文献速递瓣膜病与结构性心脏病

简约机器学习模型预测TAVR术后1年死亡与手术无效

Parsimonious machine learning model to predict 1-year mortality and procedural futility after transcatheter aortic valve replacement.
PubMed 文献 · Heart · 2026-04-10

本研究基于1025例TAVR患者回顾性队列,用52个临床和超声变量训练机器学习模型,经多目标进化算法筛选出13个术前变量并在270例独立队列外部验证。模型预测1年全因死亡的AUC在发现队列为0.81、验证队列为0.84,优于EuroSCORE II、FRANCE-2和TAVI2-SCORE,校准良好且净重分类改善显著。

要点

  • 13个常规术前变量构成的ML模型可预测TAVR术后1年全因死亡。
  • 外部验证AUC 0.84,优于EuroSCORE II、FRANCE-2和TAVI2-SCORE。
  • 模型简约且校准良好,或有助于识别手术无效高危患者。

核心结论

  • 外部验证的ML模型仅用13个常规术前变量,预测TAVR术后1年死亡显著优于现有风险评分。

研究设计与样本

  • 回顾性队列训练ML模型,纳入1025例TAVR患者,使用52个临床和超声心动图变量。
  • 通过多目标进化算法进行特征选择和模型调优,最终模型含13个术前变量。
  • 在270例独立队列中进行外部验证,并与EuroSCORE II、FRANCE-2和TAVI2-SCORE比较。

主要发现

  • ML模型AUC在发现队列为0.81,外部验证队列为0.84。
  • EuroSCORE II的AUC在发现队列和验证队列分别为0.61和0.70。
  • FRANCE-2的AUC分别为0.52和0.58,TAVI2-SCORE分别为0.56和0.64。
  • 校准图显示预测风险与观察风险高度一致。
  • 测试集NRI对比FRANCE-2为0.62(95%CI:0.49至0.75),对比TAVI2-SCORE为0.36(95%CI:0.14至0.61)。

关键数值与推荐

  • 最终模型纳入年龄、心房颤动、肌酐、血红蛋白、肺功能、衰弱标志物(Katz指数、活动能力差)和三尖瓣反流。
  • 误分类分析显示多数错误集中在决策阈值附近,无系统偏倚证据。
  • 模型性能在各亚组一致,且对时间和机构差异稳健。

临床怎么用

  • 该模型使用常规术前变量,简约且可推广,支持在真实临床决策中识别TAVR术后手术无效高危患者。

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: Current risk scores inadequately predict long-term mortality after transcatheter aortic valve replacement (TAVR), limiting their ability to guide decisions around procedural futility. We aimed to develop and externally validate a machine learning (ML) model using only preprocedural variables to predict 1-year all-cause mortality. METHODS: An ML model was trained on a retrospective cohort of 1025 TAVR patients using 52 clinical and echocardiographic variables. Feature selection and model tuning were performed via a multiobjective evolutionary algorithm to optimise predictive performance and model simplicity. The final model used 13 preprocedural variables and was externally validated in an independent cohort of 270 patients. Performance was compared with European System for Cardiac Operative Risk Evaluation II (EuroSCORE II), FRANCE-2 and TAVI2-SCORE using the area under the curve (AUC), calibration and net reclassification improvement (NRI). RESULTS: The ML model demonstrated excellent discrimination, with AUCs of 0.81 in the discovery cohort and 0.84 in the external validation cohort. This exceeded the performance of EuroSCORE II (AUC: 0.61 and 0.70), FRANCE-2 (0.52 and 0.58) and TAVI2-SCORE (0.56 and 0.64). Calibration plots showed strong agreement between predicted and observed risks. NRI in the test set compared with FRANCE-2 was 0.62 (95% CI: 0.49 to 0.75); compared with TAVI2-SCORE, it was 0.36 (95% CI: 0.14 to 0.61). The final model incorporated age, atrial fibrillation, creatinine, haemoglobin, pulmonary function, frailty markers (Katz Index, poor mobility) and tricuspid regurgitation. Misclassification analysis revealed that most errors were clustered near the decision threshold, with no evidence of systematic bias. Performance was consistent across subgroups and robust to temporal and institutional variation. CONCLUSION: This externally validated ML model, using 13 routinely available variables, significantly outperforms existing risk scores in predicting 1-year mortality post-TAVR. Its simplicity and generalisability support its potential use in real-world clinical decision-making to identify patients at high risk of procedural futility.

来源:Heart,查看原文。版权归原作者所有。

引用

  1. Bharucha AH, Brown S, Theofilatos K, et al. Parsimonious machine learning model to predict 1-year mortality and procedural futility after transcatheter aortic valve replacement. Heart. 2026. PMID: 40713187. doi:10.1136/heartjnl-2025-325928

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。