Help Privacy Policy Disclaimer
  Advanced SearchBrowse


  Diagnosis-informed connectivity subtyping discovers subgroups of autism with reproducible symptom profiles

Choi, H., Byeon, K., Park, B.-y., Lee, J.-e., Valk, S. L., Bernhardt, B., et al. (2022). Diagnosis-informed connectivity subtyping discovers subgroups of autism with reproducible symptom profiles. NeuroImage, 256: 119212. doi:10.1016/j.neuroimage.2022.119212.

Item is


show hide
Genre: Journal Article


show Files
hide Files
Choi_2022.pdf (Publisher version), 4MB
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
Copyright Info:




Choi, Hyoungshin1, 2, Author
Byeon, Kyoungseob1, 2, Author
Park, Bo-yong2, 3, Author
Lee, Jong-eun1, 2, Author
Valk, Sofie L.4, 5, 6, Author           
Bernhardt, Boris7, Author
Martino, Adriana Di8, Author
Milham, Michael9, 10, Author
Hong, Seok-Jun2, 9, 11, Author
Park, Hyunjin2, 12, Author
1Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Republic of Korea, ou_persistent22              
2Center for Neuroscience Imaging Research, Institute for Basic Science, Suwon, Republic of Korea, ou_persistent22              
3Department of Data Science, Inha University, Incheon, Republic of Korea, ou_persistent22              
4Otto Hahn Group Cognitive Neurogenetics, MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_3222264              
5Institute of Neuroscience and Medicine, Research Center Jülich, Germany, ou_persistent22              
6Institute of Systems Neuroscience, University Hospital Düsseldorf, Germany, ou_persistent22              
7McConnell Brain Imaging Centre, Montreal Neurological Institute and Hospital, McGill University, Montréal, QC, Canada, ou_persistent22              
8Autism Center, Child Mind Institute, New York, NY, USA, ou_persistent22              
9Center for the Developing Brain, Child Mind Institute, New York, NY, USA, ou_persistent22              
10Nathan S. Kline Institute for Psychiatric Research, Orangeburg, NY, USA, ou_persistent22              
11Department of Biomedical Engineering, Sungkyunkwan University, Suwon, Republic of Korea, ou_persistent22              
12School of Electronic and Electrical Engineering, Sungkyunkwan University, Suwon, Republic of Korea, ou_persistent22              


Free keywords: Autism; Reproducibility; Neurosubtypes; Gradient; Functional random forest; Supervised-unsupervised hybrid clustering
 Abstract: Clinical heterogeneity has been one of the main barriers to develop effective biomarkers and therapeutic strategies in autism spectrum disorder (ASD). Recognizing this challenge, much effort has been made in recent neuroimaging studies to find biologically more homogeneous subgroups (called ‘neurosubtypes’) in autism. However, most approaches have rarely evaluated how much the employed features in subtyping represent the core anomalies of ASD, obscuring its utility in actual clinical diagnosis. To address this, we combined two data-driven methods, ‘connectome-based gradient’ and ‘functional random forest’, collectively allowing to discover reproducible neurosubtypes based on resting-state functional connectivity profiles that are specific to ASD. Indeed, the former technique provides the features (as input for subtyping) that effectively summarize whole-brain connectome variations in both normal and ASD conditions, while the latter leverages a supervised random forest algorithm to inform diagnostic labels to clustering, which makes neurosubtyping driven by the features of ASD core anomalies. Applying this framework to the open-sharing Autism Brain Imaging Data Exchange repository data (discovery, n = 103/108 for ASD/typically developing [TD]; replication, n = 44/42 for ASD/TD), we found three dominant subtypes of functional gradients in ASD and three subtypes in TD. The subtypes in ASD revealed distinct connectome profiles in multiple brain areas, which are associated with different Neurosynth-derived cognitive functions previously implicated in autism studies. Moreover, these subtypes showed different symptom severity, which degree co-varies with the extent of functional gradient changes observed across the groups. The subtypes in the discovery and replication datasets showed similar symptom profiles in social interaction and communication domains, confirming a largely reproducible brain-behavior relationship. Finally, the connectome gradients in ASD subtypes present both common and distinct patterns compared to those in TD, reflecting their potential overlap and divergence in terms of developmental mechanisms involved in the manifestation of large-scale functional networks. Our study demonstrated a potential of the diagnosis-informed subtyping approach in developing a clinically useful brain-based classification system for future ASD research.


Language(s): eng - English
 Dates: 2022-03-282021-12-102022-04-132022-04-142022-08-01
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1016/j.neuroimage.2022.119212
Other: online ahead of print
PMID: 35430361
 Degree: -



Legal Case


Project information

show hide
Project name : -
Grant ID : 2019-0-00421
Funding program : AI Graduate School Support Program
Funding organization : -
Project name : -
Grant ID : 28436
Funding program : -
Funding organization : Brain & Behavior Research Foundation

Source 1

Title: NeuroImage
Source Genre: Journal
Publ. Info: Orlando, FL : Academic Press
Pages: - Volume / Issue: 256 Sequence Number: 119212 Start / End Page: - Identifier: ISSN: 1053-8119
CoNE: https://pure.mpg.de/cone/journals/resource/954922650166