Electrocardiogram-based prediction of conduction disturbances after transcatheter aortic valve replacement with convolutional neural network

Aims

Permanent pacemaker implantation and left bundle branch block are common complications after transcatheter aortic valve replacement (TAVR) and are associated with impaired prognosis. This study aimed to develop an artificial intelligence (AI) model for predicting conduction disturbances after TAVR using pre-procedural 12-lead electrocardiogram (ECG) images.

Methods and results

We collected pre-procedural 12-lead ECGs of patients who underwent TAVR at West China Hospital between March 2016 and March 2022. A hold-out testing set comprising 20% of the sample was randomly selected. We developed an AI model using a convolutional neural network, trained it using five-fold cross-validation and tested it on the hold-out testing cohort. We also developed and validated an enhanced model that included additional clinical features. After applying exclusion criteria, we included 1354 ECGs of 718 patients in the study. The AI model predicted conduction disturbances in the hold-out testing cohort with an area under the curve (AUC) of 0.764, accuracy of 0.743, F1 score of 0.752, sensitivity of 0.876, and specificity of 0.624, based solely on pre-procedural ECG images. The performance was better than the Emory score (AUC = 0.704), as well as the logistic (AUC = 0.574) and XGBoost (AUC = 0.520) models built with previously identified high-risk ECG patterns. After adding clinical features, there was an increase in the overall performance with an AUC of 0.779, accuracy of 0.774, F1 score of 0.776, sensitivity of 0.794, and specificity of 0.752.

Conclusion

Artificial intelligence-enhanced ECGs may offer better predictive value than traditionally defined high-risk ECG patterns.

The impact of permanent pacemaker implantation on long-term survival after cardiac surgery: A systematic review and meta-analysis

OBJECTIVES

The long-term impact of permanent pacemaker (PPM) implantation on survival after cardiac surgery remains ill defined. We aimed to investigate the effect of PPM on survival and explore factors driving outcomes using meta-regression according to the type of surgery.

METHODS

MEDLINE, EMBASE, and the Cochrane Library Central Register of Controlled Trials were searched through October 2023 to identify studies reporting the long-term outcomes of PPM implantation. The primary outcome was all-cause mortality during follow-up. The secondary outcome was heart failure rehospitalization. The subgroup analysis and meta-regression analysis were performed according to the type of surgery.

RESULTS

A total of 28 studies met the inclusion criteria. 183,555 patients (n = 6298; PPM, n = 177,257; no PPM) were analyzed for all-cause mortality, with a weighted median follow-up of 79.7 months. PPM implantation was associated with increased risks of all-cause mortality during follow-up (hazard ratio, 1.22; confidence interval, 1.08-1.38, P < .01) and heart failure rehospitalization (hazard ratio, 1.24; confidence interval, 1.01-1.52, P = .04). Meta-regression demonstrated the adverse impact of PPM was less prominent in patients undergoing mitral or tricuspid valve surgery, whereas studies with a greater proportion with aortic valve replacement were associated with worse outcomes. Similarly, a greater proportion with atrioventricular block as an indication of PPM was associated with worse survival.

CONCLUSIONS

PPM implantation after cardiac surgery is associated with a greater risk of long-term all-cause mortality and heart failure rehospitalization. This impact is more prominent in patients undergoing aortic valve surgery or atrioventricular block as an indication than those undergoing mitral or tricuspid valve surgery.

Bicuspid Aortic Valve Disease: Classifications, Treatments, and Emerging Transcatheter Paradigms

Bicuspid aortic valve (BAV) is a common congenital valvular malformation, which may lead to early aortic valve disease and bicuspid-associated aortopathy. A novel BAV classification system was recently proposed to coincide with transcatheter aortic valve replacement being increasingly considered in younger patients with symptomatic BAV, with good clinical results, yet without randomized trial evidence. Procedural technique, along with clinical outcomes, have considerably improved in BAV patients compared with tricuspid aortic stenosis patients undergoing transcatheter aortic valve replacement. The present review summarizes the novel BAV classification systems and examines contemporary surgical and transcatheter approaches.

