Developing a modular architecture for creation of rule-based clinical diagnostic criteria

Na Hong, Guoqian Jiang, Jyotishman Pathak, Christopher G. Chute

Research output: Contribution to journalConference articlepeer-review


With recent advances in computerized patient records system, there is an urgent need for producing computable and standards-based clinical diag-nostic criteria. For example, constructing rule-based clinical diagnosis criteria has become one of the goals in the International Classification of Diseases (ICD)-11 revision. However, few studies have been done in building a unified architecture to support the need for diagnostic criteria computerization. In this study, we present a modular architecture for creation of rule-based clinical di-agnostic criteria leveraging Semantic Web technologies. The architecture con-sists of two major modules: one is an authoring module that utilizes a standards-based information model and the other is a translation module that utilizes Se-mantic Web Rule Language (SWRL). In a prototype implementation, for the authoring module, we developed a diagnostic criteria upper ontology that inte-grates ICD-11 content model with Quality Data Model (QDM); for the transla-tion module, we developed a transformation tool that converts QDM-based di-agnostic criteria into Semantic Web Rule Language (SWRL) representation. We evaluated the domain coverage of the upper ontology model by annotating 20 randomly selected diagnostic criteria. We also tested the transformation al-gorithms using 6 QDM templates for ontology population and 15 QDM-based criteria data for rule generation. In summary, our efforts in developing and pro-totyping a modular architecture provide useful insights into building a scalable solution to support diagnostic criteria representation and computerization.


  • Diagnostic criteria
  • ICD-11
  • Ontology
  • QDM
  • SWRL

ASJC Scopus subject areas

  • Computer Science(all)


Dive into the research topics of 'Developing a modular architecture for creation of rule-based clinical diagnostic criteria'. Together they form a unique fingerprint.

Cite this