Ontology-driven generation of parameters for health technology assessment models: a prompt engineering study
International Journal of Technology Assessment in Health Care · 2026 · 42 (1)
DOI: 10.1017/s0266462326103754 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Technology Assessment in Health Care, online erschienen am 16.04.2026. Verfasst von Evelio González-González und 2 weiteren Autor:innen. Beteiligte Einrichtung: Departamento de Ingeniería Informática y de Sistemas, https://ror.org/01r9z8p25Universidad de La Laguna, Spain. Hauptthemen laut MEDLINE: Technology Assessment, Biomedical, Models, Theoretical. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
Objectives
Ontologies support transparent and reproducible conceptual modeling in Health Technology Assessment (HTA), but their population remains resource-intensive and reliant on expert input. This study evaluates the feasibility, reliability, and methodological implications of using generative artificial intelligence (GenAI) to populate ontology individuals for HTA applications.
Methods
A factorial experimental framework was developed using the Ontology for Simulation Modeling (OSDi) and three HTA-relevant use cases of varying complexity. Two GenAI systems were evaluated under multiple experimental conditions, including prompting strategy, serialization format, and provision of supporting information. Generated ontology individuals were validated by an HTA expert and assessed across four quality dimensions: consistency, relevance, completeness, and adequacy. Multivariate and regression analyses were conducted to examine the effects of experimental factors on quality outcomes and hallucination likelihood.
Results
GenAI systems successfully generated ontology individuals across use cases, although performance varied by quality dimension and experimental condition. Iterative prompting significantly improved completeness, while serialization format strongly influenced reliability, with Turtle serialization associated with substantially lower hallucination likelihood compared with XML. Other factors showed dimension-specific effects, highlighting the multidimensional nature of ontology quality. Errors occurred more frequently in structurally complex ontology components, suggesting a relationship between ontological complexity and generative performance.
Conclusions
GenAI-assisted ontology population can enhance the efficiency and scalability of HTA conceptual modeling, enhancing the agility of HTA agencies in exploratory phases. Its effective use requires structured prompting, appropriate representation formats, and expert validation. Further research should evaluate its impact on HTA decision modeling workflows and validation frameworks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Departamento de Ingeniería Informática y de Sistemas, https://ror.org/01r9z8p25Universidad de La Laguna, Spain.
ORCID-Profile: Iván Castilla-Rodríguez, Joel Aday Dorta-Hernández
Zitieren
APA
González-González, E., Castilla-Rodríguez, I., & Dorta-Hernández, J. A. (2026). Ontology-driven generation of parameters for health technology assessment models: a prompt engineering study. International Journal of Technology Assessment in Health Care, 42(1). https://doi.org/10.1017/s0266462326103754
Vancouver
González-González E, Castilla-Rodríguez I, Dorta-Hernández JA. Ontology-driven generation of parameters for health technology assessment models: a prompt engineering study. International Journal of Technology Assessment in Health Care. 2026;42(1). doi:10.1017/s0266462326103754
BibTeX
@article{GonzlezGonzlez2026,
author = {González-González, Evelio and Castilla-Rodríguez, Iván and Dorta-Hernández, Joel Aday},
title = {Ontology-driven generation of parameters for health technology assessment models: a prompt engineering study},
journal = {International Journal of Technology Assessment in Health Care},
year = {2026},
volume = {42},
number = {1},
doi = {10.1017/s0266462326103754}
}
EUVIMED