in the present Information age, Data mining plays a vital role in various research areas like marketing, customer behavior analysis and various medical researches such as cancer prediction system which provides effective preventive strategy. Data mining algorithms are used on medical database in order to predict survivability of cancer patients. Blood cancer causes serious issues and hence Data mining techniques are broadly utilized to predict blood cancer from test data collection. The Data mining algorithms along with semantic knowledge using Ontology is used for predicting blood cancer. Earlier system used genetic and environmental factors in order to predict cancer. This paper uses data mining technologies such as classification, clustering along with semantic analysis in order to predict leukemia. The parameters from complete blood count (CBC) and peripheral smear are taken to analyze possibilities of leukemia’s presence. Data mining is used for analyzing Semantic relationship among parameters in Datasets. The gathered data is preprocessed fed into the database and classified to obtain significant patterns using Data mining algorithms. Then the data is clustered in order to separate malicious and non-malicious leukemia. Then finally by analyzing Ontology based semantic relationship, prediction of leukemia can be easily done, before it becomes severe. The experimental results show the better performance compared with existing techniques.