Fritz

That will address major challenges hampering the deployment of AI technology. These grand challenges are fundamental in nature. Addressing them in a sustainable manner requires a lighthouse rooted in scientific excellence and rigorous methods. We will develop a strategic research agenda which is supported by research programmes that focus on “technical robustness and safety”,“privacy preserving techniques and infrastructures” and “human agency and oversight”. Furthermore, we focus our efforts to detect, prevent, and mitigate threats and enable recovery from harm by 3 grand challenges: “Robustness guarantees and certification”,“Private and robust collaborative learning at scale” and “Human-in-the-loop decision making: Integrated governance to ensure meaningful oversight” that cut across 6 use cases: health, autonomous driving, robotics, cybersecurity, multi-media, and document intelligence. Throughout our project, we seek to integrate robust technical approaches with legal and ethical principles supported by meaningful and effective governance architectures to nurture and sustain the development and deployment of AI technology that serves and promotes foundational European values. Our initiative builds on and expands the internationally recognized, highly successful and fully operational network of excellence ELLIS. We build on its 3 pillars: research programmes, a set of research units, and a PhD/PostDoc programme, thereby connecting a network of over 100 organizations and more than 337 ELLIS Fellows and Scholars (113 ERC grants) committed to shared standards of excellence. Not only will we establish a virtual center of excellence, but all our activities will also be inclusive and open to input, interactions, and collaboration of AI researchers and industrial partners in order to drive the entire field forward.

Funding Body

Funding Body

European Commission

Ever since the last Coronavirus epidemic caused by SARS-CoV-1, plans and tools for the containment of epidemics are being developed. However, an appropriate early warning system for local health authorities addressing this need on a regional, targeted level is not available. In the current SARS-CoV-2 pandemic, the need for such a system becomes increasingly obvious. The heterogeneity of different regions and localized outbreaks require a locally adapted monitoring and evaluation of infection dynamics.

Early recognition of an emerging epidemic is a crucial part of a successful intervention. The comparison of Germany to other European nations illustrates how crucial a timely implementation of non-pharmaceutical interventions is for the containment of an epidemic. Hence, continuous monitoring of infection processes is indispensable. For strategic planning of political interventions, epidemiological modelling and scenario calculations for forecasting and evaluation of interventions and scenarios have shown their importance. The accuracy of such forecasts largely depends on the robustness and broadness of the underlying data. Further, there is a need for an intelligible presentation of often complex simulation results without oversimplification of their interpretation and inherent uncertainty.

In this proposal, we develop a platform that integrates data streams from various sources in a privacy preserving manner. For their analysis, a variety of methods from machine learning to epidemiological modeling are employed to detect local outbreaks early on and enable an evaluation for different assumptions and on different scales. These models will be integrated into automatized workflows and presented in an interactive web application with custom scenario simulations. The platform will be based on insights gained by retrospective and prospective evaluation of the COVID-19 pandemic, using SARS-CoV-2 as a blueprint for the prevention and containment of future respiratory virus epidemics. The platform will be transferred to the Academy for Public Health Services and optimized in pilot projects with selected local health authorities under real-world conditions.

Funding Body

Funding Body

Helmholtz-Gemeinschaft e.V.; Impuls- und Vernetzungsfonds

Partner

Project Partner

Helmholtz-Zentrum für Infektionsforschung (HZI)

Project Partner

Deutsches Zentrum für Luft- und Raumfahrt (DLR)

Project Partner

Forschungszentrum Jülich

Project Partner

Helmholtz-Zentrum für Umweltforschung (UFZ)

Das Ziel von PrivateAIM ist die Entwicklung einer föderierten Plattform für maschinelles Lernen (ML) und Datenanalyse im Rahmen der Medizininformatik-Initiative (MII), bei der die Analysen zu den Daten gebracht werden und nicht die Daten zu den Analysen. Methoden, die eine verteilte Datenverarbeitung in den von der MII eingerichteten Datenintegrationszentren ermöglichen, sind aus mehreren Gründen wichtig: 1) Daten von Patientinnen und Patienten dürfen ohne Einwilligung nur verwendet werden, wenn Anonymität gewährleistet ist; 2) föderierte Technologien können dazu beitragen, die MII mit anderen Gesundheitsdatennetzen zu verbinden. Die derzeit in der MII etablierten Mechanismen weisen jedoch erhebliche Einschränkungen auf und sind beispielsweise nicht für komplexe ML- und Data-Science-Tasks geeignet. Darüber hinaus sind föderierte Plattformen, die in anderen Zusammenhängen entwickelt wurden, 1) kompliziert einzurichten und zu betreiben, 2) unterstützen eine begrenzte Anzahl von Analyse- oder ML-Methoden, 3) implementieren keine modernen Technologien zur Wahrung der Privatheit und 4) sind nicht skalierbar oder ausgereift. Das PrivateAIM-Konsortium, das von allen MII-Konsortien unterstützt wird, bringt Experten zusammen, um die nächste Generation der föderierten Analyse- und ML-Plattform für die MII zu entwickeln. Die Plattform für föderierte Lern- und Analysemethoden (FLAME) wird modernste Föderierungsmethoden mit innovativen Datenschutzmodellen für multimodale Daten kombinieren. Unter Verwendung von Komponenten zur Überwachung und Kontrolle des Schutzniveaus werden diese in eine verteilte Infrastruktur integriert, die von den Datenintegrationszentren leicht übernommen werden kann. Die Umsetzung in die Praxis wird durch die Berücksichtigung von Herausforderungen an der Schnittstelle von Technologie und Recht, die Entwicklung von Konzepten für den Betrieb durch die IT-Abteilungen der Krankenhäuser und die Abstimmung mit Ethikkommissionen sowie Datenschutzbeauftragten begleitet.

