A Stacked Ensemble-Based model for the prediction of breast cancer using Decision Tree and XGBoost
Korivi Baby Naina Tara, Nikhitha Vadlamudi, Guttikonda Kranthi Kumar · 2023
Breast cancer is one of the most common and lethal types of cancer affecting women worldwide. In 2020, the World Health organization (WHO) predicts that 2.3 million women will receive a breast cancer diagnosis, and 685,000 individuals will pass away from the condition. Early detection of breast cancer can greatly improve treatment outcomes, increasing the likelihood that the patient will survive. Machine learning algorithms have been shown to be effective in predicting breast cancer. In this study, we explore the use of ensemble technique for the prediction of breast cancer using the WDBC dataset. The dataset has 569 instances and 30 attributes that describe the radius, texture, perimeter, area, smoothness, compactness, concavity, symmetry, and the fractal dimension of breast mass. We achieved a remarkable accuracy of 97.66%. This study highlights the potential of decision tree and XGBoost algorithms in predicting breast cancer and could aid in early detection, leading to better treatment outcomes.