{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T10:05:01Z","timestamp":1775556301833,"version":"3.50.1"},"reference-count":81,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T00:00:00Z","timestamp":1766361600000},"content-version":"vor","delay-in-days":3,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["205321_176005"],"award-info":[{"award-number":["205321_176005"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["205321_176005"],"award-info":[{"award-number":["205321_176005"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["205321_176005"],"award-info":[{"award-number":["205321_176005"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["205321_176005"],"award-info":[{"award-number":["205321_176005"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["205321_176005"],"award-info":[{"award-number":["205321_176005"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["205321_176005"],"award-info":[{"award-number":["205321_176005"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ETH Core funding","award":["Core-GR"],"award-info":[{"award-number":["Core-GR"]}]},{"name":"ETH Core funding","award":["Core-GR"],"award-info":[{"award-number":["Core-GR"]}]},{"name":"ETH Core funding","award":["Core-GR"],"award-info":[{"award-number":["Core-GR"]}]},{"name":"ETH Core funding","award":["Core-GR"],"award-info":[{"award-number":["Core-GR"]}]},{"name":"ETH Core funding","award":["Core-GR"],"award-info":[{"award-number":["Core-GR"]}]},{"name":"ETH Core funding","award":["Core-GR"],"award-info":[{"award-number":["Core-GR"]}]},{"name":"ETH Core funding","award":["Core-GR"],"award-info":[{"award-number":["Core-GR"]}]},{"name":"ETH Core funding","award":["Core-GR"],"award-info":[{"award-number":["Core-GR"]}]},{"name":"ETH Strategic Focus Area \u201cPersonalized Health and Related Technologies (PHRT)\u201d","award":["#2022-278"],"award-info":[{"award-number":["#2022-278"]}]},{"name":"ETH Strategic Focus Area \u201cPersonalized Health and Related Technologies (PHRT)\u201d","award":["#2022-278"],"award-info":[{"award-number":["#2022-278"]}]},{"name":"ETH Strategic Focus Area \u201cPersonalized Health and Related Technologies (PHRT)\u201d","award":["#2022-278"],"award-info":[{"award-number":["#2022-278"]}]},{"name":"ETH Strategic Focus Area \u201cPersonalized Health and Related Technologies (PHRT)\u201d","award":["#2022-278"],"award-info":[{"award-number":["#2022-278"]}]},{"name":"ETH Strategic Focus Area \u201cPersonalized Health and Related Technologies (PHRT)\u201d","award":["#2022-278"],"award-info":[{"award-number":["#2022-278"]}]},{"name":"ETH Strategic Focus Area \u201cPersonalized Health and Related Technologies (PHRT)\u201d","award":["#2022-278"],"award-info":[{"award-number":["#2022-278"]}]},{"name":"ETH Strategic Focus Area \u201cPersonalized Health and Related Technologies (PHRT)\u201d","award":["#2022-278"],"award-info":[{"award-number":["#2022-278"]}]},{"name":"ETH Strategic Focus Area \u201cPersonalized Health and Related Technologies (PHRT)\u201d","award":["#2022-278"],"award-info":[{"award-number":["#2022-278"]}]},{"name":"AI Center at ETH Zurich","award":["Fellowship-AP"],"award-info":[{"award-number":["Fellowship-AP"]}]},{"name":"AI Center at ETH Zurich","award":["Fellowship-AP"],"award-info":[{"award-number":["Fellowship-AP"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Acute hypoxemic respiratory failure (RF) occurs frequently in critically ill patients and is associated with substantial morbidity, mortality and resource use. We developed a comprehensive machine-learning\u2013based monitoring system to support ICU physicians in managing RF through early detection, continuous monitoring, assessment of extubation readiness, and prediction of extubation failure (EF). In study patients, the model predicted 80% of RF events with 45% precision, identifying 65% of events more than 10\u2009hours before, significantly outperforming standard clinical monitoring based on oxygenation index. The model was successfully validated in an external ICU cohort. We also demonstrated how predicted EF risk could help prevent extubation failure and unnecessarily prolonged ventilation. Lastly, we illustrated how prediction of RF risk, along with ventilator need and extubation readiness, helped ICU resource planning for mechanical ventilation. Our model predicted ICU-level ventilator demand 8\u201316\u2009hours ahead, with a mean absolute error of 0.4 ventilators per 10 patients.