Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun;21(7):489-494.
doi: 10.1080/14796678.2025.2498866. Epub 2025 Apr 29.

AI-based prediction of left bundle branch block risk post-TAVI using pre-implantation clinical parameters

Cheilas Vasileios  1 , Filandrianos Giorgos  2 , Martinos Antonios  1 , Kostopoulou Anna  1
Affiliations

AI-based prediction of left bundle branch block risk post-TAVI using pre-implantation clinical parameters

Cheilas Vasileios et al. Future Cardiol. 2025 Jun.

Abstract

Background and aims: Transcatheter Aortic Valve Implantation (TAVI) has revolutionized the treatment of severe aortic stenosis. Although its clinical efficacy is well established, the development of new-onset left bundle branch block (LBBB) following TAVI remains a frequent and concerning complication. This study aims to develop pre-implantation predictive models for new-onset LBBB after TAVI using both conventional machine learning (ML) algorithms and Large Language Models (LLMs).

Methods: Of the 1113 patients who underwent TAVI over a 15-year period, 469 were included after excluding those with preexisting LBBB, pacing rhythm, or missing relevant data. Pre-procedural clinical parameters - such as valve type, valve size, patient demographics, and comorbidities - were analyzed. The dataset was split into training and testing sets. Several ML algorithms were employed, and performance was evaluated using accuracy, precision, and F1 score. Additionally, LLMs (GPT-3.5 and GPT-4) were assessed using Few-Shot and Chain of Thought (CoT) prompting.

Results: New-onset persistent LBBB occurred in 15.29% of patients. Among ML models, XGBoost performed best. GPT-4 with CoT prompting demonstrated superior predictive performance compared to both conventional ML and GPT-3.5.

Conclusions: The current study establishes a predictive model leveraging pre-implantation parameters to anticipate the occurrence of new-onset left bundle branch block (LBBB) post-Transcatheter Aortic Valve Implantation (TAVI).

Keywords: LLMs; Transcatheter aortic valve replacement; aortic stenosis; artificial intelligence; individualized risk assessment; left bundle branch block; pre implantation predictors.

Plain language summary

Transcatheter Aortic Valve Replacement (TAVR) is a less invasive procedure used to treat patients with severe narrowing of the aortic valve. While it has significantly improved patient outcomes, some individuals develop a new heart rhythm problem called left bundle branch block (LBBB) after the procedure. LBBB can affect the heart’s electrical system and, in some cases, lead to complications such as the need for a permanent pacemaker.This study aimed to predict which patients are most likely to develop LBBB before the TAVR procedure by using artificial intelligence (AI) models. We analyzed data from 469 patients and tested different machine learning techniques, including traditional AI models and large language models (LLMs) such as GPT-4. Our results showed that XGBoost, a machine learning algorithm, was the most accurate in predicting LBBB risk, while GPT-4 performed well when prompted using a specific reasoning approach (Chain of Thought method).These findings suggest that AI models can help identify high-risk patients before the procedure, allowing doctors to make better treatment decisions. However, further studies with larger patient groups are needed to confirm the accuracy of these predictions and improve personalized care for TAVR patients.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest related to this research. There are no financial or non-financial affiliations, involvements, or relationships with any organization or entity that could influence the objectivity, integrity, or impartiality of the study.

References

    1. Leon MB, Smith CR, Mack M, et al. Transcatheter aortic-valve implantation for aortic stenosis in patients who cannot undergo surgery. N Engl J Med. 2010;363(17):1597–1607. doi: 10.1056/NEJMoa1008232 - DOI - PubMed
    1. Auffret V, Puri R, Urena M, et al. Conduction disturbances after transcatheter aortic valve replacement: current status and future perspectives. Circulation. 2017;136(11):1049–1069. doi: 10.1161/CIRCULATIONAHA.117.028352 - DOI - PubMed
    1. Chamandi C, Barbanti M, Munoz-Garcia A, et al. Long-term outcomes in patients with new-onset persistent left bundle branch block following TAVR. JACC Cardiovasc Interv. 2019;12(12):1175–1184. doi: 10.1016/j.jcin.2019.03.025 - DOI - PubMed
    1. Urena M, Webb JG, Cheema A, et al. Impact of new-onset persistent left bundle branch block on late clinical outcomes in patients undergoing transcatheter aortic valve implantation with a balloon-expandable valve. JACC Cardiovasc Interv. 2014;7(2):128–136. doi: 10.1016/j.jcin.2013.08.015 - DOI - PubMed
    1. Kim K, Ko Y-G, Shim CY.. Impact of new-onset persistent left bundle branch block on reverse cardiac remodeling and clinical outcomes after transcatheter aortic valve replacement. Front Cardiovasc Med. 2022;9:893878. doi: 10.3389/fcvm.2022.893878 - DOI - PMC - PubMed

    2. •• This study is highly relevant as it explores the long-term effects of persistent LBBB post-TAVR, particularly its impact on cardiac remodeling and adverse events, which aligns with the objectives of our study.

LinkOut - more resources