IJRTI
International Journal for Research Trends and Innovation
International Peer Reviewed & Refereed Journals, Open Access Journal
ISSN Approved Journal No: 2456-3315 | Impact factor: 8.14 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)

Call For Paper

For Authors

Forms / Download

Published Issue Details

Editorial Board

Other IMP Links

Facts & Figure

Impact Factor : 8.14

Issue per Year : 12

Volume Published : 11

Issue Published : 118

Article Submitted : 21574

Article Published : 8528

Total Authors : 22430

Total Reviewer : 805

Total Countries : 159

Indexing Partner

Licence

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Published Paper Details
Paper Title: AUTISM SPECTRUM DISORDER DETECTION USING MULTIMODAL DATA EEG AND Q-CHAT
Authors Name: SUBATHRA R , HARIHARAN T , PRASANNA KUMAR S , VIJAYANANDH A
Download E-Certificate: Download
Author Reg. ID:
IJRTI_207219
Published Paper Id: IJRTI2511065
Published In: Volume 10 Issue 11, November-2025
DOI: https://doi.org/10.56975/ijrti.v10i11.207219
Abstract: : Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by challenges in social communication, restricted interests, and repetitive behaviors. The early and accurate diagnosis of ASD plays a crucial role in improving intervention outcomes and quality of life. Traditional diagnostic methods rely heavily on behavioral observations and subjective assessments conducted by clinicians, which are time-consuming, inconsistent, and prone to human bias. This research presents a multimodal machine learning framework for the automated detection of ASD by integrating electroencephalogram (EEG) data with behavioral questionnaire responses to improve diagnostic precision and robustness. The proposed approach leverages a combination of neurophysiological signals and behavioral features to form a comprehensive feature space that captures both brain activity patterns and self-reported behavioral traits. The dataset used in this study comprises two modalities—EEG features extracted from alpha, beta, and theta frequency bands, and responses from standardized autism screening questionnaires. A robust preprocessing pipeline was implemented, involving data normalization, categorical encoding (YES/NO → 1/0 transformation), missing value imputation, and feature scaling to ensure data uniformity across modalities. Feature selection techniques, such as ANOVA F1-score , Recursive Feature Elimination (RFE), and tree-based importance ranking, were used to identify the most discriminative attributes contributing to ASD prediction. A set of machine learning algorithms were employed and compared, including Logistic Regression, Random Forest, GradientBoost , Naïve Bayes, Decision Tree, and , the latter being a recent deep learning model introduced in 2020 for tabular data. Stratified K-Fold cross-validation was used to assess model performance, ensuring a balanced evaluation across ASD and non-ASD classes. Experimental results demonstrate that the multimodal fusion approach significantly enhances classification accuracy compared to unimodal models (EEG-only or questionnaire-only). Among the tested algorithms, Random Forest achieved superior performance, with the combined model yielding over 95% accuracy, outperforming traditional baselines. The developed system provides an interpretable, data-driven mechanism to assist clinicians and researchers in identifying individuals at risk for ASD. Moreover, the integration of EEG and behavioral modalities reflects a step toward holistic, objective, and reproducible diagnostic methodologies. The study concludes that multimodal machine learning frameworks hold great promise in advancing neuropsychiatric screening, reducing diagnostic latency, and enabling scalable, early-stage detection of autism in both clinical and community settings.
Keywords: : Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by challenges in social communication, restricted interests, and repetitive behaviors. The early and accurate diagnosis of ASD plays a crucial role in improving intervention outcomes and quality of life. Traditional diagnostic methods rely heavily on behavioral observations and subjective assessments conducted by clinicians, which are time-consuming, inconsistent, and prone to human bias. This research presents a multimodal machine learning framework for the automated detection of ASD by integrating electroencephalogram (EEG) data with behavioral questionnaire responses to improve diagnostic precision and robustness. The proposed approach leverages a combination of neurophysiological signals and behavioral features to form a comprehensive feature space that captures both brain activity patterns and self-reported behavioral traits. The dataset used in this study comprises two modalities—EEG features extracted from alpha, beta, and theta frequency bands, and responses from standardized autism screening questionnaires. A robust preprocessing pipeline was implemented, involving data normalization, categorical encoding (YES/NO → 1/0 transformation), missing value imputation, and feature scaling to ensure data uniformity across modalities. Feature selection techniques, such as ANOVA F1-score , Recursive Feature Elimination (RFE), and tree-based importance ranking, were used to identify the most discriminative attributes contributing to ASD prediction. A set of machine learning algorithms were employed and compared, including Logistic Regression, Random Forest, GradientBoost , Naïve Bayes, Decision Tree, and , the latter being a recent deep learning model introduced in 2020 for tabular data. Stratified K-Fold cross-validation was used to assess model performance, ensuring a balanced evaluation across ASD and non-ASD classes. Experimental results demonstrate that the multimodal fusion approach significantly enhances classification accuracy compared to unimodal models (EEG-only or questionnaire-only). Among the tested algorithms, Random Forest achieved superior performance, with the combined model yielding over 95% accuracy, outperforming traditional baselines. The developed system provides an interpretable, data-driven mechanism to assist clinicians and researchers in identifying individuals at risk for ASD. Moreover, the integration of EEG and behavioral modalities reflects a step toward holistic, objective, and reproducible diagnostic methodologies. The study concludes that multimodal machine learning frameworks hold great promise in advancing neuropsychiatric screening, reducing diagnostic latency, and enabling scalable, early-stage detection of autism in both clinical and community settings.
Cite Article: "AUTISM SPECTRUM DISORDER DETECTION USING MULTIMODAL DATA EEG AND Q-CHAT", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 11, page no.a547-a557, November-2025, Available :http://www.ijrti.org/papers/IJRTI2511065.pdf
Downloads: 000267
ISSN: 2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publication Details: Published Paper ID: IJRTI2511065
Registration ID:207219
Published In: Volume 10 Issue 11, November-2025
DOI (Digital Object Identifier): https://doi.org/10.56975/ijrti.v10i11.207219
Page No: a547-a557
Country: krishnagiri, tamilnadu, India
Research Area: Engineering
Publisher : IJ Publication
Published Paper URL : https://www.ijrti.org/viewpaperforall?paper=IJRTI2511065
Published Paper PDF: https://www.ijrti.org/papers/IJRTI2511065
Share Article:

Share Facebook Twitter Google+ Pinterest LinkedIn Email Tumblr WhatsApp Google Gmail

Click Here to Download This Article

Article Preview
Click Here to Download This Article
Major Indexing from www.ijrti.org
Google Scholar ResearcherID Thomson Reuters Mendeley : reference manager Academia.edu
arXiv.org : cornell university library Research Gate CiteSeerX DOAJ : Directory of Open Access Journals
DRJI Index Copernicus International Scribd DocStoc

ISSN Details

ISSN: 2456-3315
Impact Factor: 8.14 and ISSN APPROVED, Journal Starting Year (ESTD) : 2016

DOI (A digital object identifier)


Providing A digital object identifier by DOI.ONE
How to Get DOI?

Conference

Open Access License Policy

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License

Creative Commons License This material is Open Knowledge This material is Open Data This material is Open Content

Important Details

Join RMS/Earn 300
IJRTI

WhatsApp
Click Here

Indexing Partner
Copyright © 2026 - All Rights Reserved - IJRTI