Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 8, 2026

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

CVAE-guided triage and modular classifiers for multimodal ASD detection.

Susovan Pradhan¹, Prasenjit Mukherjee¹, Baisakhi Chakraborty¹

¹CSE Department, National Institute of Technology, Durgapur, India.

Computers in Biology and Medicine

|May 6, 2026

Summary

This study introduces a modular framework for autism spectrum disorder (ASD) assessment, integrating various data types like neuroimaging and behavior. The framework shows high accuracy in identifying ASD risk, paving the way for improved diagnostic tools.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Stimulated Full-Thickness Cutaneous Wound Healing with Bioactive Dressings of Zinc and Cobalt Ion-Doped Bioactive Glass-Coated Eggshell Membranes in a Diabetic Rabbit Model.

ACS biomaterials science & engineering·2024

Same author

Recent trends of stem cell therapies in the management of orthopedic surgical challenges.

International journal of surgery (London, England)·2024

Same author

Synergistic Improvement of Antibacterial and Osteogenic Differentiation of Thermomechanically Processed Mg-Zr-Sr-Ce Alloy: Insights into the Role of Precipitate Evolution Supported by AIMD Simulation Study.

ACS applied bio materials·2024

Same author

Biomaterials-Based Strategies to Enhance Angiogenesis in Diabetic Wound Healing.

ACS biomaterials science & engineering·2024

Same author

In vitro and in vivo assessment of decellularized platelet-rich fibrin-loaded strontium doped porous magnesium phosphate scaffolds in bone regeneration.

Journal of the mechanical behavior of biomedical materials·2022

Same author

Effects of COVID-19 lockdown and unlock on the health of tropical large river with associated human health risk.

Environmental science and pollution research international·2022

Area of Science:

Neuroscience
Computer Science
Medical Diagnostics

Background:

Autism spectrum disorder (ASD) diagnosis is complex due to its heterogeneous nature and data scattered across multiple domains.
Current diagnostic challenges necessitate innovative approaches for comprehensive ASD assessment.

Purpose of the Study:

To develop and evaluate a screening-guided modular framework for autism spectrum disorder (ASD) assessment.
To integrate diverse data modalities including neuroimaging, facial expressions, physiological signals, and behavioral data for enhanced ASD detection.

Main Methods:

A Conditional Variational Autoencoder-guided Quantitative Checklist for Autism in Toddlers (Q-CHAT) module for initial risk estimation.
Development of five modality-specific classifiers for MRI, facial images, gastrointestinal endoscopy, eye-tracking with fNIRS, and Activities of Daily Living (ADL) motion signals.

Keywords:

Autism spectrum disorder (ASD)Behavioural signal analysis Eye tracking and fNIRS Multimodal diagnostic framework Neuroimaging Q-CHAT screening Region-aware attention Visual–language fusion

More Related Videos

Cross-Modal Multivariate Pattern Analysis

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

Related Experiment Videos

Last Updated: May 8, 2026

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

Cross-Modal Multivariate Pattern Analysis

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

Utilized advanced machine learning techniques including 3D CNNs, GCNs, attention-based CNNs, BiLSTMs, and cross-attention mechanisms for feature extraction and classification.

Main Results:

The Q-CHAT module achieved approximately 99.05% accuracy in screening.
Individual modality classifiers demonstrated strong performance: MRI (95%), facial analysis (95%), eye-tracking/fNIRS (96%), GI-based classification (94%), and ADL assessment (93%).
The modular framework proved feasible and scalable for future multimodal ASD research.

Conclusions:

The proposed modular framework offers a promising blueprint for scalable and clinically relevant multimodal ASD assessment.
Individual components demonstrated high efficacy, supporting the potential for a comprehensive, multi-modal diagnostic system.
Further research and patient-level multimodal deployment are warranted to fully validate the late-fusion strategy.