The effective management of Emergency Department (ED) overcrowding is essential for improving patient outcomes and optimizing healthcare resource allocation. This study validates hospital admission prediction models initially developed using a small local dataset from a Greek hospital by leveraging the comprehensive MIMIC-IV dataset. After preprocessing the MIMIC-IV data, five algorithms—Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Random Forest (RF), Recursive Partitioning and Regression Trees (RPART), and Support Vector Machines (svmRadial)—were evaluated. Among these, RF demonstrated superior performance, achieving an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.9999, sensitivity of 0.9997, and specificity of 0.9999 when applied to the MIMIC-IV data. These findings underscore the robustness of RF in handling complex datasets for admission prediction, establishing MIMIC-IV as a valuable benchmark for validating models based on smaller local datasets and providing actionable insights for steering ED management strategies in the right direction.
ButunAKafdagEEGunduzH, et al.Emergency department overcrowding: causes and solutions. Emergency and Critical Care Medicine2023; 3: 171–176.
2.
FabbriCLombardiMMalagutiE,et al.On-line strategy selection for reducing overcrowding in an emergency department. Omega (Westport)2024; 127: 103098.
3.
JonesCHDolstenM. Healthcare on the brink: navigating the challenges of an aging society in the United States. npj Aging2024; 10: 22.
4.
PearceSMarrEShannonT, et al.Overcrowding in emergency departments: an overview of reviews describing global solutions and their outcomes. Intern Emerg Med2024; 19: 483–491.
5.
DarrajAHudaysAHazaziA, et al.The association between emergency department overcrowding and delay in treatment: a systematic review. In: Healthcare. Vol. 11, 385. Basel, Switzerland: MDPI, 2023.
6.
LupoRMarchisioDBustoF, et al.The quality perceived in emergency departments between patients and caregivers according to waiting time: a cross sectional multicenter study. Acta Biomed2024; 95: 1–12.
7.
OskvarekJJZocchiMSBlackBS, et al.US Acute care solutions research group. Emergency department volume, severity, and crowding since the onset of the coronavirus disease 2019 pandemic. Ann Emerg Med2023; 82: 650–660.
8.
MostafaREl-AtawiK. Strategies to measure and improve emergency department performance: a review. Cureus2024; 16.
9.
Álvarez-ChavesHSpruitM; R-MorenoMD. Improving ED admissions forecasting by using generative AI: an approach based on DGAN. Comput Methods Programs Biomed2024; 256: 108363.
10.
HaasRBrundisiniFBarbaraA, et al.Emergency department overcrowding: an environmental scan of contributing factors and a summary of systematic review evidence on interventions. Canadian Journal of Health Technologies2023; 3: 11.
11.
TylerSOlisMAustN, et al.Use of artificial intelligence in triage in hospital emergency departments: a scoping review. Cureus2024; 16.
12.
MonahanACFeldmanSS. The utility of predictive modeling and a systems process approach to reduce emergency department crowding: a position paper. Interact J Med Res2023; 12: e42016.
13.
FeretzakisGSakagianniAAnastasiouA, et al.Machine learning in medical triage: a predictive model for emergency department disposition. Appl Sci2024; 14: 6623.
14.
El ArissABKijpaisalratanaNAhmedS, et al.Development and validation of a machine learning framework for improved resource allocation in the emergency department. Am J Emerg Med2024; 84: 141–148.
15.
JiangSLiuQDingB. A systematic review of the modelling of patient arrivals in emergency departments. Quant Imaging Med Surg2023; 13: 1957.
16.
XieFZhouJLeeJW, et al.Benchmarking emergency department prediction models with machine learning and public electronic health records. Sci Data2022; 9: 658.
17.
BuiHWarrierH,GuptaY.Benchmarking with MIMIC-IV, an irregular, spare clinical time series dataset. arXiv preprint arXiv:2401.152902024.
18.
DolciTAmataLMancoC, et al.Tools for healthcare data lake infrastructure benchmarking. Inf Syst Front2024: 1–22.
19.
JohnsonAEBulgarelliLShenL, et al.MIMIC-IV, a freely accessible electronic health record dataset. Sci Data2023; 10: 1.
20.
TsoniRKaldisVKapogianniI., et al.A machine learning pipeline using KNIME to predict hospital admission in the MIMIC-IV database. In: 2023 14th international conference on information, intelligence, systems & applications (IISA). USA: IEEE2023, pp. 1–6.
