{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T12:12:46Z","timestamp":1781871166673,"version":"3.54.5"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000050","name":"National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["F31HL156498"],"award-info":[{"award-number":["F31HL156498"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"name":"UCSF Liver Center Grant","award":["P30DK026743"],"award-info":[{"award-number":["P30DK026743"]}]},{"DOI":"10.13039\/100000062","name":"National Institute of Diabetes and Digestive and Kidney Diseases","doi-asserted-by":"publisher","award":["K23DK139455"],"award-info":[{"award-number":["K23DK139455"]}],"id":[{"id":"10.13039\/100000062","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Background<\/jats:title>\n            <jats:p>Determining extubation readiness in pediatric intensive care units (PICU) is challenging. We used expert-augmented machine learning (EAML), a method that combines machine learning with human expert knowledge, to predict successful extubation.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>We extracted electronic health record data from patients in two PICUs. Data from patients in one unit was split into 80% training and 20% test, while patients in the other served as an external test set. EAML begins by training RuleFit, which converts gradient-boosted trees into decision rules. Then, expert clinicians were asked to assess the relative probability of successful extubation of the subgroup defined by each rule compared with the entire sample. The rules were ranked in order of increasing chance of successful extubation according to (1) the RuleFit model and (2) clinician assessment, and differences between the two rankings were calculated. The initial RuleFit model was then regularized based on these differences, producing the EAML model.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>The RuleFit model selected 46 rules; we surveyed 25 clinician experts to provide feedback on them. All clinicians worked in a PICU setting and were from multiple disciplines; over half (56%) had\u2009&gt;\u20095 years of PICU experience. As expected, the added regularization slightly lowered performance of EAML compared with RuleFit in the internal test set, although the difference was not statistically significant (RuleFit AUC\u2009=\u20090.817 vs. best-performing EAML model AUC\u2009=\u20090.814, difference\u2009=\u20090.003, 95% CI of difference = -0.009, 0.003). EAML had superior performance in the external test set (RuleFit AUC\u2009=\u20090.791 vs. best-performing EAML model AUC\u2009=\u20090.799, difference\u2009=\u20090.007, 95% CI of difference\u2009=\u20090.002, 0.013).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions<\/jats:title>\n            <jats:p>When creating a model to predict successful extubation in PICU patients, incorporating expert knowledge directly into the model construction process via EAML produced a model more generalizable to an external test set.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1186\/s12911-025-03070-z","type":"journal-article","created":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T12:43:31Z","timestamp":1751373811000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Expert-augmented machine learning for predicting extubation readiness in the pediatric intensive care unit"],"prefix":"10.1186","volume":"25","author":[{"given":"Jean","family":"Digitale","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deborah","family":"Franzon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles","family":"McCulloch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark J.","family":"Pletcher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Efstathios D.","family":"Gennatas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"issue":"1","key":"3070_CR1","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1164\/rccm.201610-2076ST","volume":"195","author":"GA Schmidt","year":"2016","unstructured":"Schmidt GA, Girard TD, Kress JP, Morris PE, Ouellette DR, Alhazzani W, et al. Official executive summary of an American thoracic society\/american college of chest physicians clinical practice guideline: liberation from mechanical ventilation in critically ill adults. Am J Respir Crit Care Med. 2016;195(1):115\u20139.","journal-title":"Am J Respir Crit Care Med"},{"issue":"1","key":"3070_CR2","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1164\/rccm.201610-2075ST","volume":"195","author":"TD