Meeting Banner
Abstract #3287

Support Vector Machine Classification of Spontaneous Cognition Using Whole-Brain Resting-State Functional Connectivity

Ying-Hui Chou1, Pooja Gaur2, Carol P. Weingarten1, Mei-Lan Chu1, David Madden1, Allen W. Song1, Nan-Kuei Chen3

1Duke University Medical Center, Durham, NC, United States; 2Vanderbilt University, Nashville, TN, United States; 3Duke University, Durham, NC, United States

In this study, we demonstrated that the behavior-based connectivity analysis and support vector machine methods can be used to decode the whole-brain resting-state functional connectivity patterns and classify individuals who reported inner language as the dominant mental activity during resting-state fMRI scan from those who did not with a sensitivity of 0.88 and a specificity of 0.9. Our findings can lead to a better understanding of variations in resting-state fMRI signals and their dependence on the spontaneous cognition/mind wandering.

Keywords

achieved acquisition activities activity adjusted although among anticipated approved assess audience awareness better brain bull carol centrally cerebral characterize choosing classification classified classifier classify clustering cognition committee components comprised connect connected connectivity content correction correlated correlation cortex cortical cross debriefing dependence detected distinct domain domains dominant duke employed exists finally findings fixate fluid frontal functional future grants healthy identified identify identifying imagery imagining immediately indeed individuals inferior informed inner instructed inter interview investigate investigations involved keeping language leave links local machine majority males manipulation memories mental middle mind mixture monitoring motion musical needed network neurological normalization ongoing orbital overt part participant participants patterns performance permutation permutations phrases plays positively predict preprocessed presently previously production reality regression reliably reported resting scanner sensitivity seven song space specificity speech spending spent spontaneous still strategy strength structure subsets suggested superior support target terms thought thoughts understanding underway unique validation variations vector visual wandering whether whole