Effectiveness Research in Inflammatory Bowel Disease: A Necessity and a Methodological Challenge.

Efficacy, safety and economic issues are the main factors influencing the use of inflammatory bowel disease [IBD]-related medications. The best level of evidence comes from randomised clinical trials. The benefit of the intervention observed in a clinical trial could be reduced once it is implemented in clinical practice: its real-life efficacy, known as effectiveness, could be questioned. That is why effectiveness research based on observational studies is required to obtain-long term data on natural history, including surgery or hospitalisation, and safety. Before starting these real-life studies, it is crucial to be aware of the inherent risks of bias and confounding, to develop a good study plan, and to select the optimal design. Even if the choice of the design is optimal and if the risks of bias and confounding are minimised, the implementation of robust statistical methodology is necessary to increase the validity of the results and allow their dissemination into clinical practice. The objective of this paper is to highlight some inherent methodological problems in effectiveness research and to review some statistical tools with a focus on IBD studies and trials.