Girard","year":"2016","unstructured":"Girard TD, Alhazzani W, Kress JP, Ouellette DR, Schmidt GA, Truwit JD, et al. An official American thoracic society\/american college of chest physicians clinical practice guideline: liberation from mechanical ventilation in critically ill adults. Rehabilitation protocols, ventilator liberation protocols, and cuff leak tests. Am J Respir Crit Care Med. 2016;195(1):120\u201333.","journal-title":"Am J Respir Crit Care Med"},{"issue":"1","key":"3070_CR3","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1016\/j.chest.2016.10.036","volume":"151","author":"DR Ouellette","year":"2017","unstructured":"Ouellette DR, Patel S, Girard TD, Morris PE, Schmidt GA, Truwit JD, et al. Liberation from mechanical ventilation in critically ill adults: an official American college of chest physicians\/american thoracic society clinical practice guideline: inspiratory pressure augmentation during spontaneous breathing trials, protocols minimizing sedation, and noninvasive ventilation immediately after extubation. Chest. 2017;151(1):166\u201380.","journal-title":"Chest"},{"issue":"1","key":"3070_CR4","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.chest.2016.10.037","volume":"151","author":"GA Schmidt","year":"2017","unstructured":"Schmidt GA, Girard TD, Kress JP, Morris PE, Ouellette DR, Alhazzani W, et al. Liberation from mechanical ventilation in critically ill adults: executive summary of an official American college of chest physicians\/american thoracic society clinical practice guideline. Chest. 2017;151(1):160\u20135.","journal-title":"Chest"},{"issue":"6, Supplement","key":"3070_CR5","doi-asserted-by":"publisher","first-page":"S375","DOI":"10.1378\/chest.120.6_suppl.375S","volume":"120","author":"NR MacIntyre","year":"2001","unstructured":"MacIntyre NR. Evidence-Based guidelines for weaning and discontinuing ventilatory support: A collective task force facilitated by the American college of chest physicians; the American association for respiratory care; and the American college of critical care medicine. Chest. 2001;120(6, Supplement):S375\u201395.","journal-title":"Chest"},{"issue":"20","key":"3070_CR6","doi-asserted-by":"publisher","first-page":"2561","DOI":"10.1001\/jama.288.20.2561","volume":"288","author":"AG Randolph","year":"2002","unstructured":"Randolph AG, Wypij D, Venkataraman ST, Hanson JH, Gedeit RG, Meert KL, et al. Effect of mechanical ventilator weaning protocols on respiratory outcomes in infants and children: A randomized controlled trial. JAMA. 2002;288(20):2561\u20138.","journal-title":"JAMA"},{"issue":"1","key":"3070_CR7","first-page":"1","volume":"10","author":"CJL Newth","year":"2009","unstructured":"Newth CJL, Venkataraman S, Willson DF, Meert KL, Harrison R, Dean JM, et al. Weaning and extubation readiness in pediatric patients. Pediatr Crit Care Med J Soc Crit Care Med World Fed Pediatr Intensive Crit Care Soc. 2009;10(1):1\u201311.","journal-title":"Pediatr Crit Care Med J Soc Crit Care Med World Fed Pediatr Intensive Crit Care Soc"},{"issue":"10","key":"3070_CR8","doi-asserted-by":"publisher","first-page":"1601","DOI":"10.4187\/respcare.07810","volume":"65","author":"CJ Newth","year":"2020","unstructured":"Newth CJ, Hotz JC, Khemani RG. Ventilator liberation in the pediatric ICU. Respir Care. 2020;65(10):1601\u201310.","journal-title":"Respir Care"},{"key":"3070_CR9","doi-asserted-by":"publisher","first-page":"867739","DOI":"10.3389\/fped.2022.867739","volume":"10","author":"E Poletto","year":"2022","unstructured":"Poletto E, Cavagnero F, Pettenazzo M, Visentin D, Zanatta L, Zoppelletto F, et al. Ventilation weaning and extubation readiness in children in pediatric intensive care unit: A review. Front Pediatr. 