Data-Driven Analysis for Detecting Transitions in Health Status in Traumatic Brain Injury: Implications For Prevention

Abstract

<h3>Research Objectives</h3> To apply computational and data visualization techniques to categorize health records of patients with traumatic brain injury (TBI) in Ontario Canada, from preceding injury to the injury event. <h3>Design</h3> Big data reduction techniques, conditional logistic regression modeling, correlation matrices, and hierarchical clustering. <h3>Setting</h3> Health administrative data on publicly funded services provided to residents of Ontario, Canada, including information on acute care hospitalizations and emergency department (ED) visits. <h3>Participants</h3> Data from 235,003 unique patients with TBI and the same number of reference patients discharged from the ED or acute care hospitals during the same study period for a reason other than TBI, individually matched by sex, age, place of residence, and income quintile. <h3>Interventions</h3> None. <h3>Main Outcome Measures</h3> We identified main and associated diagnoses according to the International Statistical Classification of Diseases and Related Health Problems, Tenth Revision that were associated with a TBI event. To understand health status transitions from the time preceding TBI to the TBI event, we clustered all factors from each period into a single heatmap. <h3>Results</h3> Data-driven analysis revealed a remarkable extent of meaningful associations and health status transitions as they concern external causes of injury and injury severity. The strongest associations between health status preceding TBI and health status at the injury event were between clusters of multiple body system pathology and advanced age-related brain pathology. <h3>Conclusions</h3> Application of a health status transitions perspective to contextual injury event, and recognition that health status preceding injury makes a person more or less susceptible to TBI due to specific external cause of injury and developing a more or less severe TBI, entails new approaches to injury taxonomy, treatment and rehabilitation, and predictive classifications. <h3>Author(s) Disclosures</h3> The research reported in this presentation was supported by the Eunice Kennedy Shriver National Institute of Child Health & Human Development of the National Institutes of Health under Award R21HD089106 and the National Institute Of Neurological Disorders And Stroke of the National Institutes of Health under Award R01NS117921, and in part, by the Canada Research Chairs Program.