21.
SubudhiSVermaAPatelAB, et al.Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19. NPJ digital Medicine2021; 4: 87.
22.
DoudaLHasnatHSchwankJ, et al.Predictors of intensive care unit admissions in patients presenting with coronavirus disease 2019. Avicenna J Med2024; 14: 045–053.
23.
FennADavisCBucklandDM, et al.Development and validation of machine learning models to predict admission from emergency department to inpatient and intensive care units. Ann Emerg Med2021; 78: 290–302.
24.
NguyenMCorbinCKEulalioT, et al.Developing machine learning models to personalize care levels among emergency room patients for hospital admission. J Am Med Inform Assoc2021; 28: 2423–2432.
25.
IpWXenochristouMSuiE, et al.Hospitalization prediction from the emergency department using computer vision AI with short patient video clips. npj Digital Medicine2024; 7: 371.
26.
AhmedAAshourOAliH,et al.An integrated optimization and machine learning approach to predict the admission status of emergency patients. Expert Syst Appl2022; 202: 117314.
27.
MonahanACFeldmanSSFitzgeraldTP. Reducing crowding in emergency departments with early prediction of hospital admission of adult patients using biomarkers collected at triage: retrospective cohort study. JMIR Bioinformatics and Biotechnology2022; 3: e38845.
28.
PaiDRRajanBJairathP,et al.Predicting hospital admission from emergency department triage data for patients presenting with fall-related fractures. Intern Emerg Med2023; 18: 219–227.
29.
GlicksbergBSTimsinaPPatelD, et al.Evaluating the accuracy of a state-of-the-art large language model for prediction of admissions from the emergency room. J Am Med Inform Assoc2024; 31: ocae103.
30.
LileyJBohnerGEmersonSR, et al.Development and assessment of a machine learning tool for predicting emergency admission in Scotland. npj Digital Medicine2024; 7: 277.
31.
FeretzakisGKarlisGLoupelisE, et al.Using machine learning techniques to predict hospital admission at the emergency department. The Journal of Critical Care Medicine2022; 8: 107–116.
32.
StylianouNYoungJPedenCJ,et al.Developing and validating a predictive model for future emergency hospital admissions. Health Informatics J2022; 28: 14604582221101538.
33.
KingZFarringtonJUtleyM, et al.Machine learning for real-time aggregated prediction of hospital admission for emergency patients. NPJ Digital Medicine2022; 5: 104.
34.
CusidóJComalrenaJAlaviH,et al.Predicting hospital admissions to reduce crowding in the emergency departments. Appl Sci2022; 12: 10764.
35.
Álvarez-ChavesHSpruitM; R-MorenoMD. Improving ED admissions forecasting by using generative AI: an approach based on DGAN. Comput Methods Programs Biomed2024; 256: 108363.
36.
De HondARavenWSchinkelshoekL, et al.Machine learning for developing a prediction model of hospital admission of emergency department patients: hype or hope?Int J Med Inf2021; 152: 104496.
37.
BrossardCGoetzCCatoireP, et al.Predicting emergency department admissions using a machine-learning algorithm: a proof of concept with retrospective study. BMC Emerg Med2025; 25: 3.
38.
LeonardFGilliganJBarrettMJ. Development of a low-dimensional model to predict admissions from triage at a pediatric emergency department. Journal of the American College of Emergency Physicians Open2022; 3: e12779.
39.
PandeyDJahanabadiHD'ArcyJ, et al.Early prediction of intensive care unit admission in emergency department patients using machine learning. Aust Crit Care2024; 38: 101143.
40.
KishoreKBraitbergGHolmesNE,et al.Early prediction of hospital admission of emergency department patients. Emerg Med Australas2023; 35: 572–588.
41.
HigginsOChalupSKWilsonRL. Machine learning model reveals determinators for admission to acute mental health wards from emergency department presentations. Int J Ment Health Nurs2024; 33: 2354–2369.
42.
LeeJTHsiehCCLinCH, et al.Prediction of hospitalization using artificial intelligence for urgent patients in the emergency department. Sci Rep2021; 11: 19472.
43.
ZahidMKhanAAAtaF, et al.Medical Admission Prediction Score (MAPS): a simple tool to predict medical admissions in the emergency department. PLOS ONE2023; 18: e0293140.
44.
