Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Device innovation or systemic risk management?-rethinking priorities in diabetic percutaneous coronary intervention.

Cardiovascular diagnosis and therapy·2026
Same author

Conduction system pacing in TAVR patients requiring permanent pacemaker implantation.

Heart rhythm·2026
Same author

Hypoattenuated Leaflet Thickening After TAVR: Incidence, Predictors, and the Role of Platelet Reactivity: A Prospective Multicenter Observational Study.

Journal of clinical medicine·2026
Same author

Contrast use and radiation exposure during transcatheter aortic valve implantation according to valve design.

Kardiologia polska·2026
Same author

Mitral Valve Leaflet Modification: A Working Group Position Statement on Best Practices and Step-by-Step Guide.

JACC. Cardiovascular interventions·2026
Same author

Balloon-Assisted Translocation of the Mitral Anterior Leaflet to Prevent Outflow Tract Obstruction During TMVR: The BATMAN Registry.

JACC. Cardiovascular interventions·2026

Related Experiment Video

Updated: Aug 28, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

Predictive Power for Thrombus Detection after Atrial Appendage Closure: Machine Learning vs. Classical Methods.

Pablo Antúnez-Muiños1,2, Víctor Vicente-Palacios3, Pablo Pérez-Sánchez1,2

  • 1CIBERCV, University Hospital of Salamanca, 37007 Salamanca, Spain.

Journal of Personalized Medicine
|September 23, 2022
PubMed
Summary

Machine learning and multivariable methods show similar predictive power for device-related thrombus after left atrial appendage closure. Results question previous predictor findings and highlight methodological disparities.

Keywords:
atrial fibrillationdevice-related thrombosisleft atrial appendage closuremachine learningmultivariable analysispredictors

More Related Videos

Catheter Ablation in Combination With Left Atrial Appendage Closure for Atrial Fibrillation
28:13

Catheter Ablation in Combination With Left Atrial Appendage Closure for Atrial Fibrillation

Published on: February 26, 2013

33.5K
Echocardiographic Evaluation of Atrial Communications before Transcatheter Closure
07:41

Echocardiographic Evaluation of Atrial Communications before Transcatheter Closure

Published on: February 8, 2022

3.8K

Related Experiment Videos

Last Updated: Aug 28, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Catheter Ablation in Combination With Left Atrial Appendage Closure for Atrial Fibrillation
28:13

Catheter Ablation in Combination With Left Atrial Appendage Closure for Atrial Fibrillation

Published on: February 26, 2013

33.5K
Echocardiographic Evaluation of Atrial Communications before Transcatheter Closure
07:41

Echocardiographic Evaluation of Atrial Communications before Transcatheter Closure

Published on: February 8, 2022

3.8K

Area of Science:

  • Cardiology
  • Medical Devices
  • Data Science

Background:

  • Device-related thrombus (DRT) following left atrial appendage (LAA) closure is a rare complication associated with increased thromboembolic risk.
  • Identifying predictors of DRT is crucial for patient management and improving procedural outcomes.
  • Previous studies using multivariable methods have yielded inconsistent results regarding DRT predictors.

Purpose of the Study:

  • To compare the predictive power of machine learning techniques versus traditional multivariable methods for DRT detection after LAA occlusion.
  • To identify and compare the predictors of DRT derived from both methodologies.
  • To evaluate the impact of data resampling on the performance of predictive models.

Main Methods:

  • A multicenter study analyzing data from 1150 patients who underwent LAA closure.
  • Application of both multivariable and machine learning methodologies to the dataset.
  • Experiments conducted with and without data resampling to assess model robustness.
  • Comparison of predictive performance using Receiver Operating Characteristic (ROC) curves and analysis of extracted predictors.

Main Results:

  • Without resampling, machine learning (ROC AUC 0.7974) demonstrated higher predictive power than multivariable analysis (ROC AUC 0.5446).
  • With resampling, no significant difference in predictive performance was observed between the two methods (ROC AUC ~0.52-0.53).
  • Discrepancies were noted in the predictors identified by each methodology, with multivariable analysis showing greater stability.

Conclusions:

  • The predictive power of machine learning and multivariable methods for DRT after LAA closure may be comparable, particularly when data resampling is employed.
  • The findings challenge the consistency and validity of previously reported DRT predictors.
  • Neither technique demonstrated clear superiority for predicting DRT in this dataset, suggesting a need for further investigation into robust predictor identification.