2022;10:867739.","journal-title":"Front Pediatr"},{"issue":"3","key":"3070_CR10","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.cnur.2014.05.006","volume":"49","author":"S Bankhead","year":"2014","unstructured":"Bankhead S, Chong K, Kamai S. Preventing extubation failures in a pediatric intensive care unit. Nurs Clin North Am. 2014;49(3):321\u20138.","journal-title":"Nurs Clin North Am"},{"issue":"2","key":"3070_CR11","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1177\/0885066613494338","volume":"30","author":"JL Laham","year":"2015","unstructured":"Laham JL, Breheny PJ, Rush A. Do clinical parameters predict first planned extubation outcome in the pediatric intensive care unit?? J Intensive Care Med. 2015;30(2):89\u201396.","journal-title":"J Intensive Care Med"},{"issue":"3","key":"3070_CR12","doi-asserted-by":"publisher","first-page":"334","DOI":"10.4187\/respcare.02469","volume":"59","author":"MJ Mhanna","year":"2014","unstructured":"Mhanna MJ, Anderson IM, Iyer NP, Baumann A. The use of extubation readiness parameters: A survey of pediatric critical care physicians. Respir Care. 2014;59(3):334\u20139.","journal-title":"Respir Care"},{"issue":"11","key":"3070_CR13","doi-asserted-by":"publisher","first-page":"2657","DOI":"10.1097\/01.CCM.0000094228.90557.85","volume":"31","author":"S Kurachek","year":"2003","unstructured":"Kurachek S, Newth C, Quasney M, Rice T, Sachdeva R, Patel N, et al. Extubation failure in pediatric intensive care: A multiple-center study of risk factors and outcomes. Crit Care Med. 2003;31(11):2657\u201364.","journal-title":"Crit Care Med"},{"issue":"3","key":"3070_CR14","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1097\/01.PCC.0000161119.05076.91","volume":"6","author":"S Baisch","year":"2005","unstructured":"Baisch S, Wheeler W, Kurachek S, Cornfield D. Extubation failure in pediatric intensive care incidence and outcomes. Pediatr Crit Care Med. 2005;6(3):312\u20138.","journal-title":"Pediatr Crit Care Med"},{"issue":"10","key":"3070_CR15","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1007\/s001340101035","volume":"27","author":"J Farias","year":"2001","unstructured":"Farias J, Retta A, Al\u00eda I, Olazarri F, Esteban A, Golubicki A, et al. A comparison of two methods to perform a breathing trial before extubation in pediatric intensive care patients. Intensive Care Med. 2001;27(10):1649\u201354.","journal-title":"Intensive Care Med"},{"issue":"6","key":"3070_CR16","doi-asserted-by":"publisher","first-page":"e330","DOI":"10.1097\/PCC.0b013e3182231220","volume":"12","author":"LP Ferguson","year":"2011","unstructured":"Ferguson LP, Walsh BK, Munhall D, Arnold JH. A spontaneous breathing trial with pressure support overestimates readiness for extubation in children. Pediatr Crit Care Med. 2011;12(6):e330.","journal-title":"Pediatr Crit Care Med"},{"issue":"1","key":"3070_CR17","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/s41030-022-00204-w","volume":"9","author":"P Ng","year":"2023","unstructured":"Ng P, Tan HL, Ma YJ, Sultana R, Long V, Wong JJM, et al. Tests and indices predicting extubation failure in children: A systematic review and Meta-analysis. Pulm Ther. 2023;9(1):25\u201347.","journal-title":"Pulm Ther"},{"issue":"4","key":"3070_CR18","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1097\/01.PCC.0000225001.92994.29","volume":"7","author":"A Chavez","year":"2006","unstructured":"Chavez A, dela Cruz R, Zaritsky A. Spontaneous breathing trial predicts successful extubation in infants and children. Pediatr Crit Care Med. 2006;7(4):324\u20138.","journal-title":"Pediatr Crit Care Med"},{"issue":"11","key":"3070_CR19","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1097\/CCM.0b013e3182257520","volume":"39","author":"FK Foronda","year":"2011","unstructured":"Foronda FK, Troster EJ, Farias JA, Barbas CS, Ferraro AA, Faria LS, et al. The impact of daily evaluation and spontaneous breathing test on the duration of pediatric mechanical ventilation: A randomized controlled trial. Crit Care Med. 2011;39(11):2526\u201333.","journal-title":"Crit Care Med"},{"key":"3070_CR20","doi-asserted-by":"crossref","unstructured":"Marupudi NK, Steurer-Muller M, Franzon D. The Decision to Extubate: The Association Between Clinician Impressions and Objective Extubation Readiness Criteria in a Pediatric Intensive Care Unit. J Pediatr Intensive Care [Internet]. 2022 Jan 21 [cited 2022 Feb 24]; Available from: http:\/\/www.thieme-connect.de\/DOI\/DOI?10.1055\/s-0041-1741403","DOI":"10.1055\/s-0041-1741403"},{"issue":"1","key":"3070_CR21","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1097\/CCM.0000000000002024","volume":"45","author":"EV Faustino","year":"2017","unstructured":"Faustino EV, Gedeit R, Schwarz A, Asaro L, Wypij D, Curley M. Accuracy of an extubation readiness test in predicting successful extubation in children with acute respiratory failure from lower respiratory tract disease. Crit Care Med. 2017;45(1):94\u2013102.","journal-title":"Crit Care Med"},{"key":"3070_CR22","unstructured":"Gennatas ED, Friedman JH, Ungar LH, Pirracchio R, Eaton E, Reichmann LG et al. Expert-augmented machine learning. Proc Natl Acad Sci [Internet]. 