Significant patterns for oral cancer detection: association rule on clinical examination and history data

Abstract

This paper presents an application of data mining in healthcare and discusses how the generated patterns can be used by physicians for early detection and hence prevention of oral cancer. One of the popular association rule mining algorithms, Apriori is used to extract a set of significant rules from the data pertaining to clinical examination, history, and survivability of the cancer patients. These rules suggest various investigations and also help predicting distribution of cancer in oral cavity. In spite of the fact that the clinical judgment happens by means of examination of the oral cavity and tongue using various diagnostic tools, the majority of cases present to a healthcare setups at later stages of tumor subtypes, thereby lessening the chances of survival due to delay in diagnosis. Nevertheless, the data mining rules would certainly assist the practitioners in early detection of oral cancer and prediction of distribution of cancer in the oral cavity that can be helpful preventing the disease. The experimental results demonstrate that all the generated rules hold the highest confidence level, thereby making them useful for early detection and prevention of the oral cancer.