<\/jats:p>","DOI":"10.1038\/s41746-025-02081-4","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T21:19:09Z","timestamp":1766179149000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["RMS: a ML-based system for ICU respiratory monitoring and resource planning"],"prefix":"10.1038","volume":"8","author":[{"given":"Matthias","family":"H\u00fcser","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinrui","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Faltys","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aliz\u00e9e","family":"Pace","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Berger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marine","family":"Hoche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephanie L.","family":"Hyland","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hugo","family":"Y\u00e8che","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Burger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tobias M.","family":"Merz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gunnar","family":"R\u00e4tsch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,19]]},"reference":[{"key":"2081_CR1","doi-asserted-by":"publisher","first-page":"S296","DOI":"10.1097\/01.CCM.0000057906.89552.8F","volume":"31","author":"JL Vincent","year":"2003","unstructured":"Vincent, J. L., Sakr, Y. & Ranieri, V. M. Epidemiology and outcome of acute respiratory failure in intensive care unit patients. Crit. Care Med. 31, S296\u2013S299 (2003).","journal-title":"Crit. Care Med."},{"key":"2081_CR2","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1001\/jama.2016.0291","volume":"315","author":"G Bellani","year":"2016","unstructured":"Bellani, G. et al. Epidemiology, patterns of care, and mortality for patients with acute respiratory distress syndrome in intensive care units in 50 countries. JAMA 315, 788\u2013800 (2016).","journal-title":"JAMA"},{"key":"2081_CR3","doi-asserted-by":"crossref","unstructured":"Vincent, J.-L. et al. The epidemiology of acute respiratory failure in critically ill patients(*). Chest 121, 1602\u20131609 (2002).","DOI":"10.1378\/chest.121.5.1602"},{"key":"2081_CR4","first-page":"316","volume":"8","author":"Y Donchin","year":"2002","unstructured":"Donchin, Y. & Seagull, F. J. The hostile environment of the intensive care unit. Curr. Opin. Crit. Care 8, 316\u2013320 (2002).","journal-title":"Curr. Opin. Crit. Care"},{"key":"2081_CR5","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1016\/j.chest.2018.04.037","volume":"154","author":"LN Sanchez-Pinto","year":"2018","unstructured":"Sanchez-Pinto, L. N., Luo, Y. & Churpek, M. M. Big data and data science in critical care. Chest 154, 1239\u20131248 (2018).","journal-title":"Chest"},{"key":"2081_CR6","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.cnc.2018.02.001","volume":"30","author":"S-F Wung","year":"2018","unstructured":"Wung, S.-F., Malone, D. C. & Szalacha, L. Sensory overload and technology in critical care. Crit. Care Nurs. Clin. North Am. 30, 179\u2013190 (2018).","journal-title":"Crit. Care Nurs. Clin. North Am."},{"key":"2081_CR7","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1038\/s41591-020-0789-4","volume":"26","author":"SL Hyland","year":"2020","unstructured":"Hyland, S. L. et al. Early prediction of circulatory failure in the intensive care unit using machine learning. Nat. Med. 26, 364\u2013373 (2020).","journal-title":"Nat. Med."},{"key":"2081_CR8","doi-asserted-by":"publisher","first-page":"1050849","DOI":"10.3389\/fphys.2022.1050849","volume":"13","author":"Y Bai","year":"2022","unstructured":"Bai, Y., Xia, J., Huang, X., Chen, S. & Zhan, Q. Using machine learning for the early prediction of sepsis-associated ARDS in the ICU and identification of clinical phenotypes with differential responses to treatment. Front. Physiol. 13, 1050849 (2022).","journal-title":"Front. Physiol."