A1043
Title: Change point functional connectivity outperforms sliding window and static methods for resting-state fMRI classification
Authors: Martin Ondrus - University of Alberta (Canada) [presenting]
Ivor Cribben - Alberta School of Business (Canada)
Abstract: The most widely used inputs in classification models of brain disorders such as early mild cognitive impairment (eMCI) or Alzheimer's disease are estimates of static-based functional connectivity (SFC) and sliding window dynamic functional connectivity (swDFC). Although these methods are convenient for estimation and computational purposes, as they keep the estimation tractable, they present a simplified version of a highly integrated and dynamic phenomenon. Changepoint dynamic functional connectivity (cpDFC) methods offer an alternative to swDFC approaches. A classification task is considered between controls and patients with eMCI using resting-state functional magnetic resonance imaging data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Results indicate that the DFC methods are generally superior to the SFC methods when used as inputs into the classification task. Most importantly, it is found that the cpDFC methods are generally superior to the widely used swDFC methods. It is discussed how cpDFC methods offer many distinct advantages over swDFC methods, namely, the parsimony of network features and ease of interpretability. These findings call into question the validity of numerous fMRI studies that have utilized SFC and swDFC as inputs to classification models to predict brain disorders. Results suggest that functional networks are dynamic and multiscale and that different FC methods capture distinct information for classification efficacy.
