Comparative Analysis of Bayesian Networks for Breast Cancer Classification: Naive Bayes vs. Tree-Augmented Naive Bayes

Breast cancer is the most common cancer among women, with nearly 1.7 million new cases diagnosed worldwide each year. Early detection and accurate diagnosis are crucial for improving patient outcomes and reducing mortality rates. This study applies Bayesian Networks, specifically Naive Bayes and Tree-Augmented Naive Bayes (TAN), along with Decision Tree and Random Forest models to classify breast cancer using the Breast Cancer Wisconsin Data Set. We explore different methods for learning the structure and parameters of these networks and compare their performance with a Decision Tree and Random Forest model. The comparative analysis reveals that while Naive Bayes achieves the highest specificity, Random Forest provides a well-balanced accuracy and sensitivity. Our results offer insights into the strengths and weaknesses of each approach, helping to guide their application in clinical settings.