A0515
Title: A hidden semi-Markov model approach to dynamic brain network analysis: Recent developments and future directions
Authors: Heather Shappell - Wake Forest University School of Medicine (United States) [presenting]
Abstract: The study of functional brain networks has grown tremendously over the past decade. Most functional connectivity (FC) analyses assume that FC networks are stationary across time. However, there is interest in studying changes in FC over time. Hidden Markov models (HMMs) are a useful modeling approach for FC. However, a severe limitation is that HMMs assume the sojourn time (number of consecutive time points in a state) is geometrically distributed. This encourages state switches too often. The focus is on a hidden semi-Markov model (HSMM) approach for inferring functional brain networks from functional magnetic resonance imaging (fMRI) data, which explicitly models the sojourn distribution. Specifically, it proposes using HSMMs to find each subject's most probable series of network states, the cumulative time in each state, and the networks associated with each state. The approach is demonstrated on fMRI data from a study on older adults with obesity. Lastly, an extension to the HSMM will be discussed, where the sojourn distribution may depend on a number of covariates. This extension allows for a direct comparison of sojourn times across patient populations. Challenges and future directions will be presented throughout.
