Functional modelling of recurrent events on time-to-event processes


Statistical learning
Health Analytics
Functional modelling of recurrent events on time-to-event processes
Thursday 16th April 2020
Spreafico, M.; Ieva, F.
Download link:
In clinical practice many situations can be modelled in the framework of recurrent events. It is often the case where the association between the occurrence of events and time-to-event outcomes is of interest. The purpose of our study is to enrich the information available for modelling survival with relevant dynamic features, properly taking into account their possibly time-varying nature, as well as to provide a new setting for quantifying the association between time-varying processes and time-to-event outcomes. We propose an innovative methodology to model information carried out by time-varying processes by means of functional data. The main novelty we introduce consists in modelling each time-varying variable as the compensator of marked point process the recurrent events are supposed to derive from. By means of Functional Principal Component Analysis (FPCA), a suitable dimensional reduction of these objects is carried out in order to plug them into a survival Cox regression model. We applied our methodology to data retrieved from the administrative databases of Lombardy Region (Italy), related to patients hospitalized for Heart Failure (HF) between 2000 and 2012. We focused on time-varying processes of HF hospitalizations and multiple drugs consumption and we studied how they influence patients’ long-term survival. The introduction of this novel way to account for time-varying variables allowed for modelling self-exciting behaviours, for which the occurrence of events in the past increases the probability of a new event, and to make personalized predictions, quantifying the effect of personal behaviours and therapeutic patterns on survival.
This report, or a modified version of it, has been also submitted to, or published on
Biometrical Journal 2021; 63(5):948-967.