乳房再造并发症预测:机器学习模型的开发与前瞻性验证
本研究基于2015年1月至2019年7月在本机构接受保留乳头乳晕复合体乳房切除术(NSM)并即刻乳房再造的回顾性队列数据,训练随机森林分类模型预测乳头乳晕复合体(NAC)坏死,并在2020年6月至2021年6月的前瞻性队列中验证。模型在前瞻性队列中预测NAC坏死的准确率达97%(95%CI 0.89-0.99;P=0.009),与回顾性队列的准确率(0.97;95%CI 0.95-0.99)一致;前瞻性验证中特异度为0.98(95%CI 0.90-1.0),阴性预测值为0.98(95%CI 0.90-1.0)。植入物重量是预测风险增加的最重要因素,重量大于400 g与NAC缺血关联最强。
要点
- 机器学习模型前瞻性预测NAC坏死准确率达97%(95%CI 0.89-0.99;P=0.009)。
- 前瞻性验证特异度0.98(95%CI 0.90-1.0),阴性预测值0.98(95%CI 0.90-1.0)。
- 植入物重量大于400 g与NAC缺血关联最强,为可调整的危险因素。
核心结论
- 机器学习模型可前瞻性高准确度预测NAC坏死。
- 植入物重量是重要预测因素,为可调整的危险因素,可调整以降低NAC坏死及相关术后并发症风险。
研究设计与样本
- 回顾性收集2015年1月至2019年7月在本机构(高容量三级学术中心)接受NSM并即刻乳房再造的患者数据,训练随机森林分类模型预测NAC坏死。
- 模型在2020年6月至2021年6月接受NSM并即刻乳房再造的前瞻性队列中验证。
主要发现
- 前瞻性队列中模型预测NAC坏死的准确率为97%(95%CI 0.89-0.99;P=0.009)。
- 回顾性队列中预测准确率为0.97(95%CI 0.95-0.99),与前瞻性结果一致。
- 前瞻性验证特异度为0.98(95%CI 0.90-1.0),阴性预测值为0.98(95%CI 0.90-1.0)。
- 植入物重量是预测风险增加的最重要因素,重量大于400 g与NAC缺血关联最强。
临床怎么用
- 作者认为植入物重量是可调整的危险因素,可调整以降低NAC坏死及相关术后并发症风险。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
IMPORTANCE: Necrosis of the nipple-areolar complex (NAC) is the Achilles heel of nipple-sparing mastectomy (NSM), and it can be difficult to assess which patients are at risk of this complication (Ann Surg Oncol 2014;21(1):100-106). OBJECTIVE: To develop and validate a model that accurately predicts NAC necrosis in a prospective cohort. DESIGN: Data were collected from a retrospectively reviewed cohort of patients who underwent NSM and immediate breast reconstruction between January 2015 and July 2019 at our institution, a high -volume, tertiary academic center. Preoperative clinical characteristics, operative variables, and postoperative complications were collected and linked to NAC outcomes. These results were utilized to train a random-forest classification model to predict necrosis. Our model was then validated in a prospective cohort of patients undergoing NSM with immediate breast reconstruction between June 2020 and June 2021. RESULTS: Model predictions of NAC necrosis in the prospective cohort achieved an accuracy of 97% (95% confidence interval [CI], 0.89-0.99; P = 0.009). This was consistent with the accuracy of predictions in the retrospective cohort (0.97; 95% CI, 0.95-0.99). A high degree of specificity (0.98; 95% CI, 0.90-1.0) and negative predictive value (0.98; 95% CI, 0.90-1.0) were also achieved prospectively. Implant weight was the most predictive of increased risk, with weights greater than 400 g most strongly associated with NAC ischemia. CONCLUSIONS AND RELEVANCE: Our machine learning model prospectively predicted cases of NAC necrosis with a high degree of accuracy. An important predictor was implant weight, a modifiable risk factor that could be adjusted to mitigate the risk of NAC necrosis and associated postoperative complications.
引用
- Braun SE, Sinik LM, Meyer AM, et al. Predicting Complications in Breast Reconstruction: Development and Prospective Validation of a Machine Learning Model. Ann Plast Surg. 2023. PMID: 37489971. doi:10.1097/SAP.0000000000003621
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。