SEARCH

SEARCH BY CITATION

Keywords:

  • functional data analysis;
  • generalized linear models;
  • Public Health Database;
  • recurrent events processes

Abstract.

An effective methodology for dealing with data extracted from clinical surveys on heart failure linked to the Public Health Database is proposed. A model for recurrent events is used for modelling the occurrence of hospital readmissions in time, thus deriving a suitable way to compute individual cumulative hazard functions. Estimated cumulative hazard trajectories are then treated as functional data, and they are used as covariates along with clinical survey data within the framework of generalized linear models with functional covariates.