A method for selecting data subsets from large medical data bases.

Abstract

Because of the exponential increase in health care expenditures, attention has been drawn to the cost and effectiveness of health care delivered. The use of electronic data bases as a means for assessing health care effectiveness has been advocated as powerful computer systems have become commonplace. The need to work efficiently with extremely large data bases presents difficult challenges to researchers who wish to focus on specific aspects of the data. This paper describes a computer program written to facilitate the analysis of large medical data sets by providing a straightforward way to specify and select data subsets from the aggregate data base.