NIRS Ontology: Clinical Concepts for Non-Invasive Respiratory Support

Md Fantacher Islam developed the NIRS Ontology, a formal knowledge representation for non-invasive respiratory support in acute care. The ontology contains 145 classes, 11 object properties, and 18 data properties across 949 axioms, with 392 annotations for concept standardization. It was evaluated in May 2026 using SPARQL queries on 6 patient scenarios to validate rule-based clinical reasoning.

Use Cases

• Supporting rule-based clinical reasoning for therapy recommendations based on the included Semantic Web Rule Language (SWRL) rules.
• Enhancing data clarity and interoperability for NIRS documentation practices based on the unified ontological structure.
• Querying patient outcomes and therapy parameters using SPARQL based on the formal representation of ventilation modalities and patient characteristics.
• Laying groundwork for EHR integration and advanced outcome analysis based on the ontology's standardized clinical concepts.

Strengths

• Formally structured with 949 axioms defining concept relationships.
• Includes 392 annotations for descriptive definitions based on controlled vocabularies.
• Successfully validated with SPARQL queries across 6 test patient scenarios.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating a limited, proof-of-concept scope.

Provenance

Source

Md Fantacher Islam via figshare.

Collection Method

Developed using Web Ontology Language (OWL) and Protégé, with added SWRL rules for reasoning.

Time Range

Proof-of-concept evaluation date implied as 2026.

Freshness

Last updated 2026-05-04 17:39:25; freshness should be verified.

Geography

null