Related Experiment Video
Updated: May 28, 2026
Four-Dimensional Computed Tomography-Guided Valve Sizing for Transcatheter Pulmonary Valve Replacement
Published on: January 20, 2022
A Transformer-Based Machine Learning Framework for Risk Stratification of Left Bundle Branch Block After
Hayoung Ahn1, Sungwoo Hur1, Cheol Hyun Lee2
1Graduate School of AI, Pohang University of Science and Technology, Pohang 37673, Republic of Korea.
Insights
Machine learning models can predict left bundle branch block (LBBB) after transcatheter aortic valve replacement (TAVR) by analyzing complex patient data. This approach aids in identifying key risk factors for better procedural planning.
Area of Science:
- Cardiology
- Medical Informatics
- Artificial Intelligence in Medicine
Background:
- Left bundle branch block (LBBB) is a frequent complication post-transcatheter aortic valve replacement (TAVR), linked to poorer patient outcomes.
- Predicting LBBB is difficult due to intricate anatomical, procedural, and clinical factors.
Purpose of the Study:
- To create a machine learning (ML) framework for predicting LBBB after TAVR.
- To identify crucial features contributing to LBBB development.
Main Methods:
- A multicenter retrospective analysis of 242 patients undergoing TAVR.
- Development of an ML framework using transformer-based feature selection and classifiers.
- Model performance assessed via accuracy, precision, recall, F1-score, and AUC with bootstrap validation.
Main Results:
- A gradient boosting model achieved 78.05% accuracy and a 50.46% F1-score (AUC 0.61).
- ML identified key predictors like coronary height, LVOT/annulus ratio, and valve size.
- The model highlighted features not typically emphasized in conventional analyses.
Conclusions:
- ML-based feature selection effectively captures complex interactions for LBBB risk stratification post-TAVR.
- While performance was modest, ML shows promise for personalized TAVR planning.
- Further external validation in larger cohorts is recommended.
Abstract:
Background/Objectives: Left bundle branch block (LBBB) remains a common complication after transcatheter aortic valve replacement (TAVR) and is associated with adverse clinical outcomes. However, accurate prediction of LBBB remains challenging due to the complex interactions among the anatomical, procedural, and clinical factors. This study aimed to develop a machine learning (ML)-based framework to predict LBBB and identify relevant contributing features. Methods: In this multicenter retrospective study, we analyzed 242 patients undergoing TAVR across three institutions. A machine learning framework incorporating transformer-based feature selection and conventional classifiers was developed. Model performance was evaluated using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Internal validation was performed using bootstrap resampling. Results: The gradient boosting model using ML-derived features demonstrated the most balanced performance, achieving an accuracy of 78.05% and an F1-score of 50.46%, with modest discrimination (AUC 0.61). The ML-based approach identified clinically relevant features, including coronary height, left ventricular outflow tract/annulus ratio, and prosthetic valve size, as well as additional variables not emphasized in conventional analyses. Conclusions: ML-based feature selection can capture complex feature interactions beyond traditional statistical approaches and provide clinically meaningful insights into risk stratification for LBBB after TAVR. Although predictive performance was modest, this approach highlights the potential of ML for improved risk stratification and individualized procedural planning. Further large-scale external validation is warranted.
