Effectiveness of applying Machine Learning techniques and Ontologies in Breast Cancer detection
Hakim El Massari, Noreddine Gherabi, Sajida Mhammedi, Zineb Sabouri, Hamza Ghandi, Fatima Qanouni
Abstract
Breast cancer is a disease that primarily affects women, but it can also affect men, although in a much smaller percentage. Recently, doctors have made great strides in this trend of early detection and treatment of breast cancer to reduce the number of deaths caused by this serious disease. Moreover, researchers are analyzing massive amounts of sophisticated medical data using a combination of statistical and machine learning approaches to help clinicians predict breast cancer. In the presented work, an ontological model based on the decision tree algorithm capable of reliably predicting breast cancer has been demonstrated. The method consists of extracting rules from the decision tree algorithm that distinguish between malignant and benign breast cancer patients, and then implementing these rules in the ontological reasoner via the Semantic Web Rule Language (SWRL). The results indicated that the ontological model achieved the highest prediction accuracy of 97.10%.