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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In recent years, research interest in personalised treatments has beengrowing. However, treatment effect heterogeneity and possibly time-varyingtreatment effects are still often overlooked in clinical studies. Statisticaltools are needed for the identification of treatment response patterns, takinginto account that treatment response is not constant over time. We aim toprovide an innovative method to obtain dynamic treatment effect phenotypes on atime-to-event outcome, conditioned on a set of relevant effect modifiers. Theproposed method does not require the assumption of proportional hazards for thetreatment effect, which is rarely realistic. We propose a spline-based survivalneural network, inspired by the Royston-Parmar survival model, to estimatetime-varying conditional treatment effects. We then exploit the functionalnature of the resulting estimates to apply a functional clustering of thetreatment effect curves in order to identify different patterns of treatmenteffects. The application that motivated this work is the discontinuation oftreatment with Mineralocorticoid receptor Antagonists (MRAs) in patients withheart failure, where there is no clear evidence as to which patients it is thesafest choice to discontinue treatment and, conversely, when it leads to ahigher risk of adverse events. The data come from an electronic health recorddatabase. A simulation study was performed to assess the performance of thespline-based neural network and the stability of the treatment responsephenotyping procedure. In light of the results, the suggested approach has thepotential to support personalized medical choices by assessing unique treatmentresponses in various medical contexts over a period of time.

Dynamic treatment effect phenotyping through functional survival analysis