English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Insights from an autism imaging biomarker challenge: Promises and threats to biomarker discovery

Traut, N., Heuer, K., Lemaître, G., Beggiato, A., Germanaud, D., Elmaleh, M., et al. (2022). Insights from an autism imaging biomarker challenge: Promises and threats to biomarker discovery. NeuroImage, 255: 119171. doi:10.1016/j.neuroimage.2022.119171.

Item is

Basic

show hide
Genre: Journal Article

Files

show Files
hide Files
:
Traut_2022.pdf (Publisher version), 2MB
Name:
Traut_2022.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Traut, Nicolas1, Author
Heuer, Katja2, Author              
Lemaître, Guillaume1, Author
Beggiato, Anita1, Author
Germanaud, David1, Author
Elmaleh, Monique1, Author
Bethegnies, Alban1, Author
Bonnasse-Gahot, Laurent1, Author
Cai, Weidong1, Author
Chambon, Stanislas1, Author
Cliquet, Freddy1, Author
Ghriss, Ayoub1, Author
Guigui, Nicolas1, Author
de Pierrefeu, Amicie1, Author
Wang, Meng1, Author
Zantedeschi, Valentina1, Author
Boucaud, Alexandre1, Author
van den Bossche, Joris1, Author
Kegl, Balázs1, Author
Delorme, Richard1, Author
Bourgeron, Thomas1, AuthorToro, Roberto1, AuthorVaroquaux, Gaël1, Author more..
Affiliations:
1External Organizations, ou_persistent22              
2Department Neuropsychology, MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_634551              

Content

show
hide
Free keywords: -
 Abstract: MRI has been extensively used to identify anatomical and functional differences in Autism Spectrum Disorder (ASD). Yet, many of these findings have proven difficult to replicate because studies rely on small cohorts and are built on many complex, undisclosed, analytic choices. We conducted an international challenge to predict ASD diagnosis from MRI data, where we provided preprocessed anatomical and functional MRI data from > 2,000 individuals. Evaluation of the predictions was rigorously blinded. 146 challengers submitted prediction algorithms, which were evaluated at the end of the challenge using unseen data and an additional acquisition site. On the best algorithms, we studied the importance of MRI modalities, brain regions, and sample size. We found evidence that MRI could predict ASD diagnosis: the 10 best algorithms reliably predicted diagnosis with AUC∼0.80 - far superior to what can be currently obtained using genotyping data in cohorts 20-times larger. We observed that functional MRI was more important for prediction than anatomical MRI, and that increasing sample size steadily increased prediction accuracy, providing an efficient strategy to improve biomarkers. We also observed that despite a strong incentive to generalise to unseen data, model development on a given dataset faces the risk of overfitting: performing well in cross-validation on the data at hand, but not generalising. Finally, we were able to predict ASD diagnosis on an external sample added after the end of the challenge (EU-AIMS), although with a lower prediction accuracy (AUC=0.72). This indicates that despite being based on a large multisite cohort, our challenge still produced biomarkers fragile in the face of dataset shifts.

Details

show
hide
Language(s): eng - English
 Dates: 2022-02-162021-11-262022-03-302022-04-102022-07-15
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1016/j.neuroimage.2022.119171
Other: online ahead of print
PMID: 35413445
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: NeuroImage
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Orlando, FL : Academic Press
Pages: - Volume / Issue: 255 Sequence Number: 119171 Start / End Page: - Identifier: ISSN: 1053-8119
CoNE: https://pure.mpg.de/cone/journals/resource/954922650166