{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T12:31:57Z","timestamp":1771331517574,"version":"3.50.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,8,18]],"date-time":"2024-08-18T00:00:00Z","timestamp":1723939200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,8,18]],"date-time":"2024-08-18T00:00:00Z","timestamp":1723939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Emerg Med"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Crowding has been a longstanding issue in emergency departments. To address this, a fast-track system for avoidable patients is being implemented in the Paediatric Emergency Department where our study is conducted. Our goal is to develop an optimized Decision Support System that helps in directing patients to this fast track. We evaluated various Machine Learning models, focusing on a balance between complexity, predictive performance, and interpretability.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>This is a retrospective study considering all visits to a university-affiliated metropolitan hospital\u2019s PED between 2014 and 2019. Using information available at the time of triage, we trained several models to predict whether a visit is avoidable and should be directed to a fast-track area.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>A total of 507,708 visits to the PED were used in the training and testing of the models. Regarding the outcome, 41.6% of the visits were considered avoidable. Except for the classification made by triage rules, i.e. considering levels 1,2, and 3 as non-avoidable and 4 and 5 as avoidable, all models had similar results in model\u2019s evaluation metrics, e.g. Area Under the Curve ranging from 74% to 80%.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Regarding predictive performance, the pruned decision tree had evaluation metrics results that were comparable to the other ML models. Furthermore, it offers a low complexity and easy to implement solution. When considering interpretability, a paramount requisite in healthcare since it relates to the trustworthiness and transparency of the system, the pruned decision tree excels.<\/jats:p>\n                <jats:p>Overall, this paper contributes to the growing body of research on the use of machine learning in healthcare. It highlights practical benefits for patients and healthcare systems of the use ML-based DSS in emergency medicine. Moreover, the obtained results can potentially help to design patients\u2019 flow management strategies in PED settings, which has been sought as a solution for addressing the long-standing problem of overcrowding.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12873-024-01029-3","type":"journal-article","created":{"date-parts":[[2024,8,18]],"date-time":"2024-08-18T15:01:43Z","timestamp":1723993303000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Identification of avoidable patients at triage in a Paediatric Emergency Department: a decision support system using predictive analytics"],"prefix":"10.1186","volume":"24","author":[{"given":"Jo\u00e3o","family":"Viana","sequence":"first","affiliation":[]},{"given":"J\u00falio","family":"Souza","sequence":"additional","affiliation":[]},{"given":"Ruben","family":"Rocha","sequence":"additional","affiliation":[]},{"given":"Almeida","family":"Santos","sequence":"additional","affiliation":[]},{"given":"Alberto","family":"Freitas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,18]]},"reference":[{"key":"1029_CR1","unstructured":"H. R. Rasouli et al., \u201cOutcomes of Crowding in Emergency Departments; a Systematic Review,\u201d Arch. Acad. Emerg. Med., vol. 7, no. 1, Aug. 2019. Available: \nhttps:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC6785211\/.\u00a0Accessed: Apr. 30, 2021."},{"issue":"7","key":"1029_CR2","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1093\/pch\/pxx111","volume":"22","author":"M Chan","year":"2017","unstructured":"Chan M, Meckler G, Doan Q. Paediatric emergency department overcrowding and adverse patient outcomes. Paediatr Child Health. 2017;22(7):377\u201381. https:\/\/doi.org\/10.1093\/pch\/pxx111.","journal-title":"Paediatr Child Health"},{"issue":"23","key":"1029_CR3","doi-asserted-by":"publisher","first-page":"E627","DOI":"10.1503\/cmaj.181426","volume":"191","author":"Q Doan","year":"2019","unstructured":"Doan Q, et al. The impact of pediatric emergency department crowding on patient and health care system outcomes: a multicentre cohort study. CMAJ Can Med Assoc J J Assoc Med Can. 2019;191(23):E627\u201335. https:\/\/doi.org\/10.1503\/cmaj.181426.","journal-title":"CMAJ Can Med Assoc J J Assoc Med Can."