Development and Evaluation of an Ontology for Non-Invasive Respiratory Support in Acute Care

Jarrod Mosier; Md Fantacher Islam; Vignesh Subbian

arxiv: 2507.19992 · v4 · submitted 2025-07-26 · 🧬 q-bio.OT · cs.AI

Development and Evaluation of an Ontology for Non-Invasive Respiratory Support in Acute Care

Md Fantacher Islam , Jarrod Mosier , Vignesh Subbian This is my paper

Pith reviewed 2026-05-19 03:20 UTC · model grok-4.3

classification 🧬 q-bio.OT cs.AI

keywords noninvasive respiratory supportontologyOWLacute careSWRLSPARQLclinical reasoningknowledge representation

0 comments

The pith

An ontology unifies concepts for noninvasive respiratory support to aid clinical reasoning in acute care

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces an ontology for Non-Invasive Respiratory Support (NIRS) to address the lack of a unified structure for guiding its use in patients with respiratory failure. Using the Web Ontology Language (OWL) and Protege, the authors organize clinical concepts and relationships into 145 classes with added SWRL rules for reasoning beyond simple hierarchies. They evaluate the structure by applying it to six patient scenarios and running SPARQL queries that retrieve targeted inferences for therapy recommendations. This work matters to a sympathetic reader because it could enable more consistent documentation, better data interoperability across systems, and structured analysis of NIRS outcomes in acute care settings.

Core claim

The authors created the NIRS ontology with 145 classes, 11 object properties, 18 data properties, and 949 axioms, plus 392 annotations drawn from controlled vocabularies. They incorporated SWRL rules to support rule-based reasoning and tested the system by adding six patient scenarios, then used SPARQL queries to confirm that the ontology produces correct inferences for therapy recommendations.

What carries the argument

The NIRS ontology built in OWL with SWRL rules, which defines classes and relationships for noninvasive respiratory support modalities and patient conditions to enable logical inferences and SPARQL queries for clinical recommendations.

Load-bearing premise

The six hand-crafted patient scenarios sufficiently test the ontology's handling of real-world clinical variability and the chosen class definitions plus SWRL rules accurately capture current medical practice.

What would settle it

Applying SPARQL queries to the ontology with a larger collection of real patient cases from acute care and finding that the generated therapy recommendations do not align with expert clinician judgments.

Figures

Figures reproduced from arXiv: 2507.19992 by Jarrod Mosier, Md Fantacher Islam, Vignesh Subbian.

**Figure 5.** Figure 5: Retrieving Mapping Annotations by SPARQL. (Example A) Patient’s indications and outcomes classes related to Competency question 1. (Example B) Patient’s indications and therapy type classes related to Competency question 2. (Example A or B: Mapping) Shows retrieved classes, labels, or definitions and Ontology mapping. 5. Discussion In this study, we developed the NIRS ontology to provide a unified framewor… view at source ↗

read the original abstract

Managing patients with respiratory failure increasingly involves noninvasive respiratory support (NIRS) strategies to support respiration, often preventing the need for invasive mechanical ventilation. However, despite the rapidly expanding use of NIRS, there remains a significant challenge to its optimal use across all medical circumstances. It lacks a unified ontological structure, complicating guidance on NIRS modalities across healthcare systems. This study introduced NIRS ontology to support knowledge representation in acute care settings by providing a unified framework that enhances data clarity and interoperability, laying the groundwork for future clinical decision-making. We developed NIRS ontology using the Web Ontology Language (OWL) 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 a sample of 6 patient scenarios and used SPARQL queries to retrieve and test targeted inferences. The ontology has 145 classes, 11 object properties, and 18 data properties across 949 axioms that establish concept relationships. To standardize clinical concepts, we added 392 annotations, including descriptive definitions based on controlled vocabularies. SPARQL query evaluations across clinical scenarios confirmed the ontology ability to support rule based reasoning and therapy recommendations, providing a foundation for consistent documentation practices, integration into clinical data models, and advanced analysis of NIRS outcomes. In conclusion, we unified NIRS concepts into an ontological framework and demonstrated its applicability through the evaluation of patient scenarios and alignment with standardized vocabularies.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper builds a new OWL ontology for NIRS with SWRL rules for therapy suggestions, but the six hand-crafted scenarios do not show whether those rules match real clinical practice or handle variability.

