Open Access

Background Patient-reported outcomes (PROs) are playing an increasingly important role in the evaluation of treatment success and progression in oncology. As a result, PROs have also found their way into the German Cancer Society’s certification requirements for oncology centers, among other things, with regard to the provision of supportive therapy. Objective A digital ONCOlogical ROUTinE Screening (ONCO-ROUTES) tool was developed at the University Hospital Regensburg (UKR) to assess the need for supportive therapy in a standardized way and to offer patients supportive therapy that is tailored to their needs. Methods Based on already established processes and current requirements, the development and digitization was carried out in connection with the information technology infrastructure of ONCO-ROUTES with the support of experts in focus groups and interviews. Results The ONCO-ROUTES questionnaire was developed from a routine questionnaire on quality of life and needs already in use at the UKR, and includes the following domains: treatment phase, nutrition, tobacco use, alcohol use, quality of life, general condition/functional status, physical activity, psycho-oncology, social services, and further support needs. By linking the digitized questionnaire to the hospital information system, the results are immediately available in routine surgery and, thus, for the referral of patients for further supportive therapy. Conclusion Digital PROs in particular open up a wide range of clinical applications in oncology centers. ONCO-ROUTES is designed to provide supportive interdisciplinary therapy that is tailored to the patients’ needs.

Process mining often yields highly complex “Spaghetti Models”, making them difficult to interpret and impeding informed decision-making. Therefore, researchers have explored clustering of event logs to simplify process models and reduce their complexity. However, the unsupervised nature of clustering can introduce an interpretation gap, necessitating manual effort to identify differences and similarities across the resulting process models. To address these issues, we propose an explainable clustering approach that identifies key subprocesses and applies eXplainable Artificial Intelligence (XAI) techniques to clarify the rationale behind model partitioning. Moreover, we integrate a Large Language Model (LLM) into the process discovery procedure to generate natural language descriptions and compare the discovered process models, enhancing user understanding, engagement, and making complex technical details more accessible. A case study demonstrates that our method operates effectively across various LLMs, preserving vital contextual information while simplifying the process discovery workflow. Our findings reveal that larger models generally ensure completeness, whereas smaller ones offer more efficiency at the expense of explanation quality, highlighting the importance of a balanced LLM choice for practical applications.

The visual representation of log data plays a decisive role in the detection of errors in complex systems. This study uses eye-tracking and user-centered methods to investigate which design features of log visualizations support troubleshooting. Four different visualization variants were tested in a controlled study with 16 participants, whereby both objective (eye movements, recognition times) and subjective (questionnaires) data were collected. The results show that color-highlighted labels and reduced visual distractions can significantly improve error detection - especially in simple search tasks. For more complex tasks such as category-specific error searches, the differences were less clear. In addition, a non-linear search process was confirmed, which takes place in two phases - coarse and fine search. The study provides practical design recommendations for the optimization of log representations

Die Studierendenschaft an Hochschulen ist durch eine hohe Diversität geprägt. Gleichzeitig besteht bei der heterogenen Gruppe der Studierenden die Gemeinsamkeit einer beruflichen Zukunft in einer von Digitalisierung geprägten Arbeitswelt. Im Zusatzstudium Digital Skills der OTH Regensburg werden Studierenden aller Fachrichtungen begleitend zu ihrem regulären Fachstudium sogenannte ›Future Skills‹ vermittelt. Die Interdisziplinarität des Lehrangebots stellt die Lehrenden vor didaktische Chancen und Herausforderungen. Als Antwort auf die studentische Diversität werden im Zusatzstudium die folgenden didaktischen Gestaltungselemente umgesetzt: 1) Blended-Learning-Format 2) Peer-to-Peer-Coaching 3) tutorielles Angebot 4) interdisziplinäre Projektarbeit in der Gruppe.