},{"issue":"2","key":"1029_CR4","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.annemergmed.2009.05.021","volume":"55","author":"JL Wiler","year":"2010","unstructured":"Wiler JL, et al. Optimizing emergency department front-end operations. Ann Emerg Med. 2010;55(2):142\u2013160.e1. https:\/\/doi.org\/10.1016\/j.annemergmed.2009.05.021.","journal-title":"Ann Emerg Med"},{"key":"1029_CR5","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/1757-7241-19-43","volume":"19","author":"S Oredsson","year":"2011","unstructured":"Oredsson S, et al. A systematic review of triage-related interventions to improve patient flow in emergency departments. Scand J Trauma Resusc Emerg Med. 2011;19:43. https:\/\/doi.org\/10.1186\/1757-7241-19-43.","journal-title":"Scand J Trauma Resusc Emerg Med"},{"issue":"1","key":"1029_CR6","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1177\/1355819620921894","volume":"26","author":"B Parkinson","year":"2021","unstructured":"Parkinson B, Meacock R, Checkland K, Sutton M. Clarifying the concept of avoidable emergency department attendance. J Health Serv Res Policy. 2021;26(1):68\u201373. https:\/\/doi.org\/10.1177\/1355819620921894.","journal-title":"J Health Serv Res Policy"},{"issue":"11","key":"1029_CR7","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1111\/acem.12249","volume":"20","author":"R Arya","year":"2013","unstructured":"Arya R, Wei G, McCoy JV, Crane J, Ohman-Strickland P, Eisenstein RM. Reasing length of stay in the emergency department with a split emergency severity index 3 patient flow model. Acad Emerg Med. 2013;20(11):1171\u20139. https:\/\/doi.org\/10.1111\/acem.12249.","journal-title":"Acad Emerg Med"},{"issue":"1","key":"1029_CR8","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1111\/j.1742-6723.2007.01021.x","volume":"20","author":"P Kwa","year":"2008","unstructured":"Kwa P, Blake DF. Fast track: has it changed patient care in the emergency department? Emerg Med Australas. 2008;20(1):10\u20135. https:\/\/doi.org\/10.1111\/j.1742-6723.2007.01021.x.","journal-title":"Emerg Med Australas."},{"issue":"1","key":"1029_CR9","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.jemermed.2005.08.019","volume":"31","author":"M Sanchez","year":"2006","unstructured":"Sanchez M, Smally AJ, Grant RJ, Jacobs LM. Effects of a fast-track area on emergency department performance. J Emerg Med. 2006;31(1):117\u201320. https:\/\/doi.org\/10.1016\/j.jemermed.2005.08.019.","journal-title":"J Emerg Med"},{"issue":"4","key":"1029_CR10","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1071\/ah060525","volume":"30","author":"D O\u2019Brien","year":"2006","unstructured":"O\u2019Brien D, Williams A, Blondell K, Jelinek GA. Impact of streaming \u2018fast track\u2019 emergency department patients. Aust Health Rev. 2006;30(4):525\u201332. https:\/\/doi.org\/10.1071\/ah060525.","journal-title":"Aust Health Rev"},{"issue":"2","key":"1029_CR11","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1097\/TME.0000000000000351","volume":"43","author":"HA Martin","year":"2021","unstructured":"Martin HA, Noble M, Wilmarth J. Improving patient flow and decreasing patient length of stay in the Pediatric Emergency Department through implementation of a fast track. Adv Emerg Nurs J. 2021;43(2):162\u20139. https:\/\/doi.org\/10.1097\/TME.0000000000000351.","journal-title":"Adv Emerg Nurs J"},{"issue":"4","key":"1029_CR12","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1111\/j.1742-6723.2005.00761.x","volume":"17","author":"J Vance","year":"2005","unstructured":"Vance J, Sprivulis P. Triage nurses validly and reliably estimate emergency department patient complexity. Emerg Med Australas. 2005;17(4):382\u20136. https:\/\/doi.org\/10.1111\/j.1742-6723.2005.00761.x.","journal-title":"Emerg Med Australas"},{"issue":"2","key":"1029_CR13","doi-asserted-by":"publisher","first-page":"107","DOI":"10.2478\/jccm-2022-0003","volume":"8","author":"G Feretzakis","year":"2022","unstructured":"Feretzakis G, et al. Using machine learning techniques to predict hospital admission at the emergency department. J Crit Care Med. 2022;8(2):107\u201316. https:\/\/doi.org\/10.2478\/jccm-2022-0003.","journal-title":"J Crit Care Med"},{"key":"1029_CR14","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1186\/s41512-020-00084-1","volume":"4","author":"J Miles","year":"2020","unstructured":"Miles J, Turner J, Jacques R, Williams J, Mason S. Using machine-learning risk prediction models to triage the acuity of undifferentiated patients entering the emergency care system: a systematic review. Diagn Progn Res. 2020;4:16. https:\/\/doi.org\/10.1186\/s41512-020-00084-1.","journal-title":"Diagn Progn