EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

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

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

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260192 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Leonhard Hauptfeld und 4 weiteren Autor:innen. Beteiligte Einrichtung: Medexter Healthcare, Borschkegasse 7/5, 1090 Vienna, Austria. Hauptthemen laut MEDLINE: Decision Support Systems, Clinical, Knowledge Bases, Electronic Health Records. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Decision Support Systems, ClinicalKnowledge BasesElectronic Health RecordsLarge Language ModelsHumans

Stichwörter der Autor:innen

Arden SyntaxArdenSuiteClinical Decision SupportLarge Language Modelsknowledge-basedmulti-modal

Autor:innen und Institutionen

  • Medexter Healthcare, Borschkegasse 7/5, 1090 Vienna, Austria.
  • Medical University of Vienna, Center for Medical Data Science, Institute of Artificial Intelligence, Spitalgasse 23, 1090 Vienna, Austria.
  • TU Wien, Institute for Logic and Computation, 1040 Vienna, Austria.

Zitieren

APA

Hauptfeld, L., Grob, M., Liepold, J., Rappelsberger, A., & Adlassnig, K. P. (2026). Knowledge-Based Interpretation of Multi-Modal Clinical Findings: Evaluating a Local Agentic Bridge Between Worlds. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260192

Vancouver

Hauptfeld L, Grob M, Liepold J, Rappelsberger A, Adlassnig KP. Knowledge-Based Interpretation of Multi-Modal Clinical Findings: Evaluating a Local Agentic Bridge Between Worlds. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260192

BibTeX
@article{Hauptfeld2026,
  author = {Hauptfeld, Leonhard and Grob, Moritz and Liepold, Julia and Rappelsberger, Andrea and Adlassnig, Klaus-Peter},
  title = {Knowledge-Based Interpretation of Multi-Modal Clinical Findings: Evaluating a Local Agentic Bridge Between Worlds},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260192}
}
Kostenlos starten →