📝 SummarXiv

Abstract

Objective: Managing patients with respiratory failure increasingly involves non-invasive respiratory support (NIRS) strategies as alternatives to traditional ventilation methods. However, despite the rapidly expanding use of NIRS, there is a significant challenge to its best use under all medical circumstances. It lacks a unified ontological structure, complicating guidance on NIRS modalities across healthcare systems. Our goal is to develop NIRS ontology to support knowledge representation in acute care settings by providing a unified framework that enhances data clarity, interoperability, and clinical decision-making. Methods: We developed the NIRS ontology using Web Ontology Language (OWL) semantics and Protege to organize clinical concepts and relationships. To enable rule-based clinical reasoning beyond hierarchical structures, we added Semantic Web Rule Language (SWRL) rules. We evaluated logical reasoning by adding 17 hypothetical clinical scenarios. We used SPARQL queries to retrieve and test targeted inferences. Results: The ontology has 129 classes, 11 object properties, and 17 data properties across 886 axioms that establish concept relationships. To standardize clinical concepts, we added 361 annotations, including descriptive definitions based on controlled vocabularies. SPARQL queries successfully validated all test cases (rules) by retrieving appropriate patient outcomes: for instance, a patient treated with HFNC (high-flow nasal cannula) for 2 hours due to acute respiratory failure may avoid endotracheal intubation. Conclusion: We developed an ontology that captures NIRS modalities in a unified framework and demonstrated its applicability through the evaluation of hypothetical patient scenarios and alignment with standardized vocabularies, which may need to be expanded to encompass a broader scope.