Activity Number:
|
320
- Innovative Approaches for Modeling Time-to-Event Data in the Presence of Competing Risks and/or Time-Varying Covariates
|
Type:
|
Topic Contributed
|
Date/Time:
|
Tuesday, August 9, 2022 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Biometrics Section
|
Abstract #320850
|
|
Title:
|
Modeling Severe Liver Disease Outcomes and History of FIB-4 in the Presence of Competing Risks and Time-Varying Covariates
|
Author(s):
|
Mulugeta Gebregziabher* and Andrew D Schreiner and Jingwen Zhang and David G Koch and Patrick D Mauldin and William P Moran
|
Companies:
|
Medical University of South Carolina and MUSC and MUSC and MUSC and MUSC and MUSC
|
Keywords:
|
Cox model;
Competing risk;
C-statistic;
FIB-4;
Severe Liver Disease;
Time varying covariate
|
Abstract:
|
Advanced fibrosis from chronic liver disease (CLD) is associated with severe liver disease (SLD) outcomes. History of Fibrosis-4 (FIB-4) can be used to reliably assess the risk of fibrosis in patients with CLD diagnoses. We examined the association of history of FIB-4 and the incidence of SLD with CLD diagnoses after the index FIB-4 and death as competing risks. Since standard Cox model can’t be used, we examined modified Cox regression models to study the association between SLD as a time-to-event outcome and FIB-4 as a time varying covariate in the presence of competing events. A comparisons among modified Cox regression models was made using C-statistics, explained variation and AIC/BIC. We demonstrated their applications to the analysis of data from a retrospective cohort (2007-2018) of primary care patients from electronic health records and their longitudinal FIB-4 scores. The findings of this study have critically important implications to the diagnosis and treatment of liver disease patients in a primary care setting.
|
Authors who are presenting talks have a * after their name.