Work packages
Work package one
Title: Project management
Lead beneficiary: The University of Sheffield
Objectives
To ensure that the project is appropriately coordinated and managed according to the implementation plan, corrective actions being taken where necessary.
To establish a project management structure that ensures efficient operational control of administrative and financial tasks and project conduct in accordance with the Consortium Agreement.
To implement procedures, employ tools and marshal resources so as to assure contract fulfilment, with timely delivery of high-quality results.
To carry out routine reporting and administrative tasks, including progress updates to the Commission, financial distribution to partners and the preparation of project amendments as may be required.
Partner roles
USFD will lead the work package. It will chair the project management board and be responsible for all communications with the Commission. It will appoint a project manager to the task of managing this process.
All will take an active role in both the day to day and long term management of the project, and be responsible for their own budgets and the reporting of effort and expenditure against them.
Work package two
Title: Infrastructure
Lead beneficiary: CYFRONET AGH Krakow
Summary
Work package two will elaborate and operate a flexible, easy to use environment for the development, deployment and execution of large scale simulations, required for learning process development and for sensitivity analyses (a ‘Model Execution Environment’), and for the associated data storage.
The simulations will produce decision rule-sets that will be transferred from the research infrastructure to the DSS, while built-in visualisation facilities will enable access to cloud services from the local workstation.
The simulations will be run on external federated compute and storage resources exploiting recent advances in distributed computing, especially in cloud and container technologies.
Usage of resources will be optimised taking into account multiple factors including cost and execution time.
Work package two will closely collaborate with work package three in the optimisation of their software modules.
Objectives
To provide and to develop the necessary infrastructure to
collect, represent, annotate and publish the core homogeneous data
store and give secure access to the participating clinical centres and to the development partners to the necessary data
execute the models in the most appropriate computational environment (private workstation, private cloud, public cloud) according to need
support real-time multiscale visualisation
To develop an integrated security system supporting
authentication and authorisation
data encryption for secure processing in public clouds.
To deploy and operate the developed infrastructure, ensuring
quality of software components deployed and installed
quality of service, including such aspects as availability, responsiveness and cost efficiency
Partner roles
CYFRONET will lead the work package. They will develop the model execution environment, including taking responsibility for integration with the data warehouse. They will support work package five in its deployment within work package five.
STHFT will design the data warehouse and the interface to the clinical systems.
DHZB will work with STHFT on the introduction and support of the clinical data system.
Work package three
Title: Software Components
Lead beneficiary: PHILIPS
Summary
This work package provides the software components that underpin the analysis processes.
Objectives
To provide and to develop the machine learning tools
to operate on literature data to infer missing data necessary for operation of the models and/or to extract rule sets (for example on interventional outcome) to interpret the model outputs
to operate on the project’s own developing databases to infer missing data necessary for operation of the models and/or to extract rule sets (for example on interventional outcome) to interpret the model outputs
To provide and to develop the models and software components
to yield detailed anatomical representations of an individual’s mitral and aortic valve in different opening states together with the other required heart structures such as the left ventricle and the ascending aorta from CT and 3D TEE images or image sequences
to extract quantitative measures based on the segmentation results, like aortic valve opening area, aortic or mitral annulus perimeter or mitral valve regurgitant area
to facilitate subsequent blood flow simulations by providing suitable interfaces for the definition of boundary conditions and mesh models with sufficient resolution for subsequent volumetric meshing
To provide the underpinning compartmental (zero-d, lumped parameter) models that describe the distribution of flow, pressure, oxygen saturation and other physiological parameters in the cardiovascular circulation. These are important in their own right, but also provide boundary conditions for the localised anatomically accurate descriptions of the valve region, which are based on the segmentation of the medical images of the individual patient.
To provide and to develop the software components to support sensitivity studies and the derivation of confidence measures from multiple operations of the models.
Partner roles
PHILIPS will lead the work package and provide the segmentation tools.
PEN will provide the machine learning tools.
USFD will provide the existing models of systems physiology.
ANSYS, supported by USFD, will provide the Reduced Order Modelling tools that will underpin the solution of the complex valve flow dynamics in clinically-tractable timescales.
TUE with USFD will implement the tools for variation and sensitivity analysis.
Work package four
Title: DP Definition, Data Collection
Lead beneficiary: German Heart Institute Berlin
Summary
This work package collects the data on which the project depends.
These data include clinical information from each patient, and population and epidemiological data that are used both for data inference and for data and model interpretation.
All data will be appropriately annotated, organised and represented using the infrastructure developed in work package 2.1.
Objectives
1. To define the data that are important to underpin the decision support process.
2. To specify the inclusion criteria for the study.
3. To identify and recruit the cohort of patients on whom the decision support system will be tested.
4. To collect the data and to annotate, organise and represent it using the infrastructure developed in work package 2.1. Such clinically relevant data will include
demographic, laboratory and clinical data from each patient’s Electronic Health Record
acquired imaging, clinical, laboratory and ECG data before and after intervention
epidemiological data from the published literature
environmental data from pervasive monitoring
Partner roles
DHZB will lead the work package, identify (with the support of USFD), the data that will define the digital patient for this application, and co-ordinate the design of the study.
The Clinical Centres (DHZB, STHFT, Catharina) will recruit the patients and enter the data into the warehouse.
UBRISTOL will collect the environmental data to demonstrate the potential for inclusion of pervasive monitoring data in a personalised decision support environment.
Work package five
Title: Decision Support System
Lead beneficiary: THERENVA
Summary
This work package develops the primary output of the project, the Decision Support System.
Objectives
To specify the requirements for, and technical content of, the DSS.
To design an integrated system capable of co-operating with the computational infrastructure.
To include a clinically-favoured Case-Based Reasoning system, in which the extensive historical data on previous patients is used to provide insights into possible current treatment alternatives.
To build and deploy a comprehensive beta-release DS system.
To respond to user experience, incorporating improvements in a final DSS release.
Partner roles
THERENVA will lead the work package and drive the specification and DSS construction activities.
UR1-LTSI will support the DSS with the case-based reasoning feature.
PHILIPS will provide the machine-learning rules sets.
CYFRONET and STHFT will provide support in the integration of the computational infrastructure, including access to the data warehouse, into the DSS.
USFD will provide support in the integration and operation of the systems physiology model.
TUE will provide support in the integration and operation of the systems physiology model.
Work package six
Title: DSS Operation
Lead beneficiary: Catharina Hospital
Summary
Work package six will apply the DSS to the identified cohort of clinical cases.
Objectives
To operate the software components on the study cohort.
To add to the data warehouse the parameters derived from the computational operations.
To use the project’s own database to infer parameters and rule sets.
To evaluate the operation of the DSS on the patient cohort.
To evaluate the performance of the combined DSS and infrastructure system
Partner roles
CATH will lead the work package.
DHZB will direct the application of the DSS to clinical data.
USFD will organise the process.
PEN will construct the relevant rule set.
CYFRONET will coordinate the assessment of the completed DSS/platform system.
Work package seven
Title: Exploitation
Lead beneficiary: Philips Eindhoven
Summary
Work package seven is responsible for all aspects of the exploitation of the software system.
This has two essential components:
Market: Health economics assessment and market evaluation
Regulation: Assessment, strategy and planning for all aspects of regulatory approval
Partner roles
PEN will lead the work package.
THERENVA perform market analysis and dissemination.
ANSYS will provide market analysis and dissemination.
PHILIPS will provide market analysis and dissemination.
USFD will provide regulatory detail.
Related information: