MD-Paedigree represents a clinically-driven and strongly VPH-rooted project, where 7 world-renowned clinical centres of excellence pursue improved interoperability of paediatric biomedical information, data and knowledge by developing together a set of reusable and adaptable multi-scale models for more predictive, individualised, effective and safer paediatric healthcare, being scientifically and technologically supported by one of the leading industrial actors in medical applications in Europe operating in conjunction with highly qualified SMEs and some of the most experienced research partners in the VPH community.
MD-Paedigree validates and brings to maturity patient-specific computer-based predictive models of various paediatric diseases, thus increasing their potential acceptance in the clinical and biomedical lresearch environment by making them readily available not only in the form of sustainable models and simulations, but also as newly-defined workflows for personalised predictive medicine at the point of care. These tools can be accessed and used through an innovative model-driven infostructure powered by an established digital repository solution able to integrate multimodal health data, entirely focused on paediatrics and conceived of as a specific implementation of the VPH-Share project, planned to be fully interoperable with it and cooperating, through it, also with p-Medicine.
In MD-Paedigree, the VPH Infostructure is designed to accommodate the chosen paediatric clinical areas, starting from the considerable experience capitalized in the Health-e-Child and Sim-e-Child projects. The latter developed grid and cloud-based eHealth repositories, models and simulations for specific diseases, and, particularly building on top of current developments within OPBG (Ospedale Pediatrico Bambino Gesù), further eHealth tools for data management and distributed high-performance computing which aim at gradually transferring into clinical practice the most advanced modelling in paediatric cardiology to support more precise outcomes analysis of pathologies and develop optimal therapies.
MD-Paedigree’s goals therefore are to:
- integrate and share highly heterogeneous biomedical information, data and knowledge, using best
- practices from the biomedical semantic Web,
- develop holistic search strategies to seamlessly navigate through and manage the integrative model-driven infostructure and digital repository
- jointly develop reusable, adaptable and composable multi-scale VPH workflow models,
- support evidence-based translational medicine at the point of care, and
- ultimately facilitate collaborations within the VPH community.
MD-Paedigree aims at achieving high-level semantic interoperability, thus requiring standards enabling the clinical contents to be interpreted consistently across the different EHR regimes, while complete clinical interoperability between systems will require widespread and dependable access to maintained collections of coherent and quality-assured semantic resources, including models that provide clinical context, mapped to interoperability standards for EHR and PHR and biomedical data, linked to well specified terminology value sets, derived from high quality ontologies.
In order to achieve semantic support at this level, MD-Paedigree takes advantage of recent work achieved in other EC semantic health and Ontology Based Data Access (OBDA) related projects such as SemanticHealthNet and DebugIT. MD-Paedigree also intends to comply with terminological and data interchange standards currently being developed within epSOS, in particular for the Patient Summary. As for biological data, MD-Paedigree will rely on OBO Foundry resources and BioDBcore recommendations. In addition, it aims to relate research, publications, experiments, and data joining forces with other EC – open access related – projects like OpenAIRE, OpenAIREplus.
THE ICT Challenge
MD-Paedigree elaborates on a decade of developments initially pioneered in the European FP5 MammoGrid and FP6 Health-e-Child projects, which were then brought further in FP7 Sim-e-Child.
More particularly, it leverages on the grid Gateway concept, allowing scientists to abstract from the complexity of underlying grids, clouds and other computing resources they need to use. Nowadays, Science Gateways represent an important emerging paradigm for providing integrated infrastructures. According to Wilkins a Science Gateway is “a community-developed set of tools, applications, and data that are integrated via a portal or a suite of applications, usually in a graphical user interface, that is further customised to meet the needs of a specific community. Gateways enable entire communities of users associated with a common discipline to use national resources through a common interface that is configured for optimal use. Researchers can focus on their scientific goals and less on assembling the cyberinfrastructure they require. Gateways can also foster collaborations and the exchange of ideas among researchers”. MD-Paedigree thus intends to reuse the latest Service Oriented Architecture (SOA) based Gateway released in Sim-e-Child, which enables secure and reliable access to abstracts from and integrates all forms of applications and data useful to users. The Gateway materializes as a layered architecture of standard secure (generic medical) services running on top of a grid infrastructure, which is physically installed at the participating clinical centres. Thanks to these on-site access points, users can transparently utilize a number of heterogeneous computing resources, ranging from local databases, to the distributed grid infrastructure regardless of their location and available connectivity. The Gateway supports the major principles of an SOA and exposes a significant set of biomedical utilities to date.
The SOKU VISION
MD-Paedigree will extend the Gateway and demonstrate a reasonably well-scoped use-case of the Service Oriented Knowledge Utility (SOKU) vision, as published by the European Commission in the Future for European Grids: Grids and Service Oriented Knowledge Utilities report, to address the challenge of delivering personalised care to patients.
MD-Paedigree will implement the SOKU vision, to facilitate the design and development of innovative predictive models as reusable and adaptable workflows of data mining applications and turning the latter into clinically validated decision support tools, made available at the point of care. This is what illustrates where reusable VPH models (in the centre) are incubated in the system with progressive semantic enrichment and model transformations in a cycle (the yellow spiral) witnessing the intervention of both automated database-guided learning and data integration and knowledge experts validation. As these models become more mature, they are then clinically validated by participating centres and concerned clinical researchers, and ultimately made available at the point of care thanks to the physical distribution and computational nature of the MD-Paedigree model-driven infostructure. Taking its roots from a well-established distributed digital repository, the MD-Paedigree VPH infostructure will thus hatch in a plethora of breakthrough decision support applications, as is illustrated with the petals of the SOKU flower.