{"id":"46098","type":"article","url":"https://hartvaat.nl/2026/04/03/machine-learningmodel-voorspelt-periprocedurele-complicaties-bij-tavi-voor-bicus/","title":"Machine-learningmodel voorspelt periprocedurele complicaties bij TAVI voor bicuspide aortaklepstenose","title_en":"","category":"algemeen","category_label":"Algemeen","professions":["cardioloog"],"tags":[],"journal":"Open Heart","doi":"http://openheart.bmj.com/cgi/content/short/13/1/e003749?rss=1","source_url":"https://doi.org/http://openheart.bmj.com/cgi/content/short/13/1/e003749?rss=1","authors":["Mao","Y.","Chen","Y.","Zhai","M.","Jin","P.","Li","W.","Gou","Y.","Liu","Y.","Zhang","J.","Yang","J."],"significance":6,"published":"2026-07-25","source_date":"2026-04-03","image":"","kennis":["https://hartvaat.nl/kennis/kleplijden/aortastenose/","https://hartvaat.nl/kennis/kleplijden/tavi-transcatheter-aortaklepimplantatie/"],"congress":"","summary_en":"Transcatheter aortic valve replacement (TAVR) is increasingly used for severe bicuspid aortic valve (BAV) stenosis, but these patients face multiple procedural challenges. In this multicentre study (1,266 patients with BAV stenosis), a machine-learning model was developed to predict the risk of periprocedural adverse events (PAEs). Five predictors were identified: Type 0 bicuspid valve, aortic-root calcification volume, horizontal aorta, annular ellipticity and prior atrial fibrillation. The risk model had good discrimination (AUC 0.80), with a clearly graded PAE risk by quartile (0.6%, 1.7%, 3.2% and 9.6%). A nomogram enables individual risk calculation. The model can thus individualise procedural planning and in-hospital care for bicuspid TAVR.","created":"2026-07-03T20:27:19Z","updated":"2026-07-04T19:09:45Z","licence":"Citeer vrij, met bronvermelding en een link naar hartvaat.nl (de url van het record). Samenvattingen zijn redactioneel werk van HartVaat; de oorspronkelijke publicaties blijven van hun uitgevers (doi). Geen medisch advies.","body_markdown":"Transkatheter-aortaklepimplantatie (TAVI) wordt steeds vaker toegepast bij ernstige bicuspide aortaklepstenose (BAV), maar deze patiënten kennen meerdere procedurele uitdagingen. In deze multicentrische studie (1.266 patiënten met BAV-stenose) werd een machine-learningmodel ontwikkeld om het risico op periprocedurele complicaties (PAE) te voorspellen. Vijf voorspellers werden geïdentificeerd: een Type 0-bicuspide klep, het calcificatievolume van de aortawortel, een horizontale aorta, de ellipticiteit van de annulus en eerder atriumfibrilleren. Het risicomodel had een goede discriminatie (AUC 0,80), met een duidelijk oplopend complicatierisico per kwartiel (0,6%, 1,7%, 3,2% en 9,6%). Een nomogram maakt individuele risicoberekening mogelijk. Het model kan zo de procedurele planning en de zorg tijdens opname bij bicuspide-TAVI individualiseren.","abstract_original":"Background\n

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.

\n\nObjective\n

To develop a machine learning (ML) model for assessing the risk of periprocedural adverse events (PAEs) in TAVR population with BAV.

\n\nMethods\n

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.

\n\nResults\n

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.

\n\nConclusions\n

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.

\n"}