read the letter

This paper creates a domain-specific OWL ontology for noninvasive respiratory support that pulls together 145 classes, properties, and SWRL rules aimed at standardizing terminology and supporting basic reasoning in acute care. The work follows a standard ontology-building process in Protege and adds annotations drawn from controlled vocabularies, which is a reasonable way to organize concepts like different NIRS modalities and their relationships. The SPARQL queries on the scenarios demonstrate that the rules can produce inferences about therapy recommendations, at least in the narrow cases they tested. That part is useful as a starting point for anyone trying to improve data interoperability in critical care records. The main limitation is the evaluation. Six hand-crafted patient scenarios function more as consistency checks than as evidence that the class definitions and rules reflect current medical consensus or cope with the range of real presentations. There is no reported expert review of the rules against published guidelines, no comparison to existing NIRS literature, and no testing on actual EHR data. Without those steps, any mismatch between the ontology and practice would go undetected. The paper is aimed at biomedical informatics researchers and critical care teams interested in standardized data models for respiratory support. A reader looking for a reusable framework to build decision support tools could extract value from the structure and rules, though they would likely need to expand the validation themselves. It deserves peer review because the construction is competent and the topic has clear practical relevance, but referees should press for broader testing and external input on the rules.

Referee Report

1 major / 2 minor

Summary. The manuscript presents the development of an OWL-based NIRS ontology in Protege for organizing clinical concepts in noninvasive respiratory support for acute care. The ontology contains 145 classes, 11 object properties, 18 data properties, and 949 axioms, augmented with SWRL rules for rule-based reasoning. Evaluation consists of applying the ontology to six patient scenarios and using SPARQL queries to retrieve inferences and therapy recommendations, with 392 annotations for standardization against controlled vocabularies.

Significance. If the class definitions and SWRL rules are shown to align with medical consensus and handle diverse presentations, the ontology could provide a reusable framework for consistent NIRS documentation, data interoperability, and future clinical decision support tools in acute respiratory care.

major comments (1)

[Abstract, evaluation paragraph] Abstract, evaluation paragraph: The central claim that SPARQL queries on the six scenarios confirm the ontology's ability to support rule-based reasoning and therapy recommendations rests on an evaluation that uses only six hand-crafted patient scenarios. No external expert review of the SWRL rules, no direct comparison against published NIRS guidelines, and no testing on real EHR-derived cases or independent literature are reported; this leaves open the possibility that mismatches with actual practice would go undetected.

minor comments (2)

The manuscript would benefit from an explicit table or appendix listing the SWRL rules and the specific inferences each rule is intended to produce, to allow readers to assess coverage independently of the six scenarios.
Clarify whether the 949 axioms include the SWRL rules or only the OWL axioms, and provide a breakdown of how many axioms are subclass axioms versus property restrictions.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their detailed and constructive feedback on the evaluation of our NIRS ontology. We have addressed the major comment by revising the manuscript to more accurately reflect the preliminary and illustrative nature of the current evaluation.

read point-by-point responses

Referee: [Abstract, evaluation paragraph] Abstract, evaluation paragraph: The central claim that SPARQL queries on the six scenarios confirm the ontology's ability to support rule-based reasoning and therapy recommendations rests on an evaluation that uses only six hand-crafted patient scenarios. No external expert review of the SWRL rules, no direct comparison against published NIRS guidelines, and no testing on real EHR-derived cases or independent literature are reported; this leaves open the possibility that mismatches with actual practice would go undetected.

Authors: We agree that the evaluation is limited to six hand-crafted scenarios and does not include external expert review, direct guideline comparisons, or real EHR-derived cases. These scenarios were developed to represent diverse acute care presentations and to demonstrate the practical application of the SWRL rules and SPARQL queries for rule-based reasoning. The manuscript's focus was on ontology development and initial functionality testing rather than comprehensive clinical validation. In the revised version, we will modify the abstract to change 'confirmed' to 'demonstrated' and will add an explicit limitations subsection in the discussion that acknowledges the preliminary scope, the absence of external validation, and the need for future work involving expert review, published NIRS guidelines, and real-world EHR testing. These textual revisions will qualify our claims appropriately while preserving the contribution of the ontology framework and its annotations to controlled vocabularies. revision: partial

