Keywords: clinical trials, rare disease, information integration, target population, integrated estimator
For clinical trials in rare disease areas, a major challenge is the limited amount of available information for making robust statistical inference due to low disease prevalence. External data sources present data integration opportunities to enhance statistical inference. We propose an intuitive integrated inference framework to integrate information from all relevant data sources and make inference on the treatment effect over a specific target population. The method is easily implemented and extended with modern machine learning tools. It is complemented by a variance estimation procedure to facilitate statistical inference. The proposed method is shown to have good statistical properties with both theoretical development and simulation studies. We argue that the integrated inference framework not only provides an intuitive and coherent perspective for a wide range of clinical trial inference problems but also has broad application areas in clinical trial settings and beyond, as a quantitative data integration tool for making robust inference in a target population precise manner for policy and decision makers.