A multimodal machine learning model predicted VARC-3 technical failure in TAVR with moderate-to-high discrimination (AUC 0.769 cardiac, 0.788 vascular) and high negative predictive values.
Observational (n=2,937)
Can a multimodal machine learning-based model predict VARC-3 technical failure in patients undergoing TAVR?
A multimodal machine learning model can effectively predict VARC-3 technical failure in patients undergoing TAVR, potentially refining patient selection and procedural strategies.
Effect estimate: AUC 0.769 (cardiac), AUC 0.788 (vascular)
BACKGROUND: Technical failure is not uncommon and is associated with unfavorable outcomes in patients undergoing TAVR. However, predicting procedural failure remains challenging due to the complex interplay of clinical, anatomical, and procedural factors. OBJECTIVES: The objective of the study was to develop and validate a data-driven prediction model for technical failure of transcatheter aortic valve replacement (TAVR), using multimodal information and machine learning algorithms. METHODS: In a prospective TAVR registry, 184 parameters derived from clinical examination, laboratory studies, electrocardiography, echocardiography, cardiac catheterization, computed tomography, and procedural measurements were used for machine learning modeling of TAVR technical failure prediction. For the machine learning algorithm, 24 different model combinations were developed using a standardized machine learning pipeline. All model development steps were performed solely on the training set, whereas the holdout test set was kept separate for final evaluation. Technical success/failure was defined according to the Valve Academic Research Consortium (VARC)-3 definition, which differentiates between vascular and cardiac complications. RESULTS: Among 2,937 consecutive patients undergoing TAVR, the rate of cardiac and vascular technical failure was 2.4% and 7.0%, respectively. For both categories of technical failure, the best-performing model demonstrated moderate-to-high discrimination (cardiac: area under the curve: 0.769; vascular: area under the curve: 0.788), with high negative predictive values (0.995 and 0.976, respectively). Interpretability analysis showed that atherosclerotic comorbidities, computed tomography-based aortic root and iliofemoral anatomies, antithrombotic management, and procedural features were consistently identified as key determinants of VARC-3 technical failure across all models. CONCLUSIONS: Machine learning-based models that integrate multimodal data can effectively predict VARC-3 technical failure in TAVR, refining patient selection and optimizing procedural strategies.
Tomii et al. (Tue,) conducted a observational in Transcatheter aortic valve replacement (TAVR) (n=2,937). Multimodal machine learning-based prediction model was evaluated on Technical success/failure according to the Valve Academic Research Consortium (VARC)-3 definition (AUC 0.769 (cardiac), AUC 0.788 (vascular)). A multimodal machine learning model predicted VARC-3 technical failure in TAVR with moderate-to-high discrimination (AUC 0.769 cardiac, 0.788 vascular) and high negative predictive values.