TY - JOUR AU - Froud, Robert AU - Eldridge, Sandra AU - Lall, Ranjit AU - Underwood, Martin PY - 2009 DA - 2009/06/11 TI - Estimating the number needed to treat from continuous outcomes in randomised controlled trials: methodological challenges and worked example using data from the UK Back Pain Exercise and Manipulation (BEAM) trial JO - BMC Medical Research Methodology SP - 35 VL - 9 IS - 1 AB - Reporting numbers needed to treat (NNT) improves interpretability of trial results. It is unusual that continuous outcomes are converted to numbers of individual responders to treatment (i.e., those who reach a particular threshold of change); and deteriorations prevented are only rarely considered. We consider how numbers needed to treat can be derived from continuous outcomes; illustrated with a worked example showing the methods and challenges. SN - 1471-2288 UR - https://doi.org/10.1186/1471-2288-9-35 DO - 10.1186/1471-2288-9-35 ID - Froud2009 ER -