},{"key":"2081_CR9","doi-asserted-by":"crossref","unstructured":"Lam, C., Thapa, R., Maharjan, J. & Rahmani, K. Multitask learning with recurrent neural networks for acute respiratory distress syndrome prediction using only electronic health record data: model development and validation study. JMIR Med. Inform. 10, e36202 (2022).","DOI":"10.2196\/36202"},{"key":"2081_CR10","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1186\/s12890-022-01963-7","volume":"22","author":"J Wu","year":"2022","unstructured":"Wu, J. et al. Early prediction of moderate-to-severe condition of inhalation-induced acute respiratory distress syndrome via interpretable machine learning. BMC Pulm. Med. 22, 193 (2022).","journal-title":"BMC Pulm. Med."},{"key":"2081_CR11","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.jcrc.2020.07.019","volume":"60","author":"S Le","year":"2020","unstructured":"Le, S. et al. Supervised machine learning for the early prediction of acute respiratory distress syndrome (ARDS). J. Crit. Care 60, 96\u2013102 (2020).","journal-title":"J. Crit. Care"},{"key":"2081_CR12","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-019-2075-0","volume":"17","author":"X-F Ding","year":"2019","unstructured":"Ding, X.-F. et al. Predictive model for acute respiratory distress syndrome events in ICU patients in China using machine learning algorithms: a secondary analysis of a cohort study. J. Transl. Med. 17, 326 (2019).","journal-title":"J. Transl. Med."},{"key":"2081_CR13","doi-asserted-by":"publisher","first-page":"e28","DOI":"10.2196\/medinform.5909","volume":"4","author":"T Desautels","year":"2016","unstructured":"Desautels, T. et al. Prediction of sepsis in the intensive care unit with minimal electronic health record data: a machine learning approach. JMIR Med. Inf. 4, e28 (2016).","journal-title":"JMIR Med. Inf."},{"key":"2081_CR14","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2021.754348","volume":"9","author":"D Wang","year":"2021","unstructured":"Wang, D. et al. A machine learning model for accurate prediction of sepsis in ICU patients. Front. Public Health 9, 754348 (2021).","journal-title":"Front. Public Health"},{"key":"2081_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2023.102124","volume":"62","author":"M Moor","year":"2023","unstructured":"Moor, M. et al. Predicting sepsis using deep learning across international sites: a retrospective development and validation study. EClinicalMedicine 62, 102124 (2023).","journal-title":"EClinicalMedicine"},{"key":"2081_CR16","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","volume":"572","author":"N Toma\u0161ev","year":"2019","unstructured":"Toma\u0161ev, N. et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature 572, 116\u2013119 (2019).","journal-title":"Nature"},{"key":"2081_CR17","doi-asserted-by":"publisher","unstructured":"Faltys, M. et al. HiRID, a high time-resolution ICU dataset. PhysioNet https:\/\/doi.org\/10.13026\/NKWC-JS72 (2021).","DOI":"10.13026\/NKWC-JS72"},{"key":"2081_CR18","doi-asserted-by":"crossref","unstructured":"Goldberger, A. L. et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101, E215-20 (2000).","DOI":"10.1161\/01.CIR.101.23.e215"},{"key":"2081_CR19","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/51.932728","volume":"20","author":"GB Moody","year":"2001","unstructured":"Moody, G. B., Mark, R. G. & Goldberger, A. L. PhysioNet: a web-based resource for the study of physiologic signals. IEEE Eng. Med. Biol. Mag. 20, 70\u201375 (2001).","journal-title":"IEEE Eng. Med. Biol. Mag."},{"key":"2081_CR20","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1142\/S0218488502001648","volume":"10","author":"L Sweeney","year":"2002","unstructured":"Sweeney, L. K-anonymity: A model for protecting privacy. Int. J. Uncertain. Fuzziness Knowl. Based Syst. 10, 557\u2013570 (2002).","journal-title":"Int. J. Uncertain. Fuzziness Knowl. Based Syst."},{"key":"2081_CR21","doi-asserted-by":"publisher","first-page":"e563","DOI":"10.1097\/CCM.0000000000004916","volume":"49","author":"PJ Thoral","year":"2021","unstructured":"Thoral, P. J. et al. Sharing ICU Patient Data Responsibly Under the Society of Critical Care Medicine\/European Society of Intensive Care Medicine Joint Data Science Collaboration: the Amsterdam University Medical Centers Database (AmsterdamUMCdb) Example. Crit. Care Med. 49, e563\u2013e577 (2021).","journal-title":"Crit. Care Med."