人工智能风险预测工具用于异体乳房再造
本研究在2017至2023年于纪念斯隆凯特琳癌症中心接受即刻组织扩张器置入的4046例女性(共6513次置入)中,开发并评估传统统计与机器学习模型预测组织扩张器丢失、感染和血清肿。传统多变量回归的AUC为0.63至0.69,机器学习模型AUC为0.71至0.73。研究结果表明可将传统统计与机器学习分析纳入异体乳房再造患者的术前评估。
要点
- 组织扩张器丢失发生于7.6%的患者(4.8%的组织扩张器),感染发生于10%的患者(7.2%的组织扩张器),血清肿发生于11.5%的患者(6.2%的组织扩张器)。
- 传统多变量回归预测组织扩张器并发症的AUC为0.63至0.69,机器学习模型AUC为0.71至0.73。
- Shapley加性解释分析显示体重指数、胸肌前放置和化疗是组织扩张器并发症的关键预测因素。
核心结论
- 开发了使用列线图和机器学习模型预测异体乳房再造并发症的准确风险预测工具。
- 研究结果支持将传统统计和机器学习分析纳入异体乳房再造患者的术前评估,以增强数据驱动的个性化诊疗。
研究设计与样本
- 回顾性收集2017年至2023年在纪念斯隆凯特琳癌症中心接受即刻组织扩张器置入的所有女性的患者特征、手术技术和并发症。
- 开发多变量逻辑回归和机器学习模型预测组织扩张器丢失、感染和血清肿。
- 机器学习模型性能通过10折交叉验证和超参数调优进行优化。
- 评估指标包括受试者工作特征曲线下面积(AUC)、敏感性、特异性和Brier评分。
主要发现
- 研究纳入4046例女性,共6513次即刻组织扩张器置入。
- 组织扩张器丢失发生于7.6%的患者(4.8%的组织扩张器),感染发生于10%的患者(7.2%的组织扩张器),血清肿发生于11.5%的患者(6.2%的组织扩张器)。
- 传统多变量回归预测组织扩张器并发症的AUC为0.63至0.69,机器学习模型AUC为0.71至0.73。
- Shapley加性解释分析强调体重指数、胸肌前放置和化疗是组织扩张器并发症的关键预测因素。
- 表现最佳的模型被构建为列线图和基于网络的预测应用程序,以根据患者特定信息提供实时风险估计。
临床怎么用
- 研究结果表明可将传统统计和机器学习分析纳入异体乳房再造患者的术前评估,以增强数据驱动的个性化诊疗。
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
BACKGROUND: Accurate risk prediction for patients undergoing breast reconstruction with tissue expanders (TEs) can improve patient counseling and shared decision-making. This study aimed to develop and evaluate traditional statistical and machine learning (ML) approaches to predicting complications in alloplastic breast reconstruction. METHODS: Patient characteristics, surgical techniques, and complications were collected for all women undergoing immediate TE placement from 2017 to 2023 at Memorial Sloan Kettering Cancer Center. Multivariable logistic regression and ML models were developed to predict TE loss, infection, and seroma. ML model performance was optimized using 10-fold cross-validation with hyperparameter tuning. Evaluation metrics included area under the receiver operating curve (AUC), sensitivity, specificity, and Brier score. RESULTS: This study included 4046 women undergoing 6513 immediate TE placements. TE loss occurred in 7.6% of patients (4.8% of TEs), infection in 10% of patients (7.2% of TEs), and seroma in 11.5% of patients (6.2% of TEs). Traditional multivariable regression demonstrated AUCs of 0.63 to 0.69 and ML models demonstrated AUCs of 0.71 to 0.73 in predicting TE complications. Shapley Additive Explanations analysis highlighted body mass index, prepectoral placement, and chemotherapy as key predictors of TE complications. Top-performing models were built into nomograms and a web-based prediction application to provide real-time risk estimates based on patient-specific information. CONCLUSIONS: Accurate risk prediction tools using nomograms and ML models were developed to predict complications in alloplastic breast reconstruction. These findings support incorporating both traditional statistics and ML analyses into preoperative assessments of patients undergoing alloplastic breast reconstruction to enhance data-driven, personalized care.
引用
- Chen J, Gabay A, Kim M, et al. Artificial Intelligence Risk Prediction Tools for Alloplastic Breast Reconstruction. Plast Reconstr Surg. 2025. PMID: 40178533. doi:10.1097/PRS.0000000000012124
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。