Conference paper
Evaluating Models of Dynamic Functional Connectivity Using Predictive Classification Accuracy
Department of Applied Mathematics and Computer Science, Technical University of Denmark1
Cognitive Systems, Department of Applied Mathematics and Computer Science, Technical University of Denmark2
University of Maryland, College Park3
University of Oxford4
The Mind Research Network5
Copenhagen Center for Health Technology, Centers, Technical University of Denmark6
Dynamic functional connectivity has become a prominent approach for tracking the changes of macroscale statistical dependencies between regions in the brain. Effective parametrization of these statistical dependencies, referred to as brain states, is however still an open problem. We investigate different emission models in the hidden Markov model framework, each representing certain assumptions about dynamic changes in the brain.
We evaluate each model by how well they can discriminate between schizophrenic patients and healthy controls based on a group independent component analysis of resting-state functional magnetic resonance imaging data. We find that simple emission models without full covariance matrices can achieve similar classification results as the models with more parameters.
This raises questions about the predictability of dynamic functional connectivity in comparison to simpler dynamic features when used as biomarkers. However, we must stress that there is a distinction between characterization and classification, which has to be investigated further.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2018 |
Pages: | 2566-2570 |
Proceedings: | 2018 IEEE International Conference on Acoustics, Speech and Signal Processing |
ISBN: | 1538646587 , 1538646595 , 9781538646588 , 9781538646595 , 1538646579 and 9781538646571 |
ISSN: | 2379190x and 15206149 |
Types: | Conference paper |
DOI: | 10.1109/ICASSP.2018.8462310 |
ORCIDs: | Nielsen, Søren Føns Vind , Madsen, Kristoffer Hougaard , Hansen, Lars Kai and Mørup, Morten |
Brain modeling Classification Covariance matrices Data models Dynamic functional connectivity Functional magnetic resonance imaging Hidden Markov models Predictive models Schizophrenia Training
biomedical MRI brain brain states dynamic functional connectivity hidden Markov model framework hidden Markov models independent component analysis macroscale statistical dependencies medical disorders medical image processing neurophysiology predictive classification accuracy resting-state functional magnetic resonance imaging data schizophrenic patient simple emission models simpler dynamic features