TY - JOUR A1 - Freitas da Cruz, Harry A1 - Pfahringer, Boris A1 - Martensen, Tom A1 - Schneider, Frederic A1 - Meyer, Alexander A1 - Böttinger, Erwin A1 - Schapranow, Matthieu-Patrick T1 - Using interpretability approaches to update "black-box" clinical prediction models BT - an external validation study in nephrology JF - Artificial intelligence in medicine : AIM N2 - Despite advances in machine learning-based clinical prediction models, only few of such models are actually deployed in clinical contexts. Among other reasons, this is due to a lack of validation studies. In this paper, we present and discuss the validation results of a machine learning model for the prediction of acute kidney injury in cardiac surgery patients initially developed on the MIMIC-III dataset when applied to an external cohort of an American research hospital. To help account for the performance differences observed, we utilized interpretability methods based on feature importance, which allowed experts to scrutinize model behavior both at the global and local level, making it possible to gain further insights into why it did not behave as expected on the validation cohort. The knowledge gleaned upon derivation can be potentially useful to assist model update during validation for more generalizable and simpler models. We argue that interpretability methods should be considered by practitioners as a further tool to help explain performance differences and inform model update in validation studies. KW - Clinical predictive modeling KW - Nephrology KW - Validation KW - Interpretability KW - methods Y1 - 2021 U6 - https://doi.org/10.1016/j.artmed.2020.101982 SN - 0933-3657 SN - 1873-2860 VL - 111 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Borchert, Florian A1 - Mock, Andreas A1 - Tomczak, Aurelie A1 - Hügel, Jonas A1 - Alkarkoukly, Samer A1 - Knurr, Alexander A1 - Volckmar, Anna-Lena A1 - Stenzinger, Albrecht A1 - Schirmacher, Peter A1 - Debus, Jürgen A1 - Jäger, Dirk A1 - Longerich, Thomas A1 - Fröhling, Stefan A1 - Eils, Roland A1 - Bougatf, Nina A1 - Sax, Ulrich A1 - Schapranow, Matthieu-Patrick T1 - Knowledge bases and software support for variant interpretation in precision oncology JF - Briefings in bioinformatics N2 - Precision oncology is a rapidly evolving interdisciplinary medical specialty. Comprehensive cancer panels are becoming increasingly available at pathology departments worldwide, creating the urgent need for scalable cancer variant annotation and molecularly informed treatment recommendations. A wealth of mainly academia-driven knowledge bases calls for software tools supporting the multi-step diagnostic process. We derive a comprehensive list of knowledge bases relevant for variant interpretation by a review of existing literature followed by a survey among medical experts from university hospitals in Germany. In addition, we review cancer variant interpretation tools, which integrate multiple knowledge bases. We categorize the knowledge bases along the diagnostic process in precision oncology and analyze programmatic access options as well as the integration of knowledge bases into software tools. The most commonly used knowledge bases provide good programmatic access options and have been integrated into a range of software tools. For the wider set of knowledge bases, access options vary across different parts of the diagnostic process. Programmatic access is limited for information regarding clinical classifications of variants and for therapy recommendations. The main issue for databases used for biological classification of pathogenic variants and pathway context information is the lack of standardized interfaces. There is no single cancer variant interpretation tool that integrates all identified knowledge bases. Specialized tools are available and need to be further developed for different steps in the diagnostic process. KW - HiGHmed KW - personalized medicine KW - molecular tumor board KW - data integration KW - cancer therapy Y1 - 2021 U6 - https://doi.org/10.1093/bib/bbab134 SN - 1467-5463 SN - 1477-4054 VL - 22 IS - 6 PB - Oxford Univ. Press CY - Oxford ER - TY - THES A1 - Niephaus, Fabio T1 - Exploratory tool-building platforms for polyglot virtual machines N2 - Polyglot programming allows developers to use multiple programming languages within the same software project. While it is common to use more than one language in certain programming domains, developers also apply polyglot programming for other purposes such as to re-use software written in other languages. Although established approaches to polyglot programming come with significant limitations, for example, in terms of performance and tool support, developers still use them to be able to combine languages. Polyglot virtual machines (VMs) such as GraalVM provide a new level of polyglot programming, allowing languages to directly interact with each other. This reduces the amount of glue code needed to combine languages, results in better performance, and