Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA.
Kaiser Permanente Washington Health Research Institute, Kaiser Permanente Washington, Seattle, WA, USA.
J Natl Cancer Inst. 2024 Jun 7;116(6):929-937. doi: 10.1093/jnci/djae063.
Annual surveillance mammography is recommended for women with a personal history of breast cancer. Risk prediction models that estimate mammography failures such as interval second breast cancers could help to tailor surveillance imaging regimens to women's individual risk profiles.
In a cohort of women with a history of breast cancer receiving surveillance mammography in the Breast Cancer Surveillance Consortium in 1996-2019, we used Least Absolute Shrinkage and Selection Operator (LASSO)-penalized regression to estimate the probability of an interval second cancer (invasive cancer or ductal carcinoma in situ) in the 1 year after a negative surveillance mammogram. Based on predicted risks from this one-year risk model, we generated cumulative risks of an interval second cancer for the five-year period after each mammogram. Model performance was evaluated using cross-validation in the overall cohort and within race and ethnicity strata.
In 173 290 surveillance mammograms, we observed 496 interval cancers. One-year risk models were well-calibrated (expected/observed ratio = 1.00) with good accuracy (area under the receiver operating characteristic curve = 0.64). Model performance was similar across race and ethnicity groups. The median five-year cumulative risk was 1.20% (interquartile range 0.93%-1.63%). Median five-year risks were highest in women who were under age 40 or pre- or perimenopausal at diagnosis and those with estrogen receptor-negative primary breast cancers.
Our risk model identified women at high risk of interval second breast cancers who may benefit from additional surveillance imaging modalities. Risk models should be evaluated to determine if risk-guided supplemental surveillance imaging improves early detection and decreases surveillance failures.
对于有乳腺癌个人病史的女性，建议每年进行乳房 X 线筛查。能够预测乳腺癌筛查失败（如间期第二原发乳腺癌）的风险预测模型，可以帮助根据女性的个体风险特征定制监测成像方案。
在 1996 年至 2019 年期间，在乳腺癌监测联盟中接受监测乳房 X 线摄影的患有乳腺癌病史的女性队列中，我们使用最小绝对收缩和选择算子（LASSO）惩罚回归来估计阴性监测乳房 X 线摄影后 1 年内发生间期第二原发癌（浸润性癌或导管原位癌）的概率。基于这一年期风险模型的预测风险，我们为每次乳房 X 线摄影后五年生成间期第二原发癌的累积风险。在整个队列和种族及民族亚组中，使用交叉验证评估模型性能。
在 173290 次监测乳房 X 线摄影中，我们观察到 496 例间期癌。一年期风险模型具有良好的校准（预期/观察比值=1.00）和准确性（接受者操作特征曲线下面积=0.64）。模型性能在种族和民族组之间相似。五年期的中位累积风险为 1.20%（四分位距 0.93%-1.63%）。中位五年风险在诊断时年龄小于 40 岁或处于绝经前或围绝经期的女性以及雌激素受体阴性原发性乳腺癌女性中最高。
我们的风险模型确定了患有高风险间期第二原发乳腺癌的女性，这些女性可能受益于额外的监测成像方式。应评估风险模型，以确定风险指导的补充监测成像是否可以提高早期检测率并降低监测失败率。
