Deep Computational Model for the Inference of Ventricular Activation Properties

Abstract

Myocardial infarction (MI) demands precise and swift diagnosis. Cardiac digital twins (CDTs) have the potential to offer individualized evaluation of cardiac function in a non-invasive manner, making them a promising approach for personalized diagnosis and treatment planning of MI. The inference of accurate myocardial tissue properties is crucial in creating a reliable CDT platform, and particularly in the context of studying MI. In this work, we investigate the feasibility of inferring myocardial tissue properties from the electrocardiogram (ECG), focusing on the development of a comprehensive CDT platform specifically designed for MI.The platform integrates multi-modal data, such as cardiac MRI and ECG, to enhance the accuracy and reliability of the inferred tissue properties. We perform a sensitivity analysis based on computer simulations, systematically exploring the effects of infarct location, size, degree of transmurality, and electrical activity alteration on the simulated QRS complex of ECG, to establish the limits of the approach. We subsequently propose a deep computational model to infer infarct location and distribution from the simulated QRS. The in silico experimental results show that our model can effectively capture the complex relationships between the QRS signals and the corresponding infarct regions, with promising potential for clinical application in the future. The code will be released publicly once the manuscript is accepted for publication.

Periodontitis Increase the Risk of Heart Failure

“…In the future, we will consider extending our approach to a broader spectrum of data. The input features can be blood test results, demographic (age, sex, ethnicity) [47], smoking, chronic disease condition such as diabetes, imaging-derived features [49,50,62] as well as genetic information to create a more holistic and accurate characterization of the patient [8,9,63,64]. Moreover, it is interesting to increase the inclusivity and diversity of our study by considering a broader population base.…”

“…We further compare model performance using different encoder architectures, including 1) the encoder used in a variational autoencoder (VAE)-like network architecture, which has been found effective for ECG signal feature representation learning in previous works [47][48][49][50]; 2) XResNet1D [13], which is the top performing network architecture on a wide range of different ECG analysis tasks such as ECG disease classification, age regression, and form/rhythm prediction on the public PTB-XL benchmark dataset [39] and ICBEB2018 dataset [51]. We report their performance trained w/o and w/ the proposed language model informed pre-training strategy with structured SCP report in Table III.…”

Toward Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference

“…Recent advancements in multi-modal fusion methods fundamentally aim to integrate multi-modal data into a global feature space, allowing for a uniform representation of the integrated information [31], [32]. For instance, Li et al [33] employed multi-model representation learning to combine anatomical images and ECG signals for the inference of ventricular activation properties. The integration of anatomical images and ECG signals in a unified feature space enables the inverse inference of critical parameters related to ventricular activation.…”

Digital Twinning of Cardiac Electrophysiology Models From the Surface ECG: A Geodesic Backpropagation Approach

“…which can be effectively calculated using automatic differentiation of (11), or subsequent nodes (10) which are connected by a geodesic path to (x i , t i ). In particular, we use the backpropagation algorithm implemented in many ML libraries.…”

“…Hence, the parameters of eikonal-based models could be fitted from non-invasive clinical data-surface potentials and cardiac imaging-in an efficient manner. This goal can be achieved using optimization methods based on stochastic sampling strategies [8], [3], Bayesian optimization [9], gradient-descent [10], or deep learning approaches [11].…”