Diagnostic Classification Scheme in Iranian Breast Cancer Patients using a Decision Tree


Background: The objective of this study was to determine a diagnostic classification scheme using a decisiontree based model. Materials and
Methods: The study was conducted as a retrospective case-control study inImam Khomeini hospital in Tehran during 2001 to 2009. Data, including demographic and clinical-pathologicalcharacteristics, were uniformly collected from 624 females, 312 of them were referred with positive diagnosisof breast cancer (cases) and 312 healthy women (controls). The decision tree was implemented to develop adiagnostic classification scheme using CART 6.0 Software. The AUC (area under curve), was measured as theoverall performance of diagnostic classification of the decision tree.
Results: Five variables as main risk factorsof breast cancer and six subgroups as high risk were identified. The results indicated that increasing age, lowage at menarche, single and divorced statues, irregular menarche pattern and family history of breast cancer arethe important diagnostic factors in Iranian breast cancer patients. The sensitivity and specificity of the analysiswere 66% and 86.9% respectively. The high AUC (0.82) also showed an excellent classification and diagnosticperformance of the model.
Conclusions: Decision tree based model appears to be suitable for identifying riskfactors and high or low risk subgroups. It can also assists clinicians in making a decision, since it can identifyunderlying prognostic relationships and understanding the model is very explicit.