{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T01:41:56Z","timestamp":1793497316933,"version":"4.5.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T00:00:00Z","timestamp":1752710400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T00:00:00Z","timestamp":1752710400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000057","name":"NIGMS","doi-asserted-by":"crossref","award":["K23GM151611"],"award-info":[{"award-number":["K23GM151611"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Anesthesiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Background<\/jats:title>\n            <jats:p>Unplanned postoperative intensive care unit admissions (UIAs) are rare events that cause significant challenges to perioperative workflow. We describe the development of a machine-learning derived model to predict UIAs using only widely used preoperative variables.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>This was a 3-year retrospective review of all adult surgeries under the General, Vascular, and Thoracic surgical services with anticipated length of greater than 180\u00a0minutes at a single institution. A UIA was defined as any post-operative patient recovering in the post-anesthesia care unit (PACU) requiring direct transfer to the intensive care unit (ICU) for higher level of care. We developed our prediction model with a gradient-boosting decision tree algorithm (XGBoost). The model incorporated sixteen generalizable predictor variables that were derived from the demographics and surgical booking details. Validation and evaluation were performed with 10-fold cross validation, and model performance was evaluated using the area under the receiver operating characteristic (ROC) curve, sensitivity, specificity, and likelihood ratio.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>A total of 4658 patients were included for analysis. The incidence of UIAs was 2.3%. With 10-fold cross validation, the area under the ROC curve was 0.80 (95% CI 0.74\u20130.86). Two decision thresholds were used, which achieved the best specificity of 94% (95% CI 92\u201396%), best positive likelihood ratio of 4.22 (95% CI 0.99\u20138.79), and best sensitivity of 82% (95% CI 58\u2013100%).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions<\/jats:title>\n            <jats:p>Our machine learning-derived model is a reliable tool for the perioperative clinician to predict a rare outcome in high-risk patients using only preoperative variables. Future studies will include prospective validation of this model at other institutions and real-time incorporation for improvement in perioperative workflow.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1186\/s12871-025-03195-8","type":"journal-article","created":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T17:41:43Z","timestamp":1752774103000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Development of a machine learning-derived model to predict unplanned ICU admissions after major non-cardiac surgery"],"prefix":"10.1186","volume":"25","author":[{"given":"Catherine","family":"Chiu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias R.","family":"Braehler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne L.","family":"Donovan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atul J.","family":"Butte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Romain","family":"Pirracchio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew M.","family":"Bishara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,17]]},"reference":[{"issue":"3","key":"3195_CR1","doi-asserted-by":"publisher","first-page":"127","DOI":"10.4103\/ijccm.IJCCM_428_16","volume":"21","author":"M Meziane","year":"2017","unstructured":"Meziane M, El Jaouhari SDE, ElKoundi A, et al. Unplanned intensive care unit admission following elective surgical adverse events: incidence, patient characteristics, preventability, and outcome. Indian J Crit Care Med. 2017;21(3):127\u201330. https:\/\/doi.org\/10.4103\/ijccm.IJCCM_428_16.","journal-title":"Indian J Crit Care Med"},{"issue":"1","key":"3195_CR2","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1093\/bja\/aew396","volume":"118","author":"MA Gillies","year":"2017","unstructured":"Gillies MA, Harrison EM, Pearse RM, et al. Intensive care utilization and outcomes after high-risk surgery in scotland: a population-based cohort study. Br J Anaesth. 