Machine learning used for simulation of MitraClip intervention: A proof-of-concept study

Abstract

Introduction: Severe mitral regurgitation (MR) is a mitral valve disease that can lead to lifethreatening complications. MitraClip (MC) therapy is a percutaneous solution for patients who cannot tolerate surgical solutions. In MC therapy, a clip is implanted in the heart to reduce MR. To achieve optimal MC therapy, the cardiologist needs to foresee the outcomes of different scenarios for MC implantation, including the location of the MC. Although finite element (FE) modeling can simulate the outcomes of different MC scenarios, it is not suitable for clinical usage because it requires several hours to complete.Methods: In this paper, we used machine learning (ML) to predict the outcomes of MC therapy in less than 1 s. Two ML algorithms were used: XGBoost, which is a decision tree model, and a feed-forward deep learning (DL) model. The MC location, the geometrical attributes of the models and baseline stress and MR were the features of the ML models, and the predictions were performed for MR and maximum von Mises stress in the leaflets. The parameters of the ML models were determined to achieve the minimum errors obtained by applying the ML models on the validation set.Results: The results for the test set (not used during training) showed relative agreement between ML predictions and ground truth FE predictions. The accuracy of the XGBoost models were better than DL models. Mean absolute percentage error (MAPE) for the XGBoost predictions were 0.115 and 0.231, and the MAPE for DL predictions were 0.154 and 0.310, for MR and stress, respectively.Discussion: The ML models reduced the FE runtime from 6 hours (on average) to less than 1 s. The accuracy of ML models can be increased by increasing the dataset size. The results of this study have important implications for improving the outcomes of MC therapy by providing information about the outcomes of MC implantation in real-time.

Transcatheter Mitral Valve Intervention: Current and Future Role of Multimodality Imaging for Device Selection and Periprocedural Guidance

“…The utilization of AI, as proposed by recent studies and with the aid of suitable tools, holds the potential to predict the outcomes of MVI in the near future. This prospect carries significant implications, including the ability to customize procedures more precisely, optimize device and patient selection, and impartially assess anatomical variables [88,89].…”

Artificial Intelligence-assisted Medical Imaging in Interventional Management of Valvular Heart Disease

“…Although FM modeling can simulate different surgical procedures, it is time-consuming. To tackle this challenge, Dabiri et al [25] used the XGBoost decision tree model and DL model to predict the effect of TEER therapy with MC. The DL model showed an prediction accuracy comparable to that of the FE model, but its running time is less than 1 second, an astonishing increase in efficiency as compared to 6 h by the FE model, thereby effectively facilitating the process of TEER by providing real-time intraoperative information.…”

In Silico Analysis of the MitraClip in a Realistic Human Left Heart Model

“…The optimal implantation position can be evaluated using computations based on echocardiography [14]. Additionally, machine learning, relying on simulations, is capable of predicting patient outcomes [15].…”