Res"},{"issue":"1","key":"1029_CR15","doi-asserted-by":"publisher","first-page":"e740","DOI":"10.1002\/ams2.740","volume":"9","author":"B Mueller","year":"2022","unstructured":"Mueller B, Kinoshita T, Peebles A, Graber MA, Lee S. Artificial intelligence and machine learning in emergency medicine: a narrative review. Acute Med Surg. 2022;9(1):e740. https:\/\/doi.org\/10.1002\/ams2.740.","journal-title":"Acute Med Surg"},{"issue":"2","key":"1029_CR16","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1111\/acem.14190","volume":"28","author":"H Kareemi","year":"2021","unstructured":"Kareemi H, Vaillancourt C, Rosenberg H, Fournier K, Yadav K. Machine learning versus usual care for diagnostic and prognostic prediction in the emergency department: a systematic review. Acad Emerg Med. 2021;28(2):184\u201396. https:\/\/doi.org\/10.1111\/acem.14190.","journal-title":"Acad Emerg Med"},{"key":"1029_CR17","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1186\/s13054-019-2351-7","volume":"23","author":"Y Raita","year":"2019","unstructured":"Raita Y, Goto T, Faridi MK, Brown DFM, Camargo CA, Hasegawa K. Emergency department triage prediction of clinical outcomes using machine learning models. Crit Care. 2019;23:64. https:\/\/doi.org\/10.1186\/s13054-019-2351-7.","journal-title":"Crit Care"},{"key":"1029_CR18","unstructured":"\u201cStatistics Portugal. Instituto Nacional de Estat\u00edstica - Portugal.\u201d Accessed: Feb. 26, 2020. Available: https:\/\/www.ine.pt"},{"issue":"3","key":"1029_CR19","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1017\/S1481803500010149","volume":"10","author":"DW Warren","year":"2008","unstructured":"Warren DW, et al. Revisions to the Canadian Triage and Acuity Scale paediatric guidelines (PaedCTAS). CJEM. 2008;10(3):224\u201343.","journal-title":"CJEM"},{"issue":"10","key":"1029_CR20","doi-asserted-by":"publisher","first-page":"e1001885","DOI":"10.1371\/journal.pmed.1001885","volume":"12","author":"EI Benchimol","year":"2015","unstructured":"Benchimol EI, et al. The Reporting of studies conducted using observational routinely-collected health data (RECORD) statement. PLOS Med. O. 2015;12(10):e1001885. https:\/\/doi.org\/10.1371\/journal.pmed.1001885.","journal-title":"PLOS Med"},{"key":"1029_CR21","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1145\/2939672.2939785","volume-title":"\u201cXGBoost: a scalable tree boosting system,\u201d in proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, in KDD \u201916","author":"T Chen","year":"2016","unstructured":"Chen T, Guestrin C. \u201cXGBoost: a scalable tree boosting system,\u201d in proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, in KDD \u201916. New York, USA: Association for Computing Machinery; 2016. p. 785\u201394. https:\/\/doi.org\/10.1145\/2939672.2939785."},{"key":"1029_CR22","doi-asserted-by":"publisher","unstructured":"Arik S\u00d6, Pfister T. \u201cTabNet: attentive interpretable tabular learning,\u201d Proc. AAAI Conf. Artif. Intell. 2021;35(8). https:\/\/doi.org\/10.1609\/aaai.v35i8.16826.","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"1029_CR23","unstructured":"\u201cR: The R Project for Statistical Computing.\u201d Accessed: Aug. 31, 2021. Available: https:\/\/www.r-project.org\/"},{"key":"1029_CR24","unstructured":"\u201cRStudio | Open source & professional software for data science teams.\u201d Accessed: Aug. 31, 2021. Available: https:\/\/rstudio.com\/"},{"key":"1029_CR25","doi-asserted-by":"publisher","first-page":"101109","DOI":"10.1016\/j.ienj.2021.101109","volume":"60","author":"R S\u00e1nchez-Salmer\u00f3n","year":"2022","unstructured":"S\u00e1nchez-Salmer\u00f3n R, et al. Machine learning methods applied to triage in emergency services: a systematic review. Int Emerg Nurs. 2022;60:101109. https:\/\/doi.org\/10.1016\/j.ienj.2021.101109.","journal-title":"Int Emerg Nurs"},{"key":"1029_CR26","doi-asserted-by":"publisher","first-page":"101762","DOI":"10.1016\/j.artmed.2019.101762","volume":"102","author":"M Fernandes","year":"2020","unstructured":"Fernandes M, Vieira SM, Leite F, Palos C, Finkelstein S, Sousa JMC. Clinical decision support systems for triage in the emergency department using intelligent systems: a review. Artif Intell Med. J. 2020;102:101762.\u00a0https:\/\/doi.org\/10.1016\/j.artmed.2019.101762.","journal-title":"Artif Intell Med"},{"issue":"1","key":"1029_CR27","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1186\/s12873-022-00632-6","volume":"22","author":"Y-H Chang","year":"2022","unstructured":"Chang Y-H, et al. Machine learning\u2013based triage to identify low-severity patients with a short discharge length of stay in emergency department. BMC Emerg Med. 2022;22(1):88. https:\/\/doi.org\/10.1186\/s12873-022-00632-6.","journal-title":"BMC Emerg Med"},{"issue":"10","key":"1029_CR28","doi-asserted-by":"publisher","first-page":"e0205836","DOI":"10.1371\/journal.pone.0205836","volume":"13","author":"J Kwon","year":"2018","unstructured":"Kwon J, Lee Y, Lee Y, Lee S, Park H, Park J. Validation of deep-learning-based triage and acuity score using a large national dataset. PLoS ONE. 2018;13(10):e0205836.