RatnovskyARozenesSBlochE,et al.Statistical learning methodologies and admission prediction in an emergency department. Australasian Emergency Care2021; 24: 241–247.
45.
XieFZhouJLeeJW, et al.Benchmarking emergency department prediction models with machine learning and public electronic health records. Sci Data2022; 9: 658.
46.
KouhounestaniMSongLLuoL,et al.Enhancing predictive modeling in emergency departments. In: ICT4AWE2024: 37–46.
47.
ShuTHuangJDengJ, et al.Development and assessment of scoring model for ICU stay and mortality prediction after emergency admissions in ischemic heart disease: a retrospective study of MIMIC-IV databases. Intern Emerg Med2023; 18: 487–497.
48.
ChoiSKimGKwonJE,et al.Sequential anomaly detection for continuous prediction of unexpected ICU admission from emergency department. IEEE Access, IEEE, 2024.
49.
FeretzakisGSakagianniAKallesD, et al.Using machine learning for predicting the hospitalization of emergency department patients. In: Advances in informatics, management and technology in healthcare. Amsterdam, Netherlands: IOS Press2022, pp. 405–408.
50.
TukeyJW. Exploratory data analysis. Reading, MA, USA: Reading/Addison-Wesley, 1977.
51.
JakobsenJCGluudCWetterslevJ,et al.When and how should multiple imputation be used for handling missing data in randomised clinical trials – a practical guide with flowcharts. BMC Med Res Methodol2017; 17: 1–10.
52.
YangX.KimY. J.KhoshnevisanF.,et al.Missing data imputation for MIMIC-III using matrix decomposition. In: 2019 IEEE international conference on healthcare informatics (ICHI). USA: IEEE2019, pp. 1–3.
53.
GuptaMGallamozaBCutronaN, et al.An extensive data processing pipeline for mimic-iv. In: Machine Learning for Health. PMLR2022; 193: 311–325.
54.
LeeSAJainSChenA, et al.Multimodal clinical pseudo-notes for emergency department prediction tasks using multiple embedding model for ehr (meme). arXiv preprint arXiv:2402.001602024.
55.
BeunzaJJPuertasEGarcía-OvejeroE, et al.Comparison of machine learning algorithms for clinical event prediction (risk of coronary heart disease). J Biomed Inform2019; 97: 103257.
56.
ArnautFKolarskiASrećkovićVA. Random forest classification and ionospheric response to solar flares: analysis and validation. Universe2023; 9: 436.
57.
ArazOMOlsonDRamirez-NafarrateA. Predictive analytics for hospital admissions from the emergency department using triage information. Int J Prod Econ2019; 208: 199–207.
58.
MowbrayFZargoushMJonesA, et al.Predicting hospital admission for older emergency department patients: insights from machine learning. Int J Med Inf2020; 140: 104163.
59.
LuciniFRFogliattoFSda SilveiraGJ, et al.Text mining approach to predict hospital admissions using early medical records from the emergency department. Int J Med Inf2017; 100: 1–8.
60.
UzochukwuCVHewagePAdetiloyeOA.Random forest approach to predict emergency Patients’ hospitalization duration for the health sector. In: 2024 OPJU international technology conference (OTCON) on smart computing for innovation and advancement in industry 4.0. USA: IEEE, 2024, pp. 1–6.
61.
YasinPYimitYCaiX, et al.Machine learning-enabled prediction of prolonged length of stay in hospital after surgery for tuberculosis spondylitis patients with unbalanced data: a novel approach using explainable artificial intelligence (XAI). Eur J Med Res2024; 29: 383.
62.
Abd-ElrazekMAEltahawiAAAbd ElazizMH,et al.Predicting length of stay in hospitals intensive care unit using general admission features. Ain Shams Engineering Journal2021; 12: 3691–3702.
63.
AhmedAAshourOAliH,et al.An integrated optimization and machine learning approach to predict the admission status of emergency patients. Expert Syst Appl2022; 202: 117314.
64.
PradhanDSahuPTunH (eds) Artificial and Cognitive Computing for Sustainable Healthcare Systems in Smart Cities. Hoboken, NJ, USA: John Wiley & Sons, 2024, pp.5–25.
65.
AljubranMJAljubranHJAljubranM, et al.The utilizing of machine learning algorithms to improve triage in emergency departments: a retrospective observational study. Saudi Journal of Emergency Medicine2023; 4.2: 112–119.
