{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T20:17:54Z","timestamp":1795033074834,"version":"4.10.2"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T00:00:00Z","timestamp":1755475200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T00:00:00Z","timestamp":1755475200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Accurate and timely prediction of high-flow nasal cannula (HFNC) treatment failure in patients with acute hypoxemic respiratory failure (AHRF) can lower patient mortality. Previous studies have highlighted inconsistencies in the predictive performance of existing indices, such as ROX and mROX, which are limited by their reliance on oxygenation parameters alone. To address this, we developed a machine learning-based predictive model using temporal data from AHRF patients, aimed at facilitating quicker development of individualized treatment plans and intervention strategies for healthcare professionals. We extracted 15 non-invasive and 15 laboratory features, including patient demographic characteristics, Glasgow Coma Scale, blood gas analysis, chemical assay, and complete blood cell count features. In addition to five machine learning models and an ensemble classifier, an long short-term memory (LSTM) network was included to assess deep learning performance on time-series data. Our study enrolled 427 patients with 498 treatment records. The soft-voting ensemble algorithm achieved an optimal predictive performance with an AUC of 0.839 (95% CI 0.786\u20130.889) for the all-features model, while logistic regression using common features achieved an AUC of 0.767 (95% CI 0.704\u20130.825), outperforming ROX and mROX indices. Incorporating blood gas analysis features improved the non-invasive model\u2019s performance by 0.104. This study introduces a machine learning model integrated with a dynamic real-time alert system for predicting HFNC treatment failure in AHRF patients, demonstrating improved performance over traditional indices in internal validation and showing potential for decision support in select healthcare settings.<\/jats:p>","DOI":"10.1038\/s41598-025-16061-x","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T17:24:34Z","timestamp":1755537874000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Real-time prediction of HFNC treatment failure in acute hypoxemic respiratory failure using machine learning"],"prefix":"10.1038","volume":"15","author":[{"given":"Xiaojie","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunliang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingyan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiquan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiameng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanjun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panpan","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,18]]},"reference":[{"key":"16061_CR1","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/S0025-7125(16)31188-9","volume":"67","author":"R Balk","year":"1983","unstructured":"Balk, R. & Bone, R. C. Classification of acute respiratory failure. Med. Clin. N. Am. 67, 551\u2013556 (1983).","journal-title":"Med. Clin. N. Am."},{"key":"16061_CR2","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1016\/j.pulmoe.2021.01.005","volume":"27","author":"ML Vega","year":"2021","unstructured":"Vega, M. L. & Pisani, L. Nasal high flow oxygen in acute respiratory failure. Pulmonology 27, 240\u2013247 (2021).","journal-title":"Pulmonology"},{"key":"16061_CR3","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1164\/rccm.201605-0916OC","volume":"195","author":"T Mauri","year":"2017","unstructured":"Mauri, T. et al. Physiologic effects of high-flow nasal cannula in acute hypoxemic respiratory failure. Am. J. Respir. Crit. Care Med. 195, 1207\u20131215 (2017).","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"16061_CR4","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1186\/s12931-018-0908-7","volume":"19","author":"Z Xu","year":"2018","unstructured":"Xu, Z. et al. High-flow nasal cannula in adults with acute respiratory failure and after extubation: a systematic review and meta-analysis. Respir. Res. 19, 202 (2018).","journal-title":"Respir. Res."