In recent years, clinical researchers have begun to measure the effects of new therapies on novel outcomes such as health-related costs and quality of life, in addition to the more traditional outcomes like survival, morbidity and objective measures of disease activity. The adoption of these new outcome variables in clinical trials has led to new theoretical and methodologic questions for statisticians. The development of appropriate statistical methods for the design and analysis of trials involving such outcomes will further clinical research by permitting investigators to gather and analyze the required information with maximum robustness and efficiency. This application describes a proposal by a team of experienced applied statisticians to address a range of critical methodologic problems arising from their collaborative work in clinical trials of nonstandard endpoints, i.e., in outcomes research.
The first aim addresses the problem of estimating the cost-effectiveness of new interventions from randomized clinical trial data.
The second aim concerns the evaluation of incomplete longitudinal data on health-related quality of life.
The third aim develops modeling methods for predicting the times of occurrence of landmark events in clinical trials. The methods will be developed and applied in the REMATCH trial, an ongoing, NIH-funded study comparing an implantable left ventricular assist device to optimal medical management in the treatment of end-stage heart failure. It is anticipated, however, that the resulting methods will be applicable much more broadly.