66.
InselMASadeJMustuS, et al.Predicting survival of patients with heart failure by optimizing the hyperparameters. Int J Knowl-Based Intell Eng Syst2024; 29: 13272314241295925.
67.
LiuBYuWZhangF, et al.Detecting obstructive coronary artery disease with machine learning: rest-only gated single photon emission computed tomography myocardial perfusion imaging combined with coronary artery calcium score and cardiovascular risk factors. Quant Imaging Med Surg2023; 13: 1524.
68.
FaisalMScallyAHowesR, et al.A comparison of logistic regression models with alternative machine learning methods to predict the risk of in-hospital mortality in emergency medical admissions via external validation. Health Informatics J2020; 26: 34–44.
69.
HorwitzAMcCarthyKHouseSL, et al.Intensive longitudinal assessment following index trauma to predict development of PTSD using machine learning. J Anxiety Disord2024, 104: 102876.
70.
ZelkowitzRLJiangTHorváth-PuhóE, et al.Predictors of nonfatal suicide attempts within 30 days of discharge from psychiatric hospitalization: sex-specific models developed using population-based registries. J Affect Disord2022; 306: 260–268.
71.
FajrinaBHasibuanSFNugrohoA. Comparison of SVM and naïve Bayes algorithms using binary grey wolf optimizer for diabetes Mellitus prediction. International Journal of Open Information Technologies2025; 13.1: 54–60.
72.
PaliwalGBunglowalaAKanthedP. Diagnostics based patient classification for clinical decision support systems. Journal of Automation, Mobile Robotics and Intelligent Systems2024; 18: 83–96.
73.
BeneventoEAloiniDSquicciariniN. Towards a real-time prediction of waiting times in emergency departments: a comparative analysis of machine learning techniques. Int J Forecast2023; 39: 192–208.
74.
KronthalerFZöllnerS. Data analysis with RStudio. Data Analysis with RStudio2021: 1–131.
75.
KuhnMWingJWestonS, et al.Package ‘caret’. R J2020; 223: 48.
76.
TherneauTAtkinsonBRipleyB. Rpart: recursive partitioning and regression trees. R Package Version2015; 4: 1–9.
77.
ZhangZ. Too much covariates in a multivariable model may cause the problem of overfitting. J Thorac Dis2014; 6: 6–9.
78.
BhimavarapuUChintalapudiNBattineniG. Automatic detection and classification of hypertensive retinopathy with improved convolution neural network and improved SVM. Bioengineering2024; 11: 56.
79.
GreenMBjörkJForbergJ, et al.Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room. Artif Intell Med2006, 38.3: 305–318.
80.
KlonAELowrieJFDillerDJ. Improved naïve Bayesian modeling of numerical data for absorption, distribution, metabolism and excretion (ADME) property prediction. J Chem Inf Model2006, 46: 1945–1956.
81.
SharmaMPNagliaPSharmaKP. Performance analysis for predicting primary school dropouts: identifying using machine learning optimal algorithm/method. International Journal of Innovation Studies2024; 8.1: 322–347.
82.
BlochERotemTCohenJ, et al.Machine learning models for analysis of vital signs dynamics: a case for sepsis onset prediction. J Healthc Eng2019; 2019.1: 5930379.
83.
BuchholzsW. Quantitative designs for practice scholarship. Research for Advanced Practice Nurses: From Evidence to Practice2021: 143.
84.
ParkerCALiuNWuSX, et al.Predicting hospital admission at the emergency department triage: a novel prediction model. Am J Emerg Med2019; 37: 1498–1504.
85.
YapıcıMEHızıroğluKErdoğanAM. Comparing the performance of ensemble methods in predicting emergency department admissions using machine learning techniques. Artificial Intelligence Theory and Applications2024; 4.1: 11–21.
86.
GrahamBBondRQuinnM,et al.Using data mining to predict hospital admissions from the emergency department. IEEE Access2018; 6: 10458–10469.
87.
KovaluckSVKopanitsaGDerevitskiiI,et al.Three-stage intelligent support of clinical decision making for higher trust, validity, and explainability. J Biomed Inform2022; 127: 104013.
88.
ValenteFParedesSHenriquesJ, et al.Interpretability, personalization and reliability of a machine learning based clinical decision support system. Data Min Knowl Discov2022; 36: 1140–1173.
