{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T07:59:36Z","timestamp":1771487976663,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T00:00:00Z","timestamp":1631145600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T00:00:00Z","timestamp":1631145600000},"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":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Heterogeneous patient populations, complex pharmacology and low recruitment rates in the Intensive Care Unit (ICU) have led to the failure of many clinical trials. Recently, machine learning (ML) emerged as a new technology to process and identify big data relationships, enabling a new era in clinical trial design. In this study, we designed a ML model for predictively stratifying acute respiratory distress syndrome (ARDS) patients, ultimately reducing the required number of patients by increasing statistical power through cohort homogeneity. From the Philips eICU Research Institute (eRI) database, no less than 51,555 ARDS patients were extracted. We defined three subpopulations by outcome: (1) rapid death, (2) spontaneous recovery, and (3) long-stay patients. A retrospective univariate analysis identified highly predictive variables for each outcome. All 220 variables were used to determine the most accurate and generalizable model to predict long-stay patients. Multiclass gradient boosting was identified as the best-performing ML model. Whereas alterations in pH, bicarbonate or lactate proved to be strong predictors for rapid death in the univariate analysis, only the multivariate ML model was able to reliably differentiate the disease course of the long-stay outcome population (AUC of 0.77). We demonstrate the feasibility of prospective patient stratification using ML algorithms in the by far largest ARDS cohort reported to date. Our algorithm can identify patients with sufficiently long ARDS episodes to allow time for patients to respond to therapy, increasing statistical power. Further, early enrollment alerts may increase recruitment rate.<\/jats:p>","DOI":"10.1038\/s41746-021-00505-5","type":"journal-article","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T10:06:24Z","timestamp":1631181984000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome"],"prefix":"10.1038","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7385-8994","authenticated-orcid":false,"given":"E.","family":"Schwager","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8119-7137","authenticated-orcid":false,"given":"K.","family":"Jansson","sequence":"additional","affiliation":[]},{"given":"A.","family":"Rahman","sequence":"additional","affiliation":[]},{"given":"S.","family":"Schiffer","sequence":"additional","affiliation":[]},{"given":"Y.","family":"Chang","sequence":"additional","affiliation":[]},{"given":"G.","family":"Boverman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9830-5459","authenticated-orcid":false,"given":"B.","family":"Gross","sequence":"additional","affiliation":[]},{"given":"M.","family":"Xu-Wilson","sequence":"additional","affiliation":[]},{"given":"P.","family":"Boehme","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6413-7864","authenticated-orcid":false,"given":"H.","family":"Truebel","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6453-6726","authenticated-orcid":false,"given":"J. J.","family":"Frassica","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,9]]},"reference":[{"key":"505_CR1","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1016\/S2213-2600(17)30188-1","volume":"5","author":"MA Matthay","year":"2017","unstructured":"Matthay, M. A., McAuley, D. F. & Ware, L. B. Clinical trials in acute respiratory distress syndrome: challenges and opportunities. Lancet Respir. Med. 5, 524\u2013534 (2017).","journal-title":"Lancet Respir. Med."},{"key":"505_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":"505_CR3","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/s41572-019-0069-0","volume":"5","author":"MA Matthay","year":"2019","unstructured":"Matthay, M. A. et al. Acute respiratory distress syndrome. Nat. Rev. Dis. Prim. 5, 18 (2019).","journal-title":"Nat. Rev. Dis. Prim."},{"key":"505_CR4","doi-asserted-by":"publisher","DOI":"10.1186\/s40560-016-0191-y","volume":"4","author":"B Fran\u00e7ois","year":"2016","unstructured":"Fran\u00e7ois, B., Clavel, M., Vignon, P. & Laterre, P.-F. Perspective on optimizing clinical trials in critical care: how to puzzle out recurrent failures. J. Intens. Care 4, 67 (2016).","journal-title":"J. Intens. Care"},{"key":"505_CR5","first-page":"CD002787-CD","volume":"2016","author":"F Gebistorf","year":"2016","unstructured":"Gebistorf, F., Karam, O., Wetterslev, J. & Afshari, A. Inhaled nitric oxide for acute respiratory distress syndrome (ARDS) in children and adults. Cochrane Datab. Syst. Rev. 2016, CD002787-CD (2016).","journal-title":"Cochrane Datab. Syst. Rev."