Comparative effectiveness research (CER) has recently emerged as a key component of health care decision-making, specifically designed to provide evidence of the effectiveness of different health care treatments. The latter are becoming increasingly complex, and there is now intense interest in deploying advanced statistical tools to study and guide the development of such complex systems. Complex interventions might also involve interactions through time, where actions in the past affect the future decision making context. In this case, the temporal dimension should be taken into account into the statistical model, yielding in turn more precise guidelines for health care decision-making. However, current CER methodologies are not well-suited to understand such complex systems or characterise their future behaviour. Statistical methods based on dynamic modelling are therefore needed to advance progress of the state-of-the art of CER research. In particular, this fellowship will tackle the problem by developing novel statistical methodologies for the study of the temporal dynamics of complex health care interventions, both for primary research and evidence synthesis. For primary research, the fellowship will explore the emerging case of pervasive and technology-based interventions, which are by nature dynamic. For evidence synthesis - which is the procedure of summarising evidence from different primary studies of a specific health condition - the innovative tool of network meta-analysis will be deployed and an extension for dynamically monitoring and updating the results of existing network meta-analyses will be developed.
Call for proposal
See other projects for this call