Environment for epidemiological information extraction by data mining 10 years of data from the health public system

• Grant number: 06/61279-9
• Support Opportunities: Research Grants - Research in Public Policies for the National Health Care System (PP-SUS)
• Start date: September 01, 2007
• End date: August 31, 2009
• Field of knowledge: Health Sciences - Collective Health - Public Health
• Agreement: CNPq - PPSUS
• Principal Investigator: Marco Antonio Gutierrez
• Grantee: Marco Antonio Gutierrez
• Host Institution: Instituto do Coração Professor Euryclides de Jesus Zerbini (INCOR). Hospital das Clínicas da Faculdade de Medicina da USP (HCFMUSP). Secretaria da Saúde (São Paulo - Estado). São Paulo , SP, Brazil

Abstract

Computer science provides a set of techniques and tools for producing decision making information and knowledge discovery in huge data bases (data mining). The application of these techniques to the data from the DATASUS information systems can provide a significant increase in the efficiency of SUS management. It can also be of great help in epidemiological and public health studies by allowing the identification and correlation of data pattern. The current version of SUS information systems still does not uses advanced techniques and tools for producing decision making information, such as OLAP (On- Line Analytical Processing) tools. It also does not use any data mining technique. The situation becomes almost critical if we consider the fact that data in public health are produced by several non integrated monolithic systems. As a consequence, the production of management information in public health care is an extremely hard task. The integration of the databases from SUS information systems is the key requirement for the intelligent manipulation of the huge amount of data available and for the extraction of relevant information that would help the public health management tools. The main goal of this project is to evaluate the application of data mining techniques to the Brazilian Public Health System, based on the analysis of 10 years data from DATASUS data bases. The development of such project is driven by the possibility to overcome the current difficulties and provide the health managers and the researchers a great amount of meaningful information to be used to increase the quality of Brazilian Public Health. (AU)