We consider the problem of estimating life expectancy of demented and institutionalized subjects from interval-censored observations. A mixed discretecontinuous scheme of observation is a classical pattern in epidemiology because very often clinical status is assessed at discrete visit times while times of death or other events can be exactly observed. In this work we jointly modelled dementia, institutionalization and death from data of a cohort study. Due to discrete time observations, it may happen that a subject developed dementia or was institutionalized between the last visit and death. Consequently, there is an uncertainty about the precise number of diseased or institutionalized subjects. Moreover the time of onset of dementia is intervalcensored. We use a penalized likelihood approach for estimating the transition intensities of the multi-state model. With these estimators, incidence and life expectancy can be computed easily. This approach deals with incomplete data due to the presence of left-truncation and interval-censoring. It can be generalized to take explanatory variables into account. We illustrate this approach by applying this model to the analysis of a large cohort study on cerebral aging.