[Neurological scales as endpoints in stroke studies. Aspects of statistical evaluation]

Even after publication of ECASS II, the latest paper in a series of large, placebo-controlled studies on thrombolysis in acute ischaemic stroke, there is still uncertainty as to what the best clinical endpoint(s) is (are) in trial design for reliably identifying significant differences between treatment groups. If the expected treatment difference as measured by a neurological outcome scale like the Modified Rankin Scale corresponds more to a shift in dispersion (on average a majority of patients profits greatly) rather than to a shift in location (on average each patient profits much), then the power of the odds ratio test is much higher than that of the Wilcoxon test and therefore the clinical outcome parameters should be dichotomised. With respect to the time window of 0-6 hrs from symptom onset of an acute ischaemic stroke, for example, a dichotomisation of 0-2 vs. 3-6 for the Modified Rankin Scale is reasonable. In the case of multiple endpoints, a global (multivariate) test should be used, but the correlation between these endpoints must not be too high, which means that the various manifestations of the complex stroke disease should be considered.