},{"key":"505_CR6","doi-asserted-by":"publisher","first-page":"1049","DOI":"10.1001\/archsurg.134.10.1049","volume":"134","author":"ER Goodman","year":"1999","unstructured":"Goodman, E. R. et al. Role of granulocyte-macrophage colony-stimulating factor and its receptor in the genesis of acute respiratory distress syndrome through an effect on neutrophil apoptosis. Arch. Surg. 134, 1049\u20131054 (1999).","journal-title":"Arch. Surg."},{"key":"505_CR7","doi-asserted-by":"publisher","first-page":"410","DOI":"10.4037\/ajcc2009400","volume":"18","author":"L Chlan","year":"2009","unstructured":"Chlan, L., Guttormson, J., Tracy, M. F. & Bremer, K. L. Strategies for overcoming site and recruitment challenges in research studies based in intensive care units. Am. J. Crit. Care 18, 410\u2013417 (2009).","journal-title":"Am. J. Crit. Care"},{"key":"505_CR8","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1055\/s-0039-1684049","volume":"40","author":"JP Reilly","year":"2019","unstructured":"Reilly, J. P., Calfee, C. S. & Christie, J. D. Acute respiratory distress syndrome phenotypes. Semin. Respir. Crit. Care Med. 40, 19\u201330 (2019).","journal-title":"Semin. Respir. Crit. Care Med."},{"key":"505_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.178","volume":"5","author":"TJ Pollard","year":"2018","unstructured":"Pollard, T. J. & Johnson, A. E. W. The eICU collaborative research database, a freely available multi-center database for critical care research. Sci. Data 5, 180178 (2018).","journal-title":"Sci. Data"},{"key":"505_CR10","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.jclinepi.2015.12.005","volume":"74","author":"B Van Calster","year":"2016","unstructured":"Van Calster, B. et al. A calibration hierarchy for risk models was defined: from utopia to empirical data. J. Clin. Epidemiol. 74, 167\u2013176 (2016).","journal-title":"J. Clin. Epidemiol."},{"key":"505_CR11","doi-asserted-by":"publisher","first-page":"1603","DOI":"10.1001\/jama.291.13.1603","volume":"291","author":"RW Taylor","year":"2004","unstructured":"Taylor, R. W. et al. Low-dose inhaled nitric oxide in patients with acute lung injury: a randomized controlled trial. JAMA 291, 1603\u20131609 (2004).","journal-title":"JAMA"},{"key":"505_CR12","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1056\/NEJMoa051693","volume":"354","author":"KP Steinberg","year":"2006","unstructured":"Steinberg, K. P. et al. Efficacy and safety of corticosteroids for persistent acute respiratory distress syndrome. N. Engl. J. Med. 354, 1671\u20131684 (2006).","journal-title":"N. Engl. J. Med."},{"key":"505_CR13","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1378\/chest.14-1139","volume":"148","author":"DF Willson","year":"2015","unstructured":"Willson, D. F., Truwit, J. D., Conaway, M. R., Traul, C. S. & Egan, E. E. The adult calfactant in acute respiratory distress syndrome trial. Chest 148, 356\u2013364 (2015).","journal-title":"Chest"},{"key":"505_CR14","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/S0140-6736(11)61623-1","volume":"379","author":"F Gao Smith","year":"2012","unstructured":"Gao Smith, F. et al. Effect of intravenous \u03b2-2 agonist treatment on clinical outcomes in acute respiratory distress syndrome (BALTI-2): a multicentre, randomised controlled trial. Lancet 379, 229\u2013235 (2012).","journal-title":"Lancet"},{"key":"505_CR15","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1378\/chest.112.1.164","volume":"112","author":"GR Bernard","year":"1997","unstructured":"Bernard, G. R. et al. A trial of antioxidants N-acetylcysteine and procysteine in ARDS. The Antioxidant in ARDS Study Group. Chest 112, 164\u2013172 (1997).","journal-title":"Chest"},{"key":"505_CR16","doi-asserted-by":"publisher","first-page":"1995","DOI":"10.1001\/jama.283.15.1995","volume":"283","author":"The ARDS Network","year":"2000","unstructured":"The ARDS Network Ketoconazole for early treatment of acute lung injury and acute respiratory distress syndrome: a randomized controlled trial. JAMA 283, 1995\u20132002 (2000).","journal-title":"JAMA"},{"key":"505_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1097\/00003246-200201000-00001","volume":"30","author":"The ARDS Clinical Trials Network, National Heart, Lung, and Blood Institute, National Institutes of Health","year":"2002","unstructured":"The ARDS Clinical Trials Network, National Heart, Lung, and Blood Institute, National Institutes of Health Randomized, placebo-controlled trial of lisofylline for early treatment of acute lung injury and acute respiratory distress syndrome.Crit. Care Med. 30, 1\u20136 (2002).","journal-title":"Crit. Care Med."},{"key":"505_CR18","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1016\/S2213-2600(18)30418-1","volume":"7","author":"MA Matthay","year":"2019","unstructured":"Matthay, M. A. et al. Treatment with allogeneic mesenchymal stromal cells for moderate to severe acute respiratory distress syndrome (START study): a randomised phase 2a safety trial. Lancet Respir. Med. 7, 154\u2013162 (2019).","journal-title":"Lancet Respir. Med."