Ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features

Abstract Background Autism spectrum disorder (ASD) is characterized by a spectrum of social and communication impairments and rigid and stereotyped behaviors that have a neurodevelopmental origin. Although many imaging studies have reported structural and functional alterations in multiple brain reg...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yanli Zhang‐James, Jan K. Buitelaar, The ENIGMA‐ASD Working Group, Daan vanRooij, Stephen V. Faraone
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	autism spectrum disorder biomarkers classification machine learning MRI Pediatrics RJ1-570 Psychiatry RC435-571
Acceso en línea:	https://doaj.org/article/8740e006cb71439b9b6a376475e4f97f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8740e006cb71439b9b6a376475e4f97f
record_format	dspace
spelling	oai:doaj.org-article:8740e006cb71439b9b6a376475e4f97f2021-11-23T06:05:45ZEnsemble classification of autism spectrum disorder using structural magnetic resonance imaging features2692-938410.1002/jcv2.12042https://doaj.org/article/8740e006cb71439b9b6a376475e4f97f2021-10-01T00:00:00Zhttps://doi.org/10.1002/jcv2.12042https://doaj.org/toc/2692-9384Abstract Background Autism spectrum disorder (ASD) is characterized by a spectrum of social and communication impairments and rigid and stereotyped behaviors that have a neurodevelopmental origin. Although many imaging studies have reported structural and functional alterations in multiple brain regions, clinically useful diagnostic imaging biomarkers for ASD remain unavailable. Methods In this study, we applied machine learning (ML) models to regional volumetric and cortical thickness data from the largest structural magnetic resonance imaging (sMRI) dataset available from the Enhancing Neuro Imaging Genetics Through Meta‐Analysis (ENIGMA) consortium (1833 subjects with ASD and 1838 without ASD; age range: 1.5–64; average age: 15.6; male/female ratio: 4.2:1). Results The highest classification accuracy on a hold‐out test set was achieved using a stacked Extra Tree Classifier. The area under the receiver operating characteristic (ROC) curve (AUC) was 0.62 (95% confidence interval [CI]: 0.57, 0.68) and the area under the precision‐recall curve was 0.58. Learning curve analysis showed the good fit of the model and suggests that more training examples will not likely benefit model performance. Conclusions Our results suggest that sMRI volumetric and cortical thickness data alone may not provide clinically sufficient useful diagnostic biomarkers for ASD. Developing clinically useful imaging classifiers for ASD will benefit from combining other data modalities or feature types, such as functional MRI data and raw images that can leverage other machine learning (ML) techniques such as convolutional neural networks.Yanli Zhang‐JamesJan K. BuitelaarThe ENIGMA‐ASD Working GroupDaan vanRooijStephen V. FaraoneWileyarticleautism spectrum disorderbiomarkersclassificationmachine learningMRIPediatricsRJ1-570PsychiatryRC435-571ENJCPP Advances, Vol 1, Iss 3, Pp n/a-n/a (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	autism spectrum disorder biomarkers classification machine learning MRI Pediatrics RJ1-570 Psychiatry RC435-571
spellingShingle	autism spectrum disorder biomarkers classification machine learning MRI Pediatrics RJ1-570 Psychiatry RC435-571 Yanli Zhang‐James Jan K. Buitelaar The ENIGMA‐ASD Working Group Daan vanRooij Stephen V. Faraone Ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features
description	Abstract Background Autism spectrum disorder (ASD) is characterized by a spectrum of social and communication impairments and rigid and stereotyped behaviors that have a neurodevelopmental origin. Although many imaging studies have reported structural and functional alterations in multiple brain regions, clinically useful diagnostic imaging biomarkers for ASD remain unavailable. Methods In this study, we applied machine learning (ML) models to regional volumetric and cortical thickness data from the largest structural magnetic resonance imaging (sMRI) dataset available from the Enhancing Neuro Imaging Genetics Through Meta‐Analysis (ENIGMA) consortium (1833 subjects with ASD and 1838 without ASD; age range: 1.5–64; average age: 15.6; male/female ratio: 4.2:1). Results The highest classification accuracy on a hold‐out test set was achieved using a stacked Extra Tree Classifier. The area under the receiver operating characteristic (ROC) curve (AUC) was 0.62 (95% confidence interval [CI]: 0.57, 0.68) and the area under the precision‐recall curve was 0.58. Learning curve analysis showed the good fit of the model and suggests that more training examples will not likely benefit model performance. Conclusions Our results suggest that sMRI volumetric and cortical thickness data alone may not provide clinically sufficient useful diagnostic biomarkers for ASD. Developing clinically useful imaging classifiers for ASD will benefit from combining other data modalities or feature types, such as functional MRI data and raw images that can leverage other machine learning (ML) techniques such as convolutional neural networks.
format	article
author	Yanli Zhang‐James Jan K. Buitelaar The ENIGMA‐ASD Working Group Daan vanRooij Stephen V. Faraone
author_facet	Yanli Zhang‐James Jan K. Buitelaar The ENIGMA‐ASD Working Group Daan vanRooij Stephen V. Faraone
author_sort	Yanli Zhang‐James
title	Ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features
title_short	Ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features
title_full	Ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features
title_fullStr	Ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features
title_full_unstemmed	Ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features
title_sort	ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/8740e006cb71439b9b6a376475e4f97f
work_keys_str_mv	AT yanlizhangjames ensembleclassificationofautismspectrumdisorderusingstructuralmagneticresonanceimagingfeatures AT jankbuitelaar ensembleclassificationofautismspectrumdisorderusingstructuralmagneticresonanceimagingfeatures AT theenigmaasdworkinggroup ensembleclassificationofautismspectrumdisorderusingstructuralmagneticresonanceimagingfeatures AT daanvanrooij ensembleclassificationofautismspectrumdisorderusingstructuralmagneticresonanceimagingfeatures AT stephenvfaraone ensembleclassificationofautismspectrumdisorderusingstructuralmagneticresonanceimagingfeatures
_version_	1718417331151962112

Ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features

Ejemplares similares