Medical institutes use Electronic Medical Record (EMR) to record a series of medical events, including diagnostic information (diagnosis codes), procedures performed (procedure codes) and admission details. Plenty of data mining technologies are applied in the EMR data set for knowledge discovery, which is precious to medical practice. The knowledge found is conducive to develop treatment plans, improve health care and reduce medical expenses, moreover, it could also provide further assistance to predict and control outbreaks of epidemic disease. The growing social value it creates has made it a hot spot for experts and scholars. In this paper, we will summarize the research status of data mining technologies on EMR, and analyze the challenges that EMR research is confronting currently.