A simple but tough-to-beat baseline for fMRI time-series classification

Current neuroimaging studies frequently use complex machine learning models to classify human fMRI data, distinguishing healthy and disordered brains, often to validate new methods or enhance prediction accuracy. Yet, where prediction accuracy is a concern, our results suggest that precision in pred...

Full description

Bibliographic Details

Published in:	NeuroImage
Main Authors:	Pavel Popov, Usman Mahmood, Zening Fu, Carl Yang, Vince Calhoun, Sergey Plis
Format:	Article
Language:	English
Published:	Elsevier 2024-12-01
Subjects:	Resting-state fMRI Data explainability Machine learning Deep learning Brain disorders Predictive neuroimaging
Online Access:	http://www.sciencedirect.com/science/article/pii/S1053811924004063