{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T23:28:31Z","timestamp":1775863711141,"version":"3.50.1"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T00:00:00Z","timestamp":1739318400000},"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. Digit. Health"],"abstract":"<jats:p>This study aims to address the critical issue of emergency department (ED) overcrowding, which negatively affects patient outcomes, wait times, and resource efficiency. Accurate prediction of ED length of stay (LOS) can streamline operations and improve care delivery. We utilized the MIMIC IV-ED dataset, comprising over 400,000 patient records, to classify ED LOS into short (\u22644.5 hours) and long (&amp;gt;4.5 hours) categories. Using machine learning models, including Gradient Boosting (GB), Random Forest (RF), Logistic Regression (LR), and Multilayer Perceptron (MLP), we identified GB as the best performing model outperforming the other models with an AUC of 0.730, accuracy of 69.93%, sensitivity of 88.20%, and specificity of 40.95% on the original dataset. In the balanced dataset, GB had an AUC of 0.729, accuracy of 68.86%, sensitivity of 75.39%, and specificity of 58.59%. To enhance interpretability, a novel rule extraction method for GB model was implemented using relevant important predictors, such as triage acuity, comorbidity scores, and arrival methods. By combining predictive analytics with interpretable rule-based methods, this research provides actionable insights for optimizing patient flow and resource allocation. The findings highlight the importance of transparency in machine learning applications for healthcare, paving the way for future improvements in model performance and clinical adoption.<\/jats:p>","DOI":"10.3389\/fdgth.2024.1498939","type":"journal-article","created":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T07:31:29Z","timestamp":1739345489000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Leveraging machine learning and rule extraction for enhanced transparency in emergency department length of stay prediction"],"prefix":"10.3389","volume":"6","author":[{"given":"Waqar A.","family":"Sulaiman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charithea","family":"Stylianides","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andria","family":"Nikolaou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zinonas","family":"Antoniou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Constantinou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lakis","family":"Palazis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Vavlitou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Theodoros","family":"Kyprianou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Efthyvoulos","family":"Kyriacou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonis","family":"Kakas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marios S.","family":"Pattichis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas S.","family":"Panayides","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Constantinos S.","family":"Pattichis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,2,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1017\/S1481803500008204","article-title":"Access to acute care in the setting of emergency department overcrowding","volume":"5","year":"2003","journal-title":"Can J Emerg Med"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e0247042","DOI":"10.1371\/journal.pone.0247042","article-title":"The effect of overcrowding in emergency departments on the admission rate according to the emergency triage level","volume":"16","author":"Jung","year":"2021","journal-title":"PLoS One"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1427","DOI":"10.1093\/jamia\/ocz171","article-title":"Predicting emergency department orders with multilabel machine learning techniques and simulating effects on length of stay","volume":"26","author":"Hunter-Zinck","year":"2019","journal-title":"J Am Med Inform Assoc"},{"key":"B4","first-page":"34","article-title":"Applications of machine learning approaches in emergency medicine; a review article","volume":"7","author":"Shafaf","year":"2019","journal-title":"Arch Acad Emerg Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1186\/s13054-019-2351-7","article-title":"Emergency department triage prediction of clinical outcomes using machine learning models","volume":"23","author":"Raita","year":"2019","journal-title":"Crit Care"},{"key":"B6","doi-asserted-by":"publisher","first-page":"e2118467","DOI":"10.1001\/jamanetworkopen.2021.18467","article-title":"Development and assessment of an interpretable machine learning triage tool for estimating mortality after emergency admissions","volume":"4","author":"Xie","year":"2021","journal-title":"JAMA Network Open"},{"key":"B7","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1038\/s41597-022-01782-9","article-title":"Benchmarking emergency department prediction models with machine learning and public electronic health records","volume":"9","author":"Xie","year":"2022","journal-title":"Sci Data"},{"key":"B8","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s12559-023-10179-8","article-title":"Interpreting black-box models: a review on explainable artificial intelligence","volume":"16","author":"Hassija","year":"2023","journal-title":"Cognit Comput"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/8167821","article-title":"From blackbox to explainable AI in healthcare: existing tools and case