Predicting Hospital Admission of Patients at Triage in the Emergency Department at Lampang Hospital

Noppadon Seesuwan; Thanin  Lokeskrawee; Suppachai  Lawanaskol; Jayanton  Patumanond

Authors

Noppadon Seesuwan Department of Emergency medicine, Lampang Hospital, Lampang https://orcid.org/0009-0006-6735-2053
Thanin Lokeskrawee Department of Emergency medicine, Lampang Hospital, Lampang https://orcid.org/0000-0003-1808-2086
Suppachai Lawanaskol Chaiprakarn Hospital, Thailand https://orcid.org/0000-0002-9846-1491
Jayanton Patumanond Center for Clinical Epidemiology and Clinical Statistics, Chiang Mai University, Thailand https://orcid.org/0000-0001-8977-2995

Keywords:

patient admission, clinical decision rules, models, statistical, overcrowding

Abstract

Objective This study aims to develop a model that can help predict the likelihood of hospital admission for patients at the triage point in Lampang Hospital’s Emergency Department.

Methods The study was designed around Clinical Prediction Rules and was conducted as a retrospective cohort study using data from July 2021 to January 2022 input through the Smart ER program. Patients were categorized into two groups: admit and discharge. Statistical
analysis involved both univariable and multivariable logistic regression analyses, presenting discrimination values with area under the receiver operating characteristic (AUROC), testing precision with a calibration plot, analyzing internal validation using the Bootstrapping method, and creating a risk curve to find the balanced cutoff point. The study then divided the predictions into one of three groups: Admit, Consult, and Discharge. Decision curve analysis (DCA) was performed and an application was developed and integrated into the Smart ER program for real- time analysis.

Results Out of 37,474 patients screened, 18,056 were excluded leaving 19,418 patients eligible for complete case analysis. Predictors of hospital admission included age, emergency level, vital signs, mode of hospital arrival, and prominent symptoms according to criteria-based dispatch (CBD) (criteria-based dispatch). The Admission Model showed an AUROC of 0.8934 (95% CI, 0.8890-0.8980); the calibration plot demonstrated that predicted values closely matched actual observed values; internal validation using the Bootstrapping method yielded a C-statistic of 0.8920 (95% CI, 0.888-0.895); and the balanced risk curve indicated over admission at 3.8% and over discharge at 3.7%.

Conclusions The Admission Model provides high AUROC and precision values. The model’s three-group division is likely to be beneficial in practical application.

References

Department of Medical Services, Ministry of Public Health. MOPH ED Triage [Internet]. 2019 [cited 2023 Nov 10]. Available from: https://www.dms.go.th/backend//Content/Content_File/Population_Health/Attach/25621021104459AM_44.pdf?contentId=18326

Hoot N, Aronsky D. Systematic review of emergency department crowding: causes, effects, and solutions. Ann Emerg Med. 2008;52:126-36.

Asplin B, Magid D, Rhodes K, Solberg L, Lurie N. A conceptual model of emergency department crowding. Ann Emerg Med. 2003;42:173-80.

Schull M, Vermeulen M, Slaughter G, Morrison L, Daly P. Emergency department crowding and thrombolysis delays in acute myocardial infarction. Ann Emerg Med. 2004;44:577-85.

Derlet R, Richards J. Overcrowding in the nation’s emergency departments: complex causes and disturbing effects. Ann Emerg Med. 2000;35:63-8.

Sun B, Hsia R, Weiss R, Zingmond D, Liang L, Han W, et al. Effect of emergency department crowding on outcomes of admitted patients. Ann Emerg Med. 2013;61:605-11.

Nekane L, Jon K. Predicting hospital ward admission from the emergency department: a systematic review. J Pers Med. 2023;13:849. PubMed PMID: 37241019

Hong W, Haimovich A, Taylor R. Predicting hospital admission at emergency department triage using machine learning. PLoS One. 2018;13:e0201016. PubMed PMID: 30028888

Feretzakis G, Karlis G, Loupelis E, Kalles D, Chatzikyriakou R, Trakas N, et al. Using machine learning techniques to predict hospital admission at the emergency department. J Crit Care Med (Targu Mures). 2022;8: 107-16.

