Development, implementation and evaluation of a tool for forecasting short term demand for beds in an intensive care unit

The main contribution of this paper is in describing the process of implementing an abstract mathematical model in a busy intensive care unit and the independent qualitative evaluation of the work about how potential barriers to implementation were addressed as part of a “modellers in residence” programme that led to us building a software tool that is still being used by the hospital more than 4 years after initial implementation. In particular, we draw together lessons from our work that we think will benefit other operational researchers wanting to work effectively with health care organisations on similar problems.