enables tools such as debuggers to work across languages. However, only a little research has focused on novel tools that are designed to support developers in building software with polyglot VMs. One reason is that tool-building is often an expensive activity, another one is that polyglot VMs are still a moving target as their use cases and requirements are not yet well understood. In this thesis, we present an approach that builds on existing self-sustaining programming systems such as Squeak/Smalltalk to enable exploratory programming, a practice for exploring and gathering software requirements, and re-use their extensive tool-building capabilities in the context of polyglot VMs. Based on TruffleSqueak, our implementation for the GraalVM, we further present five case studies that demonstrate how our approach helps tool developers to design and build tools for polyglot programming. We further show that TruffleSqueak can also be used by application developers to build and evolve polyglot applications at run-time and by language and runtime developers to understand the dynamic behavior of GraalVM languages and internals. Since our platform allows all these developers to apply polyglot programming, it can further help to better understand the advantages, use cases, requirements, and challenges of polyglot VMs. Moreover, we demonstrate that our approach can also be applied to other polyglot VMs and that insights gained through it are transferable to other programming systems. We conclude that our research on tools for polyglot programming is an important step toward making polyglot VMs more approachable for developers in practice. With good tool support, we believe polyglot VMs can make it much more common for developers to take advantage of multiple languages and their ecosystems when building software. N2 - Durch Polyglottes Programmieren können Softwareentwickler:innen mehrere Programmiersprachen für das Bauen von Software verwenden. Während diese Art von Programmierung in einigen Programmierdomänen üblich ist, wenden Entwickler:innen Polyglottes Programmieren auch aus anderen Gründen an, wie zum Beispiel, um Software über Programmiersprachen hinweg wiederverwenden zu können. Obwohl die bestehenden Ansätze zum Polyglotten Programmieren mit erheblichen Einschränkungen verbunden sind, wie beispielsweise in Bezug zur Laufzeitperformance oder der Unterstützung durch Programmierwerkzeuge, werden sie dennoch von Entwickler:innen genutzt, um Sprachen kombinieren zu können. Mehrsprachige Ausführungsumgebungen wie zum Beispiel GraalVM bieten Polyglottes Programmieren auf einer neuen Ebene an, welche es Sprachen erlaubt, direkt miteinander zu interagieren. Dadurch wird die Menge an notwendigem Glue Code beim Kombinieren von Sprachen reduziert und die Laufzeitperformance verbessert. Außerdem können Debugger und andere Programmierwerkzeuge über mehrere Sprachen hinweg verwendet werden. Jedoch hat sich bisher nur wenig wissenschaftliche Arbeit mit neuartigen Werkzeugen beschäftigt, die darauf ausgelegt sind, Entwickler:innen beim Polyglotten Programmieren mit mehrsprachigen Ausführungsumgebungen zu unterstützen. Ein Grund dafür ist, dass das Bauen von Werkzeugen üblicherweise sehr aufwendig ist. Ein anderer Grund ist, dass sich mehrsprachige Ausführungsumgebungen immer noch ständig weiterentwickeln, da ihre Anwendungsfälle und Anforderungen noch nicht ausreichend verstanden sind. In dieser Arbeit stellen wir einen Ansatz vor, der auf selbsttragenden Programmiersystemen wie zum Beispiel Squeak/Smalltalk aufbaut, um Exploratives Programmieren, eine Praktik zum Explorieren und Erfassen von Softwareanforderungen, sowie das Wiederverwenden ihrer umfangreichen Fähigkeiten zum Bauen von Werkzeugen im Rahmen von mehrsprachigen Ausführungsumgebungen zu ermöglichen. Basierend auf TruffleSqueak, unserer Implementierung für die GraalVM, zeigen wir anhand von fünf Fallstudien, wie unser Ansatz Werkzeugentwickler:innen dabei hilft, neue Werkzeuge zum Polyglotten Programmieren zu entwerfen und zu bauen. Außerdem demonstrieren wir, dass TruffleSqueak auch von Anwendungsentwickler:innen zum Bauen und Erweitern von polyglotten Anwendungen zur Laufzeit genutzt werden kann und Sprach- sowie Laufzeitentwickler:innen dabei hilft, das dynamische Verhalten von GraalVM-Sprachen und -Interna zu verstehen. Da unsere Plattform dabei all diesen Entwickler:innen Polyglottes Programmieren erlaubt, trägt sie außerdem dazu bei, dass Vorteile, Anwendungsfälle, Anforderungen und Herausforderungen von mehrsprachigen Ausführungsumgebungen besser verstanden werden können. Darüber hinaus zeigen wir, dass unser Ansatz auch auf andere mehrsprachige Ausführungsumgebungen angewandt werden kann und dass die Erkenntnisse, die man durch unseren Ansatz gewinnen kann, auch auf andere Programmiersysteme übertragbar sind. Wir schlussfolgern, dass unsere Forschung an Werkzeugen zum Polyglotten Programmieren ein wichtiger Schritt ist, um mehrsprachige Ausführungsumgebungen zugänglicher