2017;118(1):123\u201331. https:\/\/doi.org\/10.1093\/bja\/aew396.","journal-title":"Br J Anaesth"},{"issue":"2","key":"3195_CR3","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/BF03011311","volume":"40","author":"D Swann","year":"1993","unstructured":"Swann D, Houston P, Goldberg J. Audit of intensive care unit admissions from the operating room. Can J Anaesth. 1993;40(2):137\u201341. https:\/\/doi.org\/10.1007\/BF03011311.","journal-title":"Can J Anaesth"},{"issue":"4","key":"3195_CR4","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1097\/01.CCM.0000060016.21525.3C","volume":"31","author":"U Beckmann","year":"2003","unstructured":"Beckmann U, Bohringer C, Carless R, et al. Evaluation of two methods for quality improvement in intensive care: facilitated incident monitoring and retrospective medical chart review*. Crit Care Med. 2003;31(4):1006\u201311. https:\/\/doi.org\/10.1097\/01.CCM.0000060016.21525.3C.","journal-title":"Crit Care Med"},{"key":"3195_CR5","doi-asserted-by":"crossref","unstructured":"Vlayen A, Verelst S, Bekkering GE, Schrooten W, Hellings J, Claes N. Exploring unplanned ICU admissions: a systematic review. JBI Evid Synth. 2011;9(25). https:\/\/journals.lww.com\/jbisrir\/fulltext\/2011\/09250\/exploring_unplanned_icu_admissions__a_systematic.1.aspx.","DOI":"10.11124\/jbisrir-2011-147"},{"issue":"6","key":"3195_CR6","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1097\/00000542-200512000-00004","volume":"103","author":"G Haller","year":"2005","unstructured":"Haller G, Myles PS, Wolfe R, Weeks AM, Stoelwinder J, McNeil J. Validity of unplanned admission to an intensive care unit as a measure of patient safety in surgical patients. Anesthesiology. 2005;103(6):1121\u20139. https:\/\/doi.org\/10.1097\/00000542-200512000-00004.","journal-title":"Anesthesiology"},{"issue":"5","key":"3195_CR7","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.jopan.2006.07.007","volume":"21","author":"F Dexter","year":"2006","unstructured":"Dexter F, Wachtel RE, Epstein RH. Impact of average patient acuity on staffing of the phase I PACU. J Perianesth Nurs. 2006;21(5):303\u201310. https:\/\/doi.org\/10.1016\/j.jopan.2006.07.007.","journal-title":"J Perianesth Nurs"},{"issue":"2","key":"3195_CR8","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.jopan.2005.01.001","volume":"20","author":"F Dexter","year":"2005","unstructured":"Dexter F, Epstein RH, Marcon E, De Matta R. Strategies to reduce delays in admission into a postanesthesia care unit from operating rooms. J Perianesth Nurs. 2005;20(2):92\u2013102. https:\/\/doi.org\/10.1016\/j.jopan.2005.01.001.","journal-title":"J Perianesth Nurs"},{"issue":"1","key":"3195_CR9","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1213\/ANE.0b013e318253af4b","volume":"115","author":"N Segall","year":"2012","unstructured":"Segall N, Bonifacio AS, Schroeder RA, et al. Can we make postoperative patient handovers safer?? A systematic review of the literature. Anesth Analg. 2012;115(1):102\u201315. https:\/\/doi.org\/10.1213\/ANE.0b013e318253af4b.","journal-title":"Anesth Analg"},{"issue":"2","key":"3195_CR10","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1308\/003588411X561026","volume":"93","author":"T Kamal","year":"2011","unstructured":"Kamal T, Conway R, Littlejohn I, Ricketts D. The role of a multidisciplinary pre-assessment clinic in reducing mortality after complex orthopaedic surgery. Ann R Coll Surg Engl. 2011;93(2):149\u201351. https:\/\/doi.org\/10.1308\/003588411X561026.","journal-title":"Ann R Coll Surg Engl"},{"issue":"3","key":"3195_CR11","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1097\/ALN.0b013e31829ce8fd","volume":"119","author":"JP Wanderer","year":"2013","unstructured":"Wanderer JP, Anderson-Dam J, Levine W, Bittner EA. Development and validation of an intraoperative predictive model for unplanned postoperative intensive care. Anesthesiology. 