Circularity Check

0 steps flagged

No circularity: constructive ontology development with explicit construction and consistency checks

full rationale

The paper constructs an OWL ontology (145 classes, 11 object properties, 18 data properties, 949 axioms, 392 annotations) plus SWRL rules from clinical concepts drawn from controlled vocabularies, then evaluates inferences via SPARQL on six hand-crafted scenarios. No equations, fitted parameters, predictions, or self-citations appear in the derivation chain. The central claim—that the ontology supports rule-based reasoning—is demonstrated by direct construction and query results rather than reducing to its own inputs by definition or statistical forcing. This is a standard knowledge-representation workflow whose validity rests on external medical consensus and future validation, not internal circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 1 invented entities

The central contribution is the manual construction of an ontology rather than derivation from data or first principles; background assumptions are standard semantic web technologies.

axioms (2)

standard math OWL provides a formal language for defining classes, properties, and relationships in a machine-readable way
Invoked when stating the ontology was developed using OWL and Protege
standard math SWRL rules can be added to OWL ontologies to enable rule-based inference beyond simple hierarchies
Invoked when describing addition of SWRL rules for clinical reasoning

invented entities (1)

NIRS ontology no independent evidence
purpose: To provide a unified framework for clinical concepts and relationships in noninvasive respiratory support
Newly constructed artifact; no independent evidence outside the paper is provided

pith-pipeline@v0.9.0 · 5805 in / 1641 out tokens · 49131 ms · 2026-05-19T03:20:48.862247+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Foundation/AbsoluteFloorClosure.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

We developed NIRS ontology using the Web Ontology Language (OWL) and Protege... SPARQL query evaluations across clinical scenarios confirmed the ontology ability to support rule based reasoning and therapy recommendations

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

26 extracted references · 26 canonical work pages

[1]

Noninvasive Respiratory Support in Acute Hypoxemic Respiratory Failure,

T. Piraino, “Noninvasive Respiratory Support in Acute Hypoxemic Respiratory Failure,” Respiratory Care, vol. 64, no. 6, pp. 638–646, Jun. 2019, doi: 10.4187/respcare.06735

work page doi:10.4187/respcare.06735 2019
[2]

Chronic Obstructive Pulmonary Disease and Long-Term Home Non-Invasive Ventilation: Analysis of a Telematically Controlled Unit,

M. Galdeano Lozano et al., “Chronic Obstructive Pulmonary Disease and Long-Term Home Non-Invasive Ventilation: Analysis of a Telematically Controlled Unit,” Feb. 18,

work page
[3]

doi: 10.20944/preprints202502.1167.v1

work page doi:10.20944/preprints202502.1167.v1
[4]

Prevalence and Economic Impact of Acute Respiratory Failure in the Prehospital Emergency Medical Service of the Madrid Community: Retrospective Cohort Study,

A. M. Cintora-Sanz, C. Horrillo-García, V . Quesada-Cubo, A. M. Pérez-Alonso, and A. Gutiérrez-Misis, “Prevalence and Economic Impact of Acute Respiratory Failure in the Prehospital Emergency Medical Service of the Madrid Community: Retrospective Cohort Study,” JMIR Public Health Surveill, vol. 11, pp. e66179–e66179, Jan. 2025, doi: 10.2196/66179

work page doi:10.2196/66179 2025
[5]

Noninvasive ventilation in acute respiratory failure,

A. Mas and J. Masip, “Noninvasive ventilation in acute respiratory failure,” COPD, doi: https://doi.org/10.2147/COPD.S42664

work page doi:10.2147/copd.s42664
[6]

Phenotyping COVID-19 Patients by Ventilation Therapy: Data Quality Challenges and Cohort Characterization,

P. Essay, J. Mosier, and V . Subbian, “Phenotyping COVID-19 Patients by Ventilation Therapy: Data Quality Challenges and Cohort Characterization,” in Studies in Health Technology and Informatics, J. Mantas, L. Stoicu-Tivadar, C. Chronaki, A. Hasman, P. Weber, P. Gallos, M. Crişan-Vida, E. Zoulias, and O. S. Chirila, Eds., IOS Press, 2021. doi: 10.3233/SHTI210148

work page doi:10.3233/shti210148 2021
[7]

Non-invasive respiratory support in the management of acute COVID-19 pneumonia: considerations for clinical practice and priorities for research,

S. Weerakkody et al., “Non-invasive respiratory support in the management of acute COVID-19 pneumonia: considerations for clinical practice and priorities for research,” The Lancet Respiratory Medicine, vol. 10, no. 2, pp. 199–213, Feb. 2022, doi: 10.1016/S2213- 2600(21)00414-8

work page doi:10.1016/s2213- 2022
[8]

A Taxonomy for Mechanical Ventilation: 10 Fundamental Maxims,

R. L. Chatburn, M. El-Khatib, and E. Mireles-Cabodevila, “A Taxonomy for Mechanical Ventilation: 10 Fundamental Maxims,” Respiratory Care, vol. 59, no. 11, pp. 1747–1763, Nov. 2014, doi: 10.4187/respcare.03057

work page doi:10.4187/respcare.03057 2014
[9]

Methods in biomedical ontology,

A. C. Yu, “Methods in biomedical ontology,” Journal of Biomedical Informatics, vol. 39, no. 3, pp. 252–266, Jun. 2006, doi: 10.1016/j.jbi.2005.11.006

work page doi:10.1016/j.jbi.2005.11.006 2006
[10]

Time event ontology (TEO): to support semantic representation and reasoning of complex temporal relations of clinical events,

F. Li et al., “Time event ontology (TEO): to support semantic representation and reasoning of complex temporal relations of clinical events,” Journal of the American Medical Informatics Association, vol. 27, no. 7, pp. 1046–1056, Jul. 2020, doi: 10.1093/jamia/ocaa058

work page doi:10.1093/jamia/ocaa058 2020
[11]

The ontology of medically related social entities: recent developments,

A. Hicks, J. Hanna, D. Welch, M. Brochhausen, and W. R. Hogan, “The ontology of medically related social entities: recent developments,” J Biomed Semant, vol. 7, no. 1, p. 47, Dec. 2016, doi: 10.1186/s13326-016-0087-8. 20

work page doi:10.1186/s13326-016-0087-8 2016
[12]

Standardizing electronic health record ventilation data in the pediatric long-term mechanical ventilator-dependent population.,

L. J. Kanbar et al., “Standardizing electronic health record ventilation data in the pediatric long-term mechanical ventilator-dependent population.,” Pediatr Pulmonol, vol. 58, no. 2, pp. 433–440, Feb. 2023, doi: 10.1002/ppul.26204

work page doi:10.1002/ppul.26204 2023
[13]

Rule-Based Cohort Definitions for Acute Respiratory Failure: Electronic Phenotyping Algorithm,

P. Essay, J. Mosier, and V . Subbian, “Rule-Based Cohort Definitions for Acute Respiratory Failure: Electronic Phenotyping Algorithm,” JMIR Med Inform, vol. 8, no. 4, p. e18402, Apr. 2020, doi: 10.2196/18402

work page doi:10.2196/18402 2020
[14]

and Johnson, Alistair E

T. J. Pollard, A. E. W. Johnson, J. D. Raffa, L. A. Celi, R. G. Mark, and O. Badawi, “The eICU Collaborative Research Database, a freely available multi-center database for critical care research,” Sci Data, vol. 5, no. 1, Sep. 2018, doi: 10.1038/sdata.2018.178

work page doi:10.1038/sdata.2018.178 2018
[15]

Noninvasive ventilation failure in patients with hypoxemic respiratory failure: the role of sepsis and septic shock,

J. Duan et al., “Noninvasive ventilation failure in patients with hypoxemic respiratory failure: the role of sepsis and septic shock,” Ther Adv Respir Dis, vol. 13, p. 1753466619888124, Jan. 2019, doi: 10.1177/1753466619888124

work page doi:10.1177/1753466619888124 2019
[16]

The value of local validation of a predictive model. A nomogram for predicting failure of non-invasive ventilation in patients with SARS-COV-2 pneumonia,

H. Hernández Garcés et al., “The value of local validation of a predictive model. A nomogram for predicting failure of non-invasive ventilation in patients with SARS-COV-2 pneumonia,” Medicina Intensiva (English Edition), p. 502148, Jan. 2025, doi: 10.1016/j.medine.2025.502148

work page doi:10.1016/j.medine.2025.502148 2025
[17]

