About this item:

93 Views | 181 Downloads

Author Notes:

Address for correspondence: Gordana Derado, Department of Biostatistics and Bioinformatics, Rollins School of Public Health, Emory University, 1518 Clifton Road, Atlanta, GA 30322, USA. gderado@emory.edu

The authors are grateful to Dr. Ying Guo from the Department of Biostatistics and Bioinformatics at Emory University for valuable discussions and constructive comments.


Research Funding:

This research was supported by NIH grants R01-MH079251 (Bowman) and NIH predoctoral training grant T32 GM074909-01 (Derado).


  • Science & Technology
  • Life Sciences & Biomedicine
  • Physical Sciences
  • Health Care Sciences & Services
  • Mathematical & Computational Biology
  • Medical Informatics
  • Statistics & Probability
  • Mathematics
  • neuroimaging
  • Bayesian spatial modeling
  • prediction
  • Alzheimer's disease

Predicting brain activity using a Bayesian spatial model


Journal Title:

Statistical Methods in Medical Research


Volume 22, Number 4


, Pages 382-397

Type of Work:

Article | Post-print: After Peer Review


Increasing the clinical applicability of functional neuroimaging technology is an emerging objective, e.g. for diagnostic and treatment purposes. We propose a novel Bayesian spatial hierarchical framework for predicting follow-up neural activity based on an individual's baseline functional neuroimaging data. Our approach attempts to overcome some shortcomings of the modeling methods used in other neuroimaging settings, by borrowing strength from the spatial correlations present in the data. Our proposed methodology is applicable to data from various imaging modalities including functional magnetic resonance imaging and positron emission tomography, and we provide an illustration here using positron emission tomography data from a study of Alzheimer's disease to predict disease progression.

Copyright information:

© The Author(s) 2012 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav.

Export to EndNote