},{"key":"2081_CR22","unstructured":"Patel, S., Jose, A. & Mohiuddin, S. S. PhYsiology, Oxygen Transport and Carbon Dioxide Dissociation Curve (StatPearls Publishing, 2023)."},{"key":"2081_CR23","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1055\/s-0043-1771160","volume":"44","author":"PD Wagner","year":"2023","unstructured":"Wagner, P. D. Blood gas transport: carriage of oxygen and carbon dioxide in blood. Semin. Respir. Crit. Care Med. 44, 569\u2013583 (2023).","journal-title":"Semin. Respir. Crit. Care Med."},{"key":"2081_CR24","doi-asserted-by":"crossref","unstructured":"Pandharipande, P. P. et al. Derivation and validation of Spo2\/Fio2 ratio to impute for Pao2\/Fio2 ratio in the respiratory component of the sequential organ failure assessment score. Crit. Care Med. 37, 1317\u20131321 (2009).","DOI":"10.1097\/CCM.0b013e31819cefa9"},{"key":"2081_CR25","doi-asserted-by":"publisher","first-page":"902","DOI":"10.1152\/jappl.1989.67.2.902","volume":"67","author":"RK Ellis","year":"1989","unstructured":"Ellis, R. K. Determination of PO2 from saturation. J. Appl. Physiol. 67, 902 (1989).","journal-title":"J. Appl. Physiol."},{"key":"2081_CR26","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/j.chest.2016.01.003","volume":"150","author":"SM Brown","year":"2016","unstructured":"Brown, S. M. et al. Nonlinear imputation of Pao2\/Fio2 From Spo2\/Fio2 among patients with acute respiratory distress syndrome. Chest 150, 307\u2013313 (2016).","journal-title":"Chest"},{"key":"2081_CR27","first-page":"3146","volume":"30","author":"G Ke","year":"2017","unstructured":"Ke, G. et al. LightGBM: a highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 30, 3146\u20133154 (2017).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2081_CR28","unstructured":"Y\u00e8che, H. et al. HiRID-ICU-Benchmark --- a comprehensive machine learning benchmark on high-resolution ICU data. In Proc. Neural Information Processing Systems Track on Datasets and Benchmarks Vol. 1 (NeurIPS, 2021)."},{"key":"2081_CR29","doi-asserted-by":"crossref","unstructured":"Hoche, M., Mineeva, O., Burger, M., Blasimme, A. & R\u00e4tsch, G. FAMEWS: a fairness auditing tool for medical early-warning systems. In Proc. fifth Conference on Health, Inference, and Learning Vol. 248, 297\u2013311 (PMLR, 2024).","DOI":"10.1101\/2024.02.08.24302458"},{"key":"2081_CR30","unstructured":"Lundberg, S. M. & Lee, S.-I. A Unified Approach to Interpreting Model Predictions. in Advances in Neural Information Processing Systems 30 (eds. Guyon, I. et al.) 4765\u20134774 (Curran Associates, Inc., 2017)."},{"key":"2081_CR31","doi-asserted-by":"publisher","unstructured":"Lundberg, S. M., Erion, G. G. & Lee, S.-I. Consistent individualized feature attribution for tree ensembles. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1802.03888 (2018).","DOI":"10.48550\/arXiv.1802.03888"},{"key":"2081_CR32","first-page":"2579","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten, L., Van, D. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008).","journal-title":"J. Mach. Learn. Res."},{"key":"2081_CR33","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.4187\/respcare.06878","volume":"64","author":"JB Scott","year":"2019","unstructured":"Scott, J. B., De Vaux, L., Dills, C. & Strickland, S. L. Mechanical ventilation alarms and alarm fatigue. Respir. Care 64, 1308\u20131313 (2019).","journal-title":"Respir. Care"},{"key":"2081_CR34","doi-asserted-by":"publisher","first-page":"1539","DOI":"10.1007\/s00134-022-06825-8","volume":"48","author":"R Cinotti","year":"2022","unstructured":"Cinotti, R. et al. Extubation in neurocritical care patients: the ENIO international prospective study. Intensive Care Med. 48, 1539\u20131550 (2022).","journal-title":"Intensive Care Med."