Machine learning–derived major adverse event prediction of patients undergoing transvenous lead extraction: Using the ESC EHRA EORP European lead extraction ConTRolled ELECTRa registry

TY - JOUR

T1 - Machine learning–derived major adverse event prediction of patients undergoing transvenous lead extraction

T2 - Using the ESC EHRA EORP European lead extraction ConTRolled ELECTRa registry

AU - ELECTRa Investigators Group

AU - Mehta, Vishal S.

AU - O'Brien, Hugh

AU - Elliott, Mark K.

AU - Wijesuriya, Nadeev

AU - Auricchio, Angelo

AU - Ayis, Salma

AU - Blomstrom-Lundqvist, Carina

AU - Bongiorni, Maria Grazia

AU - Butter, Christian

AU - Deharo, Jean Claude

AU - Gould, Justin

AU - Kennergren, Charles

AU - Kuck, Karl Heinz

AU - Kutarski, Andrzej

AU - Leclercq, Christophe

AU - Maggioni, Aldo P.

AU - Sidhu, Baldeep S.

AU - Wong, Tom

AU - Niederer, Steven

AU - Rinaldi, Christopher A.

N1 - Funding Information: Disclosures: Drs Gould, Elliott, and Mehta have received fellowship funding from Abbott (outside the submitted work). Dr Sidhu is funded by the National Institute for Health Research and has received speaker fees from EBR Systems (outside the submitted work). Dr Gould has received project funding from Rosetrees Trust (outside the submitted work). Dr Kennergren has presented on behalf of, advised, and performed studies with Spectranetics/Philips (outside the submitted work). Dr Deharo has received minor honoraria from Philips for lectures and consulting (outside the submitted work). Dr Auricchio is a consultant to Boston Scientific, Backbeat, Biosense Webster, Cardiac, Corvia, Daiichi Sankyo, EBR Systems, Medtronic, Merit, MicroPort CRM, Philips, and V-WAVE; he has received speakers’ fee from Daiichi Sankyo, Boston Scientific, Biosense Webster, Medtronic, MicroPort CRM, and Philips; he has participated in clinical trials sponsored by Boston Scientific, EBR Systems, and Philips; he reports intellectual properties with Boston Scientific, Biosense Webster, and MicroPort CRM (outside the submitted work). Dr Kuck reports grants and personal fees from St. Jude Medical, Biosense Webster, and Medtronic (outside the submitted work). Dr Niederer has received research funding and/or consultation fees from Siemens, Abbott, and Pfizer (outside the submitted work). Dr Rinaldi has received research funding and/or consultation fees from Abbott, Medtronic, Boston Scientific, and MicroPort, (outside the submitted work). Dr Blomstrom-Lundqvist reports personal fees from Medtronic, Boston Sci, Bayer, CathPrint, Sanofi, Johnson & Johnson (outside the submitted work). The rest of the authors report no conflicts of interest. Funding Sources: The study was supported by Boston Scientific, Cook Medical, Medtronic, Spectranetics, and Zoll. The study was also supported by the Wellcome EPSRC Centre for Medical Engineering (WT203148/Z/16/Z). The research was supported by the National Institute for Health Research (NIHR) Biomedical Research Centre based at Guy's and St Thomas’ NHS Foundation Trust and King's College London. The views expressed are those of the authors and not necessarily those of the National Health Service, the NIHR, or the Department of Health. Funding Information: Disclosures: Drs Gould, Elliott, and Mehta have received fellowship funding from Abbott (outside the submitted work). Dr Sidhu is funded by the National Institute for Health Research and has received speaker fees from EBR Systems (outside the submitted work). Dr Gould has received project funding from Rosetrees Trust (outside the submitted work). Dr Kennergren has presented on behalf of, advised, and performed studies with Spectranetics/Philips (outside the submitted work). Dr Deharo has received minor honoraria from Philips for lectures and consulting (outside the submitted work). Dr Auricchio is a consultant to Boston Scientific, Backbeat, Biosense Webster, Cardiac, Corvia, Daiichi Sankyo, EBR Systems, Medtronic, Merit, MicroPort CRM, Philips, and V-WAVE; he has received speakers’ fee from Daiichi Sankyo, Boston Scientific, Biosense Webster, Medtronic, MicroPort CRM, and Philips; he has participated in clinical trials sponsored by Boston Scientific, EBR Systems, and Philips; he reports intellectual properties with Boston Scientific, Biosense Webster, and MicroPort CRM (outside the submitted work). Dr Kuck reports grants and personal fees from St. Jude Medical, Biosense Webster, and Medtronic (outside the submitted work). Dr Niederer has received research funding and/or consultation fees from Siemens, Abbott, and Pfizer (outside the submitted work). Dr Rinaldi has received research funding and/or consultation fees from Abbott, Medtronic, Boston Scientific, and MicroPort, (outside the submitted work). Dr Blomstrom-Lundqvist reports personal fees from Medtronic, Boston Sci, Bayer, CathPrint, Sanofi, Johnson & Johnson (outside the submitted work). The rest of the authors report no conflicts of interest. Funding Information: Funding Sources: The study was supported by Boston Scientific, Cook Medical, Medtronic, Spectranetics, and Zoll. The study was also supported by the Wellcome EPSRC Centre for Medical Engineering (WT203148/Z/16/Z). The research was supported by the National Institute for Health Research (NIHR) Biomedical Research Centre based at Guy’s and St Thomas’ NHS Foundation Trust and King’s College London. The views expressed are those of the authors and not necessarily those of the National Health Service, the NIHR, or the Department of Health. Publisher Copyright: © 2022 Heart Rhythm Society

