SBSabrina Blank

Sabrina Blank

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Sabrina Blank has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Towards trustworthy medical AI ecosystems – a proposal for supporting responsible innovation practices in AI-based medical innovation

    by Christian Herzog, Sabrina Blank, Bernd Carsten Stahl

    In this article, we explore questions about the culture of trustworthy artificial intelligence (AI) through the lens of ecosystems. We draw on the European Commission’s Guidelines for Trustworthy AI and its philosophical underpinnings. Based on the latter, the trustworthiness of an AI ecosystem can be conceived of as being grounded by both the so-called rational-choice and motivation-attributing accounts—i.e., trusting is rational because solution providers deliver expected services reliably, while trust also involves resigning control by attributing one’s motivation, and hence, goals, onto another entity. Our research question is: What aspects contribute to a responsible AI ecosystem that can promote justifiable trustworthiness in a healthcare environment? We argue that especially within devising governance and support aspects of a medical AI ecosystem, considering the so-called motivation-attributing account of trust provides fruitful pointers. There can and should be specific ways and governance structures supporting and nurturing trustworthiness beyond mere reliability. After compiling a list of preliminary requirements for this, we describe the emergence of one particular medical AI ecosystem and assess its compliance with and future ways of improving its functioning as a responsible AI ecosystem that promotes trustworthiness.


  • Open Access

    Tailoring responsible research and innovation to the translational context: the case of AI-supported exergaming

    by Sabrina Blank, Celeste Mason, Frank Steinicke, Christian Herzog

    We discuss the implementation of Responsible Research and Innovation (RRI) within a project for the development of an AI-supported exergame for assisted movement training, outline outcomes and reflect on methodological opportunities and limitations. We adopted the responsibility-by-design (RbD) standard (CEN CWA 17796:2021) supplemented by methods for collaborative, ethical reflection to foster and support a shift towards a culture of trustworthiness inherent to the entire development process. An embedded ethicist organised the procedure to instantiate a collaborative learning effort and implement RRI in a translational context. Within the interdisciplinary setting of the collaboration and with the support of a technoethicist, we successfully identified relevant, project-specific challenges and developed a roadmap with derived actions, thus meaningfully integrating RRI into the development process. We discuss the methodological procedure in terms of its effectiveness and efficiency, the allocation of responsibilities and roles, particularly regarding potential frictions in the interdisciplinary context with embedded ethics, and the challenges of the translational context. We conclude that the responsibility-by-design standard effectively established a productive workflow for collaborative investigation and work on ethical challenges. We reflect on methodological difficulties and propose possible avenues to our approach.


  • Open Access

    Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions

    by Eike Petersen, Yannik Potdevin, Esfandiar Mohammadi, Stephan Zidowitz, Sabrina Breyer, Dirk Nowotka, Sandra Henn, Ludwig Pechmann, Martin Leucker, Philipp Rostalski, et al.

    Machine learning is expected to fuel significant improvements in medical care. To ensure that fundamental principles such as beneficence, respect for human autonomy, prevention of harm, justice, privacy, and transparency are respected, medical machine learning systems must be developed responsibly. Many high-level declarations of ethical principles have been put forth for this purpose, but there is a severe lack of technical guidelines explicating the practical consequences for medical machine learning. Similarly, there is currently considerable uncertainty regarding the exact regulatory requirements placed upon medical machine learning systems. This survey provides an overview of the technical and procedural challenges involved in creating medical machine learning systems responsibly and in conformity with existing regulations, as well as possible solutions to address these challenges. First, a brief review of existing regulations affecting medical machine learning is provided, showing that properties such as safety, robustness, reliability, privacy, security, transparency, explainability, and nondiscrimination are all demanded already by existing law and regulations—albeit, in many cases, to an uncertain degree. Next, the key technical obstacles to achieving these desirable properties are discussed, as well as important techniques to overcome these obstacles in the medical context. We notice that distribution shift, spurious correlations, model underspecification, uncertainty quantification, and data scarcity represent severe challenges in the medical context. Promising solution approaches include the use of large and representative datasets and federated learning as a means to that end, the careful exploitation of domain knowledge, the use of inherently transparent models, comprehensive out-of-distribution model testing and verification, as well as algorithmic impact assessments.


  • Assoziation von Zytokinen mit Response und Prognose von Patienten mit Ösophaguskarzinomen

    by L Dreikhausen, S Blank, W Weichert, D Jäger, Mw Büchler, C Falk, K Ott, T Schmidt

    Einleitung: Ösophaguskarzinome sind durch aggressives Wachstum und eine schlechte Prognose gekennzeichnet. Patienten in fortgeschrittenen Stadien erhalten deshalb eine neoadjuvante Therapie. Jedoch sind Patientengruppen, die davon profitieren bisher nicht definiert. Als mögliche Response- und Prognoseprädiktoren geraten das Tumormikroenvironment und zirkulierende Faktoren in den Fokus. Ziel dieser Studie war es, relevante Zytokine in Serum und korrespondierendem Tumorgewebe zu analysieren. Methodik: Von 2007 bis 2012 wurde von 78 Patienten mit Plattenepithelkarzinomen des Ösophagus (SCC) und Karzinomen des gastroösophagealen Übergangs (AEG) nach neoadjuvanter (Radio)Chemotherapie Serum und korrespondierendes Tumorgewebe (n = 54), nur Serum (n = 20) oder nur Tumorgewebe (n = 4) gewonnen. Mittels Multiplex Immunoassays wurden 17 Zytokine analysiert und mit Prognose, klinikopathologischen Faktoren und der Response korreliert. Ergebnis: Das mediane Überleben betrug 28,5 ± 5,8 Monate. Zwischen SCC und AEG bestand kein signifikanter Unterschied in der Überlebenszeit (p = 0,90). 26 waren histopathologische Responder. Dies war grenzwertig prognostisch relevant (p = 0,05). Im Tumorgewebe waren Eotaxin und IP-10 mit der Prognose der Patienten assoziiert (p = 0,022; p = 0,002). Für TGF-β3 zeigte sich ein Trend zu besserer Prognose bei niedrigeren Konzentrationen im Tumorgewebe (p = 0,102). In der Subgruppe der AEG waren niedrigere Konzentrationen an TGF-β3 in Serum und Tumorgewebe mit einer signifikant besseren Prognose assoziiert (p = 0,035; p = 0,006). Eine Assoziation mit der histopathologischen Response wurde für IL-12 (p70) und IP-10 im Serum gefunden (p = 0,041; p = 0,032). Im Tumorgewebe wiesen histopathologische Responder signifikant niedrigere Konzentrationen an TGF-β1 und TGF-β2 auf, ein Trend zeigte sich für TGF-β3 (p = 0,033; p = 0,007; p = 0,097). Schlussfolgerung: Zwei Faktoren im posttherapeutischen Tumorgewebe (Eotaxin und IP-10) sind mit der Prognose von Patienten mit Ösophaguskarzinomen assoziiert. TGF-β scheint vor allem in AEG eine Rolle zu spielen und war in dieser Studie sowohl mit der Prognose als auch der Response assoziiert. Die Ergebnisse sind erfolgsversprechend und sollten prospektiv, optimalerweise sequentiell prä- und posttherapeutisch weiterverfolgt werden.