Interim monitoring of clinical trials based on long-term binary endpoints

This paper discusses interim analysis of randomized clinical trials for whi ch the primary endpoint is observed tit a specific long-term follow-up time . For such trials subjects only yield direct information on the primary end point once they have been followed through to the long-term follow-up time, potentially eliminating a large proportion of the accrued sample from an i nterim analysis of the primary endpoint. We advocate mure efficient interim analysis of long-term endpoints by augmenting long-term information with s hort-term information on subjects who have not yet been followed through to the long-term follow-up time. While retaining the long-term endpoint as th e subject of the analysis, methods of jointly analysing short- and long-ter m data are discussed for reversible binary endpoints. It is shown theoretic ally and by simulation that the use of short-term information improves the efficiency with which long-term treatment differences are assessed based on interim data. Sequential analysis of treatment differences is discussed ba sed on spending functions, and is illustrated with a numerical example from a cholesterol treatment trial. Copyright (C) 2001 John Wiley & Sons. Ltd.