Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA.
Department of Biostatistics, Harvard University T H Chan School of Public Health, Boston, MA.
J Natl Cancer Inst. 2020 May 1;112(5):489-497. doi: 10.1093/jnci/djz177.
Several breast cancer risk-assessment models exist. Few studies have evaluated predictive accuracy of multiple models in large screening populations.
We evaluated the performance of the BRCAPRO, Gail, Claus, Breast Cancer Surveillance Consortium (BCSC), and Tyrer-Cuzick models in predicting risk of breast cancer over 6 years among 35 921 women aged 40-84 years who underwent mammography screening at Newton-Wellesley Hospital from 2007 to 2009. We assessed model discrimination using the area under the receiver operating characteristic curve (AUC) and assessed calibration by comparing the ratio of observed-to-expected (O/E) cases. We calculated the square root of the Brier score and positive and negative predictive values of each model.
Our results confirmed the good calibration and comparable moderate discrimination of the BRCAPRO, Gail, Tyrer-Cuzick, and BCSC models. The Gail model had slightly better O/E ratio and AUC (O/E = 0.98, 95% confidence interval [CI] = 0.91 to 1.06, AUC = 0.64, 95% CI = 0.61 to 0.65) compared with BRCAPRO (O/E = 0.94, 95% CI = 0.88 to 1.02, AUC = 0.61, 95% CI = 0.59 to 0.63) and Tyrer-Cuzick (version 8, O/E = 0.84, 95% CI = 0.79 to 0.91, AUC = 0.62, 95% 0.60 to 0.64) in the full study population, and the BCSC model had the highest AUC among women with available breast density information (O/E = 0.97, 95% CI = 0.89 to 1.05, AUC = 0.64, 95% CI = 0.62 to 0.66). All models had poorer predictive accuracy for human epidermal growth factor receptor 2 positive and triple-negative breast cancers than hormone receptor positive human epidermal growth factor receptor 2 negative breast cancers.
In a large cohort of patients undergoing mammography screening, existing risk prediction models had similar, moderate predictive accuracy and good calibration overall. Models that incorporate additional genetic and nongenetic risk factors and estimate risk of tumor subtypes may further improve breast cancer risk prediction.
存在多种乳腺癌风险评估模型。很少有研究在大规模筛查人群中评估多种模型的预测准确性。
我们评估了 BRCAPRO、Gail、Claus、乳腺癌监测联盟（BCSC）和 Tyrer-Cuzick 模型在预测 2007 年至 2009 年期间在牛顿威尔斯利医院接受乳房 X 线筛查的 35921 名 40-84 岁女性在 6 年内患乳腺癌风险的表现。我们使用接收者操作特征曲线下的面积（AUC）评估模型的区分度，并通过比较观察到的与预期的（O/E）病例的比值来评估校准。我们计算了每个模型的平方根、Brier 评分和阳性及阴性预测值。
我们的结果证实了 BRCAPRO、Gail、Tyrer-Cuzick 和 BCSC 模型具有良好的校准和相当的中度区分能力。Gail 模型的 O/E 比值和 AUC（O/E=0.98，95%置信区间[CI]：0.91-1.06，AUC=0.64，95%CI：0.61-0.65）略高于 BRCAPRO（O/E=0.94，95%CI：0.88-1.02，AUC=0.61，95%CI：0.59-0.63）和 Tyrer-Cuzick（版本 8，O/E=0.84，95%CI：0.79-0.91，AUC=0.62，95%CI：0.60-0.64）在整个研究人群中，而 BCSC 模型在有可用乳腺密度信息的女性中具有最高的 AUC（O/E=0.97，95%CI：0.89-1.05，AUC=0.64，95%CI：0.62-0.66）。所有模型对人类表皮生长因子受体 2 阳性和三阴性乳腺癌的预测准确性均低于激素受体阳性、人类表皮生长因子受体 2 阴性乳腺癌。
在进行乳房 X 线筛查的大型患者队列中，现有的风险预测模型具有相似的、中等的预测准确性和整体良好的校准。纳入其他遗传和非遗传风险因素并估计肿瘤亚型风险的模型可能会进一步提高乳腺癌风险预测。
