While data mining has become a much-lauded tool in business and related fields, its role in the healthcare arena is still being explored. Currently, most applications of data mining in healthcare can be categorized into two areas: decision support for clinical practice, and policy planning/decision making. However, it is challenging to find empirical literature in this area since a substantial amount of existing work in data mining for health care is conceptual in nature. In this paper, we review the challenges that limit the progress made in this area and present considerations for the future of data mining in healthcare.