Institut de Santé Publique,
d'Épidémiologie et de Développement

Centre Inserm U897
Equipe Biostatistique

A R package for the estimation of illness-death models for interval-censored data.


In an irreversible illness-death model, subjects are initially healthy and may become diseased and then die, or die disease-free. SmoothHazard fits illness-death models to exact time-to-death and possibly interval-censored time-to-disease. SmoothHazard fits also survival models with possibly interval-censored time-to-event. Left-truncated data are allowed. Proportional transition intensities models allow covariates on the three transitions. Estimation is either parametric (Weibull parametrization for the baseline transition intensities and likelihood maximization), or semi-parametric (spline approximation of the baseline transition intensities and maximization of a penalized likelihood) leading to smooth transition intensity functions. The output object of an illness-death model can then be used to do some predictions (transition probabilities, life expectancies) for a given set of covariates.


  • Joly, P., Commenges, D., Helmer, C., & Letenneur, L. (2002). A penalized likelihood approach for an illness–death model with interval–censored data: application to age–specific incidence of dementia. Biostatistics, 3(3), 433-443.
  • Touraine, C., Helmer, C., & Joly, P. (2013). Predictions in an illness-death model. Statistical methods in medical research.


Pierre Joly
Célia Touraine
Thomas Gerds
Amadou Diakité

Inserm U897
146 rue Léo Saignat
33076 Bordeaux Cedex




This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.


Back to main page: >