studies","volume":"2022","author":"Srinivasu","year":"2022","journal-title":"Mobile Inf Syst"},{"key":"B10","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-3-030-55340-1_8","article-title":"The impact of rule evaluation metrics as a conflict resolution strategy","volume":"1183","author":"Al-A\u2019araji","year":"2020","journal-title":"Commun Comput Inf Sci"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3233\/jifs-219375","article-title":"Clinical notes classification system for automated identification of diabetic patients: hybrid approach integrating rules, information extraction and machine learning","volume":"47","author":"Zavala-D\u00edaz","year":"2024","journal-title":"J Intell Fuzzy Syst"},{"key":"B12","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/s41598-021-04608-7","article-title":"An explainable machine learning framework for lung cancer hospital length of stay prediction","volume":"12","author":"Alsinglawi","year":"2022","journal-title":"Sci Rep"},{"key":"B13","first-page":"53","article-title":"Classifying emergency patients into fast-track and complex cases using machine learning","volume":"15","author":"Karajeh","year":"2024","journal-title":"Int J Artif Intell Appl"},{"key":"B14","first-page":"1","article-title":"A deep learning approach for length of stay prediction in clinical settings from medical records","author":"Zebin","year":"2019"},{"key":"B15","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.annemergmed.2020.01.010","article-title":"Predicting hospital admission and prolonged length of stay in older adults in the emergency department: the PRO-AGE scoring system","volume":"76","author":"Curiati","year":"2020","journal-title":"Ann Emerg Med"},{"key":"B16","doi-asserted-by":"publisher","first-page":"ooae074","DOI":"10.1093\/jamiaopen\/ooae074","article-title":"In-hospital mortality, readmission, and prolonged length of stay risk prediction leveraging historical electronic patient records","volume":"7","author":"Bopche","year":"2024","journal-title":"JAMIA Open"},{"key":"B17","doi-asserted-by":"publisher","first-page":"42243","DOI":"10.1109\/ACCESS.2022.3168045","article-title":"Prediction of length of stay in the emergency department for COVID-19 patients: a machine learning approach","volume":"10","author":"Etu","year":"2022","journal-title":"IEEE Access"},{"key":"B18","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1186\/s12873-022-00632-6","article-title":"Machine learning\u2013based triage to identify low-severity patients with a short discharge length of stay in emergency department","volume":"22","author":"Chang","year":"2022","journal-title":"BMC Emerg Med"},{"key":"B19","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1111\/1742-6723.13421","article-title":"Using data mining to predict emergency department length of stay greater than 4\u2009h: derivation and single-site validation of a decision tree algorithm","volume":"32","author":"Rahman","year":"2019","journal-title":"Emerg Med Australas"},{"key":"B20","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1111\/1742-6723.12964","article-title":"Why do \u201cfast track\u201d patients stay more than four hours in the emergency department? An investigation of factors that predict length of stay","volume":"30","author":"Gill","year":"2018","journal-title":"Emerg Med Australas"},{"key":"B21","doi-asserted-by":"publisher","first-page":"3321","DOI":"10.1111\/jgs.17944","article-title":"Unplanned intensive care unit admission in hospitalized older patients: association with a geriatric vulnerability score","volume":"70","author":"Silva","year":"2022","journal-title":"J Am Geriatr Soc"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data"},{"key":"B23","article-title":"Addressing deficiencies from missing data in electronic health records. Mitedu","author":"Zhou","year":"2021"},{"key":"B24","doi-asserted-by":"publisher","first-page":"96304","DOI":"10.1109\/ACCESS.2024.3426675","article-title":"Sequential anomaly detection for continuous prediction of unexpected ICU admission from emergency department","volume":"12","author":"Choi","year":"2024","journal-title":"IEEE Access"},{"key":"B25","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1145\/3368555.3384469","article-title":"MIMIC-extract: a data extraction, preprocessing, and representation pipeline for MIMIC-III","volume":"20","author":"Wang","year":"2020","journal-title":"ACM Chil"},{"key":"B26","article-title":"YerevaNN\/Mimic3-benchmarks. GitHub","author":"Harutyunyan","year":""},{"key":"B27","doi-asserted-by":"crossref","DOI":"10.1109\/ICDM.2008.17","article-title":"Isolation forest","author":"Liu","year":""},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/bdcc5010001","article-title":"A review of local outlier factor algorithms for outlier detection in big data streams","volume":"5","author":"Alghushairy","year":"2020","journal-title":"Big Data Cogn Comput"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1109\/ICDSNS62112.2024.10691111","article-title":"Bridging data gaps: a comparative study of different imputation methods for numeric datasets","author":"Prakash","year":""},{"key":"B30","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1142\/9789813207813_0021","article-title":"Missing data imputation in the electronic health record using deeply learned autoencoders","volume":"2017","author":"Beaulieu-Jones","year":"2016","journal-title":"Biocomputing"},{"key":"B31","doi-asserted-by":"publisher","first-page":"100930","DOI":"10.1016\/j.ienj.2020.100930","article-title":"Long