für Entwickler:innen in der Praxis zu machen. Wir sind davon überzeugt, dass diese Ausführungsumgebungen mit guter Werkzeugunterstützung dazu führen können, dass Softwareentwickler:innen häufiger von den Vorteilen der Verwendung mehrerer Programmiersprachen zum Bauen von Software profitieren wollen. KW - polyglot programming KW - polyglottes Programmieren KW - programming tools KW - Programmierwerkzeuge KW - Smalltalk KW - Smalltalk KW - GraalVM KW - GraalVM KW - virtual machines KW - virtuelle Maschinen Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-571776 ER - TY - GEN A1 - Meythaler, Antonia A1 - Baumann, Annika A1 - Krasnova, Hanna A1 - Hinz, Oliver A1 - Spiekermann, Sarah T1 - Technology for humanity T2 - Business & information systems engineering Y1 - 2023 U6 - https://doi.org/10.1007/s12599-023-00831-w SN - 2363-7005 SN - 1867-0202 VL - 65 IS - 5 SP - 487 EP - 496 PB - Springer Fachmedien CY - Wiesbaden ER - TY - THES A1 - Dehnert, Maik T1 - Studies on the Digital Transformation of Incumbent Organizations T1 - Studien zur Digitalen Transformation traditioneller Organisationen BT - Causes, Effects and Solutions for Banking BT - Ursachen, Wirkungen und Lösungen für das Bankwesen N2 - Traditional organizations are strongly encouraged by emerging digital customer behavior and digital competition to transform their businesses for the digital age. Incumbents are particularly exposed to the field of tension between maintaining and renewing their business model. Banking is one of the industries most affected by digitalization, with a large stream of digital innovations around Fintech. Most research contributions focus on digital innovations, such as Fintech, but there are only a few studies on the related challenges and perspectives of incumbent organizations, such as traditional banks. Against this background, this dissertation examines the specific causes, effects and solutions for traditional banks in digital transformation − an underrepresented research area so far. The first part of the thesis examines how digitalization has changed the latent customer expectations in banking and studies the underlying technological drivers of evolving business-to-consumer (B2C) business models. Online consumer reviews are systematized to identify latent concepts of customer behavior and future decision paths as strategic digitalization effects. Furthermore, the service attribute preferences, the impact of influencing factors and the underlying customer segments are uncovered for checking accounts in a discrete choice experiment. The dissertation contributes here to customer behavior research in digital transformation, moving beyond the technology acceptance model. In addition, the dissertation systematizes value proposition types in the evolving discourse around smart products and services as key drivers of business models and market power in the platform economy. The second part of the thesis focuses on the effects of digital transformation on the strategy development of financial service providers, which are classified along with their firm performance levels. Standard types are derived based on fuzzy-set qualitative comparative analysis (fsQCA), with facade digitalization as one typical standard type for low performing incumbent banks that lack a holistic strategic response to digital transformation. Based on this, the contradictory impact of digitalization measures on key business figures is examined for German savings banks, confirming that the shift towards digital customer interaction was not accompanied by new revenue models diminishing bank profitability. The dissertation further contributes to the discourse on digitalized work designs and the consequences for job perceptions in banking customer advisory. The threefold impact of the IT support perceived in customer interaction on the job satisfaction of customer advisors is disentangled. In the third part of the dissertation, solutions are developed design-oriented for core action areas of digitalized business models, i.e., data and platforms. A consolidated taxonomy for data-driven business models and a future reference model for digital banking have been developed. The impact of the platform economy is demonstrated here using the example of the market entry by Bigtech. The role-based e3-value modeling is extended by meta-roles and role segments and linked to value co-creation mapping in VDML. In this way, the dissertation extends enterprise modeling research on platform ecosystems and value co-creation using the example of banking. N2 - Traditionelle Unternehmen sehen sich angesichts des zunehmend digitalen Kundenverhaltens und gesteigerten digitalen Wettbewerbs damit konfrontiert, ihr Geschäftsmodell adäquat für das digitale Zeitalter weiterzuentwickeln. Insbesondere etablierte Unternehmen befinden sich dabei in einem Spannungsfeld aus Bewahrung und Erneuerung. Der Großteil jüngerer Forschungsbeiträge zum Bankwesen fokussiert sich auf digitale Fintech-Innovationen, nur