Propensity score matched augmented controls in randomized clinical trials: A case study

• DOI: 10.1002/pst.1879
• Publication Date: 2018-08-01T12:37:21Z
• Authors: Junjing Lin; Margaret Gamalo‐S...; Ram Tiwari
• Keywords: Restricted randomization

Existing statutes in the United States and Europe require manufacturers to demonstrate evidence of effectiveness through conduct adequate well‐controlled studies obtain marketing approval a therapeutic product. What constitutes is usually interpreted as randomized controlled trials (RCTs). However, these are sometimes unfeasible because their size, duration, cost, patient preference, or some cases, ethical concerns. For example, RCTs may not be fully powered rare diseases infections caused by multidrug resistant pathogens low number enrollable patients. In this case, data available from external controls (including historical observational registries) can complement information provided RCT. Propensity score matching methods used select “borrow” additional patients controls, for maintaining one‐to‐one randomization between treatment arm active control, new control units based on set measured covariates, ie, model‐based pairing that similar terms observable pretreatment characteristics. To end, 2 schemes propensity scores explored applied real clinical example with objective using observations augment trial where disproportionate asymmetric.