Many methods for analyzing data from RCTs cannot be directly applied and the usage of causal inference framework is preferrable in RWD analysis. Comparability of patients across treatments and sources is a key requirement for valid assessment of treatment effect. Propensity score based on individual patient data (IPD) is often used for patient matching to ensure the comparability. However, sharing sensitive IPD is subject to strict regulations and is logistically prohibitive. In such a scenario, propensity scores for individual patients will not be available to the analysis sponsor and the alternative methods should be applied to match RWD or count for heterogeneity across multiple data sources. In this research, we propose the use of a double inverse probability weighting approach for patient matching and result generalizability for the case without the need of IPD to the analysis sponsor. Based on the formulations of the data analysis, we can see the required components of summary statistics or functions needed from the individual data owners. As demonstrated, through assembling of these components in data analysis, we can achieve the purpose of data matching and valid analysis.