},{"key":"16061_CR5","doi-asserted-by":"publisher","first-page":"1465","DOI":"10.1001\/jama.2019.14901","volume":"322","author":"AW Thille","year":"2019","unstructured":"Thille, A. W. et al. Effect of postextubation high-flow nasal oxygen with noninvasive ventilation vs high-flow nasal oxygen alone on reintubation among patients at high risk of extubation failure: a randomized clinical trial. JAMA 322, 1465 (2019).","journal-title":"JAMA"},{"key":"16061_CR6","doi-asserted-by":"publisher","first-page":"1780","DOI":"10.1007\/s00134-011-2354-6","volume":"37","author":"B Sztrymf","year":"2011","unstructured":"Sztrymf, B. et al. Beneficial effects of humidified high flow nasal oxygen in critical care patients: a prospective pilot study. Intensive Care Med. 37, 1780\u20131786 (2011).","journal-title":"Intensive Care Med."},{"key":"16061_CR7","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.jcrc.2021.03.001","volume":"64","author":"R Patnaik","year":"2021","unstructured":"Patnaik, R. et al. Evaluation of ventilator associated events in critically ill patients with invasive mechanical ventilation: A prospective cohort study at a resource limited setting in Northern India. J. Crit. Care 64, 29\u201335 (2021).","journal-title":"J. Crit. Care"},{"key":"16061_CR8","doi-asserted-by":"publisher","first-page":"2561","DOI":"10.1042\/BCJ20160002","volume":"473","author":"AM Evans","year":"2016","unstructured":"Evans, A. M., Mahmoud, A. D., Moral-Sanz, J. & Hartmann, S. The emerging role of AMPK in the regulation of breathing and oxygen supply. Biochem. J. 473, 2561\u20132572 (2016).","journal-title":"Biochem. J."},{"key":"16061_CR9","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.jinf.2009.05.009","volume":"59","author":"P Linsuwanon","year":"2009","unstructured":"Linsuwanon, P. et al. High prevalence of human rhinovirus C infection in Thai children with acute lower respiratory tract disease. J. Infect. 59, 115\u2013121 (2009).","journal-title":"J. Infect."},{"key":"16061_CR10","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1007\/s00134-015-3693-5","volume":"41","author":"BJ Kang","year":"2015","unstructured":"Kang, B. J. et al. Failure of high-flow nasal cannula therapy may delay intubation and increase mortality. Intensive Care Med. 41, 623\u2013632 (2015).","journal-title":"Intensive Care Med."},{"key":"16061_CR11","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1097\/CCM.0000000000001359","volume":"44","author":"KN Kangelaris","year":"2016","unstructured":"Kangelaris, K. N. et al. Timing of intubation and clinical outcomes in adults with acute respiratory distress syndrome. Crit. Care Med. 44, 120\u2013129 (2016).","journal-title":"Crit. Care Med."},{"key":"16061_CR12","doi-asserted-by":"crossref","unstructured":"R, M.-A. et al. Predictors of failure with high-flow nasal oxygen therapy in COVID-19 patients with acute respiratory failure: a multicenter observational study. J. Intensive Care 9, (2021).","DOI":"10.1186\/s40560-021-00538-8"},{"key":"16061_CR13","doi-asserted-by":"publisher","first-page":"2238","DOI":"10.1007\/s00134-020-06228-7","volume":"46","author":"J-D Ricard","year":"2020","unstructured":"Ricard, J.-D. et al. Use of nasal high flow oxygen during acute respiratory failure. Intensive Care Med. 46, 2238\u20132247 (2020).","journal-title":"Intensive Care Med."},{"key":"16061_CR14","doi-asserted-by":"crossref","unstructured":"Nedel, W. L., Deutschendorf, C. & Moraes Rodrigues Filho, E. High-flow nasal cannula in critically ill subjects with or at risk for respiratory failure: a systematic review and meta-analysis. Respir. Care 62, 123\u2013132 (2017).","DOI":"10.4187\/respcare.04831"},{"key":"16061_CR15","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s12931-022-01951-9","volume":"23","author":"Z Junhai","year":"2022","unstructured":"Junhai, Z., Jing, Y., Beibei, C. & Li, L. The value of ROX index in predicting the outcome of high flow nasal cannula: a systematic review and meta-analysis. Respir. Res. 23, 33 (2022).","journal-title":"Respir. Res."},{"key":"16061_CR16","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1186\/s12890-022-02017-8","volume":"22","author":"Z Li","year":"2022","unstructured":"Li, Z. et al. Prediction of high-flow nasal cannula outcomes at the early phase using the modified respiratory rate oxygenation index. BMC Pulm. Med. 22, 227 (2022).","journal-title":"BMC Pulm. Med."