Optimising non-invasive ventilation in acute COPD exacerbations: Beyond pressure and volume settings,

C. Crimi, A. Carlucci, and S. Nava, “Optimising non-invasive ventilation in acute COPD exacerbations: Beyond pressure and volume settings,” Pulmonology, vol. 31, no. 1, p. 2448080, Dec. 2025, doi: 10.1080/25310429.2024.2448080

work page doi:10.1080/25310429.2024.2448080 2025
[18]

Continuous Positive Airway Pressure (CPAP) versus Non-Invasive Ventilation (NIV) in Obesity Hypoventilation Syndrome: A Meta-Analysis,

Meliza Wahyuni, Yessy Susanty Sabri, and Fenty Anggrainy, “Continuous Positive Airway Pressure (CPAP) versus Non-Invasive Ventilation (NIV) in Obesity Hypoventilation Syndrome: A Meta-Analysis,” Bioscmed, vol. 9, no. 5, pp. 7299–7310, Feb. 2025, doi: 10.37275/bsm.v9i5.1274

work page doi:10.37275/bsm.v9i5.1274 2025
[19]

Efficacy and safety of non-invasive ventilation in the treatment of acute cardiogenic pulmonary edema – a systematic review and meta-analysis,

J. C. Winck, L. F. Azevedo, A. Costa-Pereira, M. Antonelli, and J. C. Wyatt, “Efficacy and safety of non-invasive ventilation in the treatment of acute cardiogenic pulmonary edema – a systematic review and meta-analysis,” Crit Care, vol. 10, no. 2, p. R69, Apr. 2006, doi: 10.1186/cc4905

work page doi:10.1186/cc4905 2006
[20]

Isolated Pulmonary Valve Infective Endocarditis With Persistent Staphylococcus aureus Bacteremia and Rapid Clearance With Ertapenem Plus Cefazolin,

P. Fernandes, J. Maia Oliveira, A. R. Rocha, S. Carvalho, and J. Vaz, “Isolated Pulmonary Valve Infective Endocarditis With Persistent Staphylococcus aureus Bacteremia and Rapid Clearance With Ertapenem Plus Cefazolin,” Cureus, Jan. 2025, doi: 10.7759/cureus.77335

work page doi:10.7759/cureus.77335 2025
[21]

Noninvasive vs invasive respiratory support for patients with acute hypoxemic respiratory failure,

J. M. Mosier et al., “Noninvasive vs invasive respiratory support for patients with acute hypoxemic respiratory failure,” PLoS ONE, vol. 19, no. 9, p. e0307849, Sep. 2024, doi: 10.1371/journal.pone.0307849

work page doi:10.1371/journal.pone.0307849 2024
[22]

ESICM guidelines on acute respiratory distress syndrome: definition, phenotyping and respiratory support strategies,

G. Grasselli et al., “ESICM guidelines on acute respiratory distress syndrome: definition, phenotyping and respiratory support strategies,” Intensive Care Med, vol. 49, no. 7, pp. 727–759, 2023, doi: 10.1007/s00134-023-07050-7

work page doi:10.1007/s00134-023-07050-7 2023
[23]

A Comparison of Different Guidelines for the Treatment of Acute Heart Failure and Their Extensibility to Emergency Departments: A Critical Reappraisal,

L. Falsetti et al., “A Comparison of Different Guidelines for the Treatment of Acute Heart Failure and Their Extensibility to Emergency Departments: A Critical Reappraisal,” JCM, vol. 14, no. 10, p. 3522, May 2025, doi: 10.3390/jcm14103522

work page doi:10.3390/jcm14103522 2025
[24]

Z. Wang, M. Wilson, and C. C. Dobler, Noninvasive Positive Pressure Ventilation in the Home [Internet]. Rockville (MD): Agency for Healthcare Research and Quality (US); 2019 Mar 14. Available from: https://www.ncbi.nlm.nih.gov/books/NBK554171/

work page 2019
[25]

Non-invasive ventilation in elderly patients with acute hypercapnic respiratory failure: a randomised controlled trial,

