Rule Generation Methods for Medical Data (Heart Disease) Using Rough Set Approach

One of the important steps of data mining is to find the hidden patterns. For exploring the hidden patterns in the data sets of medical domain Medical data mining has a great potential. These extracted hidden patterns may apply for further medical analysis and examination. Even so, the applicable raw clinical data are miscellaneous, voluminous and broadly distributed. The clinical data sets are stored in a database called medical data base. These databases may have a huge amount of knowledge and information about the patients, their fitness condition and diseases. Medical data may have incomplete information, noise, and inconsistent data. To represent this type of data we need to do manipulations in various levels. For manipulation we have data pre-processing. In this paper, Rough Set Theory is used for getting the relationship among data, evaluation of attributes, explore the hidden patterns and generate the decision rules for the satisfactory classification. Rough set approach is basically rule based classifier and there are benefits of rules based classifiers as they are easy to understand and can be merged into human’s language to help medical experts in decision making. In this paper rules are achieved by rough set. We have concluded that decision rules provide some medical awareness and theses rules are also valuable for medical professionals to evaluate the problems adequately.