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

Related Concept Videos

Autism Spectrum Disorder

Autism Spectrum Disorder

Autism spectrum disorder (ASD) is a neurodevelopmental condition marked by persistent deficits in social communication and interaction alongside restrictive and repetitive behaviors or interests. ASD is sometimes accompanied by intellectual impairment.
These core symptoms manifest differently among individuals, ranging from mild to severe. The disorder's complexity extends beyond its clinical presentation, encompassing a diverse range of biological, cognitive, and sociocultural influences.

You might also read

Related Articles

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

Sort by

Same author

GAT-LI: a graph attention network based learning and interpreting method for functional brain network classification.

BMC bioinformatics·2021

Same author

Document-Level Biomedical Relation Extraction Leveraging Pretrained Self-Attention Structure and Entity Replacement: Algorithm and Pretreatment Method Validation Study.

JMIR medical informatics·2020

Same author

A Multichannel 2D Convolutional Neural Network Model for Task-Evoked fMRI Data Classification.

Computational intelligence and neuroscience·2020

Same author

PipeMEM: A Framework to Speed Up BWA-MEM in Spark with Low Overhead.

Genes·2019

Same author

Investigations of coupling characters in ionic liquids formed between the 1-ethyl-3-methylimidazolium cation and the glycine anion.

The journal of physical chemistry. B·2008

Same author

Mercury exposure in the population from Wuchuan mercury mining area, Guizhou, China.

The Science of the total environment·2008

Same journal

Correction to "Mathematical Modelling of COVID-19 Transmission in Kenya: A Model with Reinfection Transmission Mechanism".

Computational and mathematical methods in medicine·2025

Same journal

RETRACTION: Ligustrazine Inhibits Lung Phosphodiesterase Activity in a Rat Model of Allergic Asthma.

Computational and mathematical methods in medicine·2025

Same journal

RETRACTION: Delivery of miR-224-5p by Exosomes from Cancer-Associated Fibroblasts Potentiates Progression of Clear Cell Renal Cell Carcinoma.

Computational and mathematical methods in medicine·2025

Same journal

RETRACTION: Empirical Analysis of the Nursing Effect of Intelligent Medical Internet of Things in Postoperative Osteoarthritis.

Computational and mathematical methods in medicine·2025

Same journal

RETRACTION: Evaluation and Analysis of the Intervention Effect of Systematic Parent Training Based on Computational Intelligence on Child Autism.

Computational and mathematical methods in medicine·2024

Same journal

RETRACTION: Humanistic Spirit Training of Medical Students Based on Multisource Medical Data Fusion.

Computational and mathematical methods in medicine·2024

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 19, 2025

Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging

Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging

Published on: September 12, 2011

Interpretable Learning Approaches in Resting-State Functional Connectivity Analysis: The Case of Autism Spectrum

Jinlong Hu^1,2, Lijie Cao^1,2, Tenghui Li^1,2

¹School of Computer Science and Engineering, South China University of Technology, Guangzhou, China.

Computational and Mathematical Methods in Medicine

|June 9, 2020

Summary

This summary is machine-generated.

This study introduces an interpretable neural network for identifying autism spectrum disorder (ASD) using fMRI data, achieving superior accuracy. The model provides precise explanations for its classifications, aiding in understanding ASD biomarkers.

More Related Videos

Comparing Eye-tracking Data of Children with High-functioning ASD, Comorbid ADHD, and of a Control Watching Social Videos

Comparing Eye-tracking Data of Children with High-functioning ASD, Comorbid ADHD, and of a Control Watching Social Videos

Published on: December 7, 2018

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

Related Experiment Videos

Last Updated: Dec 19, 2025

Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging

Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging

Published on: September 12, 2011

Comparing Eye-tracking Data of Children with High-functioning ASD, Comorbid ADHD, and of a Control Watching Social Videos

Comparing Eye-tracking Data of Children with High-functioning ASD, Comorbid ADHD, and of a Control Watching Social Videos

Published on: December 7, 2018

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

Area of Science:

Neuroscience
Machine Learning
Medical Imaging

Background:

Deep neural networks show promise in identifying autism spectrum disorder (ASD) but often lack interpretability.
Understanding the internal logic of these networks is crucial for clinical applications, especially in analyzing functional magnetic resonance imaging (fMRI) data.

Purpose of the Study:

To develop and evaluate an interpretable neural network model for classifying individuals with ASD versus healthy controls (HC) using fMRI data.
To provide a precise and consistent method for interpreting the model's decisions and identifying key features contributing to ASD classification.

Main Methods:

Proposed a piecewise linear neural network (PLNN) using LeakyReLU activation, termed a fully connected neural network (FCNN), for ASD classification based on resting-state functional connectivity (rsFC).
Compared the FCNN model against support vector machine (SVM), random forest, and other deep learning models using the ABIDE I dataset (871 subjects).
Developed a novel interpretation method to generate precise linear formulas and identify decision features for each sample.

Main Results:

The proposed FCNN model achieved the highest classification accuracy compared to all benchmark models.
The interpretation method successfully provided precise explanations for individual classifications and highlighted significant decision features.
The study demonstrated the effectiveness of interpretable models in fMRI data analysis for ASD.

Conclusions:

Interpretable neural networks, like the proposed FCNN, offer a powerful and transparent approach for ASD identification from fMRI data.
The developed interpretation method enhances the clinical utility of machine learning models by providing clear insights into ASD-related brain connectivity patterns.
This approach facilitates a deeper understanding of the neural underpinnings of ASD and supports precise biomarker discovery.