The University of Maribor

Institution information

The University of Maribor’s Faculty of Health Sciences (UM FHS), based in Maribor, Slovenia, provides education and conducts research in nursing and health sciences. Research activities are coordinated through its Research Institute and Institute for Nursing Care, with staff actively involved in national and international projects and scientific publishing.

Work in SynHealth

UM’s role in the project is to design and implement advanced AI-based solutions that support the interpretation and use of scientific and clinical evidence in healthcare. This includes validating the developed tools with healthcare professionals and delivering tailored, evidence-based outputs to support decision-making and personalized advice.

Researchers involved

Gregor Štiglic
Gregor Štiglic
Primož Kocbek
Primož Kocbek
Adrijana Svenšek
Adrijana Svenšek
Lucija Gosak
Lucija Gosak
Leon Kopitar
Leon Kopitar

Host Institutions / Labs

Past Publications

  • Svenšek, Adrijana, et al. "The role of visualization in estimating cardiovascular disease risk: scoping review." JMIR public health and surveillance 10.1 (2024): e60128.
  • Kopitar, L., Bedrač, L., Strath, L. J., Bian, J., & Stiglic, G. (2025). Improving Personalized Meal Planning with Large Language Models: Identifying and Decomposing Compound Ingredients. Nutrients, 17(9), 1492.
  • Kopitar, L., & Stiglic, G. (2025). LLM in Personalized Health: Automating HEI Scoring. In MEDINFO 2025—Healthcare Smart× Medicine Deep (pp. 1784-1785). IOS Press.
  • Kocbek P, Kopitar L, Stiglic G. Plain Language Adaptations of Biomedical Text Using LLMs: Comparision of Evaluation Metrics. In Proceedings of the MEDINFO 2025—Healthcare Smart× Medicine Deep (pp. 779-783). IOS Press. doi: 10.3233/SHTI250946.
  • Kocbek P, Kopitar L, Zhang Z, Aydın E, Topaz M, Stiglic G. UM_FHS at TREC 2024 PLABA: Exploration of Fine-tuning and AI agent approach for plain language adaptations of biomedical text. In Proceedings of the Thirty-Third Text REtrieval Conference (TREC) 2024. NIST.
  • Kocbek P, Stiglic G. UM_FHS at the CLEF 2025 SimpleText Track: Comparing No-Context and Fine-Tune Approaches for GPT-4.1 Models in Sentence and Document-Level Text Simplification. In Working Notes of the Conference and Labs of the Evaluation Forum (CLEF) 2025 (pp.

Past Financed Projects