{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T14:52:55Z","timestamp":1775832775926,"version":"3.50.1"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"\n Background<\/jats:title>\n Early identification of noninvasive respiratory support (NIRS) failure in acute respiratory failure (ARF) is clinically relevant, as delayed intubation is associated with worse outcomes. Machine learning-based prediction models have been proposed to support escalation decisions, but their performance and reliability remain uncertain.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n To systematically evaluate the discriminative performance of machine learning-based models for predicting NIRS failure in adults with ARF.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We conducted a systematic review and meta-analysis following PRISMA 2020 guidelines and registered the protocol in PROSPERO (CRD420251167330). PubMed, Web of Science, and Scopus were searched from January 2010 to the final search date. Cohort studies developing or validating machine learning models to predict NIRS failure, primarily defined as endotracheal intubation, were included. Discrimination was assessed using the area under the receiver operating characteristic curve (AUC). Logit-transformed AUCs were synthesized using random-effects models with restricted maximum likelihood estimation and Hartung\u2013Knapp confidence intervals. Risk of bias and certainty of evidence were assessed using PROBAST-AI and GRADE, respectively.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Fourteen cohort studies comprising 34,500 patients were included. The descriptive pooled AUC was 0.84 (95% CI, 0.78\u20130.89) with extreme heterogeneity (I\n 2<\/jats:sup>\n \u202f=\u202f99.5%) and wide prediction intervals. Subgroup analyses showed no statistically significant differences by validation strategy or type of noninvasive respiratory support. All studies were rated at high risk of bias, and the certainty of evidence was very low.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n Machine learning-based models demonstrate moderate discrimination; however, extreme heterogeneity, high risk of bias, and very low certainty of evidence preclude clinical implementation.<\/jats:p>\n <\/jats:sec>\n \n Systematic review registration<\/jats:title>\n \n https:\/\/www.crd.york.ac.uk\/PROSPERO\/view\/CRD420251167330<\/jats:ext-link>\n .\n <\/jats:p>\n <\/jats:sec>","DOI":"10.3389\/fmed.2026.1775670","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T14:02:38Z","timestamp":1775829758000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning-based prediction models for noninvasive respiratory support failure in acute respiratory failure: a systematic review and meta-analysis"],"prefix":"10.3389","volume":"13","author":[{"given":"Kadir Burak","family":"Akg\u00fcn","sequence":"first","affiliation":[{"name":"Department of Pulmonology, Faculty of Medicine, Hatay Mustafa Kemal University","place":["Hatay, T\u00fcrkiye"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hajed M.","family":"Al-Otaibi","sequence":"additional","affiliation":[{"name":"Department of Respiratory Therapy, Faculty of Medical Rehabilitation Sciences, King Abdulaziz University","place":["Jeddah, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaspar R.","family":"Chiappa","sequence":"additional","affiliation":[{"name":"Faculty of Health Sciences, Universidad Aut\u00f3noma de Chile, Providencia","place":["Santiago, Chile"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdullah A.","family":"Alqarni","sequence":"additional","affiliation":[{"name":"Department of Respiratory Therapy, Faculty of Medical Rehabilitation Sciences, King Abdulaziz University","place":["Jeddah, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Troxell","sequence":"additional","affiliation":[{"name":"Graduate Program, Eastern University","place":["Philadelphia, PA, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franciszek","family":"Przybylski","sequence":"additional","affiliation":[{"name":"Student Scientific Society at 2nd Department of Pulmonary Diseases, Lung Cancer and Internal Medicine, Medical University of Bia\u0142ystok","place":["Bia\u0142ystok, Poland"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio M.","family":"Esquinas","sequence":"additional","affiliation":[{"name":"Intensive Care Unit, Hospital Meseguer Meseguer.NIV-ICU Group, Biomedical Research Institute Pascual Parrilla\u2013IMIB","place":["Murcia, Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,10]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.ccc.2024.01.002","article-title":"Diagnosis and management of acute respiratory failure","volume":"40","author":"Lagina","year":"2024","journal-title":"Crit Care Clin"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.47191\/ijmscrs\/v4-i06-05","article-title":"Acute respiratory failure: pathophysiology, diagnosis, and current therapeutic modalities","volume":"4","author":"Flores","year":"2024","journal-title":"Int J Med Sci Clin Res Stud"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s40560-023-00658-3","article-title":"Guideline-based management of acute respiratory failure and acute respiratory distress syndrome","volume":"11","author":"Fujishima","year":"2023","journal-title":"J Intensive Care"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.mpmed.2016.03.008","article-title":"Invasive and non-invasive mechanical ventilation","volume":"44","author":"Popat","year":"2016","journal-title":"Medicine (Baltimore)"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1186\/s40001-024-02082-1","article-title":"Impact of mechanical power on ICU mortality in ventilated critically ill patients: a retrospective study with continuous real-life data","volume":"29","author":"Manrique","year":"2024","journal-title":"Eur J Med Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"7443","DOI":"10.3390\/jcm14207443","article-title":"Bridging the gap: the role of non-invasive respiratory supports in weaning from invasive mechanical ventilation","volume":"14","author":"Panzuti","year":"2025","journal-title":"J Clin Med"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1379","DOI":"10.4187\/respcare.05073","article-title":"The impact of ventilator-associated events in critically ill subjects with prolonged mechanical ventilation","volume":"62","author":"Kobayashi","year":"2017","journal-title":"Respir Care"},{"key":"ref8","first-page":"155","article-title":"Clinical characteristics and computed tomographical features of pulmonary thromboembolic disease associated with COVID-19 infection: a tertiary hospital analysis","volume":"78","author":"Tan","year":"2023","journal-title":"Med J Malaysia"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.ajem.2024.01.044","article-title":"Evaluation