{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T06:48:35Z","timestamp":1767682115481,"version":"3.48.0"},"reference-count":50,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"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. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Patients with severe COVID-19 may require MV or ECMO. Predicting who will require interventions and the duration of those interventions are challenging due to the diverse responses among patients and the dynamic nature of the disease. As such, there is a need for better prediction of the duration and outcomes of MV use in patients, to improve patient care and aid with MV and ECMO allocation. Here we develop and examine the performance of ML models to predict MV duration, ECMO, and mortality for patients with COVID-19.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this retrospective prognostic study, hierarchical machine-learning models were developed to predict MV duration and outcome prediction from demographic data and time-series data consisting of vital signs and laboratory results. We train our models on 10,378 patients with positive severe acute respiratory syndrome-related coronavirus (SARS-CoV-2) virus testing from Emory\u2019s COVID CRADLE Dataset who sought treatment at Emory University Hospital between February 28, 2020, to January 24, 2022. Analysis was conducted between January 10, 2022, and April 5, 2024. The main outcomes and measures were the AUROC, AUPRC and the F-score for MV duration, need for ECMO, and mortality prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Data from 10,378 patients with COVID-19 (median [IQR] age, 60 [48\u201372] years; 5,281 [50.89%] women) were included. Overall MV class distributions for 0\u2009days, 1\u20134\u2009days, 5\u20139\u2009days, 10\u201314\u2009days, 15\u201319\u2009days, 20\u201324\u2009days, 25\u201329\u2009days, and \u226530\u2009days of MV were 8,141 (78.44%), 812 (7.82%), 325 (3.13%), 241 (2.32%), 153 (1.47%), 97 (0.93%), 87 (0.84%), and 522 (5.03%), respectively. Overall ECMO use and mortality rates were 15 (0.14%) and 1,114 (10.73%), respectively. On MV duration, ECMO use, and mortality outcomes, the highest-performing model reached weighted average AUROC scores of 0.873, 0.902, and 0.774, and the highest-performing model reached weighted average AUPRC scores of 0.790, 0.999, and 0.893.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions and relevance<\/jats:title>\n                    <jats:p>Hierarchical ML models trained on vital signs, laboratory results, and demographic data show promise for the prediction of MV duration, ECMO use, and mortality in COVID-19 patients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1661637","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T06:45:32Z","timestamp":1767681932000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Use of machine learning models to predict mechanical ventilation, ECMO, and mortality in COVID-19"],"prefix":"10.3389","volume":"8","author":[{"given":"Nina","family":"Moorman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erin","family":"Hedlund-Botti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grace","family":"Gombolay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew C.","family":"Gombolay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,6]]},"reference":[{"key":"ref1","volume-title":"TensorFlow: a system for large-scale machine learning. In OSDI\u201916: Proc. 12th USENIX Conf. Operating systems design and implementation (chairs Keeton, K. & Roscoe, T.) 265\u2013283 (USENIX Association","author":"Abadi","year":"2015"},{"key":"ref2","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"10748","DOI":"10.1038\/s41598-022-13072-w","article-title":"Preparing for the next pandemic via transfer learning from existing diseases with hierarchical multi-modal BERT: a study on COVID-19 outcome prediction","volume":"12","author":"Agarwal","year":"2022","journal-title":"Sci. Rep."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1093\/bioinformatics\/btq134","article-title":"Permutation importance: a corrected feature importance measure","volume":"26","author":"Altmann","year":"2010","journal-title":"Bioinformatics"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1020","DOI":"10.1513\/AnnalsATS.202008-1080OC","article-title":"Noninvasive ventilatory support of patients with COVID-19 outside the intensive care units (WARd-COVID)","volume":"18","author":"Bellani","year":"2021","journal-title":"Ann. Am. Thorac. Soc."},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","first-page":"1769","DOI":"10.1007\/s11739-022-02981-3","article-title":"Correlation of SpO2\/FiO2 and PaO2\/FiO2 in patients with symptomatic COVID-19: an observational, retrospective study","volume":"17","author":"Bonaventura","year":"2022","journal-title":"Intern. Emerg. Med."},{"key":"ref8","first-page":"108","author":"Buitinck","year":"2013"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e0277498","DOI":"10.1371\/journal.pone.0277498","article-title":"Mechanical ventilation for COVID-19: outcomes following discharge from inpatient treatment","volume":"18","author":"Butler","year":"2023","journal-title":"PLoS One"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1113\/EP089400","article-title":"Mechanical ventilation in COVID-19: a physiological perspective","volume":"107","author":"Cronin","year":"2022","journal-title":"Exp. Physiol."