Predictive structural dynamic network analysis

Rong Chen; Edward H Herskovits; Alzheimer's Disease Neuroimaging Initiative

doi:10.1016/j.jneumeth.2015.02.011

Back

Predictive structural dynamic network analysis

Journal article

Peer reviewed

Predictive structural dynamic network analysis

Rong Chen, Edward H Herskovits and Alzheimer's Disease Neuroimaging Initiative

Journal of neuroscience methods, Vol.245, pp.58-63

04/30/2015

DOI: 10.1016/j.jneumeth.2015.02.011

PMCID: PMC6201756

PMID: 25707306

Files and links (1)

url

https://www.ncbi.nlm.nih.gov/pmc/articles/6201756View

Open Access

Abstract

Classifying individuals based on magnetic resonance data is an important task in neuroscience. Existing brain network-based methods to classify subjects analyze data from a cross-sectional study and these methods cannot classify subjects based on longitudinal data. We propose a network-based predictive modeling method to classify subjects based on longitudinal magnetic resonance data. Our method generates a dynamic Bayesian network model for each group which represents complex spatiotemporal interactions among brain regions, and then calculates a score representing that subject's deviation from expected network patterns. This network-derived score, along with other candidate predictors, are used to construct predictive models. We validated the proposed method based on simulated data and the Alzheimer's Disease Neuroimaging Initiative study. For the Alzheimer's Disease Neuroimaging Initiative study, we built a predictive model based on the baseline biomarker characterizing the baseline state and the network-based score which was constructed based on the state transition probability matrix. We found that this combined model achieved 0.86 accuracy, 0.85 sensitivity, and 0.87 specificity. For the Alzheimer's Disease Neuroimaging Initiative study, the model based on the baseline biomarkers achieved 0.77 accuracy. The accuracy of our model is significantly better than the model based on the baseline biomarkers (p-value=0.002). We have presented a method to classify subjects based on structural dynamic network model based scores. This method is of great importance to distinguish subjects based on structural network dynamics and the understanding of the network architecture of brain processes and disorders.

Magnetic Resonance Imaging

Nonlinear Dynamics

Brain - anatomy & histology

Follow-Up Studies

Humans

Male

Alzheimer Disease - pathology

Image Processing, Computer-Assisted

Computer Simulation

Bayes Theorem

Brain Mapping

Female

Models, Neurological

Details

Title: Subtitle: Predictive structural dynamic network analysis
Creators: Rong Chen - Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland, School of Medicine, 100N. Greene St, 4th Floor, 22 S. Greene St., Baltimore, MD 21201, USA. Electronic address: rchen@umm.edu
Edward H Herskovits - Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland, School of Medicine, 100N. Greene St, 4th Floor, 22 S. Greene St., Baltimore, MD 21201, USA
Alzheimer's Disease Neuroimaging Initiative
Contributors: Laura L Boles-Ponto (Contributor) - University of Iowa, Radiology
Resource Type: Journal article
Publication Details: Journal of neuroscience methods, Vol.245, pp.58-63
DOI: 10.1016/j.jneumeth.2015.02.011
PMID: 25707306
PMCID: PMC6201756
NLM abbreviation: J Neurosci Methods
ISSN: 0165-0270
eISSN: 1872-678X
Publisher: Netherlands
Grant note: U01 AG024904 / NIA NIH HHS P30 AG013846 / NIA NIH HHS
Language: English
Date published: 04/30/2015
Academic Unit: Radiology; Pharmaceutical Sciences and Experimental Therapeutics
Record Identifier: 9984051787902771

Metrics

20 Record Views

9 Times Cited - Web of Science