본문 바로가기
  • Home

A Clinical Decision Support System Using SOM-Based Patient State Clustering and FHIR Ontology Mapping

  • Journal of Internet of Things and Convergence
  • Abbr : JKIOTS
  • 2026, 12(1), pp.175~180
  • Publisher : The Korea Internet of Things Society
  • Research Area : Engineering > Computer Science > Internet Information Processing
  • Received : January 6, 2026
  • Accepted : February 16, 2026
  • Published : February 28, 2026

Guijung Kim 1

1백석대학교

Accredited

ABSTRACT

This paper proposes a clinical decision support system that integrates SOM-based patient state clustering with FHIR ontology mapping using patient data collected in IoT-based healthcare environments. Patient state data exhibit high inter-individual variability and lack clearly defined labels, which limits the applicability of conventional supervised learning approaches. To address this issue, a Self-Organizing Map (SOM) is employed to identify latent patterns in patient states through unsupervised clustering. The resulting clusters are mapped to HL7 FHIR-based ontology structures, enabling clinically interpretable representations of patient states. Through this mapping process, clustering results are transformed from analytical outputs into semantically meaningful information that can be integrated with clinical information systems. Furthermore, patient states are categorized into stable, transitional, risk, and high-risk levels to support clinical decision-making. Case-based evaluation demonstrates that the proposed system can effectively assist in patient state assessment and clinical decision support. The proposed approach provides a meaningful decision support framework that enhances both interpretability and clinical applicability of patient state analysis results. Key Words : Patient State Analysis, Self-Organizing Map, Unsupervised Learni

Citation status

* References for papers published after 2024 are currently being built.