S. Nava et al., “Non-invasive ventilation in elderly patients with acute hypercapnic respiratory failure: a randomised controlled trial,” Age and Ageing, vol. 40, no. 4, pp. 444– 450, Jul. 2011, doi: 10.1093/ageing/afr003. 21

work page doi:10.1093/ageing/afr003 2011
[26]

Development of a deep learning model that predicts Bi-level positive airway pressure failure,

D. D. Im, E. Laksana, D. R. Ledbetter, M. D. Aczon, R. G. Khemani, and R. C. Wetzel, “Development of a deep learning model that predicts Bi-level positive airway pressure failure,” Sci Rep, vol. 12, no. 1, May 2022, doi: 10.1038/s41598-022-12984-x. APPENDIX A A.1 SWRL Rules This section describes the Semantic Web Rule Language (SWRL) rules that are design...

work page doi:10.1038/s41598-022-12984-x 2022

[1] [1]

Noninvasive Respiratory Support in Acute Hypoxemic Respiratory Failure,

T. Piraino, “Noninvasive Respiratory Support in Acute Hypoxemic Respiratory Failure,” Respiratory Care, vol. 64, no. 6, pp. 638–646, Jun. 2019, doi: 10.4187/respcare.06735

work page doi:10.4187/respcare.06735 2019

[2] [2]

Chronic Obstructive Pulmonary Disease and Long-Term Home Non-Invasive Ventilation: Analysis of a Telematically Controlled Unit,

M. Galdeano Lozano et al., “Chronic Obstructive Pulmonary Disease and Long-Term Home Non-Invasive Ventilation: Analysis of a Telematically Controlled Unit,” Feb. 18,

work page

[3] [3]

doi: 10.20944/preprints202502.1167.v1

work page doi:10.20944/preprints202502.1167.v1

[4] [4]

Prevalence and Economic Impact of Acute Respiratory Failure in the Prehospital Emergency Medical Service of the Madrid Community: Retrospective Cohort Study,

A. M. Cintora-Sanz, C. Horrillo-García, V . Quesada-Cubo, A. M. Pérez-Alonso, and A. Gutiérrez-Misis, “Prevalence and Economic Impact of Acute Respiratory Failure in the Prehospital Emergency Medical Service of the Madrid Community: Retrospective Cohort Study,” JMIR Public Health Surveill, vol. 11, pp. e66179–e66179, Jan. 2025, doi: 10.2196/66179

work page doi:10.2196/66179 2025

[5] [5]

Noninvasive ventilation in acute respiratory failure,

A. Mas and J. Masip, “Noninvasive ventilation in acute respiratory failure,” COPD, doi: https://doi.org/10.2147/COPD.S42664

work page doi:10.2147/copd.s42664

[6] [6]

Phenotyping COVID-19 Patients by Ventilation Therapy: Data Quality Challenges and Cohort Characterization,

P. Essay, J. Mosier, and V . Subbian, “Phenotyping COVID-19 Patients by Ventilation Therapy: Data Quality Challenges and Cohort Characterization,” in Studies in Health Technology and Informatics, J. Mantas, L. Stoicu-Tivadar, C. Chronaki, A. Hasman, P. Weber, P. Gallos, M. Crişan-Vida, E. Zoulias, and O. S. Chirila, Eds., IOS Press, 2021. doi: 10.3233/SHTI210148

work page doi:10.3233/shti210148 2021

[7] [7]

Non-invasive respiratory support in the management of acute COVID-19 pneumonia: considerations for clinical practice and priorities for research,

S. Weerakkody et al., “Non-invasive respiratory support in the management of acute COVID-19 pneumonia: considerations for clinical practice and priorities for research,” The Lancet Respiratory Medicine, vol. 10, no. 2, pp. 199–213, Feb. 2022, doi: 10.1016/S2213- 2600(21)00414-8

work page doi:10.1016/s2213- 2022

[8] [8]

A Taxonomy for Mechanical Ventilation: 10 Fundamental Maxims,

R. L. Chatburn, M. El-Khatib, and E. Mireles-Cabodevila, “A Taxonomy for Mechanical Ventilation: 10 Fundamental Maxims,” Respiratory Care, vol. 59, no. 11, pp. 1747–1763, Nov. 2014, doi: 10.4187/respcare.03057

work page doi:10.4187/respcare.03057 2014

[9] [9]

