CoChat

Divide and Conquer: Sub-Grouping of ASD Improves ASD Detection Based on Brain Morphometry

Open access

The DOI matches its Crossref record; 59 of the 60 references it cites were found in a registry or an index, and 1 are not checked yet.

Abstract

Low success (<60%) in autism spectrum disorder (ASD) classification using brain morphometry from the large multi-site ABIDE dataset and inconsistent findings on brain morphometric abnormalities in ASD can be attributed to the ASD heterogeneity. In this study, we show that ASD brain morphometry is highly heterogeneous, and demonstrate that the heterogeneity can be mitigated and classification improved if autism severity (AS), verbal IQ (VIQ) and age are used with morphometric features. Morphometric features from structural MRIs (sMRIs) of 734 males (ASD: 361, controls: 373) of ABIDE were derived using FreeSurfer. Applying the Random Forest classifier, an AUC of 0.61 was achieved. Adding VIQ and age to morphometric features, AUC improved to 0.68. Sub-grouping the subjects by AS, VIQ and age improved the classification with the highest AUC of 0.8 in the moderate-AS sub-group (AS = 7-8). Matching subjects on age and/or VIQ in each sub-group further improved the classification with the highest AUC of 0.92 in the low AS sub-group (AS = 4-5). AUC decreased with AS and VIQ, and was the lowest in the mid-age sub-group (13-18 years). The important features were mainly from the frontal, temporal, ventricular, right hippocampal and left amygdala regions. However, they highly varied with AS, VIQ and age. The curvature and folding index features from frontal, temporal, lingual and insular regions were dominant in younger subjects suggesting their importance for early detection. When the experiments were repeated using the Gradient Boosting classifier similar results were obtained. Our findings suggest that identifying brain biomarkers in sub-groups of ASD can yield more robust and insightful results than searching across the whole spectrum. Further, it may allow identification of sub-group specific brain biomarkers that are optimized for early detection and monitoring, increasing the utility of sMRI as an important tool for early detection of ASD.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0153331

Cites

59 of 60 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig 1 Improvement in classification by sub-grouping based on autism severity (AS), age and Verbal IQ (VIQ). The AUC scores of the classification in the sub-groups are presented. A point represents the mean and an error bar represents the one standard deviation of the AUC scores from 10 test folds. A) Smaller classes were up-sampled in each training fold to balance the number of ASD & TDC subjects. Sub-grouping improved the classification with the most and least improvements from sub-grouping by AS and age respectively. B) Larger classes were down-sampled matching the demographics of the smaller classes. This scheme further improved the classification performance.
Fig 1 Improvement in classification by sub-grouping based on autism severity (AS), age and Verbal IQ (VIQ). The AUC scores of the classification in the sub-groups are presented. A point represents the mean and an error bar represents the one standard deviation of the AUC scores from 10 test folds. A) Smaller classes were up-sampled in each training fold to balance the number of ASD & TDC subjects. Sub-grouping improved the classification with the most and least improvements from sub-grouping by AS and age respectively. B) Larger classes were down-sampled matching the demographics of the smaller classes. This scheme further improved the classification performance.CC BY · PubMed Central
Fig 2 Important features for classification are different across sub-groups. Top 10 important features for autism spectrum disorder (ASD) vs. typically developing controls (TDC) classification in each sub-group (by AS, VIQ, age) are presented. Each feature is represented by a colored bar; the length of the bar represents the relative % importance for classification with respect to the top feature. The features have been grouped and color-coded by volume, area, thickness mean, thickness standard deviation, folding index, mean curvature and Gaussian curvature. Before each feature, Cohen’s d and two sample t-test significance (P<0.005** and P<0.05*) of ASD vs. TDC group difference are presented. The important features for classification varied across the sub-groups demonstrating the heterogeneity in ASD brain morphometry.
Fig 2 Important features for classification are different across sub-groups. Top 10 important features for autism spectrum disorder (ASD) vs. typically developing controls (TDC) classification in each sub-group (by AS, VIQ, age) are presented. Each feature is represented by a colored bar; the length of the bar represents the relative % importance for classification with respect to the top feature. The features have been grouped and color-coded by volume, area, thickness mean, thickness standard deviation, folding index, mean curvature and Gaussian curvature. Before each feature, Cohen’s d and two sample t-test significance (P<0.005** and P<0.05*) of ASD vs. TDC group difference are presented. The important features for classification varied across the sub-groups demonstrating the heterogeneity in ASD brain morphometry.CC BY · PubMed Central
Fig 3 Variability of the important features with autism severity (AS), verbal IQ (VIQ) and age. A total of 13 important features for classification are presented; the top feature for each sub-group (nine in total) and the four important features for all subjects. The magnitude and direction of the ASD vs. TDC group differences of the top features varied with AS, VIQ and age demonstrating the heterogeneity in brain morphometry.
Fig 3 Variability of the important features with autism severity (AS), verbal IQ (VIQ) and age. A total of 13 important features for classification are presented; the top feature for each sub-group (nine in total) and the four important features for all subjects. The magnitude and direction of the ASD vs. TDC group differences of the top features varied with AS, VIQ and age demonstrating the heterogeneity in brain morphometry.CC BY · PubMed Central
Fig 4 Folding index and curvature features are important for classification in young subjects i.e. in the young-age sub-group. The important folding index and curvature features from the young-age sub-group and/or whose ASD vs. TDC group differences across all subjects were statistically significant (multiple comparisons uncorrected) are presented. The features are mainly from frontal, temporal, lingual and insular region, and are larger in ASD. However, the group differences decrease with age and even the direction of the group difference flips for 12 out of 17 features.
Fig 4 Folding index and curvature features are important for classification in young subjects i.e. in the young-age sub-group. The important folding index and curvature features from the young-age sub-group and/or whose ASD vs. TDC group differences across all subjects were statistically significant (multiple comparisons uncorrected) are presented. The features are mainly from frontal, temporal, lingual and insular region, and are larger in ASD. However, the group differences decrease with age and even the direction of the group difference flips for 12 out of 17 features.CC BY · PubMed Central
Fig 5 ASD vs. TDC group difference in ventricular volumes decreases with verbal IQ (VIQ). The ventricular volumes were normalized by total intracranial volume. Across all subjects, except 3rd and 4th, all ventricles and total intracranial volumes were larger in ASD. When the subjects were sub-grouped by VIQ, the group differences were the largest in the low-VIQ sub-group but decreased with VIQ. For some ventricular, the direction of group difference even flipped in the high-VIQ sub-group i.e. volumes were larger in TDC for some ventricles.
Fig 5 ASD vs. TDC group difference in ventricular volumes decreases with verbal IQ (VIQ). The ventricular volumes were normalized by total intracranial volume. Across all subjects, except 3rd and 4th, all ventricles and total intracranial volumes were larger in ASD. When the subjects were sub-grouped by VIQ, the group differences were the largest in the low-VIQ sub-group but decreased with VIQ. For some ventricular, the direction of group difference even flipped in the high-VIQ sub-group i.e. volumes were larger in TDC for some ventricles.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

