Use of the cumulative proportion of responders analysis graph to present pain data over a range of cut-off points: making clinical trial data more understandable.

Abstract

In randomized controlled trials, no single definition of response is ideal for all purposes. We propose a method to present in a simple fashion the likelihood of response over a full range of response levels, which will facilitate a better understanding of clinical trial data. We present the technique called the cumulative proportion of responders analysis (CPRA) and its application to four pain clinical trial data sets as examples. The CPRA can be used to present the proportion of responders over the entire range of possible cut-off points as a graph. This allows the reader to compare treatment groups at any responder level that is valid for their patient population. Whether as a primary or secondary approach to a clinical trial of pain therapy, the display of data in a CPRA format may be useful in the understanding of results and applicability to patient care.