Exploratory reconstructability analysis of accident TBI data

Martin Zwick, Nancy Carney, Rosemary Nettleton

Research output: Contribution to journalArticle

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.

Original languageEnglish (US)
Pages (from-to)174-191
Number of pages18
JournalInternational Journal of General Systems
Volume47
Issue number2
DOIs
StatePublished - Feb 17 2018

Fingerprint

Exploratory Analysis
Accidents
Confounding
Automobile
Conditional probability
Conditional Distribution
Decision trees
Hypergraph
Decision tree
Probability distributions
Percent
Automobiles
Intuitive
Brain
Probability Distribution
Model
Uncertainty
Predict

Keywords

  • health care analytics
  • information theory
  • machine learning
  • OCCAM
  • Reconstructability analysis
  • traumatic brain injury

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Information Systems
  • Modeling and Simulation
  • Computer Science Applications

Cite this

Exploratory reconstructability analysis of accident TBI data. / Zwick, Martin; Carney, Nancy; Nettleton, Rosemary.

In: International Journal of General Systems, Vol. 47, No. 2, 17.02.2018, p. 174-191.

Research output: Contribution to journalArticle

Zwick, Martin ; Carney, Nancy ; Nettleton, Rosemary. / Exploratory reconstructability analysis of accident TBI data. In: International Journal of General Systems. 2018 ; Vol. 47, No. 2. pp. 174-191.
@article{a406f9d908864a6f996311ce8d75a5a6,
title = "Exploratory reconstructability analysis of accident TBI data",
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.",
keywords = "health care analytics, information theory, machine learning, OCCAM, Reconstructability analysis, traumatic brain injury",
author = "Martin Zwick and Nancy Carney and Rosemary Nettleton",
year = "2018",
month = "2",
day = "17",
doi = "10.1080/03081079.2017.1412435",
language = "English (US)",
volume = "47",
pages = "174--191",
journal = "International Journal of General Systems",
issn = "0308-1079",
publisher = "Taylor and Francis Ltd.",
number = "2",

}

TY - JOUR

T1 - Exploratory reconstructability analysis of accident TBI data

AU - Zwick, Martin

AU - Carney, Nancy

AU - Nettleton, Rosemary

PY - 2018/2/17

Y1 - 2018/2/17

N2 - 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.

AB - 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.

KW - health care analytics

KW - information theory

KW - machine learning

KW - OCCAM

KW - Reconstructability analysis

KW - traumatic brain injury

UR - http://www.scopus.com/inward/record.url?scp=85041445524&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041445524&partnerID=8YFLogxK

U2 - 10.1080/03081079.2017.1412435

DO - 10.1080/03081079.2017.1412435

M3 - Article

AN - SCOPUS:85041445524

VL - 47

SP - 174

EP - 191

JO - International Journal of General Systems

JF - International Journal of General Systems

SN - 0308-1079

IS - 2

ER -