emergency department length of stay: a concept analysis","volume":"53","author":"Andersson","year":"2020","journal-title":"Int Emerg Nurs"},{"key":"B32","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1136\/emj.2003.008003","article-title":"Reforming emergency care and ambulance services","volume":"21","author":"Judge","year":"2004","journal-title":"Emerg Med J"},{"key":"B33","article-title":"imblearn: toolbox for imbalanced dataset in machine learning. PyPI","year":""},{"key":"B34","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1007\/978-3-030-22744-9_31","article-title":"A novel distribution analysis for SMOTE oversampling method in handling class imbalance","volume":"11538","author":"Elreedy","year":"2019","journal-title":"Lect Notes Comput Sci"},{"key":"B35","article-title":"ADASYN: Adaptive synthetic sampling approach for imbalanced learning","author":"He","year":""},{"key":"B36","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1109\/TSMC.1976.5409182","article-title":"Two modifications of CNN","author":"Tomek","year":"1976","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"B37","doi-asserted-by":"publisher","first-page":"585","DOI":"10.14569\/IJACSA.2023.0140864","article-title":"A new approach of hybrid sampling SMOTE and ENN to the accuracy of machine learning methods on unbalanced diabetes disease data","volume":"14","author":"Hairani","year":"2023","journal-title":"Int J Adv Comput Sci Appl"},{"key":"B38","doi-asserted-by":"publisher","first-page":"2878","DOI":"10.1007\/s11999-014-3686-7","article-title":"The elixhauser comorbidity method outperforms the charlson index in predicting inpatient death after orthopaedic surgery","volume":"472","author":"Menendez","year":"2014","journal-title":"Clin Orthop Relat Res"},{"key":"B39","article-title":"pandas.get_dummies\u2014pandas 1.2.4 documentation","year":""},{"key":"B40","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/j.chemolab.2010.12.004","article-title":"Empirical comparison of tree ensemble variable importance measures","volume":"105","author":"Auret","year":"2011","journal-title":"Chemometr Intell Lab Syst"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1136\/fmch-2019-000262","article-title":"Variable selection strategies and its importance in clinical prediction modelling","volume":"8","author":"Chowdhury","year":"2020","journal-title":"Family Med Community Health"},{"key":"B42","article-title":"Scikit-learn: machine learning in python. Scikit-Learn.org (2019)","year":""},{"key":"B43","article-title":"GitHub repository (2015)","author":"Chollet","year":""},{"key":"B44","doi-asserted-by":"publisher","first-page":"2009","DOI":"10.1007\/s00180-020-00999-9","article-title":"What is an optimal value of k in k-fold cross-validation in discrete Bayesian network analysis?","volume":"36","author":"Marcot","year":"2020","journal-title":"Comput Stat"},{"key":"B45","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-18305-3_4","article-title":"Performance evaluation in machine learning","author":"Japkowicz","year":"2015"},{"key":"B46","article-title":"TE2Rules: explaining tree ensembles using rules","author":"Lal","year":""},{"key":"B47","article-title":"Te2rules: python library to explain tree ensembles using rules. PyPI","author":"Lal","year":""},{"key":"B48","doi-asserted-by":"publisher","first-page":"419","DOI":"10.3233\/FI-2016-1455","article-title":"Rule quality measures settings in classification, regression and survival rule induction \u2013 an empirical approach","volume":"149","author":"Wr\u00f3bel","year":"2016","journal-title":"Fundam Inform"},{"key":"B49","doi-asserted-by":"publisher","first-page":"1937","DOI":"10.1007\/s10462-020-09896-5","article-title":"A comparative analysis of gradient boosting algorithms","volume":"54","author":"Bent\u00e9jac","year":"2020","journal-title":"Artif Intell Rev"},{"key":"B50","doi-asserted-by":"publisher","first-page":"808","DOI":"10.3233\/SHTI240534","article-title":"An overview of explainable AI studies in the prediction of sepsis onset and sepsis mortality","volume":"316","author":"Nicolaou","year":"2024","journal-title":"Stud Health Technol Inform"},{"key":"B51","article-title":"Examining patients length of stay estimation with explainable artificial intelligence methods","author":"K\u00fcbra","year":""},{"key":"B52","doi-asserted-by":"publisher","first-page":"1812","DOI":"10.3233\/SHTI240783","article-title":"Emergency department length of stay classification based on ensemble methods and rule extraction","volume":"316","author":"Aziz","year":"2024","journal-title":"Stud Health Technol Inform"},{"key":"B53","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3233\/AAC-181006","article-title":"GORGIAS: applying argumentation","volume":"10","author":"Kakas","year":"2019","journal-title":"Argument Comput"},{"key":"B54","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-98074-4","volume-title":"Learning From Imbalanced Data Sets","author":"Fern\u00e1ndez","year":"2018"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2024.1498939\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T07:31:34Z","timestamp":1739345494000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2024.1498939\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,12]]},"references-count":54,"alternative-id":["10.3389\/fdgth.2024.1498939"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2024.1498939","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,12]]},"article-number":"1498939"}}