of HACOR scale as a predictor of non-invasive ventilation failure in acute cardiogenic pulmonary oedema patients: a prospective observational study","volume":"79","author":"Chong","year":"2024","journal-title":"Am J Emerg Med"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.4187\/respcare.11544","article-title":"Using the ROX index to predict treatment outcome for high-flow nasal cannula and\/or noninvasive ventilation in patients with COPD exacerbations","volume":"69","author":"Schaeffer","year":"2024","journal-title":"Respir Care"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/s12245-023-00477-1","article-title":"ROX index versus HACOR scale in predicting success and failure of high-flow nasal cannula in the emergency department for patients with acute hypoxemic respiratory failure: a prospective observational study","volume":"16","author":"Praphruetkit","year":"2023","journal-title":"Int J Emerg Med"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1186\/s13054-025-05336-4","article-title":"Machine learning models compared with current clinical indices to predict the outcome of high flow nasal cannula therapy in acute hypoxemic respiratory failure","volume":"29","author":"Yu","year":"2025","journal-title":"Crit Care"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"giaf036","DOI":"10.1093\/gigascience\/giaf036","article-title":"External validation of machine learning models\u2014registered models and adaptive sample splitting","volume":"14","author":"Gallitto","year":"2025","journal-title":"GigaScience"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"100","DOI":"10.70749\/ijbr.v3i9.2171","article-title":"Non-invasive ventilation in acute exacerbations of COPD: a systematic review and meta-analysis of mortality, morbidity, and hospital outcomes","volume":"3","author":"Alniazi","year":"2025","journal-title":"Indus J Biosci Res"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1186\/s12890-015-0139-3","article-title":"Performance of noninvasive ventilation in acute respiratory failure in critically ill patients: a prospective, observational, cohort study","volume":"15","author":"Corr\u00eaa","year":"2015","journal-title":"BMC Pulm Med"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"10573","DOI":"10.1038\/s41598-022-14758-x","article-title":"A novel machine learning model to predict respiratory failure and invasive mechanical ventilation in critically ill patients suffering from COVID-19","volume":"12","author":"Bendavid","year":"2022","journal-title":"Sci Rep"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s12911-022-01767-z","article-title":"Efficacy prediction of noninvasive ventilation failure based on the stacking ensemble algorithm and autoencoder","volume":"22","author":"Liang","year":"2022","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"488","DOI":"10.4187\/respcare.10382","article-title":"Predicting failure of noninvasive respiratory support using deep recurrent learning","volume":"68","author":"Essay","year":"2023","journal-title":"Respir Care"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"3628","DOI":"10.1111\/jocn.17518","article-title":"Predicting high-flow nasal cannula oxygen therapy failure in patients with acute Hypoxaemic respiratory failure using machine learning: model development and external validation","volume":"34","author":"Cheng","year":"2025","journal-title":"J Clin Nurs"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"103802","DOI":"10.1016\/j.jbi.2021.103802","article-title":"Learning from past respiratory failure patients to triage COVID-19 patient ventilator needs: a multi-institutional study","volume":"119","author":"Carmichael","year":"2021","journal-title":"J Biomed Inform"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1186\/s12890-022-02096-7","article-title":"Early prediction of noninvasive ventilation failure after extubation: development and validation of a machine-learning model","volume":"22","author":"Wang","year":"2022","journal-title":"BMC Pulm Med"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1825","DOI":"10.1038\/s41598-024-52061-z","article-title":"Machine learning prediction of the failure of high-flow nasal oxygen therapy in patients with acute respiratory failure","volume":"14","author":"Wang","year":"2024","journal-title":"Sci Rep"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"30245","DOI":"10.1038\/s41598-025-16061-x","article-title":"Real-time prediction of HFNC treatment failure in acute hypoxemic respiratory failure using machine learning","volume":"15","author":"Li","year":"2025","journal-title":"Sci Rep"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"e1059","DOI":"10.1097\/CCE.0000000000001059","article-title":"Racial differences in accuracy of predictive models for high-flow nasal cannula failure in COVID-19","volume":"6","author":"Yang","year":"2024","journal-title":"Crit Care Explor"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"e46905","DOI":"10.2196\/46905","article-title":"A hybrid decision tree and deep learning approach combining medical imaging and electronic medical records to predict intubation among hospitalized patients with COVID-19: algorithm development and validation","volume":"7","author":"Nguyen","year":"2023","journal-title":"JMIR Form Res"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"337","DOI":"10.17305\/bb.2023.9754","article-title":"Early machine learning prediction of hospitalized patients at low risk of respiratory deterioration or mortality in community-acquired pneumonia: derivation and validation of a multivariable model","volume":"24","author":"Odeyemi","year":"2024","journal-title":"Biomol Biomed"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1016\/j.bja.2020.11.034","article-title":"Clinically applicable approach for predicting mechanical ventilation in patients with COVID-19","volume":"126","author":"Douville","year":"2021","journal-title":"Br J Anaesth"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"e31750","DOI":"10.1016\/j.heliyon.2024.e31750","article-title":"ChatGPT achieves comparable accuracy to specialist physicians in predicting the efficacy of high-flow oxygen therapy","volume":"10","author":"Liu","year":"2024","journal-title":"Heliyon"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1775670\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T14:02:39Z","timestamp":1775829759000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1775670\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,10]]},"references-count":28,"alternative-id":["10.3389\/fmed.2026.1775670"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1775670","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,10]]},"article-number":"1775670"}}