Abstract
Functional connections in the brain are frequently represented by weighted networks, with nodes representing locations in the brain and edges representing the strength of connectivity between these locations. One challenge in analyzing such data is that inference at the individual edge level is not particularly biologically meaningful; interpretation is more useful at the level of so-called functional systems or groups of nodes and connections between them; this is often called “graph-aware” inference in the neuroimaging literature. However, pooling over functional regions leads to significant loss of information and lower accuracy. Another challenge is correlation among edge weights within a subject which makes inference based on independence assumptions unreliable. We address both of these challenges with a linear mixed effects model, which accounts for functional systems and for edge dependence, while still modeling individual edge weights to avoid loss of information. The model allows for comparing two populations, such as patients and healthy controls, both at the functional regions level and at individual edge level, leading to biologically meaningful interpretations. We fit this model to resting state fMRI data on schizophrenic patients and healthy controls, obtaining interpretable results consistent with the schizophrenia literature.
Funding Statement
This research was supported in part by NSF DMS grants 1521551, 1646108, and 1916222, ONR grant N000141612910, a Rackham Predoctoral Fellowship from the University of Michigan awarded to D. Kessler, and a Dana Foundation grant to E. Levina as well as by computational resources and services provided by Advanced Research Computing at the University of Michigan, Ann Arbor.
Acknowledgments
We thank Professor Stephan Taylor (Psychiatry, University of Michigan) and Professor Chandra Sripada (Psychiatry and Philosophy, University of Michigan) and members of both of their labs for many useful discussions, and the Taylor lab for providing processed schizophrenia data. We thank Jesús Arroyo Relión (Statistics, Texas A&M University) for his help with the data.
Citation
Yura Kim. Daniel Kessler. Elizaveta Levina. "Graph-aware modeling of brain connectivity networks." Ann. Appl. Stat. 17 (3) 2095 - 2117, September 2023. https://doi.org/10.1214/22-AOAS1709
Information