Authors: Carlos A. Perez, Eman M. El-Sheikh, Clark Glymour
Addresses: Institute for Human and Machine Cognition, 15 SE Osceola Avenue, Ocala, FL 34471, USA. ' College of Arts and Sciences, University of West Florida, 11000 University Parkway, Pensacola, FL 32514, USA. ' Department of Philosophy, Baker Hall 135L, Carnegie Mellon University, Pittsburgh, PA 15213 USA
Abstract: Functional magnetic resonance imaging (fMRI) data have been used for identifying brain regions that activate when a subject is presented a stimulus or performs a task. Beyond identifying which regions of the brain are active during a task, it is also of interest to discover causal relationships among activity in those regions, that is, which regions of the brain influence, which other regions of the brain during a task. Two algorithms for causal discovery were applied to fMRI data, the greedy equivalence search (GES) algorithm and the independent multiple-sample greedy equivalence search (iMAGES). GES applies to individual datasets, and iMAGES to multiple datasets. We consider the stability of the GES results across subjects and experimental repetitions with the same subject. We find that some iMAGES connections agree with previous knowledge of the functional roles of the brain regions. The strengths and limitations of the research work and opportunities for future work are also discussed.
Keywords: artificial intelligence; brain regions; causal modelling; effective connectivity; functional MRI; magnetic resonance imaging; fMRI; healthcare technology; local search; knowledge discovery.
International Journal of Computers in Healthcare, 2010 Vol.1 No.1, pp.86 - 102
Published online: 15 Jul 2010 *Full-text access for editors Access for subscribers Free access Comment on this article