Publications by authors named "S Charlifue"
Data standards are available for spinal cord injury (SCI). The International SCI Data Sets were created in 2002 and there are currently 27 freely available. In 2014 the National Institute of Neurological Disorders and Stroke developed clinical common data elements to promote clinical data sharing in SCI.
View Article and Find Full Text PDFObjective: To develop composite measures of neighborhood economic factors for use with the national Spinal Cord Injury Model Systems (SCIMSs) database in cross-sectional and longitudinal investigations of the social determinants of health.
Design: Secondary data analysis of administrative data from the 2009, 2014, and 2019 American Community Survey (ACS) 5-year estimates and survey data collected for the SCIMS database.
Setting: Community.
Objectives: The development of venous thromboembolism (VTE) is a common complication following spinal cord injury (SCI) and brain injury (BI), leading to significant morbidity and mortality. The purpose of this study was to explore the incidence of VTE in patients with the dual diagnosis (DD) of SCI and concomitant BI using ultrasonography.
Design: Retrospective study.
Article Synopsis
- - A retrospective multi-site cohort study aimed to create a machine learning model to predict ambulatory status in spinal cord injury (SCI) patients one year after their injury, using data from the SCI Model System database collected between January 2000 and May 2019.
- - The study analyzed data from 4,523 patients, comparing traditional prediction methods with machine learning algorithms, finding that the Elastic Net Penalized Logistic Regression (ENPLR) model had the best predictive accuracy.
- - The ENPLR model showed improved performance metrics over traditional methods, indicating that machine learning could more accurately identify patients' likelihood to walk post-injury, suggesting future research could enhance these predictions by incorporating additional variables.