ABIDE-1 rs-fMRI functional connectivity and phenotypic features using ElasticNet Logistic Regression, Linear SVM, Ridge Classifier, and SGD LogLoss classifier. The questionnaire based models achieved strong performance, with ASD classification on child behavioral dataset framework obtaining a best accuracy of 97% using Linear SVM and Multi-cohort ASD classification framework reaching up to 100% accuracy in selected real and traditional oversampling settings for logistic Regression and linear SVM. SMOTE and ADASYN produced more stable performance than CTGAN and TVAE. ABIDE-1 multi-modal ASD classification framework achieved a best accuracy of 70% using ElasticNet Logistic Regression, reflecting the grater complexity of neuroimaging based ASD classification.
Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder which necessitates early and precise diagnosis to facilitate prompt intervention and enhance long-term results. Using behavioural and demographic data, this research offers a machine learningbased method for identifying ASD. The proposed system incorporates comprehensive data preprocessing techniques, such as addressing missing values, encoding categorical features, and feature scaling, to increase model efficiency. Additionally, the most pertinent characteristics that contribute to the classification of ASD are found using feature selection techniques. The predictive power of four machine learning (ML) algorithms: Support Vector Machine (SVM), Random Forest (RF), Cat-Boost (CB), and Light Gradient Boosting Machine (LGBM) is assessed through implementation. Following training and validation using appropriate data partitioning methodologies, the model's performance is evaluated using different performance metrics. A comparative study is undertaken to find out how well every model represents complex trends in the dataset. According to the experimental results, boosting-based methods in particular, Cat-Boost and LGBM perform better because they can effectively handle categorical variables and minimise overfitting. Cat-Boost achieved best results with an accuracy of 85.14%. This study shows how cutting-edge machine learning methods can improve ASD screening and assist with data-driven clinical decision-making.
The proposed ensemble-based machine learning classifier methodology presented in this study seeks to revolutionize the diagnosis of ASD by harnessing the collective power of various machine learning algorithms to enhance diagnostic precision, mitigate the subjectivity associated with traditional diagnostic methods, and accelerate the detection process.
Shabeena Lylath, Laxmi B. Rananavare· IAES International Journal o...· 0 citations
Selecting Evidence-Based Practices learning strategies for children with Autism Spectrum Disorder requires careful consideration of children’s diverse ability profiles. This study developed a classification model for Evidence-Based Practices learning strategies using the Random Forest algorithm based on a primary dataset consisting of 106 records. The features used include child age, gender, verbal ability, Autism Spectrum Disorder severity level, learning media, and language learning difficulties. The classification target consists of four classes: ABA, Visual Method, PECS, and Speech Therapy. Model evaluation was conducted using an 80:20 hold-out split, Stratified 5-Fold Cross Validation, Repeated Stratified Cross Validation, ablation test, and feature importance analysis. In the 80:20 hold-out scenario, Random Forest achieved an accuracy of 45.45% and an F1-Macro score of 0.4393. In Stratified 5-Fold Cross Validation, the model obtained an average accuracy of 38.61% ± 7.17% and an F1-Macro score of 0.3803 ± 0.0736. The repeated cross-validation results showed an average accuracy of 34.45% ± 9.46% and an F1-Macro score of 0.3332 ± 0.0967. These findings indicate that Random Forest is able to form an initial classification model; however, its performance remains low to moderate. The limitations of this study lie in the limited dataset size, the relatively small number of samples per class, and the absence of external validation; therefore, the model cannot yet be used as a final recommendation system. This study is positioned as a preliminary study to support the development of a Decision Support System for selecting Evidence-Based Practices learning strategies for children with Autism Spectrum Disorder.
S. Septiana, Dwi Krisbiantoro, Suliswaningsih Suliswaningsih· Jambura Journal of Electrica...· 0 citations
These findings demonstrate the potential of computer vision-based analysis of children’s expressive activities as an effective, non-invasive ASD pre-screening tool and will focus on expanding dataset diversity and integrating multimodal behavioral cues to improve model generalization and clinical applicability.
Aina Khairina Ahmad Khair, Wan Mohd Yaakob Wan Bejuri, Mohd Murtadha Mohamad et al.· Bulletin of Electrical Engin...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
