Significant cancer risk factor extraction: An association rule discovery approach

Abstract

Cancer is the top most death threat for human life all over the world. Current research in the cancer area is still struggling to provide better support to a cancer patient. In this research our aim is to identify the significant risk factors for particular types of cancer. First, we constructed a risk factor data set through an extensive literature review of bladder, breast, cervical, lung, prostate and skin cancer. We further employed three association rule mining algorithms, apriori, predictive apriori and Tertius algorithm in order to discover most significant risk factors for particular types of cancer. Discovery risk factor has been identified to shows highest confidence values. We concluded that apriori indicates to be the best association rule-mining algorithm for significant risk factor discovery.