},{"key":"2081_CR35","doi-asserted-by":"publisher","first-page":"e0214465","DOI":"10.1371\/journal.pone.0214465","volume":"14","author":"D Zeiberg","year":"2019","unstructured":"Zeiberg, D. et al. Machine learning for patient risk stratification for acute respiratory distress syndrome. PLoS ONE 14, e0214465 (2019).","journal-title":"PLoS ONE"},{"key":"2081_CR36","doi-asserted-by":"publisher","first-page":"e0257056","DOI":"10.1371\/journal.pone.0257056","volume":"16","author":"L Singhal","year":"2021","unstructured":"Singhal, L. et al. eARDS: a multi-center validation of an interpretable machine learning algorithm of early onset acute respiratory distress syndrome (ARDS) among critically ill adults with COVID-19. PLoS ONE 16, e0257056 (2021).","journal-title":"PLoS ONE"},{"key":"2081_CR37","doi-asserted-by":"publisher","DOI":"10.2196\/24246","volume":"23","author":"S Bolourani","year":"2021","unstructured":"Bolourani, S. et al. A machine learning prediction model of respiratory failure within 48\u2009h of patient admission for COVID-19: model development and validation. J. Med. Internet Res. 23, e24246 (2021).","journal-title":"J. Med. Internet Res."},{"key":"2081_CR38","doi-asserted-by":"publisher","first-page":"e0239172","DOI":"10.1371\/journal.pone.0239172","volume":"15","author":"D Ferrari","year":"2020","unstructured":"Ferrari, D. et al. Machine learning in predicting respiratory failure in patients with COVID-19 pneumonia-Challenges, strengths, and opportunities in a global health emergency. PLoS ONE 15, e0239172 (2020).","journal-title":"PLoS ONE"},{"key":"2081_CR39","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-14758-x","volume":"12","author":"I Bendavid","year":"2022","unstructured":"Bendavid, I. et al. A novel machine learning model to predict respiratory failure and invasive mechanical ventilation in critically ill patients suffering from COVID-19. Sci. Rep. 12, 10573 (2022).","journal-title":"Sci. Rep."},{"key":"2081_CR40","doi-asserted-by":"publisher","first-page":"961252","DOI":"10.3389\/fmed.2022.961252","volume":"9","author":"Y Igarashi","year":"2022","unstructured":"Igarashi, Y. et al. Machine learning for predicting successful extubation in patients receiving mechanical ventilation. Front. Med. 9, 961252 (2022).","journal-title":"Front. Med."},{"key":"2081_CR41","doi-asserted-by":"publisher","first-page":"1167445","DOI":"10.3389\/fmed.2023.1167445","volume":"10","author":"K-Y Huang","year":"2023","unstructured":"Huang, K.-Y. et al. Developing a machine-learning model for real-time prediction of successful extubation in mechanically ventilated patients using time-series ventilator-derived parameters. Front. Med. 10, 1167445 (2023).","journal-title":"Front. Med."},{"key":"2081_CR42","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-022-00309-7","volume":"15","author":"Z Zeng","year":"2022","unstructured":"Zeng, Z., Tang, X., Liu, Y., He, Z. & Gong, X. Interpretable recurrent neural network models for dynamic prediction of the extubation failure risk in patients with invasive mechanical ventilation in the intensive care unit. BioData Min. 15, 21 (2022).","journal-title":"BioData Min."},{"key":"2081_CR43","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1186\/s12890-022-02096-7","volume":"22","author":"H Wang","year":"2022","unstructured":"Wang, H. et al. Early prediction of noninvasive ventilation failure after extubation: development and validation of a machine-learning model. BMC Pulm. Med. 22, 304 (2022).","journal-title":"BMC Pulm. Med."},{"key":"2081_CR44","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1272\/jnms.JNMS.2021_88-508","volume":"88","author":"T Otaguro","year":"2021","unstructured":"Otaguro, T. et al. Machine learning for prediction of successful extubation of mechanical ventilated patients in an intensive care unit: a retrospective observational study. J. Nippon Med. Sch. 88, 408\u2013417 (2021).","journal-title":"J. Nippon Med. Sch."},{"key":"2081_CR45","doi-asserted-by":"publisher","first-page":"676343","DOI":"10.3389\/fmed.2021.676343","volume":"8","author":"Q-Y Zhao","year":"2021","unstructured":"Zhao, Q.-Y. et al. Development and validation of a machine-learning model for prediction of extubation failure in intensive care units. Front. Med. 8, 676343 (2021).","journal-title":"Front. Med."