Agasthi Pradyumna, Ashraf Hasan, Pujari Sai Harika, Girardo Marlene, Tseng Andrew, Mookadam Farouk, Venepally Nithin, Buras Matthew R, Abraham Bishoy, Khetarpal Banveet K, Allam Mohamed, Md Siva K Mulpuru, Eleid Mackram F, Greason Kevin L, Beohar Nirat, Sweeney John, Fortuin David, Holmes David R Jr, Arsanjani Reza
Department of Cardiology, Mayo Clinic, Phoenix, AZ 85054, United States.
Department of Internal Medicine, The Brooklyn Hospital Center, Brooklyn, NY 11201, United States.
World J Cardiol. 2023 Mar 26;15(3):95-105. doi: 10.4330/wjc.v15.i3.95.
Atrioventricular block requiring permanent pacemaker (PPM) implantation is an important complication of transcatheter aortic valve replacement (TAVR). Application of machine learning could potentially be used to predict pre-procedural risk for PPM.
To apply machine learning to be used to predict pre-procedural risk for PPM.
A retrospective study of 1200 patients who underwent TAVR (January 2014-December 2017) was performed. 964 patients without prior PPM were included for a 30-d analysis and 657 patients without PPM requirement through 30 d were included for a 1-year analysis. After the exclusion of variables with near-zero variance or ≥ 50% missing data, 167 variables were included in the random forest gradient boosting algorithm (GBM) optimized using 5-fold cross-validations repeated 10 times. The receiver operator curve (ROC) for the GBM model and PPM risk score models were calculated to predict the risk of PPM at 30 d and 1 year.
Of 964 patients included in the 30-d analysis without prior PPM, 19.6% required PPM post-TAVR. The mean age of patients was 80.9 ± 8.7 years. 42.1 % were female. Of 657 patients included in the 1-year analysis, the mean age of the patients was 80.7 ± 8.2. Of those, 42.6% of patients were female and 26.7% required PPM at 1-year post-TAVR. The area under ROC to predict 30-d and 1-year risk of PPM for the GBM model (0.66 and 0.72) was superior to that of the PPM risk score (0.55 and 0.54) with a value < 0.001.
The GBM model has good discrimination and calibration in identifying patients at high risk of PPM post-TAVR.
需要植入永久起搏器（PPM）的房室传导阻滞是经导管主动脉瓣置换术（TAVR）的一种重要并发症。机器学习的应用可能有助于预测术前发生PPM的风险。
应用机器学习预测术前发生PPM的风险。
对1200例行TAVR的患者（2014年1月至2017年12月）进行回顾性研究。964例既往未植入PPM的患者纳入30天分析，657例30天内无需PPM的患者纳入1年分析。在排除方差接近零或缺失数据≥50%的变量后，将167个变量纳入采用5折交叉验证重复10次优化的随机森林梯度提升算法（GBM）。计算GBM模型和PPM风险评分模型的受试者工作特征曲线（ROC），以预测30天和1年时发生PPM的风险。
在纳入30天分析的964例既往未植入PPM的患者中，19.6%在TAVR术后需要植入PPM。患者的平均年龄为80.9±8.7岁。42.1%为女性。在纳入1年分析的657例患者中，患者的平均年龄为80.7±8.2岁。其中，42.6%为女性，26.7%在TAVR术后1年需要植入PPM。GBM模型预测30天和1年PPM风险的ROC曲线下面积（分别为0.66和0.72）优于PPM风险评分（分别为0.55和0.54），P值<0.001。
GBM模型在识别TAVR术后发生PPM高风险患者方面具有良好的区分度和校准能力。