Funding Body

Funding Body

Bundesministerium für Bildung und Forschung

Partner

Project Partner

Universität zu Köln

Universität zu Köln

Project Partner

Universität Leipzig

Universität Leipzig

Project Partner

Deutsches Krebsforschungszentrum (DKFZ)

Deutsches Krebsforschungszentrum (DKFZ)

Project Partner

Universität Ulm

Universität Ulm

Project Partner

Universität Heidelberg

Universität Heidelberg

Project Partner

Albert-Ludwigs-Universität Freiburg

Albert-Ludwigs-Universität Freiburg

Project Partner

Charité - Universitätsmedizin Berlin

Charité - Universitätsmedizin Berlin

Project Partner

Technische Universität München

Technische Universität München

Project Partner

Eberhard Karls Universität Tübingen

Eberhard Karls Universität Tübingen

Project Partner

TMF - Technologie- und Methodenplattform für die vernetzte medizinische Forschung e. V. Berlin

TMF - Technologie- und Methodenplattform für die vernetzte medizinische Forschung e. V. Berlin

Project Partner

Friedrich-Alexander-Universität Erlangen-Nürnberg

Friedrich-Alexander-Universität Erlangen-Nürnberg

Project Partner

Ludwig-Maximilians-Universität München

Ludwig-Maximilians-Universität München

Genetic data is highly privacy sensitive information and therefore is protected under stringent legal regulations, making them burdensome to share. However, leveraging genetic information bears great potential in diagnosis and treatment of diseases and is essential for personalized medicine to become a reality. While privacy preserving mechanisms have been introduced, they either pose significant overheads or fail to fully protect the privacy of sensitive patient data. This reduces the ability to share data with the research community which hinders scientific discovery as well as reproducibility of results. Hence, we propose a different approach using synthetic data sets that share the properties of patient data sets while respecting the privacy. We achieve this by leveraging the latest advances in generative modeling to synthesize virtual cohorts. Such synthetic data can be analyzed with established tool chains, repeated access does not affect the privacy budget and can even be shared openly with the research community. While generative modeling of high dimensional data like genetic data has been prohibitive, latest developments in deep generative models have shown a series of success stories on a wide range of domains. The project will provide tools for generative modeling of genetic data as well as insights into the long-term perspective of this technology to address open domain problems. The approaches will be validated against existing analysis that are not privacy preserving. We will closely collaborate with the scientific community and propose guidelines how to deploy and experiment with approaches that are practical in the overall process of scientific discovery. This unique project will be the first to allow the generation of synthetic high-dimensional genomic information to boost privacy compliant data sharing in the medical community.

Funding Body

Funding Body

Helmholtz-Gemeinschaft e.V.; Impuls- und Vernetzungsfonds

Partner

Project Partner

Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE)

To solve future grand challenges, data, computational power and analytics expertise need to be brought together at unprecedented scale. The need for data has become even larger in the context of recent advances in machine learning. Therefore, data-centric digital systems commonly exhibit a strong tendency towards centralized structures. While data centralization can greatly facilitate analy-sis, it also comes with several intrinsic disadvantages and threats not only from a technical but more importantly also from a legal, political and ethical perspective. Rooting in sophisticated security or trust requirements, overcoming these issues is cumbersome and time consuming. As a consequence, many research projects are substantially hindered, fail or are simply not addressed. In this interdisci-plinary project we aim at facilitating the implementation of decentralized, cooperative data analytics architectures within and beyond Helmholtz by addressing the most relevant issues in such scenarios.

Trustworthy Federated Data Analytics (TFDA) will facilitate bringing the algorithms to the data in a trustworthy and regulatory compliant way instead of going a data-centric way. TFDA will address the technical, methodical and legal aspects when ensuring trustworthiness of analysis and transparency regarding the analysis in- and outputs without violating privacy constraints. To demonstrate applica-bility and to ensure the adaptability of the methodological concepts, we will validate our develop-ments in the use case “Federated radiation therapy study” (Health) before disseminating the results.

Funding Body

Funding Body

Helmholtz-Gemeinschaft e.V. Impuls- und Vernetzungsfonds

Partner

Project Partner

Deutsches Krebsforschungszentrum (DKFZ)