Decision Tree Based Automated Detection of Breast Cancer

Breast cancer is a greatly fatal disease prevalent among women. Early and accurate detection is crucial but challenging, often requiring significant human effort. However, current diagnostic methods have limitations in efficiency and accuracy. This study addresses these challenges by exploring the application of decision tree algorithms for automatic breast cancer classification, aiming to support and enhance the diagnostic process. Using the standard Wisconsin Diagnostic Breast Cancer dataset, our experiments demonstrate that decision trees excel in classification accuracy, outperforming other common machine learning algorithms. This paper thoroughly examines and assesses the performance of the classification model from various viewpoints, highlighting the potential of decision trees to improve diagnostic reliability and efficiency, thereby underscoring their value in clinical settings. The aim is to provide patients with more timely diagnosis and treatment.