An hybrid refinement methodology for multivariate simulation in home health telecare

We deal with monitoring the health status of a patient at home so as to detect critical evolutions over a scale of several days or weeks. A multivariate simulation is used as a way to overcome the lack of experimental data required for studying this decision-making issue. The simulation process needs to be driven in a rigorous and robust way. Due to that, and to deal with heterogeneity and complexity, we make use of an hybrid and refinement methodology. It involves the fusion of several types of models and knowledge, as well as the implementation of a cascade structure for the simulation process.