A Machine Learning Approach to Predict Successful Trans-Ventricular Off-Pump Micro-Invasive Mitral Valve Repair

Background: The NeoChord procedure is a trans-ventricular, echo-guided, beating-heart mitral valve (MV) repair technique used to treat degenerative mitral regurgitation (MR) caused by leaflet prolapse and/or flail. Objectives: This study aimed to develop a machine learning (ML) scoring system using pre-procedural clinical and echocardiographic variables to predict the success of the NeoChord procedure—defined as less than moderate MR at follow-up. Methods: A total of 80 patients were included. Preoperative MV anatomical parameters were assessed using three-dimensional (3D) transesophageal echocardiography and analyzed with dedicated post-processing software (QLAB software, version 15.0, Philips Healthcare, Amstelveen, NL, The Netherlands). Two supervised ML models (random forest and decision tree) were trained on the dataset, with hyperparameters optimized via 10-fold cross-validation. The random forest model also provided a variable importance ranking using a filter-based method. Key predictors identified by the models included age, flail gap, early systolic mitral valve area, and indexed left atrial volume. Results: The mean and median cross-validated area under the curve of the ML models were 0.79 and 0.83 for the random forest model and 0.72 and 0.77 for the decision tree model, respectively. Conclusions: A machine learning approach integrating clinical and 3D echocardiographic parameters can effectively predict mid-term procedural success of the NeoChord technique. This method may support future preoperative patient selection, pending validation in larger cohorts.