},{"key":"16061_CR17","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1186\/s40560-020-00458-z","volume":"8","author":"KJ Goh","year":"2020","unstructured":"Goh, K. J. et al. Early prediction of high flow nasal cannula therapy outcomes using a modified ROX index incorporating heart rate. J. Intensive Care 8, 41 (2020).","journal-title":"J. Intensive Care"},{"key":"16061_CR18","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.pulmoe.2022.02.008","volume":"28","author":"A Gallardo","year":"2022","unstructured":"Gallardo, A., Zamarr\u00f3n-L\u00f3pez, E., Deloya-Tomas, E. & P\u00e9rez-Nieto, O. R. Advantages and limitations of the ROX index. Pulmonology 28, 320\u2013321 (2022).","journal-title":"Pulmonology"},{"key":"16061_CR19","doi-asserted-by":"publisher","first-page":"5407","DOI":"10.1007\/s12652-020-01963-7","volume":"14","author":"TR Gadekallu","year":"2023","unstructured":"Gadekallu, T. R. et al. Deep neural networks to predict diabetic retinopathy. J. Ambient Intell. Hum. Comput. 14, 5407\u20135420 (2023).","journal-title":"J. Ambient Intell. Hum. Comput."},{"key":"16061_CR20","doi-asserted-by":"crossref","unstructured":"Shah, N., Srivastava, G., Savage, D. W. & Mago, V. Assessing Canadians health activity and nutritional habits through social media. Front. Public Health. 7, (2020).","DOI":"10.3389\/fpubh.2019.00400"},{"key":"16061_CR21","doi-asserted-by":"publisher","first-page":"8869","DOI":"10.1109\/ACCESS.2017.2694446","volume":"5","author":"M Chen","year":"2017","unstructured":"Chen, M., Hao, Y., Hwang, K., Wang, L. & Wang, L. Disease prediction by machine learning over big data from healthcare communities. IEEE Access 5, 8869\u20138879 (2017).","journal-title":"IEEE Access"},{"key":"16061_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","volume":"10","author":"AEW Johnson","year":"2023","unstructured":"Johnson, A. E. W. et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci. Data 10, 1 (2023).","journal-title":"Sci. Data"},{"key":"16061_CR23","doi-asserted-by":"publisher","first-page":"2185","DOI":"10.1056\/NEJMoa1503326","volume":"372","author":"J-P Frat","year":"2015","unstructured":"Frat, J.-P. et al. High-flow oxygen through nasal cannula in acute hypoxemic respiratory failure. N. Engl. J. Med. 372, 2185\u20132196 (2015).","journal-title":"N. Engl. J. Med."},{"key":"16061_CR24","doi-asserted-by":"publisher","DOI":"10.1002\/ams2.461","volume":"7","author":"Y Koga","year":"2020","unstructured":"Koga, Y. et al. Comparison of high-flow nasal cannula oxygen therapy and non-invasive ventilation as first-line therapy in respiratory failure: a multicenter retrospective study. Acute Med. Surg. 7, e461 (2020).","journal-title":"Acute Med. Surg."},{"key":"16061_CR25","doi-asserted-by":"crossref","unstructured":"Matthay, M. A. et al. A New Global Definition of Acute Respiratory Distress Syndrome. Am. J. Respir. Crit. Care Med. 209(1), 37\u201347 (2024).","DOI":"10.1164\/rccm.202308-1369ED"},{"key":"16061_CR26","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.jcrc.2016.05.022","volume":"35","author":"O Roca","year":"2016","unstructured":"Roca, O. et al. Predicting success of high-flow nasal cannula in pneumonia patients with hypoxemic respiratory failure: The utility of the ROX index. J. Crit. Care 35, 200\u2013205 (2016).","journal-title":"J. Crit. Care"},{"key":"16061_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.104193","volume":"79","author":"H Wang","year":"2023","unstructured":"Wang, H. et al. Invasive mechanical ventilation probability estimation using machine learning methods based on non-invasive parameters. Biomed. Signal Process. Control 79, 104193 (2023).","journal-title":"Biomed. Signal Process. Control"},{"key":"16061_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107328","volume":"230","author":"W Wu","year":"2023","unstructured":"Wu, W. et al. Developing and evaluating a machine-learning-based algorithm to predict the incidence and severity of ARDS with continuous non-invasive parameters from ordinary monitors and ventilators. Comput. Methods Progr. Biomed. 230, 107328 (2023).","journal-title":"Comput. Methods Progr. Biomed."},{"key":"16061_CR29","doi-asserted-by":"publisher","first-page":"441","DOI":"10.2471\/BLT.06.034421","volume":"85","author":"Z Mei","year":"2007","unstructured":"Mei, Z. & Grummer-Strawn, L. M. Standard deviation of anthropometric Z-scores as a data quality assessment tool using the 2006 WHO growth standards: a cross country analysis. Bull. World Health Organ. 85, 441\u2013448 (2007).","journal-title":"Bull. World Health Organ."