A DECISION TREE ANALYSIS OF SEVEN YEARS PROFILE OF ORAL CANCER PATIENTS IN HOSPITAL UNIVERSITI SAINS MALAYSIA (USM) KELANTAN

Oral cancer is a disease resulting from abnormal cell growth in the mouth, lips, tongue or throat. In 2002, the American Cancer Society has estimated that 28,900 of new cases of oral cancer were diagnosed and nearly 7,400 people died from this disease. Over 90 percent of these tumors are squamous cell carcinomas, which arise from the oral mucosal lining. In spite of the ready accessibility of the oral cavity to direct examination, these malignancies still are often not detected until a late stage and the survival rate for oral cancer has remained essentially unchanged over the past three decades. In this paper, we determine the potential predictors which contribute to the mortality rate of oral cancer using decision tree analysis of seven years profile of oral cancer patients in Hospital USM Kelantan. The results of this study show that the pathology type of oral cancer is the best predictor of mortality rate followed by predictor of presence of tumor at mandible. We managed to find out that the pathology type of oral cancer and the presence of tumor at mandible are the important predictors contributing to mortality rate of oral cancer patients in Hospital USM.