The Research Of Data Mining Based On Medical Information Data Warehouse

With the rapid development of database technology, it has infiltrated to a variety of areas, including medicine. Many large and medium-sized hospitals have set up their own hospital information system (HIS). As HIS' applications and continuous development, the data quantity in the database rapid inflation, the database scale expands gradually and the complex degree increases day by day. However, despite the accumulation of a large number of business data, the real value of these data has rarely been extracted and used in clinical assistant diagnosis or hospital's daily management decision-making. In view of this kind of situation, this topic proposed to establish a medicine information data warehouse based on HIS system. In this foundation, do data mining on the medical data in monitor, forecast and hospital management assistance decision-making and so on. Provide a comprehensive analysis and decision support tools for health workers, clinical managers and researchers.This issue has studied the existing hospital information management system and data structure components. Using front data warehouse technology, analyse, extract, decide the theme from massive hospital information database according to the actual demand. Then organize data effectively to build data warehouse model. After data cleaning and transformation, load the data of data warehouse. We can do SQL queries, statistic report form, OLAP data analysis and data mining applications etc. It can effectively serve the full range of hospital management decisions.This issue has done the following work: 1. After doing a large number of data analysis and data pre-processing work, we have extracted the theme of building a data warehouse. Using the Microsoft's latest SQL Server 2008 enterprise-class data warehouse platform to build the medical information data warehouse which based on HIS, SQL Server 2008 which based on SQL Server 2005, is a complete data management and business intelligence platform, it has further improvement of the services and in the world leading position in terms of the performance and scalability.2. Use the SQL Server 2008's Business Intelligence Development Studio environment to create and use the data mining model which based on medical information data warehouse. This environment including data mining algorithms and tools, using of these algorithms and tools is more easily to generate a variety of projects for integrated solutions.3. Introduce some classic data mining algorithms, and use the data mining algorithms from SQL Server 2008's Analysis Services module to data mine and analyse the out-patient and inpatient information of the medical information data warehouse deeply and broad. Discuss the control in the disease surveillance, disease prediction, hospital management and other aspects of decision support applications of data mining.