Data Mining based Fragmentation and Prediction of Medical Data
Data mining concerns theories, methodologies, and in particular, computer systems for knowledge extraction or mining from large amounts of data. Association rule mining is a general purpose rule discovery scheme. It has been widely used for discovering rules in medical applications. The diagnosis of diseases is a significant and tedious task in medicine. The detection of heart disease from various factors or symptoms is an issue which is not free from false presumptions often accompanied by unpredictable effects. Thus the effort to utilize knowledge and experience of numerous specialists and clinical screening data of patients collected in databases to facilitate the diagnosis process is considered a valuable option. In this paper, we presented an efficient approach for the prediction of heart attack risk levels from the heart disease database. Firstly, the heart disease database is clustered using the Kmeans clustering algorithm, which will extract the data relevant to heart attack from the database. This approach allows mastering the number of fragments through its k parameter. Subsequently the frequent patterns are mined from the extracted data, relevant to heart disease, using the MAFIA (Maximal Frequent Itemset Algorithm) algorithm. The machine learning algorithm is trained with the selected significant patterns for the effective prediction of heart attack. We have employed the ID3 algorithm as the training algorithm to show level of heart attack with the decision tree. The results showed that the designed prediction system is capable of predicting the heart attack effectively.
Data mining Heart Disease Frequent Patterns MAFIA(Maximal Frequent Itemset Algorithm) ID3 Algorithm
Hnin Wint Khaing
University of Computer Studies Mandalay, Myanmar
国际会议
上海
英文
480-485
2011-03-11（万方平台首次上网日期，不代表论文的发表时间）