Prediction of permanent pacemaker implantation after transcatheter aortic valve replacement:The role of machine learning

作     者：Pradyumna Agasthi Hasan Ashraf Sai Harika Pujari Marlene Girardo Andrew Tseng Farouk Mookadam Nithin Venepally Matthew R Buras Bishoy Abraham Banveet K Khetarpal Mohamed Allam Siva K Mulpuru MD Mackram F Eleid Kevin L Greason Nirat Beohar John Sweeney David Fortuin David R Jr Holmes Reza Arsanjani 

作者机构：Department of CardiologyMayo ClinicPhoenixAZ 85054United States Department of Internal MedicineThe Brooklyn Hospital CenterBrooklynNY 11201United States Department of BiostatisticsMayo ClinicPhoenixAZ 85054United States Department of Cardiovascular DiseasesMayo ClinicRochesterMN 55905United States Department of StatisticsMayo ClinicPhoenixAZ 85054United States Department of Cardiovascular SurgeryMayo ClinicRochesterMN 55905United States Mount Sinai Medical CenterColumbia UniversityMiami BeachFL 33138United States 

出 版 物：《World Journal of Cardiology》 (世界心脏病学杂志（英文版）（电子版）)

年 卷 期：2023年第15卷第3期

页      面：95-105页

学科分类：1002[医学-临床医学] 100210[医学-外科学(含：普外、骨外、泌尿外、胸心外、神外、整形、烧伤、野战外)] 10[医学] 

基　　金：funded by Mayo Clinic Arizona Cardiovascular Clinical Research Center (MCA CV CRC) 

主　　题：Transcatheter aortic valve replacement Permanent pacemaker implantation Machine learning 

摘      要：BACKGROUND 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 preprocedural risk for *** To apply machine learning to be used to predict pre-procedural risk for *** 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 *** 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 *** 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 *** Of 964 patients included in the 30-d analysis without prior PPM,19.6%required PPM *** mean age of patients was 80.9±8.7 years.42.1%were *** 657 patients included in the 1-year analysis,the mean age of the patients was 80.7±*** those,42.6%of patients were female and 26.7%required PPM at 1-year *** 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 P value*** The GBM model has good discrimination and calibration in identifying patients at high risk of PPM post-TAVR.