2020 Feb 18 [cited 2020 Feb 18]; Available from: https:\/\/www.pnas.org\/content\/early\/2020\/02\/14\/1906831117"},{"issue":"5","key":"3070_CR23","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.jbi.2005.02.005","volume":"38","author":"GF Cooper","year":"2005","unstructured":"Cooper GF, Abraham V, Aliferis CF, Aronis JM, Buchanan BG, Caruana R, et al. Predicting dire outcomes of patients with community acquired pneumonia. J Biomed Inf. 2005;38(5):347\u201366.","journal-title":"J Biomed Inf"},{"key":"3070_CR24","doi-asserted-by":"publisher","unstructured":"Caruana R, Lou Y, Gehrke J, Koch P, Sturm M, Elhadad N. Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining [Internet]. Sydney NSW Australia: ACM; 2015 [cited 2024 Apr 23]. pp. 1721\u201330. Available from: https:\/\/doi.org\/10.1145\/2783258.2788613","DOI":"10.1145\/2783258.2788613"},{"issue":"3","key":"3070_CR25","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1214\/07-AOAS148","volume":"2","author":"JH Friedman","year":"2008","unstructured":"Friedman JH, Popescu BE. Predictive learning via rule ensembles. Ann Appl Stat. 2008;2(3):916\u201354.","journal-title":"Ann Appl Stat"},{"key":"3070_CR26","unstructured":"Gennatas ED. Towards Precision Psychiatry: Gray Matter Development and Cognition in Adolescence [Doctoral dissertation]. [Philadelphia, PA]: University of Pennsylvania; 2017."},{"key":"3070_CR27","unstructured":"Healthcare Cost and Utilization Project (HCUP). Clinical Classifications Software Refined (CCSR) [Internet]. 2022 [cited 2024 Mar 26]. Available from: https:\/\/hcup-us.ahrq.gov\/toolssoftware\/ccsr\/ccs_refined.jsp"},{"issue":"10","key":"3070_CR28","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1097\/CCM.0b013e3181ef4460","volume":"38","author":"H Wunsch","year":"2010","unstructured":"Wunsch H, Linde-Zwirble WT, Angus DC, Hartman ME, Milbrandt EB, Kahn JM. The epidemiology of mechanical ventilation use in the united States. Crit Care Med. 2010;38(10):1947\u201353.","journal-title":"Crit Care Med"},{"issue":"9","key":"3070_CR29","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1097\/PCC.0000000000000835","volume":"17","author":"K Choong","year":"2016","unstructured":"Choong K, Duffett M, Cook DJ, Randolph AG. The impact of clinical trials conducted by research networks in pediatric critical care. Pediatr Crit Care Med. 2016;17(9):837.","journal-title":"Pediatr Crit Care Med"},{"issue":"2","key":"3070_CR30","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1038\/s41390-022-02343-x","volume":"93","author":"CG Macias","year":"2023","unstructured":"Macias CG, Remy KE, Barda AJ. Utilizing big data from electronic health records in pediatric clinical care. Pediatr Res. 2023;93(2):382\u20139.","journal-title":"Pediatr Res"},{"key":"3070_CR31","doi-asserted-by":"publisher","first-page":"105869","DOI":"10.1016\/j.cmpb.2020.105869","volume":"200","author":"A Fabregat","year":"2021","unstructured":"Fabregat A, Magret M, Ferr\u00e9 JA, Vernet A, Guasch N, Rodr\u00edguez A, et al. A machine learning decision-making tool for extubation in intensive care unit patients. Comput Methods Programs Biomed. 2021;200:105869.","journal-title":"Comput Methods Programs Biomed"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-03070-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-025-03070-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-03070-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T12:43:33Z","timestamp":1751373813000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-025-03070-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["3070"],"URL":"https:\/\/doi.org\/10.1186\/s12911-025-03070-z","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]},"assertion":[{"value":"19 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We received ethical approval from the University of California, San Francisco Institutional Review Board (study #17-23751), which granted a waiver of informed consent. The study was conducted in accordance with the ethical principles outlined in the Declaration of Helsinki.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Dr. Jin Ge receives research support from Merck and Co. and consults for Astellas Pharmaceuticals\/Iota Biosciences.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"232"}}