PY - 2022/6

Y1 - 2022/6

N2 - Background: Transvenous lead extraction (TLE) remains a high-risk procedure. Objective: The purpose of this study was to develop a machine learning (ML)–based risk stratification system to predict the risk of major adverse events (MAEs) after TLE. A MAE was defined as procedure-related major complication and procedure-related death. Methods: We designed and evaluated an ML-based risk stratification system trained using the European Lead Extraction ConTRolled (ELECTRa) registry to predict the risk of MAEs in 3555 patients undergoing TLE and tested this on an independent registry of 1171 patients. ML models were developed, including a self-normalizing neural network (SNN), stepwise logistic regression model (“stepwise model”), support vector machines, and random forest model. These were compared with the ELECTRa Registry Outcome Score (EROS) for MAEs. Results: There were 53 MAEs (1.7%) in the training cohort and 24 (2.4%) in the test cohort. Thirty-two clinically important features were used to train the models. ML techniques were similar to EROS by balanced accuracy (stepwise model: 0.74 vs EROS: 0.70) and superior by area under the curve (support vector machines: 0.764 vs EROS: 0.677). The SNN provided a finite risk for MAE and accurately identified MAE in 14 of 169 “high (>80%) risk” patients (8.3%) and no MAEs in all 198 “low (<20%) risk” patients (100%). Conclusion: ML models incrementally improved risk prediction for identifying those at risk of MAEs. The SNN has the additional advantage of providing a personalized finite risk assessment for patients. This may aid patient decision making and allow better preoperative risk assessment and resource allocation.

AB - Background: Transvenous lead extraction (TLE) remains a high-risk procedure. Objective: The purpose of this study was to develop a machine learning (ML)–based risk stratification system to predict the risk of major adverse events (MAEs) after TLE. A MAE was defined as procedure-related major complication and procedure-related death. Methods: We designed and evaluated an ML-based risk stratification system trained using the European Lead Extraction ConTRolled (ELECTRa) registry to predict the risk of MAEs in 3555 patients undergoing TLE and tested this on an independent registry of 1171 patients. ML models were developed, including a self-normalizing neural network (SNN), stepwise logistic regression model (“stepwise model”), support vector machines, and random forest model. These were compared with the ELECTRa Registry Outcome Score (EROS) for MAEs. Results: There were 53 MAEs (1.7%) in the training cohort and 24 (2.4%) in the test cohort. Thirty-two clinically important features were used to train the models. ML techniques were similar to EROS by balanced accuracy (stepwise model: 0.74 vs EROS: 0.70) and superior by area under the curve (support vector machines: 0.764 vs EROS: 0.677). The SNN provided a finite risk for MAE and accurately identified MAE in 14 of 169 “high (>80%) risk” patients (8.3%) and no MAEs in all 198 “low (<20%) risk” patients (100%). Conclusion: ML models incrementally improved risk prediction for identifying those at risk of MAEs. The SNN has the additional advantage of providing a personalized finite risk assessment for patients. This may aid patient decision making and allow better preoperative risk assessment and resource allocation.

KW - Artificial intelligence

KW - ELECTRa registry

KW - Machine learning

KW - Outcomes

KW - Risk stratification

KW - Transvenous lead extraction

UR - http://www.scopus.com/inward/record.url?scp=85130122198&partnerID=8YFLogxK

U2 - 10.1016/j.hrthm.2021.12.036

DO - 10.1016/j.hrthm.2021.12.036

M3 - Article

C2 - 35490083

AN - SCOPUS:85130122198

SN - 1547-5271

VL - 19

SP - 885

EP - 893

JO - Heart Rhythm

JF - Heart Rhythm

IS - 6

ER -