Naive Bayes Classifiers: A Probabilistic Detection Model for Breast Cancer

Abstract

Naive Bayes is one of the most effective statistical and probabilistic classification algorithms. As health care environment is "information loaded" but "knowledge deprived". So to extract knowledge, effective analysis tools are constructed to discover hidden relationships in data. The aim of this work is to design a Graphical User Interface to enter the patient screening record and detect the probability of having Breast cancer disease in women in her future using Naive Bayes Classifiers, a Probabilistic Classifier. As breast cancer is considered to be second leading cause of cancer deaths in women today so early detection can improve the survival rate of women. The prediction is performed from mining the patient's historical data or data repository. Further from the experimental results it has been found that Naive Bayes Classifiers is providing improved accuracy with low computational effort and very high speed. The system has been implemented using java platform and trained using benchmark data from UCI machine learning repository. The system is expandable for the new dataset.