Periodic Reporting for period 2 - ELVIS (ELEM Virtual Heart Populations for Supercomputers)
Reporting period: 2024-03-01 to 2025-08-31
In-silico trials are emerging as powerful tools, simulating therapy effects on virtual populations before real-world testing. Providing diverse, expansive populations far exceeding the capacity of traditional clinical trials they have potential to account for broader demographics and genetic variations, leading to more generalizable results. Additionally virtual populations allow for precise control over variables, unlike in vivo trials, and mitigate the ethical concerns surrounding animal and human trials. The ELVIS platform integrates different components to make this a reality at the hand of the biomedical stakeholders.
ELEM’s main product, V.HEART is a supercomputer-based platform to perform massive in-silico clinical trials on populations of digital avatars generated through a database of real medical data, to study the outcomes of different therapies. It assesses the safety and efficacy of novel therapeutics, devices or drugs, by computing thousands of scenarios. Current capability covers classic or leadless pacing and cardiac pumps and cardiac safety of drugs. Our plan is to add new therapies whilst increasing the range of our patented virtual population technology. V.HEART generates unparalleled medical insights and new evidence for biomedical professionals whilst shortening time to market and reducing business and patient risks.
It narrows the scope for animal testing and tapers real human trials by evaluating clinical study endpoints much faster and earlier in the development process. Eventually, digital avatars become a Digital Twin of any given patient used as a predictive tool for precision medicine.
ELEM’s main product, V.HEART is a supercomputer-based platform to perform massive in-silico clinical trials on populations of digital avatars generated through a database of real medical data, to study the outcomes of different therapies. It assesses the safety and efficacy of novel therapeutics, devices or drugs, by computing thousands of scenarios. Current capability covers classic or leadless pacing and cardiac pumps and cardiac safety of drugs. Our plan is to add new therapies whilst increasing the range of our patented virtual population technology. V.HEART generates unparalleled medical insights and new evidence for biomedical professionals whilst shortening time to market and reducing business and patient risks.
It narrows the scope for animal testing and tapers real human trials by evaluating clinical study endpoints much faster and earlier in the development process. Eventually, digital avatars become a Digital Twin of any given patient used as a predictive tool for precision medicine.
The ELEM V.HEART platform, also known as ELVIS, is an integrated system designed for cardiac modelling. Its core architecture comprises the WebApp (which hosts both frontend and backend systems), the Virtual Population Generator, and the high-fidelity simulation engine, Alya Red. Significant development progress has been reported across all components.
The ELVIS WebApp
The Elvis WebApp has reached a production milestone with the successful deployment of the first version of V.HEART on commercial cloud infrastructure, ensuring access security through a two-step authentication process. This cloud-based product is now utilized by customers to study the cardiac safety of their proprietary compounds, and internal cardiotoxicity study results are also being migrated onto the platform for direct analysis. The backend system managing simulations and data feeding has been substantially improved; a rigid, unstructured architecture was replaced with a flexible, scalable alternative that provides granular control over simulation configurations. V.HEART currently integrates a high-fidelity 3D cardiac simulation engine with a newly developed AI-driven predictive model capable of forecasting QT prolongation by analyzing compound characteristics across a simulated population of virtual hearts. Future efforts will concentrate on stakeholder validation, deeper integration into the wider Virtual Human Platform, and scientifically expanding the predictive model's capabilities.
The simulation engine, Alya Red
The Alya Red simulation engine is fully operational for modeling cardiac in silico clinical trials. It is capable of efficiently solving large 3D models, each representing a virtual patient from a synthetically generated cohort. The current version allows for the simulation of cardiac electrophysiology in healthy patients and includes new implementation and model parameterization for diseased patients, leading to a better representation of real populations. Furthermore, the models have been expanded to include electromechanical coupling—adding new circulatory system models and improving the coupling mechanism—and the atrial model, moving towards a 4-chamber cardiac model.
The Virtual Population Generator
The Virtual Population Generator utilizes advanced technology to create virtual populations for conducting in silico clinical trials. Key methodological developments include a Statistical Shape Model (SSM), applied primarily to biventricular cardiac anatomies, which allows for the generation of random heart shapes similar to those observed in the training dataset. An improved rule-based fiber generation algorithm has been developed to incorporate geometry-independent cardiac coordinates, enabling the standardized representation, comparison, and transfer of patient information. An automatic pipeline prepares the computational mesh for in silico trials, generating a high-quality tetrahedral mesh and adding necessary information such as myocardial fiber orientation, cell heterogeneity, activation locations, and the placement of ECG leads for pseudo-ECG measurements. Finally, the generator allows for defining a population starting from a given heart by altering the myocyte phenotype, material properties, and activation patterns, thereby supporting the generation of a wide range of hearts and diseases.Several in silico trials have been carried out on various virtual populations produced over the year, covering conditions such as LBBB, oncological issues, myocardial infarction, and heart failure.