Pacemaker after Sutureless and Rapid-Deployment Prostheses: A Progress Report from the SURD-IR

OBJECTIVES

The aim of this study was to investigate the need for postoperative permanent pacemaker implantation (PPI) following sutureless and rapid-deployment aortic valve replacement (SuRD-AVR) in the context of a progress report from a large multicenter international registry (SURD-IR).

METHODS

We retrospectively analyzed 4,166 patients who underwent SuRD-AVR between 2008 and 2019. The primary outcome was the need for PPI before discharge. The study population was analyzed separately according to the implanted prostheses (Su cohort and RD cohort). Each cohort was divided into two groups based on the operation date: an early group ("EG" = 2008-2016) and a late group ("LG" = 2017-2019).

RESULTS

The rate of PPI decreased significantly in the Su cohort over time (EG = 10.8% vs LG = 6.3%, p < 0.001). In the Su cohort, a decrease in age, risk profile, and incidence of bicuspid aortic valve, increased use of anterior right thoracotomy, reduction of cardiopulmonary bypass time and of associated procedures, and more frequent use of smaller prostheses were observed over time. In the RD cohort, the rate of PPI was stable over time (EG = 8.8% vs LG = 9.3%, p = 0.8). In this cohort, a younger age, lower risk profile, and higher incidence of concomitant septal myectomy were observed over time.

CONCLUSION

Our analysis showed a significant decrease in the PPI rate in patients who underwent Su-AVR over time. Patient selection as well as surgical improvements and a more accurate sizing could be correlated with this phenomenon. The RD cohort revealed no significant differences either in patient's characteristics or in PPI rate between the two time periods.

Comparison of outcomes of self-expanding versus balloon-expandable valves for transcatheter aortic valve replacement: a meta-analysis of randomized and propensity-matched studies

BACKGROUND

The postoperative outcomes of transcatheter aortic valve replacement (TAVR) with the new generation of self-expanding valves (SEV) and balloon-expandable valves (BEV) remain uncertain.

METHODS

We conducted a meta-analysis based on randomized controlled trials (RCTs) and propensity score-matched (PSM) studies to evaluate the performance of the new generation TAVR devices, with a focus on Edwards SAPIEN 3/Ultra BEV, Medtronic Evolut R/PRO SEV, and Boston ACURATE neo SEV. Our primary endpoints were mortality and complications at both 30 days and one year post-operation.

RESULTS

A total of 4 RCTs and 14 PSM studies were included. Our findings showed no significant difference between SEV and BEV regarding 30-day and 1-year mortality rates. ACURATE SEV required less permanent pacemaker implantation (PPI) at 30-day as compared to SAPIEN BEV, while Evolut SEV required a higher rate of PPI than SAPIEN BEV. The incidence of stroke, major or life-threatening bleeding (MLTB), major vascular complications (MVC), coronary artery obstruction (CAO) and acute kidney injury (AKI) did not differ significantly between the two groups. SEV had a larger effective orifice area (EOA) and lower mean transvalvular gradients (MPG) compared to BEV. However, there was an increased risk of paravalvular leakage (PVL) associated with SEV.

CONCLUSIONS

In terms of 30-day mortality, stroke, bleeding, MVC, AKI, CAO, and one-year mortality, there was comparability between the two valve types following TAVR. SEV was associated with better hemodynamic outcomes, except for a higher incidence of PVL. Compared to SAPIEN BEV, ACURATE SEV had a lower risk of PPI at 30 days, while Evolut SEV was associated with a higher risk of PPI. These findings underscore the importance of personalized valve selection.

A prediction model for permanent pacemaker implantation after transcatheter aortic valve replacement

BACKGROUND

This study aims to develop a post-procedural risk prediction model for permanent pacemaker implantation (PPMI) in patients treated with transcatheter aortic valve replacement (TAVR).

METHODS

336 patients undergoing TAVR at a single institution were included for model derivation. For primary analysis, multivariate logistic regression model was used to evaluate predictors and a risk score system was devised based on the prediction model. For secondary analysis, a Cox proportion hazard model was performed to assess characteristics associated with the time from TAVR to PPMI. The model was validated internally via bootstrap and externally using an independent cohort.

