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/

Zendy Plus

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

Zendy Tools

Zendy Open

With the availability of massive amounts of data from electronic healthrecords and registry databases, incorporating time-varying patient informationto improve risk prediction has attracted great attention. To exploit thegrowing amount of predictor information over time, we develop a unifiedframework for landmark prediction using survival tree ensembles, where anupdated prediction can be performed when new information becomes available.Compared to conventional landmark prediction with fixed landmark times, ourmethods allow the landmark times to be subject-specific and triggered by anintermediate clinical event. Moreover, the nonparametric approach circumventsthe thorny issue of model incompatibility at different landmark times. In ourframework, both the longitudinal predictors and the event time outcome aresubject to right censoring, and thus existing tree-based approaches cannot bedirectly applied. To tackle the analytical challenges, we propose arisk-set-based ensemble procedure by averaging martingale estimating equationsfrom individual trees. Extensive simulation studies are conducted to evaluatethe performance of our methods. The methods are applied to the Cystic FibrosisPatient Registry (CFFPR) data to perform dynamic prediction of lung disease incystic fibrosis patients and to identify important prognosis factors.

Dynamic Risk Prediction Triggered by Intermediate Events Using Survival Tree Ensembles