Periprocedural evaluation of patients with BAV stenosis undergoing TAVR: a machine learning-based study

Clinical Snapshot

Key Findings

• P Value: p<0.001 for overall trend across risk quartiles

• Effect Size: Risk stratification across quartiles: 0.6%, 1.7%, 3.2%, and 9.6% PAE rates

• Primary Outcome: Periprocedural adverse events (PAEs) prior to discharge

• Nnt Or Sensitivity: AUC 0.801 indicating good discrimination for risk prediction

• Confidence Interval: AUC 95% CI 0.768-0.832

Clinical Application

Requires advanced imaging analysis and clinical data collection, may be challenging in routine practice without appropriate infrastructure Relevant to Australian TAVR programs, could inform PBS funding decisions and procedural planning in tertiary cardiac centres. Aligns with CSANZ guidelines for comprehensive pre-procedural assessment Patients with bicuspid aortic valve stenosis being considered for TAVR, particularly those with identified high-risk features

Abstract

BACKGROUND: Transcatheter aortic valve replacement (TAVR) has increasingly emerged as one of the primary treatments for patients with severe bicuspid aortic valve (BAV) stenosis. Nevertheless, these patients encounter multiple procedural challenges. OBJECTIVE: To develop a machine learning (ML) model for assessing the risk of periprocedural adverse events (PAEs) in TAVR population with BAV. METHODS: This multicentre study retrospectively enrolled 1266 patients with BAV stenosis. Clinical characteristics and imaging data of the patients were collected, and an ML prediction model was developed. PAE was collectively defined as all-cause death, disabling stroke, life-threatening haemorrhage, acute kidney injury (≥stage 3), major vascular complications, valve-related dysfunction necessitating reoperation and other major complications that occurred prior to discharge. RESULTS: The average age was 72.6±6.3 years, and 58.3% (n=738) of male. In the derivation dataset, five predictive factors were identified: Type 0 BAV, aortic root calcification volume, horizontal aorta, annular ellipticity and previous atrial fibrillation. A robust risk scoring model was thereby established (area under the curve=0.801 95% CI 0.768 to 0.832). A graded relationship was observed between the quartiles of the score and PAE (0.6%, 1.7%, 3.2% and 9.6%; overall p<0.001). A nomogram was constructed to enable calculation of individual scores and the corresponding PAE probabilities. Additionally, similar results were observed in the validation dataset. CONCLUSIONS: The ML model developed in this study could predict the PAEs occurrence of TAVR in patients with BAV stenosis. This is conducive to individualised procedural planning and in-hospital management.

References

1. 1.Mao, Y., Chen, Y., Zhai, M., Jin, P., Li, W., Gou, Y., Liu, Y., Zhang, J., & Yang, J. (2026). Periprocedural evaluation of patients with BAV stenosis undergoing TAVR: a machine learning-based study. Open Heart. https://doi.org/10.1136/openhrt-2025-003749