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...

Full description

Saved in:
Bibliographic Details
Published in:Human brain mapping 2020-02, Vol.41 (3), p.815-826
Main Authors: Cohen, Alexander D., Chen, Ziyi, Parker Jones, Oiwi, Niu, Chen, Wang, Yang
Format: Article
Language:English
Subjects:
Accuracy
Activation
Bagging
Comparative analysis
Correlation analysis
Elbow
fMRI
Functional magnetic resonance imaging
Learning algorithms
Machine learning
Magnetic resonance imaging
Model accuracy
Neural networks
Predictions
random‐forest bootstrap aggregation
Regression analysis
resting state
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1065-9471
1097-0193
DOI:10.1002/hbm.24841