Multimodal Machine Learning-Based Technical Failure Prediction in Patients Undergoing Transcatheter Aortic Valve Replacement

Publication

Link to Source: https://doi.org/10.1016/j.jacadv.2025.102168

Authors: Daijiro Tomii, Isaac Shiri, Giovanni Baj, Masaaki Nakase, Pooya Mohammadi Kazaj, Daryoush Samim, Joanna Bartkowiak, Fabien Praz, Jonas Lanz, Stefan Stortecky, David Reineke, Stephan Windecker, Thomas Pilgrim, Christoph Gräni Giannopoulos, George C. M. Siontis, Ronny R. Buechel, Christoph Gräni

Summary: Researchers developed a multimodal machine learning model integrating 184 clinical, anatomical, and imaging parameters to predict technical failures in transcatheter aortic valve replacement procedures, enabling better patient selection and procedural planning.

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.

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.

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.

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.

Machine learning-based models that integrate multimodal data can effectively predict VARC-3 technical failure in TAVR, refining patient selection and optimizing procedural strategies.