SURVEY ON DATA MINING ALGORITHMS TO PREDICT LEUKEMIA TYPES

Abstract

Data mining is defined as shifting through very large amounts of data for useful in formation. Some of the most important and popular data mining techniques are association rules, classification, clustering, prediction and sequential patterns. Data mining techniques are used for variety of applications. In health care industry, data mining plays an important role for predicting diseases. Recent advances in microarray technology offer the ability to measureexpression levels of thousands of genes simultaneously. Analysis of such data helpsus identifying different clinical outcomes that are caused by expression of a fewpredictive genes.. The feature extraction and classification are carried outwith combination of the high accuracy of ensemble based algorithms, and comprehensibility of a single  ecision tree. These allow deriving exact rules by describinggene expression differences among significantly expressed genes in leukemia. It isevident from our results that it is possible to achieve better accuracy in classifyingleukemia without sacrificing the level of comprehensibility.