Evaluation of the Diagnostic Power of Thermography in Breast Cancer Using Bayesian Network Classifiers

<table>Bayesian network built by procedure of Hill-Climber using the 98-case database. Only variable furrow is directly related to the outcome. Once the variable furrow is known, all the other variables are independent of the class.</table>

Computational and Mathematical Methods in Medicine

fig3

Figure 3

Figure 3: Evaluation of the Diagnostic Power of Thermography in Breast Cancer Using Bayesian Network Classifiers 