Data Mining Applications in Medical Image Mining: An Analysis of Breast Cancer using Weighted Rule Mining and Classifiers

A. Kavipriya
2013 IOSR Journal of Computer Engineering  
The Association Rule Mining methods are used to mine attribute relationships. The Support and Confidence values are estimated for all item-sets. Minimum Support and Confidence values are used to select frequent patterns. Classification technique is applied to assign labels for the transactions. Learning phase is carried out for transaction pattern identification. Testing process handles the pattern matching and label assignment task. Classification and Association Rule Mining techniques are
more » ... grated to perform disease prediction process. Decision tree or Naive Bayes Classifiers consider the feature is independent of each other. Associative Classifiers are especially fit to applications where the model may assist the domain experts in their decisions. Prediction model for medical domain needs high accuracy level. Pruning-Classification Association Rule ( PCAR) is used to predict cancer diseases. A proficient methodology for the generation of association rules from the cancer disease warehouses is used for Breast Cancer prediction. The Pima Indian Breast Cancer data warehouse is pre-processed in order to make it suitable for mining process. The cancer disease data warehouse is binning with the aid of the modified equal width binning interval approach to discretizing continuous attributes. The width of the desired interval is chosen based on the opinion of medical expert and is provided as an input parameter to the model. Associative Classifier uses Weighted Association Rule Mining (WARM) model for cancer patient diagnosis. The diseases prediction process is performed by comparing the symptoms of patients with the existing database. Different weights will be assigned for different attributes based on their predicting capability. The attribute with higher predicting capability will have higher weightage.
doi:10.9790/0661-0841823 fatcat:t5rdnn3wdrcnfn3awunzpkdrfy