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 Experiment Video

Updated: Jun 18, 2026

Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
07:25

Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia

Published on: September 22, 2020

Predicting subclinical leaflet thrombosis in self-expandable prosthesis: A multimodal machine learning analysis.

Marco Moscarelli1,2, Thanos Athanasiou2,3, Roberto Casula3

  • 1Department of Cardiovascular Surgery, Maria Eleonora Hospital, GVM Care&Research, Palermo, Italy.

JTCVS Structural and Endovascular
|June 17, 2026
PubMed
Summary

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

Interpretable machine learning using accumulated local effects to characterise predictors of subclinical leaflet thrombosis after self-expanding transcatheter aortic valve implantation.

Interdisciplinary cardiovascular and thoracic surgery·2026
Same author

Primary cardiac angiosarcoma - hybrid therapy using coronary microembolization with coiling.

Kardiologia polska·2026
Same author

Supplemented Feed for Broiler Chickens: The Influence of Red Grape Pomace and Grape Seed Flours on Meat Characteristics.

Animals : an open access journal from MDPI·2026
Same author

Catheterization laboratories open the doors for Extended Realities-review of clinical applications in cardiology.

European heart journal. Digital health·2025
Same author

Physical and psychological optimization of tele-exercise programs by establishing guidelines.

Scientific reports·2025
Same author

Chimney stenting for preventing coronary obstruction in redo-TAVI with balloon-expandable valves within self-expanding valves.

EuroIntervention : journal of EuroPCR in collaboration with the Working Group on Interventional Cardiology of the European Society of Cardiology·2025

Bicuspid aortic valve anatomy and perioperative hematological changes are key predictors of subclinical leaflet thrombosis after transcatheter aortic valve implantation. Machine learning models effectively identify these risks for improved patient outcomes.

Area of Science:

  • Cardiovascular Medicine
  • Medical Imaging
  • Machine Learning in Healthcare

Background:

  • Subclinical leaflet thrombosis (SLT) is a recognized complication post-transcatheter aortic valve implantation (TAVI).
  • Predictors of SLT remain incompletely understood, necessitating advanced analytical approaches.
  • Machine learning (ML) offers potential for uncovering complex relationships in patient data.

Purpose of the Study:

  • To identify predictors of subclinical leaflet thrombosis following transcatheter aortic valve implantation.
  • To apply a multimodal machine learning framework for enhanced risk stratification.
  • To explore the utility of routinely available clinical, anatomic, and hematological variables.

Main Methods:

  • Analysis of data from 118 patients undergoing TAVI with self-expanding valves.
Keywords:
machine learningsubclinical leaflet thrombosistranscatheter aortic valve replacement

Related Experiment Videos

Last Updated: Jun 18, 2026

Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
07:25

Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia

Published on: September 22, 2020

  • Inclusion of 120 pre- and post-procedural variables.
  • Training and validation of three ML models: LASSO logistic regression, Random Forest, and Extreme Gradient Boosting using 5-fold cross-validation.

    • Main Results:

    • Subclinical leaflet thrombosis detected in 18.6% of patients.
    • Bicuspid aortic valve morphology identified as a primary predictor across all ML models.
    • Other significant predictors included serum creatinine, hemoglobin decrease, hematocrit decrease, and platelet nadir.
    • All models demonstrated strong discriminative ability (AUC 0.84-0.89).

    Conclusions:

    • This study pioneers the use of multimodal ML to predict SLT post-TAVI.
    • Bicuspid anatomy and perioperative hematological changes are consistently linked to SLT.
    • ML models utilizing routine variables can improve post-TAVI risk stratification and guide personalized antithrombotic strategies.