Department of Surgery, Yonsei University College of Medicine, Seoul, Republic of Korea.
Department of Biostatistics and Computing, Graduate School, Yonsei University, Seoul, Korea.
Ann Surg Oncol. 2023 Nov;30(12):7281-7290. doi: 10.1245/s10434-023-13963-w. Epub 2023 Aug 16.
This study used a single-institution cohort, the Severance dataset, validated the results by using the surveillance, epidemiology, and end results (SEER) database, adjusted with propensity-score matching (PSM), and analyzed by using a machine learning method. To determine whether the 5-year, disease-free survival (DFS) and overall survival (OS) of patients undergoing nipple-sparing mastectomy (NSM) with immediate breast reconstruction (IBR) are not inferior to those of women treated with total mastectomy/skin-sparing mastectomy (TM/SSM).
The Severance dataset enrolled 611 patients with early, invasive breast cancer from 2010 to 2017. The SEER dataset contained data for 485,245 patients undergoing TM and 14,770 patients undergoing NSM between 2000 and 2018. All patients underwent mastectomy and IBR. Intraoperative, frozen-section biopsy for the retro-areolar tissue was performed in the NSM group. The SEER dataset was extracted by using operation types, including TM/SSM and NSM. The primary outcome was DFS for the Severance dataset and OS for the SEER dataset. PSM analysis was applied. Survival outcomes were analyzed by using the Kaplan-Meier method and Cox proportional hazard (Cox PH) regression model. We implemented XGBSE to predict mortality with high accuracy and evaluated model prediction performance using a concordance index. The final model inspected the impact of relevant predictors on the model output using shapley additive explanation (SHAP) values.
In the Severance dataset, 151 patients underwent NSM with IBR and 460 patients underwent TM/SSM with IBR. No significant differences were found between the groups. In multivariate analysis, NSM was not associated with reduced oncologic outcomes. The same results were observed in PSM analysis. In the SEER dataset, according to the SHAP values, the individual feature contribution suggested that AJCC stage ranks first. Analyses from the two datasets confirmed no impact on survival outcomes from the two surgical methods.
NSM with IBR is a safe and feasible procedure in terms of oncologic outcomes. Analysis using machine learning methods can be successfully applied to identify significant risk factors for oncologic outcomes.
本研究使用单机构队列（Severance 数据集），通过监测、流行病学和最终结果（SEER）数据库进行验证，采用倾向评分匹配（PSM）进行校正，并使用机器学习方法进行分析，以确定接受保留乳头的乳房切除术（NSM）联合即刻乳房重建（IBR）的患者与接受全乳切除术/皮肤保留乳房切除术（TM/SSM）的患者相比，其 5 年无病生存率（DFS）和总生存率（OS）是否不劣。
Severance 数据集纳入了 2010 年至 2017 年间 611 例早期浸润性乳腺癌患者。SEER 数据集包含了 2000 年至 2018 年间 485,245 例 TM 和 14,770 例 NSM 患者的数据。所有患者均接受了乳房切除术和 IBR。NSM 组术中对乳晕后组织进行了冷冻切片活检。SEER 数据集通过手术类型提取，包括 TM/SSM 和 NSM。主要结局是 Severance 数据集的 DFS 和 SEER 数据集的 OS。采用倾向评分匹配（PSM）分析。采用 Kaplan-Meier 方法和 Cox 比例风险（Cox PH）回归模型分析生存结果。我们使用 XGBSE 实现了高精度的死亡率预测，并使用一致性指数评估了模型预测性能。最终模型使用 SHAP 值检查相关预测因子对模型输出的影响。
在 Severance 数据集，151 例患者接受了 NSM 联合 IBR，460 例患者接受了 TM/SSM 联合 IBR。两组间无显著差异。多因素分析显示，NSM 与降低肿瘤学结局无关。PSM 分析也得到了相同的结果。在 SEER 数据集，根据 SHAP 值，个体特征贡献表明 AJCC 分期排名第一。来自两个数据集的分析证实，两种手术方法对生存结局没有影响。
NSM 联合 IBR 在肿瘤学结局方面是一种安全可行的方法。机器学习方法的分析可以成功地应用于识别肿瘤学结局的显著危险因素。
