Early Detection and Prevention of Oral Cancer: Association Rule Mining on Investigations

Early detection and prevention of oral cancer is critical, as it can increase the survival chances considerably, allow for simpler treatment and result in a better quality of life for survivors. In this research paper, the popular association rule mining algorithm, apriori is used to find the spread of cancer with the help of various investigations and then assess the chance of survival of the patient. This is achieved by extracting a set of significant rules among various laboratory tests and investigations like FNAC of neck node, LFT, Biopsy, USG, CT scan-MRI and survivability of the oral cancer patients. The rules clearly show that if FNAC of neck node, USG and CT scan/ MRI is positive then chance of survival is reduced. However, if LFT is normal, probability of survival is high. If diagnostic-biopsy results in squamous-cell-carcinoma then it clearly indicate oral cancer, which may lead to high mortality if appropriate treatment is not initiated. The experimental results demonstrate that all the generated rules hold the highest confidence level, thereby, making investigations very essential to understand the spread of cancer after clinical examination for early detection and prevention of oral cancer. Key-Words: Data Mining, Association Rule Mining, Apriori, Oral Cancer, Weka, Investigations