Optimizing patient selection for primary prevention implantable cardioverter-defibrillator implantation: utilizing multimodal machine learning to assess risk of implantable cardioverter-defibrillator non-benefit.

"programming code for ecg pre-processing time-series feature extraction and model development is available through: https://github com/deepriskaumc/optimizing-patient-selection-for-primary-prevention-icd-implantation ."

"Conflict of interest S.M.N. reports grants or contracts from National Institutes of Health (NIH), consulting fees from Abbott Inc., and royalties and licences from Up-to-date. R.E.K. reports consultancy fees and research grants from Boston Scientific, Medtronic and Abbott Inc. and has the stock options from AtaCor Medical Inc. F.V.Y.T. has grants or contracts from the Dutch Research Council (NWO) and Amsterdam Cardiovascular Sciences, and received honoraria fees from Boston Scientific and Abbott Inc. (no personal financial gain). A.A.W. has consultancy fees from ARMGO and Thyrv Therapeutics, and participates on a Data Safety Monitoring Board or Advisory Board for the LEAP trial. C.P.A. reports grants or contracts from Biotronik. I.I. reports research grants or contracts from participation of Philips, Quantib, Pie Medical Imaging and Esaote, has patents planned, issued or pending, has stock option from RadNet and has leadership or fiduciary for Chair Medical Imaging with Deep Learning (MIDL) board, MIDL Foundation and SPIE Medical Imaging, Image processing. M.Z.H.K., S.R.C., B.D., L.A.F., E.J.B., P.C., and A.C.J.L have nothing to declare."

"Funding This publication is part of the project DEEP RISK ICD (with project number 452019308) of the research programme Rubicon which is (partly) financed by the Dutch Research Council (NWO). This research is partly funded by the Amsterdam Cardiovascular Sciences."