ARAndrea Rappelsberger

Andrea Rappelsberger

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Andrea Rappelsberger has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Ask Not What Your Server Can Do For You: A Fast Query Compatibility Strategy for Navigating FHIR Implementation Gaps

    by Leonhard Hauptfeld, Andreas Csarmann, Moritz Grob, Julia Liepold, Andrea Rappelsberger, Klaus-Peter Adlassnig

    The Fast Healthcare Interoperability Resources (FHIR) standard aims to improve clinical data interoperability, but real-world implementations often fall short of full compliance, creating significant deployment hurdles. A tiered compatibility strategy for Momo, a clinical microbiology software, is presented to circumvent these server-side limitations. The strategy utilizes an adaptive query framework featuring three search resolvers (Basic, Advanced, and Full) tailored to a target server’s specific capabilities. This approach was evaluated during a pilot integration with an institution’s severely restricted FHIR server. Despite missing resources and minimal query parameters, the adaptive framework enabled successful operational deployment in just two weeks, requiring only 52 person-hours of custom development and minimal institutional coordination. Integration time can be effectively reduced through this approach, though restrictions in system functionality show that availability of search parameters remains essential.

  • Open Access

    Auto Ontology: Towards Automated Term-to-Concept Assignment in Microbiology Analytics

    by Moritz Grob, Leonhard Hauptfeld, Julia Liepold, Jakob Kainz, Andreas Csarmann, Daniel Rodrigues, Andrea Rappelsberger, Klaus-Peter Adlassnig

    Maintaining clinical ontologies requires continuous addition of new synonyms from laboratory information systems, which is currently a manual and time-consuming process. This study evaluates whether text embedding models can support semi-automated synonym-to-concept mapping for ontology maintenance. Using the Momo microbiology ontology, we indexed term embeddings locally with Qdrant and compared semantic similarity for assigning unseen terms to known concepts. Performance was assessed using Top-k recall, Mean Reciprocal Rank, and F1-score. Results show that dense embeddings, particularly BioLORD-2023-M (Top-1 recall = 0.68, F1 = 0.67), can retrieve relevant concept suggestions with sufficient accuracy for human-validated workflows, albeit not yet for automatic assignment. This approach demonstrates the potential of embedding-based semantic retrieval for supporting practical ontology curation in resource-constrained clinical settings.

  • Open Access

    Automated Differential Time to Positivity Analysis for CRBSIs Using Historical Microbiological Data

    by Julia Liepold, Leonhard Hauptfeld, Moritz Grob, Andreas Csarmann, Andrea Rappelsberger, Klaus-Peter Adlassnig

    Catheter-related bloodstream infections (CRBSIs) are often difficult to diagnose due to the variability of pathogen sources and inconsistencies in laboratory data. Differential time to positivity (DTP) offers a means to distinguish CRBSIs from secondary bacteremia, but its practical application is complicated by heterogeneous nomenclature and variable reporting formats. We implemented an algorithm that standardizes microbiological records using a custom ontology-driven framework and applies clinically established thresholds. A fuzzy matching approach was then used to classify infections as likely catheter-related, unlikely, or non-diagnostic. This proof-of-concept validates the feasibility of automated DTP analysis and highlights the potential of semantic technologies to support clinical decision-making.

  • Open Access

    Knowledge-Based Interpretation of Multi-Modal Clinical Findings: Evaluating a Local Agentic Bridge Between Worlds

    by Leonhard Hauptfeld, Moritz Grob, Julia Liepold, Andrea Rappelsberger, Klaus-Peter Adlassnig

    Contemporary clinical practice still produces unstructured data like free-text reports or scans, hindering automated interpretation by knowledge-based clinical decision support (CDS) systems that rely on structured data. Large language models (LLMs) show potential for interpreting such findings but face challenges in accuracy, infrastructure demands, and data privacy. Integrating LLMs with modular knowledge-based CDS systems could provide validated interpretations of such findings, but models need to call CDS modules with perfectly accurate parameters. The accuracy of multiple size classes of LLMs calling Arden Syntax Medical Logic Modules for hepatitis serology interpretation of varying complexity from unstructured multi-modal inputs is tested using a novel framework. Computationally lean LLMs like GPT-OSS were found to handle a small amount of low-complexity parameters with high accuracy, approaching clinical feasibility for private and reliable CDS interpretation of multi-modal data. Accuracy decreased sharply for tools involving more numerous or complex quantitative parameters.

