Simulated Clinical Trias: some design issues

Simulation is widely used to investigate real-world systems in a large number of fields, including clinical trials for drug development, since real trials are costly, frequently fail and may lead to serious side effects. This paper is a survey of the statistical issues arising in these simulated trials. We illustrate the broad applicability of this investigation tool by means of examples selected from the literature. We discuss the aims and the peculiarities of the simulation models used in this context, including a brief mention of the use of metamodels. Of special interest is the topic of the design of the virtual experiments, stressing similarities and differences with the design of real life trials. Since it is important for a computerized model to possess a satisfactory range of accuracy consistent with its intended application, real data provided by physical experiments are used to confirm the simulator : we illustrate validating techniques through a number of examples. We end the paper with some challenging questions on the scientificity, ethics and effectiveness of simulation in the clinical research, and the interesting research problem of how to integrate simulated and physical experiments in a clinical context.