Mastectomy or breast conserving surgery? Factors affecting type of surgical treatment for breast cancer--a classification tree approach

Abstract

Background: A critical choice facing breast cancer patients is which surgical treatment--mastectomy or breast conserving surgery (BCS)--is most appropriate. Several studies have investigated factors that impact the type of surgery chosen, identifying features such as place of residence, age at diagnosis, tumor size, socio-economic and racial/ethnic elements as relevant. Such assessment of "propensity" is important in understanding issues such as a reported under-utilisation of BCS among women for whom such treatment was not contraindicated. Using Western Australian (WA) data, we further examine the factors associated with the type of surgical treatment for breast cancer using a classification tree approach. This approach deals naturally with complicated interactions between factors, and so allows flexible and interpretable models for treatment choice to be built that add to the current understanding of this complex decision process.

Methods: Data was extracted from the WA Cancer Registry on women diagnosed with breast cancer in WA from 1990 to 2000. Subjects' treatment preferences were predicted from covariates using both classification trees and logistic regression.

Results: Tumor size was the primary determinant of patient choice, subjects with tumors smaller than 20 mm in diameter preferring BCS. For subjects with tumors greater than 20 mm in diameter factors such as patient age, nodal status, and tumor histology become relevant as predictors of patient choice.

Conclusion: Classification trees perform as well as logistic regression for predicting patient choice, but are much easier to interpret for clinical use. The selected tree can inform clinicians' advice to patients.

Figure 1

Classification tree for choice of surgical treatment for breast cancer based on the Western Australian database. In the figure, M denotes mastectomy, BCS breast-conserving surgery. Terminal nodes in the tree are represented using rectangular boxes, while non-terminal nodes are presented as ellipses. At each node, the treatment preferred by the majority of subjects at that node is printed within the node along with a numerical breakdown of how many subjects chose each treatment. For example, a node with the notation "BCS" and "365/504" means that, of the 869 subjects within that sub-group, the majority (504) chose BCS while the remaining 365 chose mastectomy.

Figure 2

ROC curves for the fitted tree (solid line) and logistic regression (dotted line) models.