Analysis of time-to-event for observational studies: Guidance to the use of intensity models

TL;DR

This paper offers comprehensive guidance on applying intensity (hazard) models, especially Cox regression, in observational time-to-event studies, emphasizing proper model fitting, interpretation, and avoiding biases like immortal time bias.

Contribution

It provides practical checklists and examples for fitting and assessing hazard models, with a focus on avoiding common pitfalls and ensuring valid causal inference.

Findings

Guidance on hazard model application in observational studies

Checklists for model fitting and validation

Strategies to avoid immortal time bias

Abstract

This paper provides guidance for researchers with some mathematical background on the conduct of time-to-event analysis in observational studies based on intensity (hazard) models. Discussions of basic concepts like time axis, event definition and censoring are given. Hazard models are introduced, with special emphasis on the Cox proportional hazards regression model. We provide check lists that may be useful both when fitting the model and assessing its goodness of fit and when interpreting the results. Special attention is paid to how to avoid problems with immortal time bias by introducing time-dependent covariates. We discuss prediction based on hazard models and difficulties when attempting to draw proper causal conclusions from such models. Finally, we present a series of examples where the methods and check lists are exemplified. Computational details and implementation using the freely available R software are documented in Supplementary Material. The paper was prepared as part of the STRATOS initiative.