},{"key":"2081_CR46","doi-asserted-by":"publisher","first-page":"150960","DOI":"10.1109\/ACCESS.2019.2946980","volume":"7","author":"T Chen","year":"2019","unstructured":"Chen, T. et al. Prediction of extubation failure for intensive care unit patients using light gradient boosting machine. IEEE Access 7, 150960\u2013150968 (2019).","journal-title":"IEEE Access"},{"key":"2081_CR47","doi-asserted-by":"publisher","first-page":"e0271227","DOI":"10.1371\/journal.pone.0271227","volume":"17","author":"N Lazzarini","year":"2022","unstructured":"Lazzarini, N., Filippoupolitis, A., Manzione, P. & Eleftherohorinou, H. A machine learning model on real world data for predicting progression to acute respiratory distress syndrome (ARDS) among COVID-19 patients. PLoS ONE 17, e0271227 (2022).","journal-title":"PLoS ONE"},{"key":"2081_CR48","doi-asserted-by":"crossref","unstructured":"Sayed, M., Ria\u00f1o, D. & Villar, J. Predicting duration of mechanical ventilation in acute respiratory distress syndrome using supervised machine learning. J. Clin. Med. Res. 10, 3824 (2021).","DOI":"10.3390\/jcm10173824"},{"key":"2081_CR49","doi-asserted-by":"publisher","first-page":"102087","DOI":"10.1016\/j.artmed.2021.102087","volume":"117","author":"Y Jia","year":"2021","unstructured":"Jia, Y., Kaul, C., Lawton, T., Murray-Smith, R. & Habli, I. Prediction of weaning from mechanical ventilation using convolutional neural networks. Artif. Intell. Med. 117, 102087 (2021).","journal-title":"Artif. Intell. Med."},{"key":"2081_CR50","doi-asserted-by":"crossref","unstructured":"Zeng, L. et al. VentSR: a self-rectifying deep learning method for extubation readiness prediction. In Proc. 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 1369\u20131374 (IEEE, 2022).","DOI":"10.1109\/BIBM55620.2022.9995010"},{"key":"2081_CR51","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.1016\/j.chest.2020.12.009","volume":"159","author":"SP Shashikumar","year":"2021","unstructured":"Shashikumar, S. P. et al. Development and prospective validation of a deep learning algorithm for predicting need for mechanical ventilation. Chest 159, 2264\u20132273 (2021).","journal-title":"Chest"},{"key":"2081_CR52","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-77893-3","volume":"10","author":"BMK Siu","year":"2020","unstructured":"Siu, B. M. K., Kwak, G. H., Ling, L. & Hui, P. Predicting the need for intubation in the first 24 h after critical care admission using machine learning approaches. Sci. Rep. 10, 20931 (2020).","journal-title":"Sci. Rep."},{"key":"2081_CR53","doi-asserted-by":"publisher","first-page":"e151","DOI":"10.1097\/CCM.0000000000002849","volume":"46","author":"PD Sottile","year":"2018","unstructured":"Sottile, P. D., Albers, D., Higgins, C., Mckeehan, J. & Moss, M. M. The association between ventilator dyssynchrony, delivered tidal volume, and sedation using a novel automated ventilator dyssynchrony detection algorithm. Crit. Care Med. 46, e151\u2013e157 (2018).","journal-title":"Crit. Care Med."},{"key":"2081_CR54","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1177\/08850666231166349","volume":"38","author":"L Lapp","year":"2023","unstructured":"Lapp, L., Roper, M., Kavanagh, K., Bouamrane, M.-M. & Schraag, S. Dynamic prediction of patient outcomes in the intensive care unit: a scoping review of the state-of-the-art. J. Intensive Care Med. 38, 575\u2013591 (2023).","journal-title":"J. Intensive Care Med."},{"key":"2081_CR55","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.amsu.2016.09.002","volume":"11","author":"J Calvert","year":"2016","unstructured":"Calvert, J. et al. Using electronic health record collected clinical variables to predict medical intensive care unit mortality. Ann. Med Surg. 11, 52\u201357 (2016).","journal-title":"Ann. Med Surg."},{"key":"2081_CR56","doi-asserted-by":"publisher","first-page":"102003","DOI":"10.1016\/j.artmed.2020.102003","volume":"112","author":"L Roggeveen","year":"2021","unstructured":"Roggeveen, L. et al. Transatlantic transferability of a new reinforcement learning model for optimizing haemodynamic treatment for critically ill patients with sepsis. Artif. Intell. Med. 112, 102003 (2021).","journal-title":"Artif. Intell. Med."},{"key":"2081_CR57","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-022-02090-3","volume":"22","author":"Q Chen","year":"2022","unstructured":"Chen, Q. et al. Transferability and interpretability of the sepsis prediction models in the intensive care unit. BMC Med. Inform. Decis. Mak. 22, 343 (2022).