Background Deep learning breast cancer risk models demonstrate improved accuracy compared to traditional risk models but have not been prospectively tested. We compared the accuracy of a deep learning risk score derived from the patient’s prior mammogram to traditional risk scores to prospectively identify patients with cancer in a cohort due for screening. Methods We collected data on 119,139 bilateral screening mammograms in 57,617 consecutive patients screened at five facilities between September 18, 2017, and February 1, 2021. Patient demographics were retrieved from electronic medical records, cancer outcomes determined through regional tumor registry linkage, and comparisons made across risk models using Wilcoxon and Pearson’s chi-squared two-sided tests. Deep learning, Tyrer-Cuzick and National Cancer Institute Breast Cancer Risk Assessment Tool (NCI BCRAT) risk models were compared with respect to performance metrics and area under the receiver-operating-characteristic curves (AUCs). Results Cancers detected per thousand patients screened were higher in patients at increased risk by the deep learning model (8.6, 95% CI = 7.9–9.4) compared to Tyrer-Cuzick (4.4, 95% CI = 3.9–4.9) and NCI BCRAT (3.8, 95% CI = 3.3–4.3) models (P < .001). AUC of the deep learning model (0.68, 95% CI = 0.66–0.70) was higher compared to Tyrer-Cuzick (0.57, 95% CI = 0.54–0.60) and NCI BCRAT (0.57, 95% CI = 0.54–0.60) models. Simulated screening of the top 50th percentile risk by the deep learning model captured statistically significantly more patients with cancer compared to Tyrer-Cuzick and NCI BCRAT models (P < .001). Conclusions A deep learning model to assess breast cancer risk can support feasible and effective risk-based screening and is superior to traditional models to identify patients destined to develop cancer in large screening cohorts.

中文翻译：

---

深度学习与传统乳腺癌风险模型支持基于风险的乳房X光检查筛查

背景 与传统风险模型相比，深度学习乳腺癌风险模型的准确性有所提高，但尚未经过前瞻性测试。我们将根据患者之前的乳房 X 光检查得出的深度学习风险评分的准确性与传统风险评分进行比较，以前瞻性地识别队列中需要筛查的癌症患者。方法 我们收集了 2017 年 9 月 18 日至 2021 年 2 月 1 日期间在五个机构筛查的 57,617 名连续患者的 119,139 张双边筛查乳房 X 光检查数据。从电子病历中检索患者人口统计数据，通过区域肿瘤登记链接确定癌症结果，并进行比较使用 Wilcoxon 和 Pearson 的卡方双边检验来评估风险模型。对深度学习、Tyrer-Cuzick 和国家癌症研究所乳腺癌风险评估工具 (NCI BCRAT) 风险模型的性能指标和接受者操作特征曲线 (AUC) 下的面积进行了比较。结果 与 Tyrer-Cuzick（4.4，95% CI = 3.9-4.9）和 NCI BCRAT 相比，深度学习模型筛查的风险增加患者中每千名患者检出的癌症数量更高（8.6，95% CI = 7.9-9.4）。 3.8，95% CI = 3.3–4.3）模型（P < .001）。深度学习模型的 AUC (0.68, 95% CI = 0.66–0.70) 高于 Tyrer-Cuzick (0.57, 95% CI = 0.54–0.60) 和 NCI BCRAT (0.57, 95% CI = 0.54–0.60) 模型。与 Tyrer-Cuzick 和 NCI BCRAT 模型相比，深度学习模型对前 50 个百分位风险的模拟筛查捕获了统计上显着更多的癌症患者 (P < .001)。结论 评估乳腺癌风险的深度学习模型可以支持可行且有效的基于风险的筛查，并且优于传统模型来识别大型筛查队列中注定会患癌症的患者。