},{"key":"16061_CR30","doi-asserted-by":"publisher","unstructured":"Allen, D. Automatic one-hot re-encoding for FPGAs. In Field-Programmable Gate Arrays: Architecture and Tools for Rapid Prototyping (eds. Gr\u00fcnbacher, H. & Hartenstein, R. W.) 71\u201377 (Springer, Berlin, Heidelberg, 1993). https:\/\/doi.org\/10.1007\/3-540-57091-8_31.","DOI":"10.1007\/3-540-57091-8_31"},{"key":"16061_CR31","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1016\/S1532-0464(03)00034-0","volume":"35","author":"S Dreiseitl","year":"2002","unstructured":"Dreiseitl, S. & Ohno-Machado, L. Logistic regression and artificial neural network classification models: a methodology review. J. Biomed. Inform. 35, 352\u2013359 (2002).","journal-title":"J. Biomed. Inform."},{"key":"16061_CR32","doi-asserted-by":"crossref","unstructured":"Nouraei, S. a. R., Huys, Q. J. M., Chatrath, P., Powles, J. & Harcourt, J. P. Screening patients with sensorineural hearing loss for vestibular schwannoma using a Bayesian classifier. Clin. Otolaryngol. 32, 248\u2013254 (2007).","DOI":"10.1111\/j.1365-2273.2007.01460.x"},{"key":"16061_CR33","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1186\/1472-6947-8-56","volume":"8","author":"T Verplancke","year":"2008","unstructured":"Verplancke, T. et al. Support vector machine versus logistic regression modeling for prediction of hospital mortality in critically ill patients with haematological malignancies. BMC Med. Inform. Decis. Mak. 8, 56 (2008).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"16061_CR34","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1016\/j.media.2016.08.009","volume":"35","author":"A Jog","year":"2017","unstructured":"Jog, A., Carass, A., Roy, S., Pham, D. L. & Prince, J. L. Random forest regression for magnetic resonance image synthesis. Med. Image Anal. 35, 475\u2013488 (2017).","journal-title":"Med. Image Anal."},{"key":"16061_CR35","unstructured":"Ke, G. et al. LightGBM: a highly efficient gradient boosting decision tree. In Proceedings of the 31st International Conference on Neural Information Processing Systems 3149\u20133157 (Curran Associates Inc., 2017)."},{"issue":"8","key":"16061_CR36","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997).","journal-title":"Neural Comput."},{"key":"16061_CR37","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1007\/s40846-023-00777-0","volume":"43","author":"NP Pinto","year":"2023","unstructured":"Pinto, N. P., Amaral, J. L. M., Lopes, A. J. & Melo, P. L. Diagnosis of respiratory changes in cystic fibrosis using a soft voting ensemble with bayesian networks and machine learning algorithms. J. Med. Biol. Eng. 43, 112\u2013123 (2023).","journal-title":"J. Med. Biol. Eng."},{"key":"16061_CR38","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1164\/rccm.201803-0589OC","volume":"199","author":"O Roca","year":"2019","unstructured":"Roca, O. et al. An index combining respiratory rate and oxygenation to predict outcome of nasal high-flow therapy. Am. J. Respir. Crit. Care Med. 199, 1368\u20131376 (2019).","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"16061_CR39","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1164\/rccm.202203-0561LE","volume":"206","author":"D Chen","year":"2022","unstructured":"Chen, D. et al. A Novel index to predict the failure of high-flow nasal cannula in patients with acute hypoxemic respiratory failure: a pilot study. Am. J. Respir. Crit. Care Med. 206, 910\u2013913 (2022).","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"16061_CR40","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1007\/s40484-016-0081-2","volume":"4","author":"Y Jiao","year":"2016","unstructured":"Jiao, Y. & Du, P. Performance measures in evaluating machine learning based bioinformatics predictors for classifications. Quant. Biol. 4, 320\u2013330 (2016).","journal-title":"Quant. Biol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-16061-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-16061-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-16061-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T05:19:38Z","timestamp":1757395178000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-16061-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,18]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["16061"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-16061-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,18]]},"assertion":[{"value":"4 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"30245"}}