Sponsor
This material is based in part upon work supported by the U.S. Army Contracting Command, Aberdeen Proving Ground, Natick Contracting Division, through a contract awarded to Stanford University (W911 QY-14-C- 0086), a subcontract awarded to the Brain Trauma Foundation, and a secondtier subcontract awarded to Portland State University.
Document Type
Post-Print
Publication Date
2017
Subjects
Brain damage -- Models, System analysis, Brain damage -- Medical statistics -- Analysis, Reconstructability Analysis, Information Theory, Probabilistic graphical modeling, Multivariate analysis discrete multivariate modeling, Data mining
Abstract
This paper reports the analysis of data on traumatic brain injury using a probabilistic graphical modeling technique known as reconstructability analysis (RA). The analysis shows the flexibility, power, and comprehensibility of RA modeling, which is well-suited for mining biomedical data. One finding of the analysis is that education is a confounding variable for the Digit Symbol Test in discriminating the severity of concussion; another - and anomalous - finding is that previous head injury predicts improved performance on the Reaction Time test. This analysis was exploratory, so its findings require follow-on confirmatory tests of their generalizability.
DOI
10.1109/SSCI.2017.8280843
Persistent Identifier
https://archives.pdx.edu/ds/psu/26693
Citation Details
Zwick, Martin; Carney, Nancy; and Nettleton, Rosemary, "Mining Data on Traumatic Brain Injury with Reconstructability Analysis" (2017). Systems Science Faculty Publications and Presentations. 128.
https://archives.pdx.edu/ds/psu/26693
Description
This is an Accepted Manuscript of an article published by IEEE in 2017 in IEEE Symposium Series on Computational Intelligence (SSCI). The definitive version is available here: https://doi.org/10.1109/SSCI.2017.8280843