Cargando…
Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis
Deep learning (DL) methods have been increasingly applied to neuroimaging data to identify patients with psychiatric and neurological disorders. This review provides an overview of the different DL applications within psychiatry and compares DL model accuracy to standard machine learning (SML). Fift...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8209481/ https://www.ncbi.nlm.nih.gov/pubmed/33677240 http://dx.doi.org/10.1016/j.nicl.2021.102584 |
_version_ | 1783709138259279872 |
---|---|
author | Quaak, Mirjam van de Mortel, Laurens Thomas, Rajat Mani van Wingen, Guido |
author_facet | Quaak, Mirjam van de Mortel, Laurens Thomas, Rajat Mani van Wingen, Guido |
author_sort | Quaak, Mirjam |
collection | PubMed |
description | Deep learning (DL) methods have been increasingly applied to neuroimaging data to identify patients with psychiatric and neurological disorders. This review provides an overview of the different DL applications within psychiatry and compares DL model accuracy to standard machine learning (SML). Fifty-three articles were included for qualitative analysis, primarily investigating autism spectrum disorder (ASD; n = 22), schizophrenia (SZ; n = 22) and attention-deficit/hyperactivity disorder (ADHD; n = 9). Thirty-two of the thirty-five studies that directly compared DL to SML reported a higher accuracy for DL. Only sixteen studies could be included in a meta-regression to quantitatively compare DL and SML performance. This showed a higher odds ratio for DL models, though the comparison attained significance only for ASD. Our results suggest that deep learning of neuroimaging data is a promising tool for the classification of individual psychiatric patients. However, it is not yet used to its full potential: most studies use pre-engineered features, whereas one of the main advantages of DL is its ability to learn representations of minimally processed data. Our current evaluation is limited by minimal reporting of performance measures to enable quantitative comparisons, and the restriction to ADHD, SZ and ASD as current research focusses on large publicly available datasets. To truly uncover the added value of DL, we need carefully designed comparisons of SML and DL models which are yet rarely performed. |
format | Online Article Text |
id | pubmed-8209481 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-82094812021-06-23 Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis Quaak, Mirjam van de Mortel, Laurens Thomas, Rajat Mani van Wingen, Guido Neuroimage Clin Review Article Deep learning (DL) methods have been increasingly applied to neuroimaging data to identify patients with psychiatric and neurological disorders. This review provides an overview of the different DL applications within psychiatry and compares DL model accuracy to standard machine learning (SML). Fifty-three articles were included for qualitative analysis, primarily investigating autism spectrum disorder (ASD; n = 22), schizophrenia (SZ; n = 22) and attention-deficit/hyperactivity disorder (ADHD; n = 9). Thirty-two of the thirty-five studies that directly compared DL to SML reported a higher accuracy for DL. Only sixteen studies could be included in a meta-regression to quantitatively compare DL and SML performance. This showed a higher odds ratio for DL models, though the comparison attained significance only for ASD. Our results suggest that deep learning of neuroimaging data is a promising tool for the classification of individual psychiatric patients. However, it is not yet used to its full potential: most studies use pre-engineered features, whereas one of the main advantages of DL is its ability to learn representations of minimally processed data. Our current evaluation is limited by minimal reporting of performance measures to enable quantitative comparisons, and the restriction to ADHD, SZ and ASD as current research focusses on large publicly available datasets. To truly uncover the added value of DL, we need carefully designed comparisons of SML and DL models which are yet rarely performed. Elsevier 2021-02-10 /pmc/articles/PMC8209481/ /pubmed/33677240 http://dx.doi.org/10.1016/j.nicl.2021.102584 Text en © 2021 The Author(s) https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Review Article Quaak, Mirjam van de Mortel, Laurens Thomas, Rajat Mani van Wingen, Guido Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis |
title | Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis |
title_full | Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis |
title_fullStr | Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis |
title_full_unstemmed | Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis |
title_short | Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis |
title_sort | deep learning applications for the classification of psychiatric disorders using neuroimaging data: systematic review and meta-analysis |
topic | Review Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8209481/ https://www.ncbi.nlm.nih.gov/pubmed/33677240 http://dx.doi.org/10.1016/j.nicl.2021.102584 |
work_keys_str_mv | AT quaakmirjam deeplearningapplicationsfortheclassificationofpsychiatricdisordersusingneuroimagingdatasystematicreviewandmetaanalysis AT vandemortellaurens deeplearningapplicationsfortheclassificationofpsychiatricdisordersusingneuroimagingdatasystematicreviewandmetaanalysis AT thomasrajatmani deeplearningapplicationsfortheclassificationofpsychiatricdisordersusingneuroimagingdatasystematicreviewandmetaanalysis AT vanwingenguido deeplearningapplicationsfortheclassificationofpsychiatricdisordersusingneuroimagingdatasystematicreviewandmetaanalysis |