Methods in biomedical ontology,

A. C. Yu, “Methods in biomedical ontology,” Journal of Biomedical Informatics, vol. 39, no. 3, pp. 252–266, Jun. 2006, doi: 10.1016/j.jbi.2005.11.006

work page doi:10.1016/j.jbi.2005.11.006 2006

[10] [10]

Time event ontology (TEO): to support semantic representation and reasoning of complex temporal relations of clinical events,

F. Li et al., “Time event ontology (TEO): to support semantic representation and reasoning of complex temporal relations of clinical events,” Journal of the American Medical Informatics Association, vol. 27, no. 7, pp. 1046–1056, Jul. 2020, doi: 10.1093/jamia/ocaa058

work page doi:10.1093/jamia/ocaa058 2020

[11] [11]

The ontology of medically related social entities: recent developments,

A. Hicks, J. Hanna, D. Welch, M. Brochhausen, and W. R. Hogan, “The ontology of medically related social entities: recent developments,” J Biomed Semant, vol. 7, no. 1, p. 47, Dec. 2016, doi: 10.1186/s13326-016-0087-8. 20

work page doi:10.1186/s13326-016-0087-8 2016

[12] [12]

Standardizing electronic health record ventilation data in the pediatric long-term mechanical ventilator-dependent population.,

L. J. Kanbar et al., “Standardizing electronic health record ventilation data in the pediatric long-term mechanical ventilator-dependent population.,” Pediatr Pulmonol, vol. 58, no. 2, pp. 433–440, Feb. 2023, doi: 10.1002/ppul.26204

work page doi:10.1002/ppul.26204 2023

[13] [13]

Rule-Based Cohort Definitions for Acute Respiratory Failure: Electronic Phenotyping Algorithm,

P. Essay, J. Mosier, and V . Subbian, “Rule-Based Cohort Definitions for Acute Respiratory Failure: Electronic Phenotyping Algorithm,” JMIR Med Inform, vol. 8, no. 4, p. e18402, Apr. 2020, doi: 10.2196/18402

work page doi:10.2196/18402 2020

[14] [14]

and Johnson, Alistair E

T. J. Pollard, A. E. W. Johnson, J. D. Raffa, L. A. Celi, R. G. Mark, and O. Badawi, “The eICU Collaborative Research Database, a freely available multi-center database for critical care research,” Sci Data, vol. 5, no. 1, Sep. 2018, doi: 10.1038/sdata.2018.178

work page doi:10.1038/sdata.2018.178 2018

[15] [15]

Noninvasive ventilation failure in patients with hypoxemic respiratory failure: the role of sepsis and septic shock,

J. Duan et al., “Noninvasive ventilation failure in patients with hypoxemic respiratory failure: the role of sepsis and septic shock,” Ther Adv Respir Dis, vol. 13, p. 1753466619888124, Jan. 2019, doi: 10.1177/1753466619888124

work page doi:10.1177/1753466619888124 2019

[16] [16]

The value of local validation of a predictive model. A nomogram for predicting failure of non-invasive ventilation in patients with SARS-COV-2 pneumonia,

H. Hernández Garcés et al., “The value of local validation of a predictive model. A nomogram for predicting failure of non-invasive ventilation in patients with SARS-COV-2 pneumonia,” Medicina Intensiva (English Edition), p. 502148, Jan. 2025, doi: 10.1016/j.medine.2025.502148

work page doi:10.1016/j.medine.2025.502148 2025

[17] [17]

Optimising non-invasive ventilation in acute COPD exacerbations: Beyond pressure and volume settings,

C. Crimi, A. Carlucci, and S. Nava, “Optimising non-invasive ventilation in acute COPD exacerbations: Beyond pressure and volume settings,” Pulmonology, vol. 31, no. 1, p. 2448080, Dec. 2025, doi: 10.1080/25310429.2024.2448080

work page doi:10.1080/25310429.2024.2448080 2025

[18] [18]

Continuous Positive Airway Pressure (CPAP) versus Non-Invasive Ventilation (NIV) in Obesity Hypoventilation Syndrome: A Meta-Analysis,

