Exploratory reconstructability analysis of accident TBI data. Issue 2 (17th February 2018)

• Record Type: Journal Article
• Authors: Zwick, Martin; Carney, Nancy; Nettleton, Rosemary
• Is Part Of: International journal of general systems. Volume 47:Issue 2(2018)
• Page Start: 174
• Page End: 191
• Publication Date: 2018-02-17
• Subjects: Reconstructability analysis -- machine learning -- OCCAM -- information theory -- traumatic brain injury -- health care analytics; System theory -- Periodicals; 003
• DOI: 10.1080/03081079.2017.1412435
• Languages: English
• ISSNs: 0308-1079

Abstract

Abstract: This paper describes the use of reconstructability analysis to perform a secondary study of traumatic brain injury data from automobile accidents. Neutral searches were done and their results displayed with a hypergraph. Directed searches, using both variable-based and state-based models, were applied to predict performance on two cognitive tests and one neurological test. Very simple state-based models gave large uncertainty reductions for all three DVs and sizeable improvements in percent correct for the two cognitive test DVs which were equally sampled. Conditional probability distributions for these models are easily visualized with simple decision trees. Confounding variables and counter-intuitive findings are also reported.