A Utility/Cost Analysis of Breast Cancer Risk Prediction Algorithms

Abstract

Breast cancer risk prediction algorithms are used to identify subpopulations that are at increased risk for developing breast cancer. They can be based on many different sources of data such as demographics, relatives with cancer, gene expression, and various phenotypic features such as breast density. Women who are identified as high risk may undergo a more extensive (and expensive) screening process that includes MRI or ultrasound imaging in addition to the standard full-field digital mammography (FFDM) exam. Given that there are many ways that risk prediction may be accomplished, it is of interest to evaluate them in terms of expected cost, which includes the costs of diagnostic outcomes. In this work we perform an expected-cost analysis of risk prediction algorithms that is based on a published model that includes the costs associated with diagnostic outcomes (true-positive, false-positive, etc.). We assume the existence of a standard screening method and an enhanced screening method with higher scan cost, higher sensitivity, and lower specificity. We then assess expected cost of using a risk prediction algorithm to determine who gets the enhanced screening method under the strong assumption that risk and diagnostic performance are independent. We find that if risk prediction leads to a high enough positive predictive value, it will be cost-effective regardless of the size of the subpopulation. Furthermore, in terms of the hit-rate and false-alarm rate of the of the risk-prediction algorithm, iso-cost contours are lines with slope determined by properties of the available diagnostic systems for screening.

Keywords: Risk prediction; breast cancer screening; diagnostic utility; expected cost.

Figure 1. Risk-Prediction Iso-Cost Contours in the ROC Domain

When the performance of the risk-prediction algorithm is specified in terms of True-Positive and False-Positive fractions, iso-cost contours from Equation 10 are seen to be lines with positive slope, in which cost affects the y-intercept. The lowest iso-cost line represents the break-even point where the risk-prediction guided approach is equivalent to screening with Screening Strategy 1.

Figure 2. Risk-Prediction Iso-Cost Contours in the Precision-Recall Domain

When the performance of the risk-prediction algorithm is specified in terms of precision (PPV) and Recall (Sensitivity) parameters, iso-cost contours from Equation 14 are seen to be hyperbolic curves above the break-even threshold at a PPV of 1.8%.