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"2081_CR58","doi-asserted-by":"crossref","unstructured":"Alves, T., Laender, A., Veloso, A. & Ziviani, N. Dynamic prediction of ICU mortality risk using domain adaptation. In Proc. 2018 IEEE International Conference on Big Data (Big Data) 1328\u20131336 (IEEE, 2018).","DOI":"10.1109\/BigData.2018.8621927"},{"key":"2081_CR59","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-98617-1","volume":"11","author":"SS Lorenzen","year":"2021","unstructured":"Lorenzen, S. S. et al. Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark. Sci. Rep. 11, 18959 (2021).","journal-title":"Sci. Rep."},{"key":"2081_CR60","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1038\/s41746-021-00461-0","volume":"4","author":"A Tariq","year":"2021","unstructured":"Tariq, A. et al. Patient-specific COVID-19 resource utilization prediction using fusion AI model. NPJ Digit. Med. 4, 94 (2021).","journal-title":"NPJ Digit. Med."},{"key":"2081_CR61","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/cc10588","volume":"15","author":"L Rose","year":"2011","unstructured":"Rose, L. et al. Decisional responsibility for mechanical ventilation and weaning: an international survey. Crit. Care 15, 1\u20138 (2011).","journal-title":"Crit. Care"},{"key":"2081_CR62","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","volume":"10","author":"JWTM de Kok","year":"2023","unstructured":"de Kok, J. W. T. M. et al. A guide to sharing open healthcare data under the General Data Protection Regulation. Sci. Data 10, 1\u201310 (2023).","journal-title":"Sci. Data"},{"key":"2081_CR63","doi-asserted-by":"crossref","unstructured":"Manduchi, L. et al. T-DPSOM: An interpretable clustering method for unsupervised learning of patient health states. In Proc. of the Conference on Health, Inference, and Learning (ACM, 2021).","DOI":"10.1145\/3450439.3451872"},{"key":"2081_CR64","unstructured":"Fortuin, V., H\u00fcser, M., Locatello, F., Strathmann, H. & R\u00e4tsch, G. SOM-VAE: Interpretable Discrete Representation Learning on Time Series. In International Conference on Learning Representations (2019)."},{"key":"2081_CR65","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1016\/S2213-2600(14)70097-9","volume":"2","author":"CS Calfee","year":"2014","unstructured":"Calfee, C. S. et al. Subphenotypes in acute respiratory distress syndrome: latent class analysis of data from two randomised controlled trials. Lancet Respir. Med. 2, 611\u2013620 (2014).","journal-title":"Lancet Respir. Med."},{"key":"2081_CR66","first-page":"1","volume":"28","author":"N Alipanah","year":"2022","unstructured":"Alipanah, N. & Calfee, C. S. Phenotyping in acute respiratory distress syndrome: state of the art and clinical implications. Curr. Opin. Crit. Care 28, 1\u20138 (2022).","journal-title":"Curr. Opin. Crit. Care"},{"key":"2081_CR67","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-020-2778-x","volume":"24","author":"JG Wilson","year":"2020","unstructured":"Wilson, J. G. & Calfee, C. S. ARDS subphenotypes: understanding a heterogeneous syndrome. Crit. Care 24, 102 (2020).","journal-title":"Crit. Care"},{"key":"2081_CR68","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1136\/thoraxjnl-2016-209719","volume":"72","author":"LD Bos","year":"2017","unstructured":"Bos, L. D. et al. Identification and validation of distinct biological phenotypes in patients with acute respiratory distress syndrome by cluster analysis. Thorax 72, 876\u2013883 (2017).","journal-title":"Thorax"},{"key":"2081_CR69","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.1016\/S2213-2600(21)00365-9","volume":"9","author":"LDJ Bos","year":"2021","unstructured":"Bos, L. D. J. et al. Longitudinal respiratory subphenotypes in patients with COVID-19-related acute respiratory distress syndrome: results from three observational cohorts. Lancet Respir. Med. 9, 1377\u20131386 (2021).","journal-title":"Lancet Respir. Med."},{"key":"2081_CR70","first-page":"1276","volume":"2012","author":"R Joshi","year":"2012","unstructured":"Joshi, R. & Szolovits, P. Prognostic physiology: modeling patient severity in Intensive Care Units using radial domain folding. AMIA Annu. Symp. Proc. 2012, 1276\u20131283 (2012).","journal-title":"AMIA Annu. Symp. Proc."