Diagnosis of breast cancer using Bayesian networks: A case study

Abstract We evaluate the effectiveness of seven Bayesian network classifiers as potential tools for the diagnosis of breast cancer using two real-world databases containing fine-needle aspiration of the breast lesion cases collected by a single observer and multiple observers, respectively. The resu...

Full description

Saved in:
Bibliographic Details
Published in:Computers in biology and medicine 2007-11, Vol.37 (11), p.1553-1564
Main Authors: Cruz-Ramírez, Nicandro, Acosta-Mesa, Héctor Gabriel, Carrillo-Calvet, Humberto, Alonso Nava-Fernández, Luis, Barrientos-Martínez, Rocío Erandi
Format: Article
Language:English
Subjects:
Algorithms
Bayes Theorem
Bayesian network classifiers
Biopsy, Fine-Needle
Breast cancer
Breast Neoplasms - diagnosis
Cytodiagnosis - statistics & numerical data
Cytodiagnosis of breast cancer
Databases, Factual
Diagnosis, Computer-Assisted - statistics & numerical data
Female
Fine-needle aspiration of the breast
Humans
Internal Medicine
Interobserver variability
Observer Variation
Other
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract We evaluate the effectiveness of seven Bayesian network classifiers as potential tools for the diagnosis of breast cancer using two real-world databases containing fine-needle aspiration of the breast lesion cases collected by a single observer and multiple observers, respectively. The results show a certain ingredient of subjectivity implicitly contained in these data: we get an average accuracy of 93.04% for the former and 83.31% for the latter. These findings suggest that observers see different things when looking at the samples in the microscope; a situation that significantly diminishes the performance of these classifiers in diagnosing such a disease.
ISSN:0010-4825
1879-0534
DOI:10.1016/j.compbiomed.2007.02.003