Online Program Home
My Program

Abstract Details

Activity Number: 427 - SPEED: Bayesian Methods, Part 2
Type: Contributed
Date/Time: Tuesday, July 30, 2019 : 3:05 PM to 3:50 PM
Sponsor: Section on Bayesian Statistical Science
Abstract #307874
Title: Bayesian Quantile Regression Applied to Time Between Healthcare-Associated Infection Events
Author(s): Jonathan Edwards*
Companies: Center for Disease Control & Prevention
Keywords: Healthcare; Infection; Bayesian Quantile Regression

Pursuant to federal requirements, central line-associated bloodstream infection (CLABSI) event data are reported by acute care hospitals (ICUs and select ward locations) to CDC’s National Healthcare Safety Network (NHSN) to measure hospital performance using healthcare-associated infection (HAI) data. Time Between Event (TBE) monitoring among HAIs such as CLABSI can provide additional value to measuring and improving healthcare quality. To better understand and account for factors that explain differences in TBE, Bayesian quantile regression was performed using improper uniform priors with hospital and unit/location-level covariates.

In 2017, TBE data for 17,676 CLABSIs were reported to NHSN. Patient care location types reporting ?50 CLABSIs were included. Estimation of conditional quantile functions of CLABSI TBE enable a more complete representation of each covariate effect. This permits comprehension of how changes in patient care location and hospital bed size affect the distribution of CLABSI TBE. These results can be used to further characterize CLABSI TBE, assess the performance of hospital ICUs and select wards and complement existing performance measures.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program