Meliza Wahyuni, Yessy Susanty Sabri, and Fenty Anggrainy, “Continuous Positive Airway Pressure (CPAP) versus Non-Invasive Ventilation (NIV) in Obesity Hypoventilation Syndrome: A Meta-Analysis,” Bioscmed, vol. 9, no. 5, pp. 7299–7310, Feb. 2025, doi: 10.37275/bsm.v9i5.1274

work page doi:10.37275/bsm.v9i5.1274 2025

[19] [19]

Efficacy and safety of non-invasive ventilation in the treatment of acute cardiogenic pulmonary edema – a systematic review and meta-analysis,

J. C. Winck, L. F. Azevedo, A. Costa-Pereira, M. Antonelli, and J. C. Wyatt, “Efficacy and safety of non-invasive ventilation in the treatment of acute cardiogenic pulmonary edema – a systematic review and meta-analysis,” Crit Care, vol. 10, no. 2, p. R69, Apr. 2006, doi: 10.1186/cc4905

work page doi:10.1186/cc4905 2006

[20] [20]

Isolated Pulmonary Valve Infective Endocarditis With Persistent Staphylococcus aureus Bacteremia and Rapid Clearance With Ertapenem Plus Cefazolin,

P. Fernandes, J. Maia Oliveira, A. R. Rocha, S. Carvalho, and J. Vaz, “Isolated Pulmonary Valve Infective Endocarditis With Persistent Staphylococcus aureus Bacteremia and Rapid Clearance With Ertapenem Plus Cefazolin,” Cureus, Jan. 2025, doi: 10.7759/cureus.77335

work page doi:10.7759/cureus.77335 2025

[21] [21]

Noninvasive vs invasive respiratory support for patients with acute hypoxemic respiratory failure,

J. M. Mosier et al., “Noninvasive vs invasive respiratory support for patients with acute hypoxemic respiratory failure,” PLoS ONE, vol. 19, no. 9, p. e0307849, Sep. 2024, doi: 10.1371/journal.pone.0307849

work page doi:10.1371/journal.pone.0307849 2024

[22] [22]

ESICM guidelines on acute respiratory distress syndrome: definition, phenotyping and respiratory support strategies,

G. Grasselli et al., “ESICM guidelines on acute respiratory distress syndrome: definition, phenotyping and respiratory support strategies,” Intensive Care Med, vol. 49, no. 7, pp. 727–759, 2023, doi: 10.1007/s00134-023-07050-7

work page doi:10.1007/s00134-023-07050-7 2023

[23] [23]

A Comparison of Different Guidelines for the Treatment of Acute Heart Failure and Their Extensibility to Emergency Departments: A Critical Reappraisal,

L. Falsetti et al., “A Comparison of Different Guidelines for the Treatment of Acute Heart Failure and Their Extensibility to Emergency Departments: A Critical Reappraisal,” JCM, vol. 14, no. 10, p. 3522, May 2025, doi: 10.3390/jcm14103522

work page doi:10.3390/jcm14103522 2025

[24] [24]

Z. Wang, M. Wilson, and C. C. Dobler, Noninvasive Positive Pressure Ventilation in the Home [Internet]. Rockville (MD): Agency for Healthcare Research and Quality (US); 2019 Mar 14. Available from: https://www.ncbi.nlm.nih.gov/books/NBK554171/

work page 2019

[25] [25]

Non-invasive ventilation in elderly patients with acute hypercapnic respiratory failure: a randomised controlled trial,

S. Nava et al., “Non-invasive ventilation in elderly patients with acute hypercapnic respiratory failure: a randomised controlled trial,” Age and Ageing, vol. 40, no. 4, pp. 444– 450, Jul. 2011, doi: 10.1093/ageing/afr003. 21

work page doi:10.1093/ageing/afr003 2011

[26] [26]

Development of a deep learning model that predicts Bi-level positive airway pressure failure,

D. D. Im, E. Laksana, D. R. Ledbetter, M. D. Aczon, R. G. Khemani, and R. C. Wetzel, “Development of a deep learning model that predicts Bi-level positive airway pressure failure,” Sci Rep, vol. 12, no. 1, May 2022, doi: 10.1038/s41598-022-12984-x. APPENDIX A A.1 SWRL Rules This section describes the Semantic Web Rule Language (SWRL) rules that are design...

work page doi:10.1038/s41598-022-12984-x 2022