A machine learning model integrating statistical and mechanistic data accurately predicted new conduction abnormalities after TAVI with 83% accuracy and an AUC of 0.84.
Cohort (n=151)
Yes
Does a machine learning model integrating statistical and mechanistic modelling accurately predict conduction abnormalities in patients undergoing TAVI?
A combined mechanistic modeling and machine learning approach can accurately predict the risk of conduction abnormalities after TAVI, enabling personalized procedure planning.
Abstract Aims Post-procedure conduction abnormalities (CA) remain a common complication of transcatheter aortic valve implantation (TAVI), highlighting the need for personalized prediction models. We used machine learning (ML), integrating statistical and mechanistic modelling to provide a patient-specific estimation of the probability of developing CA after TAVI. Methods and results The cohort consisted of 151 patients with normal conduction and no pacemaker at baseline who underwent TAVI in nine European centres. Devices included CoreValve, Evolut R, Evolut PRO, and Lotus. Preoperative multi-slice computed tomography was performed. Virtual valve implantation with patient-specific computer modelling and simulation (CM&S) allowed calculation of valve-induced contact pressure on the anatomy. The primary composite outcome was new onset left or right bundle branch block or permanent pacemaker implantation (PPI) before discharge. A supervised ML approach was applied with eight models predicting CA based on anatomical, procedural and mechanistic data. CA occurred in 59% of patients (n = 89), more often after mechanical than first or second generation self-expanding valves (68% vs. 60% vs. 41%). CM&S revealed significantly higher contact pressure and contact pressure index in patients with CA. The best model achieved 83% accuracy (area under the curve 0.84) and sensitivity, specificity, positive predictive value, negative predictive value, and F1-score of 100%, 62%, 76%, 100%, and 82%. Conclusion ML, integrating statistical and mechanistic modelling, achieved an accurate prediction of CA after TAVI. This study demonstrates the potential of a synergetic approach for personalizing procedure planning, allowing selection of the optimal device and implantation strategy, avoiding new CA and/or PPI.
Galli et al. (Fri,) conducted a cohort in Transcatheter aortic valve implantation (TAVI) (n=151). Machine learning and mechanistic modelling was evaluated on new onset left or right bundle branch block or permanent pacemaker implantation (PPI) before discharge. A machine learning model integrating statistical and mechanistic data accurately predicted new conduction abnormalities after TAVI with 83% accuracy and an AUC of 0.84.