Biomechanical Identification of High-Risk Patients Requiring Permanent Pacemaker After Transcatheter Aortic Valve Replacement

Abstract

BackgroundCardiac conduction disturbance requiring new permanent pacemaker implantation (PPI) is an important complication of TAVR that has been associated with increased mortality. It is extremely challenging to optimize the valve size alone to prevent a complete atrioventricular block (AVB).MethodsIn this study, we randomly took 48 patients who underwent TAVR and had been followed for at least 2 years to assess the risk of AVB. CT images of 48 patients with TAVR were analyzed using three-dimensional (3D) anatomical models of the aortic valve apparatus. The stresses were formulated according to loading force and tissue properties. Support vector regression (SVR) was used to model the relationship between AVB risk and biomechanical stresses. To avoid AVB, overlapping regions on the prosthetic valve where AV bundle passes will be removed as cylindrical sector with the angle θ. Thus, the optimization of the valve shape will be predicted with the joint optimization of the θ and valve size R.ResultsThe average AVB risk prediction accuracy was 83.33% in the range from 0.8–0.85 with 95% CI for all cases; specifically, 85.71% for Group A (no AVB), and 80.0% for Group B (undergoing AVB after the TAVR).ConclusionsThis model can estimate the optimal valve size and shape to avoid the risk of AVB after TAVR. This optimization may eliminate the excessive stresses to keep the normal function of both AV bundle and valve leaflets, leading to a favorable clinical outcome. The combination of biomechanical properties and machine learning method substantially improved prediction of surgical results.

Diagnostic Classification of Patients with Dilated Cardiomyopathy Using Ventricular Strain Analysis Algorithm

“…Therefore, it is difficult to judge a DCMP directly from original medicine images. In order for the cardiologist to achieve correct diagnosis, the echocardiogram images have to be despeckled [ 5 , 6 ].…”

Integrated VIS/NIR Spectrum and Genome-Wide Association Study for Genetic Dissection of Cellulose Crystallinity in Wheat Stems

“…Furthermore, pretreatments (standard normal variation (SNV), multiple scatter correction (MSC), first derivative (FD), and Savitzky–Golay filtering (SG)) were performed, and the transformed spectra showed a more diverse variation than the raw spectra ( Supplementary Figure S1 ). Previous studies found that a support vector machine regression (SVR) model is suitable for the prediction of a relatively small sample size, and SVR has been widely used in VIS/NIR models [ 22 , 23 ]. In this study, four models showed high determination coefficients (R 2 ) (>0.95) in the calibration dataset.…”

Mean compression ratio of a self-expandable valve is associated with the need for pacemaker implantation after transcatheter aortic valve replacement

“…To the best of our knowledge, the pressure distribution of the device landing zone is mainly simulated and predicted via preoperative finite element analysis [ 9 ], and there is no evaluation method for the actual pressure after implantation. In a previous study, the vast majority of implanted valve frames suffered from some degree of compression [ 10 ].…”