Search

The Communication and Collaboration Plan and Activities-I deliverable has a key role in laying down the principles for designing the communication and dissemination strategy activities to be followed throughout the project. The dissemination and communication strategy consist of spreading awareness of the project and its results, among specialists, general public and emerging stakeholders. To achieve these results, it will target diverse groups of people – depending on the specific goals, e.g., engage partners, inform a specific category of patients – through different media, so to maximize the spreading impact; and using a variety of tools, conceived and chosen based on the specific target. As communication and dissemination activities are running in parallel with the development of all work packages, they are in sync with the process, progress and feedback that the project receives. Therefore, the activities can and should be adapted along the way. As the initial publication package submitted – with all dissemination communication activities reported – at a very early stage of the project implementation (M2), it acts mostly as a roadmap, laying down a common understanding and an overview of the communication activities that might be needed while subject to regular monitoring and adjustment. This document will start with the purpose of the deliverable and its corelation with the other project’s deliverables and tasks, followed by the dissemination strategy and the planning of activities. We will describe iHelp dissemination channels and present promotional material and online promotion strategies.

Deliverable D8.5 is the first iteration of the exploration plans of the iHelp project and includes the strategy, the joint exploitation approach, as well as the update of the partners’ individual plans, describing their intentions for exploitation of iHelp outcomes, detail their plans to achieve the targeted exploitation goals and report progress on planned actions. The second and third iterations of the exploitation plans will be made available on M24 and M36 respectively, with the document D8.6 and D8.7.

This report summarizes the actions performed under Task 5.1 - “Techniques for early risk identification, predictions and assessment I” and more specifically provides details of the Artificial Intelligence (AI) / Machine Learning (ML) algorithms and implementation techniques that will be used to perform early identification as well as predictions of Pancreatic Cancer (PC) risks in individuals. The deliverable brings together several AI/ML techniques that are expected to be able to identify hidden patterns and trends in given data. When the data become available in the next phase of the project, these techniques will be used for performing assessment of identified risks and subsequently for making predictions. Since this is the first version of a series of deliverables, the follow-up report (i.e. D5.2) will specify the techniques to be used and linked with the datasets collected from the project pilots.

This document summarizes the actions performed under T4.1 “Personalized Health Modelling and Predictions” in the context of WP4 “Knowledge Management and Modelling in the iHelp Platform”. More specifically, D4.1 “Personalised health modelling and predictions I” provides an extended description of the mechanisms and Artificial Intelligence (AI) models that will be implemented for the realisation of personalised health and risk prediction models. The implementation of the ΑΙ algorithms that will be realized during the project’s lifecycle highly depends on the provided datasets on which they are trained. At this phase of the project, the description of the datasets that are going to be used, drive the actions under this Task towards a concrete description and specification of the AI algorithms and models that will be utilized. In addition, this document -the first one out of three versions- encapsulates the necessary and relevant information that was researched from recent bibliography to facilitate the manipulation of the available datasets, once they become available, setting the basis for the design and implementation of the models. More specifically, after an initial analysis of the datasets description, this document focuses on the advances of Machine Learning (ML) in the domain of healthcare, with special focus on the importance of Federated Learning (FL) for models trained from user interaction with tracking devices, as also is realised under the scopes of the iHelp project. Moreover, an initial analysis of pre-processing of data is being described, with focus on initial feature selection and imputation. Finally, in this deliverable are analysed the main concepts behind the models, also in compliance with an analysis of the importance of known and unknown risk factors based on the description of the clinical/primary data.

—Scientific and clinical research have advanced the ability of healthcare professionals to more precisely define diseases and classify patients into different groups based on their likelihood of responding to a given treatment, and on their future risks. However, a significant gap remains between the delivery of stratified healthcare and personalization. The latter implies solutions that seek to treat each citizen as a truly unique individual, as opposed to a member of a group with whom they share common risks or health-related characteristics. Personalisation also implies an approach that takes into accountpersonal characteristics and conditions of individuals. This paper investigates how these desirable attributes can be developed and introduces a holistic environment, the iHELP, that incorporates big data management and ArtificialIntelligence (AI) approaches to enable the realization of datadriven pathways where awareness, care and decision support is provided based on person-centric early risk prediction, prevention and intervention measures.

Part 3: AI Impacts/Big Data; International audience; Artificial Intelligence brings exciting innovations in all aspects of life and creates new opportunities across industry sectors. At the same time, it raises significant questions in terms of trust, ethics, and accountability. This paper offers an introduction to the AI4Media project, which aims to build on recent advances of AI in order to offer innovative tools to the media sector. AI4Media unifies the fragmented landscape of media-related AI technologies by investigating new learning paradigms and distributed AI, exploring issues of AI explainability, robustness and privacy, examining AI techniques for content analysis, and exploiting AI to address major societal challenges. In this paper, we focus on our vision of how such AI technologies can reshape the media sector, by discussing seven industrial use cases that range from combating disinformation in social media and supporting journalists for news story creation, to high quality video production, game design, and artistic co-creation. For each of these use cases, we highlight the present challenges and needs, and explain how they can be efficiently addressed by using innovative AI-driven solutions.

