TY - JOUR A1 - Herm, Lukas-Valentin A1 - Steinbach, Theresa A1 - Wanner, Jonas A1 - Janiesch, Christian T1 - A nascent design theory for explainable intelligent systems JF - Electronic Markets N2 - Due to computational advances in the past decades, so-called intelligent systems can learn from increasingly complex data, analyze situations, and support users in their decision-making to address them. However, in practice, the complexity of these intelligent systems renders the user hardly able to comprehend the inherent decision logic of the underlying machine learning model. As a result, the adoption of this technology, especially for high-stake scenarios, is hampered. In this context, explainable artificial intelligence offers numerous starting points for making the inherent logic explainable to people. While research manifests the necessity for incorporating explainable artificial intelligence into intelligent systems, there is still a lack of knowledge about how to socio-technically design these systems to address acceptance barriers among different user groups. In response, we have derived and evaluated a nascent design theory for explainable intelligent systems based on a structured literature review, two qualitative expert studies, a real-world use case application, and quantitative research. Our design theory includes design requirements, design principles, and design features covering the topics of global explainability, local explainability, personalized interface design, as well as psychological/emotional factors. KW - artificial intelligence KW - explainable artificial intelligence KW - XAI KW - design science research KW - design theory KW - intelligent systems Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-323809 SN - 1019-6781 VL - 32 IS - 4 ER - TY - THES A1 - Wanner, Jonas Paul T1 - Artificial Intelligence for Human Decision-Makers: Systematization, Perception, and Adoption of Intelligent Decision Support Systems in Industry 4.0 T1 - Künstliche Intelligenz für menschliche Entscheidungsträger: Systematisierung, Wahrnehmung und Akzeptanz von intelligenten Entscheidungsunterstützungssystemen im Kontext der Industrie 4.0 N2 - Innovative possibilities for data collection, networking, and evaluation are unleashing previously untapped potential for industrial production. However, harnessing this potential also requires a change in the way we work. In addition to expanded automation, human-machine cooperation is becoming more important: The machine achieves a reduction in complexity for humans through artificial intelligence. In fractions of a second large amounts of data of high decision quality are analyzed and suggestions are offered. The human being, for this part, usually makes the ultimate decision. He validates the machine’s suggestions and, if necessary, (physically) executes them. Both entities are highly dependent on each other to accomplish the task in the best possible way. Therefore, it seems particularly important to understand to what extent such cooperation can be effective. Current developments in the field of artificial intelligence show that research in this area is particularly focused on neural network approaches. These are considered to be highly powerful but have the disadvantage of lacking transparency. Their inherent computational processes and the respective result reasoning remain opaque to humans. Some researchers assume that human users might therefore reject the system’s suggestions. The research domain of explainable artificial intelligence (XAI) addresses this problem and tries to develop methods to realize systems that are highly efficient and explainable. This work is intended to provide further insights relevant to the defined goal of XAI. For this purpose, artifacts are developed that represent research achievements regarding the systematization, perception, and adoption of artificially intelligent decision support systems from a user perspective. The focus is on socio-technical insights with the aim to better understand which factors are important for effective human-machine cooperation. The elaborations predominantly represent extended grounded research. Thus, the artifacts imply an extension of knowledge in order to develop and/ or test effective XAI methods and techniques based on this knowledge. Industry 4.0, with a focus on maintenance, is used as the context for this development. N2 - Durch innovative Möglichkeiten der Datenerhebung, Vernetzung und Auswertung werden Potenziale für die Produktion freigesetzt, die bisher ungenutzt sind. Dies bedingt jedoch eine Veränderung der Arbeitsweise. Neben einer erweiterten Automatisierung wird die Mensch-Maschinen-Kooperation wichtiger: Die Maschine erreicht durch Künstliche Intelligenz eine Komplexitätsreduktion für den Menschen. In Sekundenbruchteilen werden Vorschläge aus großen Datenmengen von hoher Entscheidungsqualität geboten, während der Mensch i.d.R. die Entscheidung trifft und diese ggf. (physisch) ausführt. Beide Instanzen sind stark voneinander abhängig, um eine bestmögliche Aufgabenbewältigung zu erreichen. Es scheint daher insbesondere wichtig zu verstehen, inwiefern eine solche Kooperation effektiv werden kann. Aktuelle Entwicklungen auf dem Gebiet der Künstlichen Intelligenz zeigen, dass die Forschung hierzu insbesondere auf Ansätze Neuronaler Netze fokussiert ist. Diese gelten als hoch leistungsfähig, haben aber den Nachteil einer fehlenden Nachvollziehbarkeit. Ihre inhärenten Berechnungsvorgänge und die jeweilige Ergebnisfindung bleiben für den Menschen undurchsichtig. Einige Forscher gehen davon aus, dass menschliche Nutzer daher die Systemvorschläge ablehnen könnten. Die Forschungsdomäne erklärbare Künstlichen Intelligenz (XAI) nimmt sich der Problemstellung an und versucht Methoden zu entwickeln, um Systeme zu realisieren die hoch-leistungsfähig und erklärbar sind. Diese Arbeit soll weitere Erkenntnisse für das definierte Ziel der XAI liefern. Dafür werden Artefakte entwickelt, welche Forschungsleistungen hinsichtlich der Systematisierung, Wahrnehmung und Adoption künstlich intelligenter Entscheidungsunterstützungssysteme aus Anwendersicht darstellen. Der Fokus liegt auf sozio-technischen Erkenntnissen. Es soll besser verstanden werden, welche Faktoren für eine effektive Mensch-Maschinen-Kooperation wichtig sind. Die Erarbeitungen repräsentieren überwiegend erweiterte Grundlagenforschung. Damit implizieren die Artefakte eine Erweiterung des Wissens, um darauf aufbauend effektive XAI-Methoden und -Techniken zu entwickeln und/ oder zu erproben. Als Kontext der eigenen Erarbeitung wird die Industrie 4.0 mit Schwerpunkt Instandhaltung genutzt. KW - Künstliche Intelligenz KW - Entscheidungsunterstützungssystem KW - Industrie 4.0 KW - Explainable AI KW - Erklärbare Künstliche Intelligenz KW - Artificial Intelligence KW - Industry 4.0 KW - Decision Support Systems Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-259014 ER - TY - JOUR A1 - Köping, Maria A1 - Shehata-Dieler, Wafaa A1 - Cebulla, Mario A1 - Rak, Kristen A1 - Oder, Daniel A1 - Müntze, Jonas A1 - Nordbeck, Peter A1 - Wanner, Christoph A1 - Hagen, Rudolf A1 - Schraven, Sebastian T1 - Cardiac and renal dysfunction is associated with progressive hearing loss in patients with Fabry disease JF - PLoS ONE N2 - Background Fabry disease (FD) is an X-linked recessive hereditary lysosomal storage disorder which results in the accumulation of globotriaosylceramid (Gb3) in tissues of kidney and heart as well as central and peripheral nervous system. Besides prominent renal and cardiac organ involvement, cochlear symptoms like high-frequency hearing loss and tinnitus are frequently found with yet no comprehensive data available in the literature. Objective To examine hearing loss in patients with FD depending on cardiac and renal function. Material and methods Single-center study with 68 FD patients enrolled between 2012 and 2016 at the Department of Oto-Rhino-Laryngology, Plastic, Aesthetic and Reconstructive Head and Neck Surgery of the University of Würzburg. Every subject underwent an oto-rhino-laryngological examination as well as behavioral, electrophysiological and electroacoustical audiological testing. High-frequency thresholds were evaluated by using a modified PTA\(_{6}\) (0.5, 1, 2, 4, 6, 8) and HF-PTA (6, 8 kHz). Renal function was measured by eGFR, cardiac impairment was graduated by NYHA class. Results Sensorineural hearing loss was detected in 58.8% of the cohort, which occurred typically in sudden episodes and affected especially high frequencies. Hearing loss is asymmetric, beginning unilaterally and affecting the contralateral ear later. Tinnitus was reported by 41.2%. Renal and cardiac impairment influenced the severity of hearing loss (p < 0.05). Conclusions High frequency hearing loss is a