Data mining tools for quality management in health care

Data mining can be used for the detection of quality deficiencies in health care. Routine data are typically stored in relational databases, which are not easy to understand for end-users. OLAP-tools promise a more intuitive way of analysis and visualization. We evaluated the OLAP-tools from Oracle Corporation with data from our data warehouse, which is also realized in a common relational database management system. Our results reveal that remarkable efforts are necessary to transfer and to prepare data for the multidimensional OLAP-model. Meaningful analyses are not possible without this step. The tools rely on a business view neglecting the granularity and complexity of medical treatment. Once the tools are prepared they offer end-users flexible and graphical analyses in there own terms. We suggest a special adaptation of these tools, which should be tailored for hospital demands.