2013;119(3):516\u201324. https:\/\/doi.org\/10.1097\/ALN.0b013e31829ce8fd.","journal-title":"Anesthesiology"},{"issue":"5","key":"3195_CR12","doi-asserted-by":"publisher","first-page":"1529","DOI":"10.1213\/ANE.0000000000001827","volume":"124","author":"RA Gabriel","year":"2017","unstructured":"Gabriel RA, Waterman RS, Kim J, Ohno-Machado L. A predictive model for extended postanesthesia care unit length of stay in outpatient surgeries. Anesth Analg. 2017;124(5):1529\u201336. https:\/\/doi.org\/10.1213\/ANE.0000000000001827.","journal-title":"Anesth Analg"},{"issue":"2","key":"3195_CR13","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1097\/SHK.0000000000002490","volume":"63","author":"T Zander","year":"2025","unstructured":"Zander T, Kendall MA, Grimsley EA, PREDICTING UNPLANNED TRAUMA INTENSIVE CARE UNIT ADMISSIONS FOR INITIAL NONOPERATIVE, NON-ICU PATIENTS, et al. Shock. 2025;63(2):240\u20137. https:\/\/doi.org\/10.1097\/SHK.0000000000002490.","journal-title":"Shock"},{"key":"3195_CR14","doi-asserted-by":"publisher","unstructured":"Chowdhury S, Lin Y, Liaw B, Kerby L. Evaluation of tree based regression over multiple linear regression for Non-normally distributed data in battery performance. Published Online November. 2021;3. https:\/\/doi.org\/10.48550\/arXiv.2111.02513.","DOI":"10.48550\/arXiv.2111.02513"},{"issue":"7","key":"3195_CR15","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1177\/0885066615622124","volume":"32","author":"TD Quinn","year":"2017","unstructured":"Quinn TD, Gabriel RA, Dutton RP, Urman RD. Analysis of unplanned postoperative admissions to the intensive care unit. J Intensive Care Med. 2017;32(7):436\u201343. https:\/\/doi.org\/10.1177\/0885066615622124.","journal-title":"J Intensive Care Med"},{"issue":"9","key":"3195_CR16","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1002\/jhm.2062","volume":"8","author":"VC Douglas","year":"2013","unstructured":"Douglas VC, Hessler CS, Dhaliwal G, et al. The AWOL tool: derivation and validation of a delirium prediction rule. J Hosp Med. 2013;8(9):493\u20139. https:\/\/doi.org\/10.1002\/jhm.2062.","journal-title":"J Hosp Med"},{"key":"3195_CR17","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C, XGBoost:. A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM; 2016:785\u2013794. https:\/\/doi.org\/10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"key":"3195_CR18","doi-asserted-by":"publisher","unstructured":"Lundberg S, Lee SI. A unified approach to interpreting model predictions. Published Online November. 2017;25. https:\/\/doi.org\/10.48550\/arXiv.1705.07874.","DOI":"10.48550\/arXiv.1705.07874"},{"issue":"10","key":"3195_CR19","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","volume":"2","author":"SM Lundberg","year":"2018","unstructured":"Lundberg SM, Nair B, Vavilala MS, et al. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nat Biomed Eng. 2018;2(10):749\u201360. https:\/\/doi.org\/10.1038\/s41551-018-0304-0.","journal-title":"Nat Biomed Eng"},{"key":"3195_CR20","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","volume":"110","author":"E Christodoulou","year":"2019","unstructured":"Christodoulou E, Ma J, Collins GS, Steyerberg EW, Verbakel JY, Van Calster B. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol. 2019;110:12\u201322. https:\/\/doi.org\/10.1016\/j.jclinepi.2019.02.004.","journal-title":"J Clin Epidemiol"},{"issue":"9","key":"3195_CR21","doi-asserted-by":"publisher","first-page":"4571","DOI":"10.1073\/pnas.1906831117","volume":"117","author":"ED Gennatas","year":"2020","unstructured":"Gennatas ED, Friedman JH, Ungar LH, et al. Expert-augmented machine learning. Proc Natl Acad Sci. 2020;117(9):4571\u20137. https:\/\/doi.org\/10.1073\/pnas.1906831117.","journal-title":"Proc Natl Acad Sci"},{"issue":"3","key":"3195_CR22","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1097\/ACO.0000000000000850","volume":"33","author":"E Wang","year":"2020","unstructured":"Wang E, Brenn BR, Matava CT. State of the Art in clinical decision support applications in pediatric perioperative medicine. Curr Opin Anaesthesiol. 