{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T21:36:44Z","timestamp":1790199404551,"version":"4.1.0"},"reference-count":37,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T00:00:00Z","timestamp":1651104000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\"><jats:title>Background<\/jats:title><jats:p>Emergency general surgery (EGS) operations are associated with substantial risk of morbidity including postoperative respiratory failure (PRF). While existing risk models are not widely utilized and rely on traditional statistical methods, application of machine learning (ML) in prediction of PRF following EGS remains unexplored.<\/jats:p><\/jats:sec><jats:sec id=\"sec002\"><jats:title>Objective<\/jats:title><jats:p>The present study aimed to develop ML-based prediction models for respiratory failure following EGS and compare their performance to traditional regression models using a nationally-representative cohort.<\/jats:p><\/jats:sec><jats:sec id=\"sec003\"><jats:title>Methods<\/jats:title><jats:p>Non-elective hospitalizations for EGS (appendectomy, cholecystectomy, repair of perforated ulcer, large or small bowel resection, lysis of adhesions) were identified in the 2016\u201318 Nationwide Readmissions Database. Factors associated with PRF were identified using ML techniques and logistic regression. The performance of XGBoost and logistic regression was evaluated using the receiver operating characteristic curve and coefficient of determination (R<jats:sup>2<\/jats:sup>). The impact of PRF on mortality, length of stay (LOS) and hospitalization costs was secondarily assessed using generalized linear models.<\/jats:p><\/jats:sec><jats:sec id=\"sec004\"><jats:title>Results<\/jats:title><jats:p>Of 1,003,703 hospitalizations, 8.8% developed PRF. The XGBoost model exhibited slightly superior discrimination compared to logistic regression (0.900, 95% CI 0.899\u20130.901 vs 0.894, 95% CI 0.862\u20130.896). Compared to logistic regression, XGBoost demonstrated excellent calibration across all risk levels (R<jats:sup>2<\/jats:sup>: 0.998 vs 0.962). Congestive heart failure, neurologic disorders, and coagulopathy were significantly associated with increased risk of PRF. After risk-adjustment, PRF was associated with 10-fold greater odds (95% confidence interval (CI) 9.8\u201311.1) of mortality and incremental increases in LOS by 3.1 days (95% CI 3.0\u20133.2) and $11,900 (95% CI 11,600\u201312,300) in costs.<\/jats:p><\/jats:sec><jats:sec id=\"sec005\"><jats:title>Conclusions<\/jats:title><jats:p>Logistic regression and XGBoost perform similarly in overall classification of PRF risk. However, due to superior calibration at extremes of risk, ML-based models may prove more useful in the clinical setting, where probabilities rather than classifications are desired.<\/jats:p><\/jats:sec>","DOI":"10.1371\/journal.pone.0267733","type":"journal-article","created":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T19:49:46Z","timestamp":1651175386000},"page":"e0267733","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":18,"title":["Machine learning-based modeling of acute respiratory failure following emergency general surgery operations"],"prefix":"10.1371","volume":"17","author":[{"given":"Joseph","family":"Hadaya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arjun","family":"Verma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yas","family":"Sanaiha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramin","family":"Ramezani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nida","family":"Qadir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4705-0262","authenticated-orcid":true,"given":"Peyman","family":"Benharash","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,4,28]]},"reference":[{"key":"pone.0267733.ref001","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/S1072-7515(01)01183-8","article-title":"Identifying patient preoperative risk factors and postoperative adverse events in administrative databases: Results from the Department of Veterans Affairs National Surgical Quality Improvement Program","volume":"194","author":"WR Best","year":"2002","journal-title":"J Am Coll Surg"},{"key":"pone.0267733.ref002","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1097\/01.sla.0000179621.33268.83","article-title":"Determinants of long-term survival after major surgery and the adverse effect of postoperative complications","volume":"242","author":"SF Khuri","year":"2005","journal-title":"Ann Surg"},{"key":"pone.0267733.ref003","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1177\/1077558710396378","article-title":"Excess costs attributable to postoperative complications","volume":"68","author":"K Carey","year":"2011","journal-title":"Med Care Res Rev"},{"key":"pone.0267733.ref004","doi-asserted-by":"crossref","first-page":"581","DOI":"10.7326\/0003-4819-144-8-200604180-00009","article-title":"Preoperative pulmonary risk stratification for noncardiothoracic surgery: Systematic review for the American College of Physicians","volume":"114","author":"GW Smetana","year":"2006","journal-title":"Ann Intern Med"},{"key":"pone.0267733.ref005","unstructured":"NQF: Measuring Performance. [cited 1 Aug 2021]. Available: https:\/\/www.qualityforum.org\/Measuring_Performance\/Measuring_Performance.aspx."