Data Management Plan with CHADA workflow sheet embedded

In order to improve and maximize access to and re-use of research data generated by Horizon 2020 projects,within the Open Research Data Pilot (ORD pilot), research data that refer to information, in particular facts or numbers, are collected to be examined and considered as a basis for reasoning, discussion, or calculation. In a research context, examples of data include statistics, results of experiments, measurements, observations resulting from fieldwork, survey results, interview recordings and images. The focus is on research data that is available in digital form.The ORD pilot takes into account the need to balance openness and protection of scientific information, commercialization and Intellectual Property Rights (IPR), privacy concerns, security as well as data management and preservation questions. The ORD pilot applies primarily to the data needed to validate the results that are presented in scientific publications. However, other data can also be provided by the beneficiaries.In principle, developing a Data Management Plan (DMP) is a key element for efficient data management. DMP describes the life cycle of the data to be generated, collected and processed by a Horizon 2020 project; it is required all projects participating in the extended ORD pilot. However, projects that opt out of the ORD pilot are still encouraged to submit a DMP on a voluntary basis. Aiming for findable, accessible, interoperable and re-usable data (known as FAIR Data), an efficient DMPincludes information on: the handling of research data during &after the end of the project what data will be collected, processed and/or generated which methodology & standards will be applied whether data will be shared/made open access and how data will be curated & preserved (also after the end of the project)

This paper describes a novel methodology of data documentation in materials characterization, which has as starting point the creation and usage of any Data Management Plan (DMP) for scientific data in the field of materials science and engineering, followed by the development and exploitation of ontologies for the harnessing of data created through experimental techniques. The case study that is discussed here is nanoindentation, a widely used method for the experimental assessment of mechanical properties on a small scale. The new documentation structure for characterization data (CHADA) is based on the definition of (i) sample, (ii) method, (iii) raw data and (iv) data analysis as the main component of the metadata associated to any characterization experiment. In this way, the relevant information can be stored inside the metadata associated to the experiment. The same methodology can be applicable to a large number of techniques that produce big amount of raw data, while at the same time it can be invaluable tool for big data analysis and for the creation of an open innovation environment, where data can be accessed freely and efficiently. Other fundamental aspects are reviewed in the paper, including the taxonomy and curation of data, the creation of ontology and classification of characterization techniques, the harnessing of data in open innovation environments via database construction along with the retrieval of information via algorithms. The issues of harmonization and standardization of such novel approaches are also critically discussed. Finally, the possible implications for nanomaterial design and the potential industrial impact of the new approach are described and a critical outlook is given.

iHelp aims to early detect and mitigate the risks associated with Pancreatic Cancer applying advanced Artificial Intelligence (AI)-based techniques to support the actors of the system. Those techniques are performed on historic data of cancer patients gathered from existing cohorts and biobanks. The models developed, through the AI-based learning techniques will be useful to identify the risk earlier, and to elaborate a mitigation plan. To this end, iHelp will use and extend the paradigm of Holistic Health Records (HHR) [1], in order to aggregate and re-use data needed by the Artificial Intelligence for developing their model. Several different sources will feed the common shared informative base, and for achieving this goal, a framework for the data ingestion will be provided for the pre-elaboration of different data in order to let it flow towards the shared data model. The purpose of this deliverable is to provide the consortium with a common high-level view about the whole solution. The details of each software artefact are delegated to the respective leader and will be described in the related deliverables. During the first months, the consortium had several virtual meetings to collect information and to agree about a common starting point for the architecture. After the first phase of coarse-grained data collection, some analysis was applied to design an efficient architecture based on the requirement emerged. Other refinement phases were performed regarding the design patterns to be implemented, provided and required interfaces, interconnections and protocols. The common agreement was reached about the general view, the platform will be constituted by containerised services, both from the data ingestion and the data analysis, with slightly differences explained in this document. The input of this deliverable was the D2.1 – State of the art and Requirements Analysis [2], that was analysed, and from which the needed components and interactions are identified. This deliverable is being released at M08 of the project, and it will be useful for the T2.3 – Functional and Non-Functional specifications for defining its purpose, and to all the technical partners as reference architecture for the whole iHelp solution. This is the first release of reference architecture; the second and final one will be released at M18: D2.5 - Conceptual model and reference architecture-II.