Division of Cancer Prevention, National Cancer Institute, Bethesda, USA (SGB).
Med Decis Making. 2018 Feb;38(2):225-234. doi: 10.1177/0272989X17732994. Epub 2017 Oct 12.
When using risk prediction models, an important consideration is weighing performance against the cost (monetary and harms) of ascertaining predictors.
The minimum test tradeoff (MTT) for ruling out a model is the minimum number of all-predictor ascertainments per correct prediction to yield a positive overall expected utility. The MTT for ruling out an added predictor is the minimum number of added-predictor ascertainments per correct prediction to yield a positive overall expected utility.
An approximation to the MTT for ruling out a model is 1/[P (H(AUC)], where H(AUC) = AUC - {½ (1-AUC)}, AUC is the area under the receiver operating characteristic (ROC) curve, and P is the probability of the predicted event in the target population. An approximation to the MTT for ruling out an added predictor is 1 /[P {(H(AUC) - H(AUC )], where Model 2 includes an added predictor relative to Model 1.
The latter approximation requires the Tangent Condition that the true positive rate at the point on the ROC curve with a slope of 1 is larger for Model 2 than Model 1.
These approximations are suitable for back-of-the-envelope calculations. For example, in a study predicting the risk of invasive breast cancer, Model 2 adds to the predictors in Model 1 a set of 7 single nucleotide polymorphisms (SNPs). Based on the AUCs and the Tangent Condition, an MTT of 7200 was computed, which indicates that 7200 sets of SNPs are needed for every correct prediction of breast cancer to yield a positive overall expected utility. If ascertaining the SNPs costs $500, this MTT suggests that SNP ascertainment is not likely worthwhile for this risk prediction.
在使用风险预测模型时，需要权衡模型性能与确定预测因素的成本（货币和危害）。
排除模型的最小测试权衡（MTT）是指每正确预测一次所需的所有预测因素的最小确定数，以产生正的总体预期效用。排除附加预测因素的 MTT 是指每正确预测一次所需的附加预测因素的最小确定数，以产生正的总体预期效用。
排除模型的 MTT 的近似值为 1/[P（H（AUC）]，其中 H（AUC）= AUC - {½（1-AUC）}，AUC 是接收者操作特征（ROC）曲线下的面积，P 是目标人群中预测事件的概率。排除附加预测因素的 MTT 的近似值为 1 /[P {（H（AUC）-H（AUC ）]，其中模型 2相对于模型 1包含一个附加预测因素。
后一种近似值需要切线条件，即模型 2的 ROC 曲线上斜率为 1 的点的真阳性率大于模型 1。
这些近似值适用于粗略计算。例如，在一项预测浸润性乳腺癌风险的研究中，模型 2在模型 1的预测因素中增加了一组 7 个单核苷酸多态性（SNP）。基于 AUC 和切线条件，计算出的 MTT 为 7200，这表明每正确预测一次乳腺癌，需要进行 7200 次 SNP 检测才能产生正的总体预期效用。如果 SNP 检测的成本为 500 美元，则 MTT 表明 SNP 检测对于这种风险预测可能不值得。