},{"key":"pone.0267733.ref006","unstructured":"Patient Safety Indicators (PSI) Overview. [cited 1 Aug 2021]. Available: https:\/\/www.qualityindicators.ahrq.gov\/Modules\/psi_resources.aspx#techspecs."},{"key":"pone.0267733.ref007","unstructured":"Hospital Inpatient Quality Reporting (IQR) Program Measures. [cited 1 Aug 2021]. Available: https:\/\/qualitynet.cms.gov\/inpatient\/iqr\/measures."},{"key":"pone.0267733.ref008","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1016\/j.jamcollsurg.2007.02.070","article-title":"Multivariable Predictors of Postoperative Respiratory Failure after General and Vascular Surgery: Results from the Patient Safety in Surgery Study","volume":"204","author":"RG Johnson","year":"2007","journal-title":"J Am Coll Surg"},{"key":"pone.0267733.ref009","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1378\/chest.11-0466","article-title":"Development and validation of a risk calculator predicting postoperative respiratory failure","volume":"140","author":"H Gupta","year":"2011","journal-title":"Chest"},{"key":"pone.0267733.ref010","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1097\/TA.0000000000000517","article-title":"The excess morbidity and mortality of emergency general surgery","volume":"78","author":"JM Havens","year":"2015","journal-title":"J Trauma Acute Care Surg"},{"key":"pone.0267733.ref011","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1016\/j.amjsurg.2010.11.007","article-title":"Factors affecting morbidity in emergency general surgery","volume":"201","author":"F Akinbami","year":"2011","journal-title":"Am J Surg"},{"key":"pone.0267733.ref012","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1097\/ACO.0000000000000730","article-title":"Prediction of postoperative pulmonary complications. Current Opinion in Anaesthesiology","volume":"32","author":"SG Nijbroek","year":"2019","journal-title":"Curr Opin Anaesthesiol"},{"key":"pone.0267733.ref013","unstructured":"Sheils C, Dahlke A, Yang A, Bilimoria K. Are NSQIP Hospitals Unique? A Description of Hospitals Participating in ACS NSQIP. Presented at: Academic Surgical Congress 2016; February 3, 2016; Jacksonville, FL. Available: https:\/\/www.asc-abstracts.org\/abs2016\/51-03-are-nsqip-hospitals-unique-a-description-of-hospitals-participating-in-acs-nsqip\/."},{"key":"pone.0267733.ref014","unstructured":"NRD Overview. [cited 1 Aug 221]. Available: https:\/\/www.hcup-us.ahrq.gov\/nrdoverview.jsp."},{"key":"pone.0267733.ref015","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1016\/j.surg.2019.07.035","article-title":"Acute kidney injury is independently associated with mortality and resource use after emergency general surgery operations","volume":"167","author":"Y Sanaiha","year":"2020","journal-title":"Surgery"},{"key":"pone.0267733.ref016","doi-asserted-by":"crossref","first-page":"e160480","DOI":"10.1001\/jamasurg.2016.0480","article-title":"Use of national burden to define operative emergency general surgery","volume":"151","author":"JW Scott","year":"2016","journal-title":"JAMA Surg"},{"key":"pone.0267733.ref017","unstructured":"NRD Description of Data Elements. [cited 1 Aug 2021]. Available: https:\/\/www.hcup-us.ahrq.gov\/db\/nation\/nrd\/nrddde.jsp."},{"key":"pone.0267733.ref018","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1097\/MLR.0b013e31819432e5","article-title":"A modification of the elixhauser comorbidity measures into a point system for hospital death using administrative data","volume":"47","author":"C Van Walraven","year":"2009","journal-title":"Med Care"},{"key":"pone.0267733.ref019","unstructured":"HCUP-US Cost-to-Charge Ratio Files. [cited 1 Aug 2020]. Available: https:\/\/www.hcup-us.ahrq.gov\/db\/state\/costtocharge.jsp."