wenige Studien befassen sich mit Herausforderungen und Perspektiven traditioneller Banken. Vor diesem Hintergrund untersucht die Dissertation die Ursachen und Wirkungen der Digitalen Transformation im Bankwesen und zeigt Lösungswege für traditionelle Banken auf. Der erste Teil der Dissertation untersucht die Ursachen der Digitalen Transformation im Banking. Neuartige Einflussfaktoren und Entscheidungspfade im Kundenverhalten werden als strategische Digitalisierungstreiber für Banken identifiziert. Darauf aufbauend werden in einem Discrete-Choice-Experiment die Präferenzen deutscher Bankkunden hinsichtlich digitaler und nicht-digitaler Dienstleistungsattribute am Beispiel von Girokonten untersucht. Die Arbeit leistet einen über das Technologieakzeptanzmodell hinausgehenden Beitrag zur Erforschung des Kundenverhaltens in der Digitalen Transformation. Ein weiterer Forschungsbeitrag systematisiert anschließend wesentliche Charakteristika smarter Produkte und Dienstleistungen als Treiber von Geschäftsmodellen und Marktmacht in der Plattformökonomie. Der zweite Teil der Arbeit befasst sich zunächst mit den Auswirkungen der Digitalen Transformation auf die Strategieentwicklung von traditionellen Finanzdienstleistern, die mittels Fallstudien entlang ihres Finanzerfolgs typologisiert werden. Die Fassadendigitalisierung wird als Standardtyp traditioneller Anbieter systematisiert, die zwar zunehmend auf digitale Kundeninteraktion setzen, aber die Geschäftsmodelldimension der Digitalen Transformation vernachlässigen. Darauf aufbauend werden in Panelregressionsanalysen die Auswirkungen der Digitalisierung auf deutsche Sparkassen auf betriebswirtschaftliche Kennzahlen untersucht. Eine weitere quantitative Studie untersucht die Wirkungen neuartiger IT-Beratungswerkzeuge auf die Arbeitszufriedenheit von Bankkundenberatern. Die Dissertation leistet hiermit einen Beitrag zur Transformationsforschung in den Bereichen Bankstrategie und Arbeitsprozesse. Im dritten Teil der Dissertation werden gestaltungsorientiert Lösungsartefakte für die zentralen Handlungsfelder digitalisierter Geschäftsmodelle - Daten und Plattformen - entwickelt. Dies schließt einerseits eine konsolidierte Taxonomie für datengetriebene Geschäftsmodelle und andererseits ein Referenzmodell für zukünftige plattformbasierte Bankenökosysteme ein. Die rollenbasierte Referenzmodellierungsmethodik e3-value wird um Meta-Rollen und Rollensegmente erweitert, um die die strategischen Auswirkungen plattformbasierter Geschäftsmodelle aufzuzeigen. Hiermit erweitert die Dissertation die Unternehmensmodellierungsforschung im Bereich digitaler Plattform-Ökosysteme am Beispiel des Bankwesens. KW - digital transformation KW - digitalization KW - digital strategy KW - consumer behavior KW - platform ecosystems KW - value co-creation KW - Fintech KW - incumbent KW - bank KW - Digitale Transformation KW - Digitalisierung KW - Digitalstrategie KW - Kundenverhalten KW - Plattform-Ökosysteme KW - Wertschöpfungskooperation KW - Fintech KW - traditionelle Unternehmen KW - Bank Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-548324 ER - TY - GEN A1 - Krasnova, Hanna T1 - Interview with Christoph Neuberger on “How digital technologies are shaping our society and what we can do about it” T2 - Business & information systems engineering Y1 - 2023 U6 - https://doi.org/10.1007/s12599-023-00832-9 SN - 2363-7005 SN - 1867-0202 VL - 65 IS - 5 SP - 609 EP - 611 PB - Springer Fachmedien CY - Wiesbaden ER - TY - CHAP A1 - Gonnermann-Müller, Jana A1 - Teichmann, Malte ED - Davis, Fred D. ED - Riedl, René ED - vom Brocke, Jan ED - Léger, Pierre-Majorique ED - Randolph, Adriane B. ED - Müller-Putz, Gernot R. T1 - Examining the learner’s cognitive load in response to different learning material in high and low immersive virtual learning environments BT - an eye-tracking study T2 - Information systems and neuroscience N2 - Learning in virtual, immersive environments must be well-designed to foster learning instead of overwhelming and distracting the learner. So far, learning instructions based on cognitive load theory recommend keeping the learning instructions clean and simple to reduce the extraneous cognitive load of the learner to foster learning performance. The advantages of immersive learning, such as multiple options for realistic simulation, movement and feedback, raise questions about the tension between an increase of excitement and flow with highly realistic environments on the one hand and a reduction of cognitive load by developing clean and simple surroundings on the other hand. This study aims to gain insights into learners' cognitive responses during the learning process by continuously assessing cognitive load through eye-tracking. The experiment compares two distinct immersive learning environments and varying methods of content presentation. Y1 - 2024 SN - 978-3-031-58395-7 SN - 978-3-031-58396-4 U6 - https://doi.org/10.1007/978-3-031-58396-4_29 VL - 68 SP - 333 EP - 344 PB - Springer CY - Cham ER - TY - JOUR A1 - Baum, Katharina A1 - Baumann, Annika A1 - Batzel, Katharina T1 - Investigating innovation diffusion in gender-specific medicine BT - insights from social network analysis JF - Business & information systems engineering N2 - The field of healthcare is characterized by constant innovation, with gender-specific medicine emerging as a new subfield that addresses sex and gender disparities in clinical manifestations, outcomes, treatment, and prevention of disease. Despite its importance, the adoption of gender-specific medicine remains understudied, posing potential risks to patient outcomes due to a lack of awareness of the topic. Building on the Innovation Decision Process Theory, this study examines the spread of information about gender-specific medicine in online networks. The study applies social network analysis to a Twitter dataset reflecting online discussions about the topic to gain insights into its adoption by health professionals and patients online. Results show that the network has a community structure with limited information exchange between sub-communities and that mainly medical experts dominate the discussion. The findings suggest that the adoption of gender-specific medicine might be in its early stages, focused on knowledge exchange. Understanding the diffusion of gender-specific medicine among medical professionals and patients may facilitate its adoption and ultimately improve health outcomes. KW - health data KW - gender-specific medicine KW - social network analysis KW - diffusion of innovations KW - Twitter Y1 - 2024 U6 - https://doi.org/10.1007/s12599-024-00875-6 SN - 2363-7005 SN - 1867-0202 VL - 66 IS - 3 SP - 335 EP - 355 PB - Springer Fachmedien CY - Wiesbaden ER - TY - JOUR A1 - Abramova, Olga A1 - Gladkaya, Margarita T1 - Behind videoconferencing fatigue at work JF - Business & information systems engineering N2 - A remarkable peculiarity of videoconferencing (VC) applications – the self-view – a.k.a. digital mirror, is examined as a potential reason behind the voiced exhaustion among users. This work draws on technostress research and objective self-awareness theory and proposes the communication role (sender vs. receiver) as an interaction variable. We report the results of two studies among European employees (n1 = 176, n2 = 253) with a one-year time lag. A higher frequency of self-view in a VC when receiving a message, i.e., listening to others, indirectly increases negative affect (study 1 & 2) and exhaustion (study 2) via the increased state of public self-awareness. Self-viewing in the role of message sender, e.g., as an online presenter, also increases public self-awareness, but its overall effects are less harmful. As for individual differences, users predisposed to public self-consciousness were more concerned with how other VC participants perceived them. Gender effects were insignificant. KW - videoconferencing KW - self-view KW - Zoom fatigue KW - emote work KW - technostress KW - self-awareness Y1 - 2024 U6 - https://doi.org/10.1007/s12599-024-00874-7 SN - 2363-7005 SN - 1867-0202 PB - Springer Fachmedien CY - Wiesbaden ER - TY - CHAP A1 - Grum, Marcus ED - Shishkov, Boris T1 - Researching multi-site artificial neural networks’ activation rates and activation cycles T2 - Business modeling and software design : 14th International Symposium, BMSD 2024, Luxembourg City, Luxembourg, July 1–3, 2024, proceedings N2 - With the further development of more and more production machines into cyber-physical systems, and their greater integration with artificial intelligence (AI) techniques, the coordination of intelligent systems is a highly relevant target factor for the operation and improvement of networked processes, such as they can be found in cross-organizational production contexts spanning multiple distributed locations. This work aims to extend prior research on managing their artificial knowledge transfers as coordination instrument by examining effects of different activation types (respective activation rates and cycles) on by Artificial Neural Network (ANN)-instructed production machines. For this, it provides a new integration type of ANN-based cyber-physical production system as a tool to research artificial knowledge transfers: In a design-science-oriented way, a prototype of a simulation system is constructed as Open Source information system which will be used in on-building research to (I) enable research on ANN activation types in production networks, (II) illustrate ANN-based production networks disrupted by activation types and clarify the need for harmonizing them, and (III) demonstrate conceptual management interventions. This simulator shall establish the importance of site-specific coordination mechanisms and novel forms of management interventions as drivers of efficient artificial knowledge transfer. Y1 - 2024 SN - 978-3-031-64072-8 SN - 978-3-031-64073-5 U6 - https://doi.org/10.1007/978-3-031-64073-5_12 SP - 186 EP - 206 PB - Springer CY - Cham ER -