RESULTS

48 (14.3%) patients in the derivation set had PPMI after TAVR. Prior right bundle branch block (RBBB, OR: 10.46; p < 0.001), pre-procedural aortic valve area (AVA, OR: 1.41; p = 0.004) and post- to pre-procedural AVA ratio (OR: 1.72; p = 0.043) were identified as independent predictors for PPMI. AUC was 0.7 and 0.71 in the derivation and external validation set. Prior RBBB (HR: 5.07; p < 0.001), pre-procedural AVA (HR: 1.33; p = 0.001), post-procedural AVA to prosthetic nominal area ratio (HR: 0.02; p = 0.039) and post- to pre-procedural troponin-T difference (HR: 1.72; p = 0.017) are independently associated with time to PPMI.

CONCLUSIONS

The post-procedural prediction model achieved high discriminative power and accuracy for PPMI. The risk score system was constructed and validated, providing an accessible tool in clinical setting regarding the Chinese population.

Stentless valves for bicuspid and tricuspid aortic valve disease

Objective

To determine long-term survival and reoperation rate in patients with a bicuspid aortic valve (BAV) and patients with a tricuspid aortic valve (TAV) after stentless aortic valve replacement (AVR)/aortic root replacement (ARR).

Methods

Between 1992 and 2014, 1293 patients underwent first AVR/ARR with a stentless aortic valve using the modified inclusion operating technique, including 741 patients with a TAV and 552 with a BAV. Using propensity scoring with 26 variables, 330 matched pairs were identified with AVR with or without ascending aorta/arch replacement. Data were obtained through chart review, surveys, and the National Death Index.

Results

Patient demographics were similar in the propensity score–matched groups. Both groups had similar cardiopulmonary bypass, cross-clamp, and hypothermia circulatory arrest times, cerebral protection strategies, and rate of aortic arch replacement. The median size of implanted valves was similar (BAV: 27 mm [range, 25-29 mm] vs TAV: 27 mm [range, 25-27 mm]). Compared with the TAV group, the BAV group had a shorter hospital stay (6 days vs 7 days; P = .001) but similar 30-day mortality (1.8% vs 1.2%). The BAV group had better long-term (15-year) survival (46% vs 33%; P = .002) but a higher cumulative incidence of reoperation for structural valve deterioration (15-year: 15% vs 11%; P = .048). Cox proportional hazard analysis identified a BAV as a protective factor for long-term mortality (hazard ratio [HR], 0.71; 95% CI, 0.56-0.91; P = .006), but a risk factor for reoperation due to structural valve deterioration (HR, 1.4 [95% CI, 0.8-2.6; P = .27] in the matched cohort and 2.2 [95% CI, 1.3-3.7; P = .004] in the unmatched cohort).

Conclusions

The BAV patients had better long-term survival but a higher reoperation rate compared with TAV patients after stentless AVR. Our findings suggest caution in the use of bioprostheses for BAV patients.

The incidence and predictors of high-degree atrioventricular block in patients with bicuspid aortic valve receiving self-expandable transcatheter aortic valve implantation

BACKGROUND

The high-degree atrioventricular block (HAVB) in patients with bicuspid aortic valve (BAV) treated with transcatheter aortic valve implantation (TAVI) remains high. The study aims to explore this poorly understood subject of mechanisms and predictors for HAVB in BAV self-expandable TAVI patients.

METHODS

We retrospectively included 181 BAV patients for analysis. Using computed tomography data, the curvature of ascending aorta (AAo) was quantified by the angle (AAo angle) between annulus and the cross-section at 35 mm above annulus (where the stent interacts with AAo the most). The valvular anatomy and leaflet calcification were also characterized.

RESULTS

The 30-day HAVB rate was 16.0% (median time to HAVB was three days). Type-1 morphology was found in 79 patients (43.6%) (left- and right-coronary cusps fusion comprised 79.7%). Besides implantation below membrane septum, large AAo angle [odds ratio (OR) = 1.08, P = 0.016] and type-1 morphology (OR = 4.97, P = 0.001) were found as the independent predictors for HAVB. Together with baseline right bundle branch block, these predictors showed strong predictability for HAVB with area under the cure of 0.84 (sensitivity = 62.1%, specificity = 92.8%). Bent AAo and calcified raphe had a synergistic effect in facilitating high implantation, though the former is associated with at-risk deployment (device implanted above annulus + prothesis pop-out, versus straight AAo: 9.9% vs. 2.2%, P = 0.031).

