Cargando…

Regression‐based machine‐learning approaches to predict task activation using resting‐state fMRI

Resting‐state fMRI has shown the ability to predict task activation on an individual basis by using a general linear model (GLM) to map resting‐state network features to activation z‐scores. The question remains whether the relatively simplistic GLM is the best approach to accomplish this prediction...

Descripción completa

Detalles Bibliográficos
Autores principales: Cohen, Alexander D., Chen, Ziyi, Parker Jones, Oiwi, Niu, Chen, Wang, Yang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley & Sons, Inc. 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7267916/
https://www.ncbi.nlm.nih.gov/pubmed/31638304
http://dx.doi.org/10.1002/hbm.24841
_version_ 1783541503830786048
author Cohen, Alexander D.
Chen, Ziyi
Parker Jones, Oiwi
Niu, Chen
Wang, Yang
author_facet Cohen, Alexander D.
Chen, Ziyi
Parker Jones, Oiwi
Niu, Chen
Wang, Yang
author_sort Cohen, Alexander D.
collection PubMed
description Resting‐state fMRI has shown the ability to predict task activation on an individual basis by using a general linear model (GLM) to map resting‐state network features to activation z‐scores. The question remains whether the relatively simplistic GLM is the best approach to accomplish this prediction. In this study, several regression‐based machine‐learning approaches were compared, including GLMs, feed‐forward neural networks, and random forest bootstrap aggregation (bagging). Resting‐state and task data from 350 Human Connectome Project subjects were analyzed. First, the effect of the number of training subjects on the prediction accuracy was evaluated. In addition, the prediction accuracy and Dice coefficient were compared across models. Prediction accuracy increased with the training number up to 200 subjects; however, an elbow in the prediction curve occurred around 30–40 training subjects. All models performed well with correlation matrices, which displayed correlation between actual and predicted task activation for all subjects, exhibiting a strong diagonal trend for all tasks. Overall, the neural network and random forest bagging techniques outperformed the GLM. These approaches, however, require additional computing power and processing time. These results show that, while the GLM performs well, resting‐state fMRI prediction of task activation could benefit from more complex machine learning approaches.
format Online
Article
Text
id pubmed-7267916
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher John Wiley & Sons, Inc.
record_format MEDLINE/PubMed
spelling pubmed-72679162020-06-12 Regression‐based machine‐learning approaches to predict task activation using resting‐state fMRI Cohen, Alexander D. Chen, Ziyi Parker Jones, Oiwi Niu, Chen Wang, Yang Hum Brain Mapp Research Articles Resting‐state fMRI has shown the ability to predict task activation on an individual basis by using a general linear model (GLM) to map resting‐state network features to activation z‐scores. The question remains whether the relatively simplistic GLM is the best approach to accomplish this prediction. In this study, several regression‐based machine‐learning approaches were compared, including GLMs, feed‐forward neural networks, and random forest bootstrap aggregation (bagging). Resting‐state and task data from 350 Human Connectome Project subjects were analyzed. First, the effect of the number of training subjects on the prediction accuracy was evaluated. In addition, the prediction accuracy and Dice coefficient were compared across models. Prediction accuracy increased with the training number up to 200 subjects; however, an elbow in the prediction curve occurred around 30–40 training subjects. All models performed well with correlation matrices, which displayed correlation between actual and predicted task activation for all subjects, exhibiting a strong diagonal trend for all tasks. Overall, the neural network and random forest bagging techniques outperformed the GLM. These approaches, however, require additional computing power and processing time. These results show that, while the GLM performs well, resting‐state fMRI prediction of task activation could benefit from more complex machine learning approaches. John Wiley & Sons, Inc. 2019-10-22 /pmc/articles/PMC7267916/ /pubmed/31638304 http://dx.doi.org/10.1002/hbm.24841 Text en © 2019 The Authors. Human Brain Mapping published by Wiley Periodicals, Inc. This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Articles
Cohen, Alexander D.
Chen, Ziyi
Parker Jones, Oiwi
Niu, Chen
Wang, Yang
Regression‐based machine‐learning approaches to predict task activation using resting‐state fMRI
title Regression‐based machine‐learning approaches to predict task activation using resting‐state fMRI
title_full Regression‐based machine‐learning approaches to predict task activation using resting‐state fMRI
title_fullStr Regression‐based machine‐learning approaches to predict task activation using resting‐state fMRI
title_full_unstemmed Regression‐based machine‐learning approaches to predict task activation using resting‐state fMRI
title_short Regression‐based machine‐learning approaches to predict task activation using resting‐state fMRI
title_sort regression‐based machine‐learning approaches to predict task activation using resting‐state fmri
topic Research Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7267916/
https://www.ncbi.nlm.nih.gov/pubmed/31638304
http://dx.doi.org/10.1002/hbm.24841
work_keys_str_mv AT cohenalexanderd regressionbasedmachinelearningapproachestopredicttaskactivationusingrestingstatefmri
AT chenziyi regressionbasedmachinelearningapproachestopredicttaskactivationusingrestingstatefmri
AT parkerjonesoiwi regressionbasedmachinelearningapproachestopredicttaskactivationusingrestingstatefmri
AT niuchen regressionbasedmachinelearningapproachestopredicttaskactivationusingrestingstatefmri
AT wangyang regressionbasedmachinelearningapproachestopredicttaskactivationusingrestingstatefmri