},{"key":"2081_CR71","unstructured":"Liley, J. et al. Model updating after interventions paradoxically introduces bias. In Proc. 24th International Conference on Artificial Intelligence and Statistics, Vol. 130, 3916\u20133924 (PMLR, 2021)."},{"key":"2081_CR72","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01540-w","volume":"22","author":"E Stenwig","year":"2022","unstructured":"Stenwig, E., Salvi, G., Rossi, P. S. & Skj\u00e6rvold, N. K. Comparative analysis of explainable machine learning prediction models for hospital mortality. BMC Med. Res. Methodol. 22, 53 (2022).","journal-title":"BMC Med. Res. Methodol."},{"key":"2081_CR73","unstructured":"Faltys, M., Zimmermann, M., Lyu, X., H\u00fcser, M. & Hyland, S. HiRID, a high time-resolution ICU dataset (version 1.1. 1) Physio. Net (2021)."},{"key":"2081_CR74","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AEW Johnson","year":"2016","unstructured":"Johnson, A. E. W. et al. MIMIC-III, a freely accessible critical care database. Sci. Data 3, 160035 (2016).","journal-title":"Sci. Data"},{"key":"2081_CR75","unstructured":"Amsterdam Medical Data Science. AmsterdamUMCdb website and documentation. https:\/\/amsterdammedicaldatascience.nl\/#amsterdamumcdb."},{"key":"2081_CR76","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1097\/CCM.0000000000002514","volume":"45","author":"SM Brown","year":"2017","unstructured":"Brown, S. M. et al. Nonlinear imputation of PaO2\/FIO2 from SpO2\/FIO2 among mechanically ventilated patients in the ICU: a prospective, observational study. Crit. Care Med. 45, 1317\u20131324 (2017).","journal-title":"Crit. Care Med."},{"key":"2081_CR77","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1152\/jappl.1979.46.3.599","volume":"46","author":"JW Severinghaus","year":"1979","unstructured":"Severinghaus, J. W. Simple, accurate equations for human blood O2 dissociation computations. J. Appl. Physiol. 46, 599\u2013602 (1979).","journal-title":"J. Appl. Physiol."},{"key":"2081_CR78","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1164\/ajrccm.149.3.7509706","volume":"149","author":"GR Bernard","year":"1994","unstructured":"Bernard, G. R. et al. The American-European Consensus Conference on ARDS. Definitions, mechanisms, relevant outcomes, and clinical trial coordination. Am. J. Respir. Crit. Care Med. 149, 818\u2013824 (1994).","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"2081_CR79","first-page":"2526","volume":"307","author":"ARDS Definition Task Force","year":"2012","unstructured":"ARDS Definition Task Force et al. Acute respiratory distress syndrome: the Berlin Definition. JAMA 307, 2526\u20132533 (2012).","journal-title":"JAMA"},{"key":"2081_CR80","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1378\/chest.07-0617","volume":"132","author":"TW Rice","year":"2007","unstructured":"Rice, T. W. et al. Comparison of the SpO2\/FIO2 ratio and the PaO2\/FIO2 ratio in patients with acute lung injury or ARDS. Chest 132, 410\u2013417 (2007).","journal-title":"Chest"},{"key":"2081_CR81","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2","volume":"78","author":"GW Brier","year":"1950","unstructured":"Brier, G. W. Verification of forecasts expressed in terms of probability. Mon. Weather Rev. 78, 1\u20133 (1950).","journal-title":"Mon. Weather Rev."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02081-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02081-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02081-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T12:03:48Z","timestamp":1766405028000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02081-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,19]]},"references-count":81,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2081"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-02081-4","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,19]]},"assertion":[{"value":"19 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"S.L.H. is a board member of the not-for-profit Association for Health, Learning, and Inference (AHLI). G.R. is cofounder and member of the scientific board of Computomics GmbH.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"775"}}