common problem in patients with FD. Although not life-threatening, it can seriously reduce quality of life and should be taken into account in diagnosis and therapy. Optimized extensive hearing assessment including higher frequency thresholds should be used. KW - cardiac dysfunction KW - renal dysfunction KW - Fabry disease KW - hearing loss Y1 - 2017 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-169961 VL - 12 IS - 11 ER - TY - JOUR A1 - Köping, Maria A1 - Shehata-Dieler, Wafaa A1 - Schneider, Dieter A1 - Cebulla, Mario A1 - Oder, Daniel A1 - Müntze, Jonas A1 - Nordbeck, Peter A1 - Wanner, Christoph A1 - Hagen, Rudolf A1 - Schraven, Sebastian P. T1 - Characterization of vertigo and hearing loss in patients with Fabry disease JF - Orphanet Journal of Rare Diseases N2 - Background Fabry Disease (FD) is an X-linked hereditary lysosomal storage disorder which leads to a multisystemic intralysosomal accumulation of globotriaosylceramid (Gb3). Besides prominent renal and cardiac organ involvement, patients commonly complain about vestibulocochlear symptoms like high-frequency hearing loss, tinnitus and vertigo. However, comprehensive data especially on vertigo remain scarce. The aim of this study was to examine the prevalence and characteristics of vertigo and hearing loss in patients with FD, depending on renal and cardiac parameters and get hints about the site and the pattern of the lesions. Methods Single-center study with 57 FD patients. Every patient underwent an oto-rhino-laryngological examination as well as videonystagmography and vestibular evoked myogenic potentials (VEMPs) and audiological measurements using pure tone audiometry and auditory brainstem response audiometry (ABR). Renal function was measured by eGFR, cardiac impairment was graduated by NYHA class. Results More than one out of three patients (35.1%) complained about hearing loss, 54.4% about vertigo and 28.1% about both symptom. In 74% a sensorineural hearing loss of at least 25 dB was found, ABR could exclude any retrocochlear lesion. Caloric testing showed abnormal values in 71.9%, VEMPs were pathological in 68%. A correlation between the side or the shape of hearing loss and pathological vestibular testing could not be revealed. Conclusions Hearing loss and vertigo show a high prevalence in FD. While hearing loss seems due to a cochlear lesion, peripheral vestibular as well as central nervous pathologies cause vertigo. Thus, both the site of lesion and the pathophysiological patterns seem to differ. KW - Fabry disease KW - vertigo KW - VEMP KW - cardiomyopathy KW - chronic kidney disease KW - lysosomal storage disorder Y1 - 2018 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-222818 VL - 13 ER - TY - JOUR A1 - Wanner, Jonas A1 - Herm, Lukas-Valentin A1 - Heinrich, Kai A1 - Janiesch, Christian T1 - The effect of transparency and trust on intelligent system acceptance: evidence from a user-based study JF - Electronic Markets N2 - Contemporary decision support systems are increasingly relying on artificial intelligence technology such as machine learning algorithms to form intelligent systems. These systems have human-like decision capacity for selected applications based on a decision rationale which cannot be looked-up conveniently and constitutes a black box. As a consequence, acceptance by end-users remains somewhat hesitant. While lacking transparency has been said to hinder trust and enforce aversion towards these systems, studies that connect user trust to transparency and subsequently acceptance are scarce. In response, our research is concerned with the development of a theoretical model that explains end-user acceptance of intelligent systems. We utilize the unified theory of acceptance and use in information technology as well as explanation theory and related theories on initial trust and user trust in information systems. The proposed model is tested in an industrial maintenance workplace scenario using maintenance experts as participants to represent the user group. Results show that acceptance is performance-driven at first sight. However, transparency plays an important indirect role in regulating trust and the perception of performance. KW - user acceptance KW - intelligent system KW - artificial intelligence KW - trust KW - system transparency Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-323829 SN - 1019-6781 VL - 32 IS - 4 ER -