2 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 60 references

Research works printed but not linked: 1

  1. L Breiman, 2001, Random Forrest, Mach Learn, 1

Cited by

See all 49

Metadata

Authors
Katuwal, G. J., Baum, S. A., Cahill, N. D., & Michael, A. M.
Affiliations
Rochester Institute of Technology (US)
Corresponding author
Katuwal, Gajendra J.
Venue
PLOS ONE
Published
2016-04-11
Volume
11
Issue
4
Pages
e0153331
ISSN
1932-6203 (ISSN-L)
OpenAlex
W2326145038
Cited by
49
References
60
Citations by year
2026: 1 · 2025: 2 · 2024: 7 · 2023: 6 · 2022: 5 · 2021: 6 · 2020: 9 · 2019: 4 · 2018: 5 · 2017: 3 · 2016: 1
FWCI
2.76
Type
journal article
Language
en
Open access
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Figshare (submittedVersion, cc-by)
Funders
Geisinger Health System Foundation
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Autism Spectrum Disorder Research
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetics and Neurodevelopmental Disorders
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Functional Brain Connectivity Studies
Keywords
autism spectrum disorder, ASD heterogeneity, brain morphometry, ASD classification, autism severity, verbal IQ, age effects, structural MRI, brain biomarkers, subgroup analysis, early detection, ABIDE dataset, hippocampus, amygdala, cortical folding, curvature properties
MeSH terms
Autism Spectrum Disorder, Adolescent, Adult, Age Factors, Brain, Child, Female, Humans, Intelligence, Language, Magnetic Resonance Imaging, Male, Middle Aged, Multivariate Analysis, Case-Control Studies, Young Adult, Neuroimaging

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Divide and Conquer: Sub-Grouping of ASD Improves ASD Detection Based on Brain Morphometry. https://app.cochat.ai/papers/10.1371/journal.pone.0153331
The paper
Katuwal, G. J., Baum, S. A., Cahill, N. D., & Michael, A. M. (2016). Divide and Conquer: Sub-Grouping of ASD Improves ASD Detection Based on Brain Morphometry. PLOS ONE. https://doi.org/10.1371/journal.pone.0153331

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.