},{"key":"pone.0267733.ref020","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1001\/jama.2017.18391","article-title":"Big data and machine learning in health care","volume":"319","author":"AL Beam","year":"2018","journal-title":"JAMA"},{"key":"pone.0267733.ref021","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1016\/j.chest.2020.02.079","article-title":"Machine Learning and Prediction of All-Cause Mortality in COPD","volume":"158","author":"M Moll","year":"2020","journal-title":"Chest"},{"key":"pone.0267733.ref022","doi-asserted-by":"crossref","first-page":"428","DOI":"10.3390\/jcm7110428","article-title":"Prediction of Acute Kidney Injury after Liver Transplantation: Machine Learning Approaches vs. Logistic Regression Model","volume":"7","author":"H-C Lee","year":"2018","journal-title":"J Clin Med"},{"key":"pone.0267733.ref023","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost: A scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016: 785\u2013794. doi: 10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"pone.0267733.ref024","article-title":"Regularization and variable selection via the elastic net","author":"H Zou","year":"2005","journal-title":"J R Stat Soc B"},{"key":"pone.0267733.ref025","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression Shrinkage and Selection Via the Lasso","volume":"58","author":"R. Tibshirani","year":"1996","journal-title":"J R Stat Soc Ser B"},{"key":"pone.0267733.ref026","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1023\/A:1012487302797","article-title":"Gene selection for cancer classification using support vector machines","volume":"46","author":"I Guyon","year":"2002","journal-title":"Mach Learn"},{"key":"pone.0267733.ref027","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"pone.0267733.ref028","article-title":"The Derivation of an ICD-10-based Trauma-related Mortality Model Utilizing Machine Learning","author":"Z Tran","year":"2021","journal-title":"J. Trauma Acute Care Surg"},{"key":"pone.0267733.ref029","first-page":"498","article-title":"An acute care surgery model improves outcomes in patients with appendicitis","volume":"244","author":"AS Earley","year":"2006","journal-title":"Ann Surg"},{"key":"pone.0267733.ref030","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.jamcollsurg.2004.02.025","article-title":"Redefining the future of trauma surgery as a comprehensive trauma and emergency general surgery service","volume":"199","author":"PK Kim","year":"2004","journal-title":"J Am Coll Surg"},{"key":"pone.0267733.ref031","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1016\/j.jamcollsurg.2009.06.368","article-title":"Initial Implementation of an Acute Care Surgery Model: Implications for Timeliness of Care","volume":"209","author":"RC Britt","year":"2009","journal-title":"J Am Coll Surg"},{"key":"pone.0267733.ref032","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1097\/TA.0b013e3182516a97","article-title":"Systemic inflammation worsens outcomes in emergency surgical patients","volume":"72","author":"RD Becher","year":"2012","journal-title":"J Trauma Acute Care Surg"},{"key":"pone.0267733.ref033","first-page":"76","article-title":"Postoperative pulmonary complications: An update on risk assessment and reduction","author":"GW Smetana","year":"2009","journal-title":"Cleve Clin J Med"},{"key":"pone.0267733.ref034","doi-asserted-by":"crossref","first-page":"596","DOI":"10.7326\/0003-4819-144-8-200604180-00011","article-title":"Strategies to reduce postoperative pulmonary complications after noncardiothoracic surgery: Systematic review for the American College of Physicians","volume":"144","author":"VA Lawrence","year":"2006","journal-title":"Ann Intern Med"},{"key":"pone.0267733.ref035","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1097\/SLA.0000000000001989","article-title":"Predicting the Risk of Postoperative Respiratory Failure in Elective Abdominal and Vascular Operations Using the National Surgical Quality Improvement Program (NSQIP) Participant Use Data File","volume":"266","author":"AP Johnson","year":"2017","journal-title":"Ann Surg"},{"key":"pone.0267733.ref036","doi-asserted-by":"crossref","first-page":"1868","DOI":"10.1001\/jama.290.14.1868","article-title":"Excess Length of Stay, Charges, and Mortality Attributable to Medical Injuries during Hospitalization","volume":"290","author":"C Zhan","year":"2003","journal-title":"J Am Med Assoc"},{"key":"pone.0267733.ref037","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.jhin.2017.05.005","article-title":"Screening for sepsis in general hospitalized patients: a systematic review","volume":"96","author":"L Alberto","year":"2017","journal-title":"J Hosp Infect"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0267733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T06:59:50Z","timestamp":1727074790000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0267733"}},"subtitle":[],"editor":[{"given":"Laura","family":"Pasin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,4,28]]},"references-count":37,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0267733","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,28]]}}}