The ELVIS WebApp
The Elvis WebApp has reached a production milestone with the successful deployment of the first version of V.HEART on commercial cloud infrastructure, ensuring access security through a two-step authentication process. This cloud-based product is now utilized by customers to study the cardiac safety of their proprietary compounds, and internal cardiotoxicity study results are also being migrated onto the platform for direct analysis. The backend system managing simulations and data feeding has been substantially improved; a rigid, unstructured architecture was replaced with a flexible, scalable alternative that provides granular control over simulation configurations. V.HEART currently integrates a high-fidelity 3D cardiac simulation engine with a newly developed AI-driven predictive model capable of forecasting QT prolongation by analyzing compound characteristics across a simulated population of virtual hearts. Future efforts will concentrate on stakeholder validation, deeper integration into the wider Virtual Human Platform, and scientifically expanding the predictive model's capabilities.
The simulation engine, Alya Red
The Alya Red simulation engine is fully operational for modeling cardiac in silico clinical trials. It is capable of efficiently solving large 3D models, each representing a virtual patient from a synthetically generated cohort. The current version allows for the simulation of cardiac electrophysiology in healthy patients and includes new implementation and model parameterization for diseased patients, leading to a better representation of real populations. Furthermore, the models have been expanded to include electromechanical coupling—adding new circulatory system models and improving the coupling mechanism—and the atrial model, moving towards a 4-chamber cardiac model.
The Virtual Population Generator
The Virtual Population Generator utilizes advanced technology to create virtual populations for conducting in silico clinical trials. Key methodological developments include a Statistical Shape Model (SSM), applied primarily to biventricular cardiac anatomies, which allows for the generation of random heart shapes similar to those observed in the training dataset. An improved rule-based fiber generation algorithm has been developed to incorporate geometry-independent cardiac coordinates, enabling the standardized representation, comparison, and transfer of patient information. An automatic pipeline prepares the computational mesh for in silico trials, generating a high-quality tetrahedral mesh and adding necessary information such as myocardial fiber orientation, cell heterogeneity, activation locations, and the placement of ECG leads for pseudo-ECG measurements. Finally, the generator allows for defining a population starting from a given heart by altering the myocyte phenotype, material properties, and activation patterns, thereby supporting the generation of a wide range of hearts and diseases.Several in silico trials have been carried out on various virtual populations produced over the year, covering conditions such as LBBB, oncological issues, myocardial infarction, and heart failure.
In the context of the Engine Simulation (Alya Red) the main objectives has been the modelling features. Our last enhancements improve the electromechanics modeling of the heart, allowing our 3D-0D cardiac electromechanics model to simulate both physiological and a wide range of pathological conditions, like as: Heart Failure, Hypertrophic cardiomyopathy, Ventricular tachycardia and Atrial fibrillation. The new model has been extended to cover both the ventricles and atria, and also developed a growth and remodeling model.
We also introduced new features to evaluate Cardiac Resynchronization Therapy (CRT) using virtual patient cohorts and expanded our Fluid-Structure Interaction (FSI) models to simulate cardiac valve dynamics with validation against real data. It also improved the efficiency of our solvers and established a new “test suite” to ensure the system is both fast and reliable.
Regarding the Virtual Population generator, the focus has been on testing arrhythmogenic risk of drugs. The main results in this area made it possible to automate tasks from the previously defined pipeline (mesh morphing algorithm, myocardial fiber generation algorithm and development of the universal biventricular coordinates). During the latter half of the project, we concentrate on the following areas:
- In-silico trials: defining diverse population and conducting in-silico trials
- Software maintenance: provide ongoing maintenance for the key algorithms required for population generation
- Database development: designed a database to store and manage the generated population
- Platform integration: integrate a selection of these populations into the Elvis Platform.
We also introduced new features to evaluate Cardiac Resynchronization Therapy (CRT) using virtual patient cohorts and expanded our Fluid-Structure Interaction (FSI) models to simulate cardiac valve dynamics with validation against real data. It also improved the efficiency of our solvers and established a new “test suite” to ensure the system is both fast and reliable.
Regarding the Virtual Population generator, the focus has been on testing arrhythmogenic risk of drugs. The main results in this area made it possible to automate tasks from the previously defined pipeline (mesh morphing algorithm, myocardial fiber generation algorithm and development of the universal biventricular coordinates). During the latter half of the project, we concentrate on the following areas:
- In-silico trials: defining diverse population and conducting in-silico trials
- Software maintenance: provide ongoing maintenance for the key algorithms required for population generation
- Database development: designed a database to store and manage the generated population
- Platform integration: integrate a selection of these populations into the Elvis Platform.