},{"key":"505_CR19","doi-asserted-by":"publisher","unstructured":"Rice, T. W. et al. Enteral omega-3 fatty acid, gamma-linolenic acid, and antioxidant supplementation in acute lung injury. JAMA https:\/\/doi.org\/10.1001\/jama.2011.1435 (2011).","DOI":"10.1001\/jama.2011.1435"},{"key":"505_CR20","doi-asserted-by":"publisher","first-page":"1014","DOI":"10.4187\/respcare.05268","volume":"62","author":"RH Kallet","year":"2017","unstructured":"Kallet, R. H. et al. Severity of hypoxemia and other factors that influence the response to aerosolized prostacyclin in ARDS. Respir. Care 62, 1014\u20131022 (2017).","journal-title":"Respir. Care"},{"key":"505_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/2045893217753415","volume":"8","author":"G Calcaianu","year":"2018","unstructured":"Calcaianu, G. et al. Hemodynamic profile of pulmonary hypertension (PH) in ARDS. Pulm. Circ. 8, 1\u20135 (2018).","journal-title":"Pulm. Circ."},{"key":"505_CR22","first-page":"19","volume":"28","author":"TG Romano","year":"2016","unstructured":"Romano, T. G. et al. Metabolic acid-base adaptation triggered by acute persistent hypercapnia in mechanically ventilated patients with acute respiratory distress syndrome. Rev. Bras. Ter. Intensiv. 28, 19\u201326 (2016).","journal-title":"Rev. Bras. Ter. Intensiv."},{"key":"505_CR23","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","volume":"21","author":"EW Steyerberg","year":"2010","unstructured":"Steyerberg, E. W. et al. Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology 21, 128\u2013138 (2010).","journal-title":"Epidemiology"},{"key":"505_CR24","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/j.jbi.2014.12.016","volume":"54","author":"K Van Hoorde","year":"2015","unstructured":"Van Hoorde, K. et al. A spline-based tool to assess and visualize the calibration of multiclass risk predictions. J. Biomed. Inf. 54, 283\u2013293 (2015).","journal-title":"J. Biomed. Inf."},{"key":"505_CR25","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1016\/S2213-2600(18)30177-2","volume":"6","author":"CS Calfee","year":"2018","unstructured":"Calfee, C. S. et al. Acute respiratory distress syndrome subphenotypes and differential response to simvastatin: secondary analysis of a randomised controlled trial. Lancet Respir. Med. 6, 691\u2013698 (2018).","journal-title":"Lancet Respir. Med."},{"key":"505_CR26","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-020-02880-z","volume":"24","author":"L Gattinoni","year":"2020","unstructured":"Gattinoni, L., Chiumello, D. & Rossi, S. COVID-19 pneumonia: ARDS or not? Crit. Care 24, 154 (2020).","journal-title":"Crit. Care"},{"key":"505_CR27","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MEMB.2009.935720","volume":"29","author":"M McShea","year":"2010","unstructured":"McShea, M., Holl, R., Badawi, O., Riker, R. R. & Silfen, E. The eICU research institute\u2014a collaboration between industry, health-care providers, and academia. IEEE Eng. Med. Biol. Mag. 29, 18\u201325 (2010).","journal-title":"IEEE Eng. Med. Biol. Mag."},{"key":"505_CR28","unstructured":"Chen, T. et al. XGBoost: extreme gradient boosting. https:\/\/CRANR-projectorg\/package= xgboost R package version 09002 (2019)."},{"key":"505_CR29","first-page":"18","volume":"2","author":"A Liaw","year":"2002","unstructured":"Liaw, A. & Wiener, M. Classification and regression by randomForest. R News 2, 18\u201322 (2002).","journal-title":"R News"},{"key":"505_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v033.i01","volume":"33","author":"J Friedman","year":"2010","unstructured":"Friedman, J., Hastie, T. & Tibshirani, R. Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw. 33, 1 (2010).","journal-title":"J. Stat. Softw."},{"key":"505_CR31","doi-asserted-by":"publisher","first-page":"13","DOI":"10.18637\/jss.v036.i11","volume":"36","author":"MB Kursa","year":"2010","unstructured":"Kursa, M. B. & Rudnicki, W. R. Feature selection with the boruta package. J. Stat. Softw. 36, 13 (2010).","journal-title":"J. Stat. Softw."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00505-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00505-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00505-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T18:59:11Z","timestamp":1670093951000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00505-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,9]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["505"],"URL":"https:\/\/doi.org\/10.1038\/s41746-021-00505-5","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,9]]},"assertion":[{"value":"22 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Authors K.J. and S.S. are currently employed by Bayer AG, Wuppertal, Germany, a manufacturer of pharmaceuticals. Authors E.S., A.R., Y.C., G.B., B.G., M.X.W., and J.F. are employed by Philips Research North America\u2014a manufacturer of Medical Devices and systems. Authors P.B. and H.T. were previously employed by Bayer AG, Wuppertal, Germany, a manufacturer of pharmaceuticals.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"133"}}