Tags

Type your tag names separated by a space and hit enter

An information network flow approach for measuring functional connectivity and predicting behavior.
Brain Behav 2019; 9(8):e01346BB

Abstract

INTRODUCTION

Connectome-based predictive modeling (CPM) is a recently developed machine-learning-based framework to predict individual differences in behavior from functional brain connectivity (FC). In these models, FC was operationalized as Pearson's correlation between brain regions' fMRI time courses. However, Pearson's correlation is limited since it only captures linear relationships. We developed a more generalized metric of FC based on information flow. This measure represents FC by abstracting the brain as a flow network of nodes that send bits of information to each other, where bits are quantified through an information theory statistic called transfer entropy.

METHODS

With a sample of individuals performing a sustained attention task and resting during functional magnetic resonance imaging (fMRI) (n = 25), we use the CPM framework to build machine-learning models that predict attention from FC patterns measured with information flow. Models trained on n - 1 participants' task-based patterns were applied to an unseen individual's resting-state pattern to predict task performance. For further validation, we applied our model to two independent datasets that included resting-state fMRI data and a measure of attention (Attention Network Task performance [n = 41] and stop-signal task performance [n = 72]).

RESULTS

Our model significantly predicted individual differences in attention task performance across three different datasets.

CONCLUSIONS

Information flow may be a useful complement to Pearson's correlation as a measure of FC because of its advantages for nonlinear analysis and network structure characterization.

Authors+Show Affiliations

Department of Psychology, Yale University, New Haven, Connecticut.Department of Psychology, Yale University, New Haven, Connecticut.Department of Psychology, Yale University, New Haven, Connecticut. Department of Psychology, University of Chicago, Chicago, Illinois.Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut.Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut. Interdepartmental Neuroscience Program, Yale University, New Haven, Connecticut. Department of Neurosurgery, Yale School of Medicine, New Haven, Connecticut.Department of Psychiatry, Yale School of Medicine, New Haven, Connecticut.Interdepartmental Neuroscience Program, Yale University, New Haven, Connecticut. Department of Psychiatry, Yale School of Medicine, New Haven, Connecticut. Department of Neuroscience, Yale School of Medicine, New Haven, Connecticut.Department of Psychology, Yale University, New Haven, Connecticut. Interdepartmental Neuroscience Program, Yale University, New Haven, Connecticut. Department of Neuroscience, Yale School of Medicine, New Haven, Connecticut.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

31286688

Citation

Kumar, Sreejan, et al. "An Information Network Flow Approach for Measuring Functional Connectivity and Predicting Behavior." Brain and Behavior, vol. 9, no. 8, 2019, pp. e01346.
Kumar S, Yoo K, Rosenberg MD, et al. An information network flow approach for measuring functional connectivity and predicting behavior. Brain Behav. 2019;9(8):e01346.
Kumar, S., Yoo, K., Rosenberg, M. D., Scheinost, D., Constable, R. T., Zhang, S., ... Chun, M. M. (2019). An information network flow approach for measuring functional connectivity and predicting behavior. Brain and Behavior, 9(8), pp. e01346. doi:10.1002/brb3.1346.
Kumar S, et al. An Information Network Flow Approach for Measuring Functional Connectivity and Predicting Behavior. Brain Behav. 2019;9(8):e01346. PubMed PMID: 31286688.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - An information network flow approach for measuring functional connectivity and predicting behavior. AU - Kumar,Sreejan, AU - Yoo,Kwangsun, AU - Rosenberg,Monica D, AU - Scheinost,Dustin, AU - Constable,R Todd, AU - Zhang,Sheng, AU - Li,Chiang-Shan R, AU - Chun,Marvin M, Y1 - 2019/07/09/ PY - 2019/03/14/received PY - 2019/04/13/revised PY - 2019/04/21/accepted PY - 2019/7/10/pubmed PY - 2019/7/10/medline PY - 2019/7/10/entrez KW - functional connectivity KW - information flow KW - predictive model KW - resting-state fMRI connectivity KW - sustained attention SP - e01346 EP - e01346 JF - Brain and behavior JO - Brain Behav VL - 9 IS - 8 N2 - INTRODUCTION: Connectome-based predictive modeling (CPM) is a recently developed machine-learning-based framework to predict individual differences in behavior from functional brain connectivity (FC). In these models, FC was operationalized as Pearson's correlation between brain regions' fMRI time courses. However, Pearson's correlation is limited since it only captures linear relationships. We developed a more generalized metric of FC based on information flow. This measure represents FC by abstracting the brain as a flow network of nodes that send bits of information to each other, where bits are quantified through an information theory statistic called transfer entropy. METHODS: With a sample of individuals performing a sustained attention task and resting during functional magnetic resonance imaging (fMRI) (n = 25), we use the CPM framework to build machine-learning models that predict attention from FC patterns measured with information flow. Models trained on n - 1 participants' task-based patterns were applied to an unseen individual's resting-state pattern to predict task performance. For further validation, we applied our model to two independent datasets that included resting-state fMRI data and a measure of attention (Attention Network Task performance [n = 41] and stop-signal task performance [n = 72]). RESULTS: Our model significantly predicted individual differences in attention task performance across three different datasets. CONCLUSIONS: Information flow may be a useful complement to Pearson's correlation as a measure of FC because of its advantages for nonlinear analysis and network structure characterization. SN - 2162-3279 UR - https://www.unboundmedicine.com/medline/citation/31286688/An_information_network_flow_approach_for_measuring_functional_connectivity_and_predicting_behavior_ L2 - https://doi.org/10.1002/brb3.1346 DB - PRIME DP - Unbound Medicine ER -