A tree augmented naive Bayesian network experiment for breast cancer prediction

TL;DR

This study uses a tree-augmented naive Bayesian network to improve breast cancer prediction accuracy on a large clinical dataset, suggesting a higher biopsy threshold for older women.

Contribution

It introduces a novel application of tree-augmented naive Bayesian networks for breast cancer prediction on a comprehensive clinical dataset.

Findings

Higher biopsy threshold (>2%) recommended for aging population.

Model achieves reliable prediction across all age groups.

Supports decision-making in clinical breast cancer diagnosis.

Abstract

In order to investigate the breast cancer prediction problem on the aging population with the grades of DCIS, we conduct a tree augmented naive Bayesian network experiment trained and tested on a large clinical dataset including consecutive diagnostic mammography examinations, consequent biopsy outcomes and related cancer registry records in the population of women across all ages. The aggregated results of our ten-fold cross validation method recommend a biopsy threshold higher than 2% for the aging population.