2020;33(3):388\u201394. https:\/\/doi.org\/10.1097\/ACO.0000000000000850.","journal-title":"Curr Opin Anaesthesiol"},{"issue":"6","key":"3195_CR23","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1213\/ANE.0000000000005085","volume":"131","author":"EL Whitlock","year":"2020","unstructured":"Whitlock EL, Braehler MR, Kaplan JA, et al. Derivation, validation, sustained performance, and clinical impact of an electronic medical Record\u2013Based perioperative delirium risk stratification tool. Anesth Analg. 2020;131(6):1901\u201310. https:\/\/doi.org\/10.1213\/ANE.0000000000005085.","journal-title":"Anesth Analg"}],"container-title":["BMC Anesthesiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12871-025-03195-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12871-025-03195-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12871-025-03195-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T17:41:44Z","timestamp":1752774104000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcanesthesiol.biomedcentral.com\/articles\/10.1186\/s12871-025-03195-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,17]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["3195"],"URL":"https:\/\/doi.org\/10.1186\/s12871-025-03195-8","relation":{},"ISSN":["1471-2253"],"issn-type":[{"value":"1471-2253","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,17]]},"assertion":[{"value":"21 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 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":"Approval for this retrospective review of electronic medical records was obtained by the University of California, San Francisco Institutional Review Board (IRB, # 19-27979), and the requirement for written informed consent was waived by the IRB. This study was conducted in accordance with the principles of 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":"AMB is a founder of Bezel Health, a company building software to measure and improve healthcare quality interventions. AJB was a co-founder and consultant to Personalis and NuMedii; consultant to Samsung, Mango Tree Corporation, and in the recent past, 10x Genomics, Helix, Pathway Genomics, and Verinata (Illumina); had served on paid advisory panels or boards for Geisinger Health, Regenstrief Institute, Gerson Lehman Group, AlphaSights, Covance, Novartis, Genentech, and Merck, and Roche; was a shareholder in Personalis and NuMedii; was a minor shareholder in Apple, Facebook, Alphabet (Google), Microsoft, Amazon, Snap, 10x Genomics, Illumina, CVS, Nuna Health, Assay Depot, Vet24seven, Regeneron, Sanofi, Royalty Pharma, AstraZeneca, Moderna, Biogen, and Sutro, and several other non-health related companies and mutual funds; and had received honoraria and travel reimbursement for invited talks from Johnson and Johnson, Roche, Genentech, Pfizer, Merck, Lilly, Takeda, Varian, Mars, Siemens, Optum, Abbott, Celgene, AstraZeneca, AbbVie, Westat, and many academic institutions, medical or disease specific foundations and associations, and health systems. Atul Butte received royalty payments through Stanford University, for several patents and other disclosures licensed to NuMedii and Personalis. Atul Butte\u2019s research had been funded by NIH, Northrup Grumman (as the prime on an NIH contract), Genentech, Johnson and Johnson, FDA, Robert Wood Johnson Foundation, Leon Lowenstein Foundation, Intervalien Foundation, Priscilla Chan and Mark Zuckerberg, the Barbara and Gerson Bakar Foundation, and in the recent past, the March of Dimes, Juvenile Diabetes Research Foundation, California Governor\u2019s Office of Planning and Research, California Institute for Regenerative Medicine, L\u2019Oreal, and Progenity. 3.The above organizations had no direct involvement in study design; in the collection, analysis, and interpretation of data; in the writing of the report; or in the decision to submit the article for publication. 4.The remainder of authors declare no conflicts of interest. As these competing interests have no relationship with the study, we have stated \u201cNone\u201d in the manuscript as instructed by the editing team.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"351"}}