CONCLUSIONS

AAo curvature and type-1 morphology are novel predictors for HAVB in BAV patients following self-expandable TAVI. For patients with bent AAo or calcified raphe, a progressive approach to implant the device above the lower edge of membrane septum is favored, though should be done cautiously to avoid pop-out.

Incidence, Predictors, and Implications of Permanent Pacemaker Requirement After Transcatheter Aortic Valve Replacement

Transcatheter aortic valve replacement (TAVR) is a safe and feasible alternative to surgery in patients with symptomatic severe aortic stenosis regardless of the surgical risk. Conduction abnormalities requiring permanent pacemaker (PPM) implantation remain a common finding after TAVR due to the close proximity of the atrioventricular conduction system to the aortic root. High-grade atrioventricular block and new onset left bundle branch block (LBBB) are the most commonly reported conduction abnormalities after TAVR. The overall rate of PPM implantation after TAVR varies and is related to pre-procedural and intraprocedural factors. The available literature regarding the impact of conduction abnormalities and PPM requirement on morbidity and mortality is still conflicting. Pre-procedural conduction abnormalities such as right bundle branch block and LBBB have been linked with increased PPM implantation and mortality after TAVR. When screening patients for TAVR, heart teams should be aware of various anatomical and pathophysiological conditions that make patients more susceptible to increased risk of conduction abnormalities and PPM requirement after the procedure. This is particularly important as TAVR has been recently approved for patients with low surgical risk. The purpose of this review is to discuss the incidence, predictors, impact, and management of the various conduction abnormalities requiring PPM implantation in patients undergoing TAVR.

Evaluation and Management of Heart Block After Transcatheter Aortic Valve Replacement

Transcatheter aortic valve replacement (TAVR) has developed substantially since its inception. Improvements in valve design, valve deployment technologies, preprocedural imaging and increased operator experience have led to a gradual decline in length of hospitalisation after TAVR. Despite these advances, the need for permanent pacemaker implantation for post-TAVR high-degree atrioventricular block (HAVB) has persisted and has well-established risk factors which can be used to identify patients who are at high risk and advise them accordingly. While most HAVB occurs within 48 hours of the procedure, there is a growing number of patients developing HAVB after initial hospitalisation for TAVR due to the trend for early discharge from hospital. Several observation and management strategies have been proposed. This article reviews major known risk factors for HAVB after TAVR, discusses trends in the timing of HAVB after TAVR and reviews some management strategies for observing transient HAVB after TAVR.

Transcatheter Aortic Valve Replacement in Bicuspid Aortic Valve Stenosis

After 15 years of successive randomized, controlled trials, indications for transcatheter aortic valve replacement (TAVR) are rapidly expanding. In the coming years, this procedure could become the first line treatment for patients with a symptomatic severe aortic stenosis and a tricuspid aortic valve anatomy. However, randomized, controlled trials have excluded bicuspid aortic valve (BAV), which is the most frequent congenital heart disease occurring in 1% to 2% of the total population and representing at least 25% of patients 80 years of age or older referred for aortic valve replacement. The use of a less invasive transcatheter therapy in this elderly population became rapidly attractive, and approximately 10% of patients currently undergoing TAVR have a BAV. The U.S. Food and Drug Administration and the "European Conformity" have approved TAVR for low-risk patients regardless of the aortic valve anatomy whereas international guidelines recommend surgical replacement in BAV populations. Given this progressive expansion of TAVR toward younger and lower-risk patients, heart teams are encountering BAV patients more frequently, while the ability of this therapy to treat such a challenging anatomy remains uncertain. This review will address the singularity of BAV anatomy and associated technical challenges for the TAVR procedure. We will examine and summarize available clinical evidence and highlight critical knowledge gaps regarding TAVR utilization in BAV patients. We will provide a comprehensive overview of the role of computed tomography scans in the diagnosis, and classification of BAV and TAVR procedure planning. Overall, we will offer an integrated framework for understanding the current role of TAVR in the treatment of bicuspid aortic stenosis and for guiding physicians in clinical decision-making.