Riley RD, Ensor J, Snell KIE, Harrell FE Jr, Martin GP, Reitsma JB, et al. Calculating the sample size required for developing a clinical prediction model. BMJ. 2020;368:m441. PubMed PMID: 32188600

National Institute of Emergency Medicine. Emergency Medical Triage Protocol and Criteria Based Dispatch by NIEM 2013. National Institute of Emergency Medicine [Internet]. 2013 [cited 2023 Nov 10]. Available from: https://www.niems.go.th/1/Ebook/Detail/272?group=21

Kishore K, Braitberg G, Holmes N, Bellomo R. Early prediction of hospital admission of emergency department patients. Emerg Med Australas. 2023;35: 572-88.

Cameron A, Rodgers K, Ireland A, Jamdar R, McKay GA. A simple tool to predict admission at the time of triage. Emerg Med J. 2015;32:174-9.

Lucke JA, de Gelder J, Clarijs F, Heringhaus C, de Craen AJM, Fogteloo AJ, et al. Early prediction of hospital admission for emergency department patients: a comparison between patients younger or older than 70 years. Emerg Med J. 2018; 35:18-27.

Ebker-White A, Bein KJ, Berendsen Russell S, Dinh MM. The Sydney triage to admission risk tool (START) to improve patient flow in an emergency department: a model of care implementation pilot study. BMC Emerg Med. 2019;19:79. Pubmed PMID: 31805874

Lowthian JA, Curtis AJ, Cameron PA, Stoelwinder JU, Cooke MW, McNeil JJ. Systematic review of trends in emergency department attendances: an Australian perspective. Emerg Med J. 2011;28:373-7.

Wuerz R, Milne LW, Eitel DR, Travers D, Gilboy N. Reliability and validity of a new five-level triage instrument. Acad Emerg Med. 2000;7:236-42.

Pencina MJ, D’Agostino RB. Evaluating discrimination of risk prediction models: the C statistic. JAMA. 2015;314:1063-4.

Batko K, Ślęzak A. The use of big data analytics in healthcare. J Big Data. 2022;9:3. PubMed PMID: 35013701

Godfrey C, Payton M, Tasker S, Proestel S, Schouten JT. Ensuring participant safety and trial integrity with clinical trials oversight. J Acquir Immune Defic Syndr. 2014;65 Suppl 1doi:10.1097/QAI.0000000000000041. PMID: 24321985; PMCID: PMC3916962

Brink A, Alsma J, van Attekum LA, Bramer WM, Zietse R, Lingsma H, et al. Predicting in-hospital admission at the emergency department: a systematic review. Emerg Med J. 2022;39:191-8.

Monahan A, Feldman S. Models predicting hospital admission of adult patients utilizing prehospital data: systematic review using PROBAST and CHARMS. JMIR Med Inform. 2021;9:e30022. PubMed PMID: 34528893.

Strum R, Mowbray F, Zargoush M, Jones A. Prehospital prediction of hospital admission for emergent acuity patients transported by paramedics: A population-based cohort study using machine learning. PLoS One. 2023;18:e0289429. PubMed PMID: 37616228

De Hond A, Raven W, Schinkelshoek L, Gaakeer M, Avest E, Sir O, et al. Machine learning for developing a prediction model of hospital admission of emergency department patients: hype or hope? Int J Med Inform.2021;152:104496. PubMed PMID: 34020171

Steyerberg E, Vickers A, Cook N, Gerds T, Gonen M, Obuchowski N, et al. Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology. 2010;21:128-38.

Kerr K, Brown M, Zhu K, Janes H. Assessing the clinical impact of risk prediction models with decision curves: guidance for correct interpretation and appropriate use. J Clin Oncol. 2016;34:2534-40.

O’Cathain A, Knowles E, Maheswaran R, Pearson T, Turner J, Hirst E, et al. A system-wide approach to explaining variation in potentially avoidable emergency admissions: national ecological study. BMJ Qual Saf. 2014;23:47-55.

Lewis Hunter A, Spatz E, Bernstein S, Rosenthal M. Factors influencing hospital admission of non-critically ill patients presenting to the emergency department: a cross-sectional study. J Gen Intern Med. 2016;31:37-44.

Riley R, Ensor J, Snell K, Debray T, Altman D, Moons K, et al. External validation of clinical prediction models using big datasets from e-health records or IPD meta-analysis: opportunities and challenges. BMJ. 2016;353:i3140. PubMed PMID: 27334381.