\u00a0https:\/\/doi.org\/10.1371\/journal.pone.0205836.","journal-title":"PLoS ONE"},{"key":"1029_CR29","doi-asserted-by":"publisher","unstructured":"F. S. van Royen, F. W. Asselbergs, F. Alfonso, P. Vardas, and M. van Smeden, \u201cFive critical quality criteria for artificial intelligence-based prediction models,\u201d Eur. Heart J., p. ehad727, Oct. 2023, https:\/\/doi.org\/10.1093\/eurheartj\/ehad727.","DOI":"10.1093\/eurheartj\/ehad727"},{"key":"1029_CR30","doi-asserted-by":"publisher","unstructured":"P. Madumal, T. Miller, L. Sonenberg, and F. Vetere, \u201cExplainable Reinforcement Learning Through a Causal Lens.\u201d arXiv, Nov. 20, 2019. https:\/\/doi.org\/10.48550\/arXiv.1905.10958.","DOI":"10.48550\/arXiv.1905.10958"},{"key":"1029_CR31","doi-asserted-by":"publisher","first-page":"102423","DOI":"10.1016\/j.artmed.2022.102423","volume":"133","author":"C Combi","year":"2022","unstructured":"Combi C, et al. A manifesto on explainability for artificial intelligence in medicine. Artif Intell Med. N. 2022;133:102423.\u00a0https:\/\/doi.org\/10.1016\/j.artmed.2022.102423.","journal-title":"Artif Intell Med"},{"key":"1029_CR32","doi-asserted-by":"publisher","first-page":"103473","DOI":"10.1016\/j.artint.2021.103473","volume":"296","author":"M Langer","year":"2021","unstructured":"Langer M, et al. What do we want from Explainable Artificial Intelligence (XAI)? \u2013 A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research. Artif Intell. J. 2021;296:103473.\u00a0https:\/\/doi.org\/10.1016\/j.artint.2021.103473.","journal-title":"Artif Intell"},{"issue":"12","key":"1029_CR33","doi-asserted-by":"publisher","first-page":"870","DOI":"10.1097\/PEC.0b013e31818fa79d","volume":"24","author":"RD Mistry","year":"2008","unstructured":"Mistry RD, Brousseau DC, Alessandrini EA. Urgency classification methods for emergency department visits: do they measure up? Pediatr Emerg Care. 2008;24(12):870\u20134. https:\/\/doi.org\/10.1097\/PEC.0b013e31818fa79d.","journal-title":"Pediatr Emerg Care"},{"issue":"5","key":"1029_CR34","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1093\/intqhc\/mzx081","volume":"29","author":"RY Hsia","year":"2017","unstructured":"Hsia RY, Niedzwiecki M. Avoidable emergency department visits: a starting point. Int J Qual Health Care. 2017;29(5):642\u20135. https:\/\/doi.org\/10.1093\/intqhc\/mzx081.","journal-title":"Int J Qual Health Care"},{"issue":"1","key":"1029_CR35","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s41512-022-00136-8","volume":"6","author":"M Sperrin","year":"2022","unstructured":"Sperrin M, Riley RD, Collins GS, Martin GP. Targeted validation: validating clinical prediction models in their intended population and setting. Diagn Progn Res. 2022;6(1):24. https:\/\/doi.org\/10.1186\/s41512-022-00136-8.","journal-title":"Diagn Progn Res"}],"container-title":["BMC Emergency Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12873-024-01029-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12873-024-01029-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12873-024-01029-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T06:37:34Z","timestamp":1724049454000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcemergmed.biomedcentral.com\/articles\/10.1186\/s12873-024-01029-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,18]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["1029"],"URL":"https:\/\/doi.org\/10.1186\/s12873-024-01029-3","relation":{},"ISSN":["1471-227X"],"issn-type":[{"value":"1471-227X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,18]]},"assertion":[{"value":"6 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The ethics committee of \u201cCentro Hospitalar Universit\u00e1rio de S\u00e3o Jo\u00e3o\u201d (comissao.etica@chsj.min-saude.pt) granted authorization for this study and assigned the number 180\/18. All the methods were carried out in accordance with the relevant guidelines and regulations. The data was anonymized, and the informed consent was waived by an institutional review board \u201cGabinete do Respons\u00e1vel pelo Acesso \u00e0 Informa\u00e7\u00e3o (RAI)\u201d (rai@chsj.min-saude.pt) for all the participants according to the hospital\u2019s administration\u2019s regulations for research on secondary data.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"149"}}