  • Open Access

    Fine-Tuning an Existing Large Language Model with Knowledge from the Medical Expert System Hepaxpert

    by Jakob Kainz, Philipp Seisl, Moritz Grob, Leonhard Hauptfeld, Jonas Wahringer, Andrea Rappelsberger, Klaus-Peter Adlassnig

    The analysis and individual interpretation of hepatitis serology test results is a complex task in laboratory medicine, requiring either experienced physicians or specialized expert systems. This study explores fine-tuning a large language model (LLM) for hepatitis serology interpretation using a single graphics processing unit (GPU). A custom dataset based on the Hepaxpert expert system was used to train the LLM. Fine-tuning was performed on an Nvidia RTX 6000 Ada GPU via torchtune. The fine-tuned LLM showed significant performance improvements over the base model when compared to Hepaxpert using the METEOR algorithm. The findings highlight the potential of LLMs in enhancing medical expert systems as well as the significance of domain-specific fine-tuning.


  • Open Access

    Standards-Based Interoperability for Clinical Decision Support Systems

    by Moritz Grob, Leonhard Hauptfeld, Andrea Rappelsberger, Klaus-Peter Adlassnig

    This paper presents a narrative analysis of standards-based interoperability approaches in clinical decision support systems, focusing on the ArdenSuite platform. We examine how both semantic and technical interoperability challenges are addressed through its modular architecture and support for multiple healthcare standards including HL7’s Arden Syntax, FHIR, openEHR, and CDS Hooks. The platform’s implementation at University Hospital Vienna demonstrates practical applications in automated guideline processing and pandemic alert services. Our findings suggest that standards-based interoperability solutions can effectively bridge the gap between disparate healthcare systems while enabling sophisticated clinical decision support capabilities. The approach presented offers insights for addressing the growing challenge of healthcare system fragmentation in an increasingly digitalized medical landscape.


  • Open Access

    FHIR-Based Arden Syntax Compiler for Clinical Decision Support

    by Christian Weich, Moritz Grob, Andrea Rappelsberger, Klaus-Peter Adlassnig

    The Arden Syntax is a language designed for the encoding of medical knowledge into clinical decision support systems. Its evolution is overseen by Health Level 7. A significant enhancement in its new version 3.0 is the incorporation of FHIR for data retrieval, which addresses the long-standing curly braces problem. We introduce a newly developed compiler for Arden Syntax 3.0, which employs modern tools such as ANTLR for lexical and parsing analysis and GraalVM with the Truffle Language Implementation Framework for semantic processing, optimization, and language execution. Comprehensive testing against a legacy compiler revealed substantial improvements in execution speed, memory efficiency, and code quality. These advancements, coupled with superior maintainability and extensibility, position the Truffle compiler as a robust replacement, supporting future development and enhancing the user experience with Arden-Syntax-based clinical decision support.


  • Open Access

    Enhancing Arden-Syntax-Based Clinical Reasoning with Ontologies

    by Moritz Grob, Jakob Kainz, Andreas Csarmann, Andrea Rappelsberger, Klaus-Peter Adlassnig

    We present a new methodological approach based on integrating Arden-Syntax-based clinical decision support (CDS) with an upstream ontology service. Incoming linguistic patient data, such as single reports about detected germs or viruses, shall be identified by the applied ontology at a low level. Then, higher-level concepts are activated by ontology-based bottom-up reasoning. Access to these high-level concepts is then provided by Arden-Syntax-based CDS. The results suggest promising directions for future enhancements in knowledge-based artificial intelligence.

  • Open Access

    Integrated Perspectives on Clinical Decision Support: A Comparative Analysis of Knowledge Management Approaches

    by Moritz Grob, Robert A. Jenders, Andrea Rappelsberger, Klaus-Peter Adlassnig

    We analyze five approaches to knowledge management in clinical decision support (CDS) systems: pattern recognition based on annotated imaging data, mining of stored structured medical data, text mining of published texts, computable knowledge design, and general or specific text corpora for large language models. Each method’s strengths and limitations in automating clinical knowledge management while striving for a zero-error policy are evaluated, offering insights into their roles in enhancing healthcare through intelligent decision support. The study aims to inform decisions in the development of effective, transparent CDS systems in clinical and patient care settings.


  • Open Access

    A Microbiology Analytics Tool to Evaluate the Burden of Antibiotic-Resistant Infections

    by Moritz Grob, Christian Watzinger, Birgit Willinger, Florian Thalhammer, Walter Koller, Andrea Rappelsberger, Klaus-Peter Adlassnig

    Leveraging the capabilities of a microbiological clinical analytics tool, this study delves into quantifying the public health impact of antibiotic-resistant bacteria. Focusing on eight predominant antibiotic-resistant bacteria, the study utilizes University Hospital Vienna’s data to calculate the burden of antibiotic-resistant infections in disability-adjusted life years. The results highlight the potential of extended analytics tools in epidemiological research and underscore the pressing challenge of antimicrobial drug resistance.