scholarly journals Deep Learning-based Prediction of Early Cerebrovascular Events after Transcatheter Aortic Valve Replacement

2021 ◽  
Author(s):  
Taishi Okuno ◽  
Pavel Overtchouk ◽  
Masahiko Asami ◽  
Daijiro Tomii ◽  
Stefan Stortecky ◽  
...  
Keyword(s):  
Deep Learning ◽  
Aortic Valve ◽  
Aortic Valve Replacement ◽  
Predictive Model ◽  
Valve Replacement ◽  
Transcatheter Aortic Valve Replacement ◽  
Feature Reduction ◽  
Risk Of Death ◽  
Transcatheter Aortic Valve ◽  
Cerebrovascular Events

Background: Cerebrovascular events (CVE) are one of the most feared complications of transcatheter aortic valve replacement (TAVR). CVE appear difficult to predict due to their multifactorial origin incompletely explained by clinical predictors. We aimed to build a deep learning-based predictive tool for TAVR-related CVE. Methods: Integrated clinical and imaging characteristics from consecutive patients enrolled into a prospective TAVR registry were analysed. CVE comprised any strokes and transient ischemic attacks. Predictive variables were selected by recursive feature reduction to train an autoencoder predictive model. Area under the curve (AUC) represented the model`s performance to predict 30-day CVE. Results: Among 2,279 patients included between 2007 and 2019, both clinical and imaging data were available in 1,492 patients. Median age was 83 years and STS score was 4.6%. Acute (<24 hours) and subacute (day 2-30) CVE occurred in 19 (1.3%) and 36 (2.4%) patients, respectively. The occurrence of CVE was associated with an increased risk of death (HR [95%CI]: 2.62 [1.82-3.78]). The constructed predictive model uses less than 107 clinical and imaging variables and has an AUC of 0.79 (0.65-0.93). Conclusions: TAVR-related CVE can be estimated using a deep learning-based predictive algorithm. The model was implemented online for broad usage. (https://www.welcome.alviss.ai/#/cvecalculator).

scholarly journals Deep learning-based prediction of early cerebrovascular events after transcatheter aortic valve replacement

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Taishi Okuno ◽  
Pavel Overtchouk ◽  
Masahiko Asami ◽  
Daijiro Tomii ◽  
Stefan Stortecky ◽  
...  
Keyword(s):  
Deep Learning ◽  
Aortic Valve ◽  
Aortic Valve Replacement ◽  
Predictive Model ◽  
Valve Replacement ◽  
Transcatheter Aortic Valve Replacement ◽  
Feature Reduction ◽  
Risk Of Death ◽  
Transcatheter Aortic Valve ◽  
Cerebrovascular Events

AbstractCerebrovascular events (CVE) are among the most feared complications of transcatheter aortic valve replacement (TAVR). CVE appear difficult to predict due to their multifactorial origin incompletely explained by clinical predictors. We aimed to build a deep learning-based predictive tool for TAVR-related CVE. Integrated clinical and imaging characteristics from consecutive patients enrolled into a prospective TAVR registry were analysed. CVE comprised any strokes and transient ischemic attacks. Predictive variables were selected by recursive feature reduction to train an autoencoder predictive model. Area under the curve (AUC) represented the model’s performance to predict 30-day CVE. Among 2279 patients included between 2007 and 2019, both clinical and imaging data were available in 1492 patients. Median age was 83 years and STS score was 4.6%. Acute (< 24 h) and subacute (day 2–30) CVE occurred in 19 (1.3%) and 36 (2.4%) patients, respectively. The occurrence of CVE was associated with an increased risk of death (HR [95% CI] 2.62 [1.82–3.78]). The constructed predictive model uses less than 107 clinical and imaging variables and has an AUC of 0.79 (0.65–0.93). TAVR-related CVE can be predicted using a deep learning-based predictive algorithm. The model is implemented online for broad usage.

Outcomes of permanent pacemaker implantation following transcatheter aortic valve replacement

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
L Fauchier ◽  
A Bodin ◽  
A Bisson ◽  
J Herbert ◽  
T Lacour ◽  
...  
Keyword(s):  
Heart Failure ◽  
Aortic Valve ◽  
Aortic Valve Replacement ◽  
Valve Replacement ◽  
Transcatheter Aortic Valve Replacement ◽  
Cardiac Resynchronization ◽  
Resynchronization Therapy ◽  
Risk Of Death ◽  
Transcatheter Aortic Valve ◽  
Increased Risk

Abstract Background Conduction abnormalities leading to permanent pacemaker (PPM) implantation are common complications following transcatheter aortic valve replacement (TAVR). Whether PPM implantation placement is associated with adverse outcomes is unclear. The purpose of this study was to evaluate the incidence, predictors, and clinical outcomes of PPI following TAVR. Methods Based on the administrative hospital-discharge database, we collected information for all patients treated with TAVR between 2010 and 2019 in France. Results A total of 49,201 patients with aortic stenosis treated with transcatheter aortic valve replacement (TAVR) using the balloon-expandable (BE) Edwards SAPIEN valve or the self-expanding (SE) Medtronic CoreValve were found in the database. Among them, 10,019 (20.4%) had prior PPM implantation, including 476 (4.8%) treated with cardiac resynchronization therapy (CRT). New PPM implantation was required within 30 days of TAVR in 11,010 patients (22.4%), which varied among those receiving self-expanding valves (24.7%) versus balloon-expanding valves (20.9%). There were 349/10,010 patients (3.1%) treated with cardiac resynchronization therapy (CRT) within 30 days following TAVR. In a multivariable analysis comprising 38 variables (including among others underlying conduction disorders, Euroscore 2, Charlson comorbidity index, frailty score and type of implanted valve), prior PPM implantation was associated with an increased risk of all-cause death (adjusted hazard ratio [HR]: 1.10 95% CI 1.04–1.16). New PPM implantation was associated with even higher risk of mortality (adjusted HR: 1.21 95% CI 1.15–1.28). By contrast, previous CRT was associated with a lower risk of death during follow-up (adjusted HR: 0.78 95% CI 0.63–0.96), while PPM with CRT within 30 days of TAVR was not associated with a different risk of death (adjusted HR: 1.00 95% CI 0.80–1.24). Prior PPM and new PPM implantation were also associated with an increased risk of rehospitalization for heart failure (adjusted HR: 1.26 95% CI 1.19–1.32 and 1.18 95% CI 1.12–1.24, respectively). Previous CRT was associated with a non-significant lower risk of rehospitalization for heart failure (adjusted HR: 0.92 95% CI 0.77–1.09). Conclusions Both previous PPM and early PPM implantation following TAVR are commonly seen in patients treated with TAVR, and they are associated with a higher risk of death and rehospitalisation for heart failure when compared to patients with no PPM. The fact that CRT when implanted before TAVR was associated with a better survival may deserve consideration when elaborating future optimal approaches for management of conduction disturbances in patients treated with TAVR. Funding Acknowledgement Type of funding source: None

Sign in / Sign up

Export Citation Format

Share Document