},{"key":"ref11","year":""},{"key":"ref12","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.puhe.2022.03.012","article-title":"A meta-analysis of COVID-19 vaccine attitudes and demographic characteristics in the United States","volume":"207","author":"Dhanani","year":"2022","journal-title":"Public Health"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1177\/0267659121995997","article-title":"ECMO in COVID-19\u2014prolonged therapy needed? A retrospective analysis of outcome and prognostic factors","volume":"36","author":"Dreier","year":"2021","journal-title":"Perfusion"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1016\/j.jiph.2022.06.008","article-title":"Machine learning decision tree algorithm role for predicting mortality in critically ill adult COVID-19 patients admitted to the ICU","volume":"15","author":"Elhazmi","year":"2022","journal-title":"J. Infect. Public Health"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1164\/rccm.201212-2169OC","article-title":"Evolution of mortality over time in patients receiving mechanical ventilation","volume":"188","author":"Esteban","year":"2013","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"e0248357","DOI":"10.1371\/journal.pone.0248357","article-title":"COVID-IRS: a novel predictive score for risk of invasive mechanical ventilation in patients with COVID-19","volume":"16","author":"Garcia-Gordillo","year":"2021","journal-title":"PLoS One"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"e0253443","DOI":"10.1371\/journal.pone.0253443","article-title":"Deep learning to predict long-term mortality in patients requiring 7 days of mechanical ventilation","volume":"16","author":"George","year":"2021","journal-title":"PLoS One"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e31549","DOI":"10.2196\/31549","article-title":"The development and validation of simplified machine learning algorithms to predict prognosis of hospitalized patients with COVID-19: multicenter, retrospective study","volume":"24","author":"He","year":"2022","journal-title":"J. Med. Internet Res."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.jcrc.2020.03.011","article-title":"Poor survival with extracorporeal membrane oxygenation in acute respiratory distress syndrome (ARDS) due to coronavirus disease 2019 (COVID-19): pooled analysis of early reports","volume":"58","author":"Henry","year":"2020","journal-title":"J. Crit. Care"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"5979","DOI":"10.1038\/s41598-022-09954-8","article-title":"On evaluation metrics for medical applications of artificial intelligence","volume":"12","author":"Hicks","year":"2022","journal-title":"Sci. Rep."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1918","DOI":"10.1093\/ije\/dyaa171","article-title":"Early prediction of mortality risk among patients with severe COVID-19, using machine learning","volume":"49","author":"Hu","year":"2020","journal-title":"Int. J. Epidemiol."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"e112424","DOI":"10.5812\/aapm.112424","article-title":"Predicting risk score for mechanical ventilation in hospitalized adult patients suffering from COVID-19","volume":"11","author":"Kafan","year":"2021","journal-title":"Anesthesiol. Pain Med."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"2172","DOI":"10.3390\/jcm10102172","article-title":"Machine learning models to predict 30-day mortality in mechanically ventilated patients","volume":"10","author":"Kim","year":"2021","journal-title":"J. Clin. Med."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"113389","DOI":"10.1016\/j.socscimed.2020.113389","article-title":"Resilience and demographic characteristics predicting distress during the COVID-19 crisis","volume":"265","author":"Kimhi","year":"2020","journal-title":"Soc. Sci. Med."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1080\/20479700.2023.2295111","article-title":"Invasive mechanical ventilation duration prediction using survival analysis","volume":"18","author":"Kobara","year":"2023","journal-title":"Int. J. Healthc. Manag."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"744100","DOI":"10.3389\/fpubh.2021.744100","article-title":"Recurrent neural network and reinforcement learning model for COVID-19 prediction","volume":"9","author":"Kumar","year":"2021","journal-title":"Front. Public Health"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s44158-021-00002-x","article-title":"COVID-19 ICU mortality prediction: a machine learning approach using SuperLearner algorithm","volume":"1","author":"Lorenzoni","year":"2021","journal-title":"J. Anesth. Analg. Crit. Care"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"26","DOI":"10.5935\/0103-507X.20150006","article-title":"The reality of patients requiring prolonged mechanical ventilation: a multicenter study","volume":"27","author":"Loss","year":"2015","journal-title":"Revista Brasileira de terapia intensiva."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1186\/s13054-022-04187-7","article-title":"Trends in survival during the pandemic in patients with critical COVID-19 receiving mechanical ventilation with or without ECMO: analysis of the Japanese national registry data","volume":"26","author":"Ohshimo","year":"2022","journal-title":"Crit. Care"},{"key":"ref34","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Machine Learn. Res."