English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We recently developed a new method riAFT-BART to draw causal inferences aboutpopulation treatment effect on patient survival from clustered and censoredsurvival data while accounting for the multilevel data structure. The practicalutility of this method goes beyond the estimation of population averagetreatment effect. In this work, we exposit how riAFT-BART can be used to solvetwo important statistical questions with clustered survival data: estimatingthe treatment effect heterogeneity and variable selection. Leveraging thelikelihood-based machine learning, we describe a way in which we can drawposterior samples of the individual survival treatment effect from riAFT-BARTmodel runs, and use the drawn posterior samples to perform an exploratorytreatment effect heterogeneity analysis to identify subpopulations who mayexperience differential treatment effects than population average effects.There is sparse literature on methods for variable selection among clusteredand censored survival data, particularly ones using flexible modelingtechniques. We propose a permutation based approach using the predictor'svariable inclusion proportion supplied by the riAFT-BART model for variableselection. To address the missing data issue frequently encountered in healthdatabases, we propose a strategy to combine bootstrap imputation and riAFT-BARTfor variable selection among incomplete clustered survival data. We conduct anexpansive simulation study to examine the practical operating characteristicsof our proposed methods. Finally, we demonstrate the methods via a case studyof predictors for in-hospital mortality among severe COVID-19 patients andestimating the heterogeneous treatment effects of three COVID-specificmedications. The methods developed in this work are readily available in the$\R$ package $\textsf{riAFTBART}$.

A new method for clustered survival data]{A new method for clustered  survival data: Estimation of treatment effect heterogeneity and variable  selection