Mining biomedical text can be useful for validating new disease subgroups or summarizing information to guide policies and decision making. Yet, existing work predominately focuses on efficient information retrieval. There are other applications where mining biomedical text can be useful. As two motivating examples, researchers are discovering new disease subgroups from secondary analyses of electronic health records. However, such subgroups need to be validated or aligned with current literature. Similarly, systematic reviews serve as a mechanism to summarize current evidence related to a research question. In both scenarios, the abundance of articles can be overwhelming to process manually. In this talk, I will first introduce a scalable framework that produces evidence sets (or relevant articles) using a large corpus of online medical literature. I will discuss some of the challenges associated with term representation and mining biomedical text. I will then present recent work on automating the screening process to allow health services researchers to more efficiently summarize the current findings.