},{"key":"ref35","first-page":"1","volume-title":"Proceedings of the AAAI\u20192000 workshop on imbalanced data sets","author":"Provost","year":"2000"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"e415","DOI":"10.1016\/S2589-7500(22)00049-8","article-title":"Recurrent neural network models (CovRNN) for predicting outcomes of patients with COVID-19 on admission to hospital: model development and validation using electronic health record data","volume":"4","author":"Rasmy","year":"2022","journal-title":"Lancet Digital Health."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1093\/jamia\/ocab029","article-title":"Development and validation of prediction models for mechanical ventilation, renal replacement therapy, and readmission in COVID-19 patients","volume":"28","author":"Rodriguez","year":"2021","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.amsu.2020.09.044","article-title":"Mortality prediction model for the triage of COVID-19, pneumonia, and mechanically ventilated ICU patients: a retrospective study","volume":"59","author":"Ryan","year":"2020","journal-title":"Ann. Med. Surg."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"e0118432","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"Saito","year":"2015","journal-title":"PLoS One"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1097\/MCC.0000000000001000","article-title":"COVID-19: dealing with ventilator shortage","volume":"28","author":"Santini","year":"2022","journal-title":"Curr. Opin. Crit. Care"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1007\/s00134-020-06331-9","article-title":"Extracorporeal membrane oxygenation in patients with severe respiratory failure from COVID-19","volume":"47","author":"Shaefi","year":"2021","journal-title":"Intensive Care Med."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.1111\/aor.14542","article-title":"Validation of extracorporeal membrane oxygenation mortality prediction and severity of illness scores in an international COVID-19 cohort","volume":"47","author":"Shah","year":"2023","journal-title":"Artif. Organs"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.1016\/j.chest.2020.12.009","article-title":"Development and prospective validation of a deep learning algorithm for predicting need for mechanical ventilation","volume":"159","author":"Shashikumar","year":"2021","journal-title":"Chest"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-020-01359-9","article-title":"Predicting COVID-19 disease progression and patient outcomes based on temporal deep learning","volume":"21","author":"Sun","year":"2021","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"170","DOI":"10.3390\/membranes11030170","article-title":"Outcome prediction in patients with severe COVID-19 requiring extracorporeal membrane oxygenation\u2014a retrospective international multicenter study","volume":"11","author":"Supady","year":"2021","journal-title":"Membranes"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"1983","DOI":"10.1016\/j.athoracsur.2020.12.050","article-title":"Mortality risk assessment in COVID-19 venovenous extracorporeal membrane oxygenation","volume":"112","author":"Tabatabai","year":"2021","journal-title":"Ann. Thorac. Surg."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"e0277641","DOI":"10.1371\/journal.pone.0277641","article-title":"Risk factors for mechanical ventilation and ECMO in COVID-19 patients admitted to the ICU: a multicenter retrospective observational study","volume":"17","author":"Takada","year":"2022","journal-title":"PLoS One"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"733657","DOI":"10.3389\/fmed.2021.733657","article-title":"Predictive biomarkers of intensive care unit and mechanical ventilation duration in critically-ill coronavirus disease 2019 patients","volume":"8","author":"Taleb","year":"2021","journal-title":"Front. Med."},{"key":"ref49","doi-asserted-by":"publisher","first-page":"100089","DOI":"10.1016\/j.cmpbup.2022.100089","article-title":"Predicting the evolution of COVID-19 mortality risk: a recurrent neural network approach","volume":"3","author":"Villegas","year":"2023","journal-title":"Computer Methods Programs Biomed. Update"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"e0249285","DOI":"10.1371\/journal.pone.0249285","article-title":"Machine learning methods to predict mechanical ventilation and mortality in patients with COVID-19","volume":"16","author":"Yu","year":"2021","journal-title":"PLoS One"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"E158","DOI":"10.1111\/aor.13873","article-title":"Role of extracorporeal membrane oxygenation in critically ill COVID-19 patients and predictors of mortality","volume":"45","author":"Zayat","year":"2021","journal-title":"Artif. Organs"},{"key":"ref52","first-page":"190","author":"Zhang","year":"2003"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1661637\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T06:45:35Z","timestamp":1767681935000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1661637\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,6]]},"references-count":50,"alternative-id":["10.3389\/frai.2025.1661637"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1661637","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,6]]},"article-number":"1661637"}}