{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:25:27Z","timestamp":1777613127496,"version":"3.51.4"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T00:00:00Z","timestamp":1652745600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T00:00:00Z","timestamp":1652745600000},"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 Med Inform Decis Mak"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background and objective<\/jats:title>\n                <jats:p>Emergency Department (ED) overcrowding is a chronic international issue that is associated with adverse treatment outcomes. Accurate forecasts of future service demand would enable intelligent resource allocation that could alleviate the problem. There has been continued academic interest in ED forecasting but the number of used explanatory variables has been low, limited mainly to calendar and weather variables. In this study we investigate whether predictive accuracy of next day arrivals could be enhanced using high number of potentially relevant explanatory variables and document two feature selection processes that aim to identify which subset of variables is associated with number of next day arrivals. Performance of such predictions over longer horizons is also shown.\n<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>We extracted numbers of total daily arrivals from Tampere University Hospital ED between the time period of June 1, 2015 and June 19, 2019. 158 potential explanatory variables were collected from multiple data sources consisting not only of weather and calendar variables but also an extensive list of local public events, numbers of website visits to two hospital domains, numbers of available hospital beds in 33 local hospitals or health centres and Google trends searches for the ED. We used two feature selection processes: Simulated Annealing (SA) and Floating Search (FS) with Recursive Least Squares (RLS) and Least Mean Squares (LMS). Performance of these approaches was compared against autoregressive integrated moving average (ARIMA), regression with ARIMA errors (ARIMAX) and Random Forest (RF). Mean Absolute Percentage Error (MAPE) was used as the main error metric.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Calendar variables, load of secondary care facilities and local public events were dominant in the identified predictive features. RLS-SA and RLS-FA provided slightly better accuracy compared ARIMA. ARIMAX was the most accurate model but the difference between RLS-SA and RLS-FA was not statistically significant.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Our study provides new insight into potential underlying factors associated with number of next day presentations. It also suggests that predictive accuracy of next day arrivals can be increased using high-dimensional feature selection approach when compared to both univariate and nonfiltered high-dimensional approach. Performance over multiple horizons was similar with a gradual decline for longer horizons. However, outperforming ARIMAX remains a challenge when working with daily data. Future work should focus on enhancing the feature selection mechanism, investigating its applicability to other domains and in identifying other potentially relevant explanatory variables.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12911-022-01878-7","type":"journal-article","created":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T05:02:43Z","timestamp":1652763763000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Forecasting daily emergency department arrivals using high-dimensional multivariate data: a feature selection approach"],"prefix":"10.1186","volume":"22","author":[{"given":"Jalmari","family":"Tuominen","sequence":"first","affiliation":[]},{"given":"Francesco","family":"Lomio","sequence":"additional","affiliation":[]},{"given":"Niku","family":"Oksala","sequence":"additional","affiliation":[]},{"given":"Ari","family":"Palom\u00e4ki","sequence":"additional","affiliation":[]},{"given":"Jaakko","family":"Peltonen","sequence":"additional","affiliation":[]},{"given":"Heikki","family":"Huttunen","sequence":"additional","affiliation":[]},{"given":"Antti","family":"Roine","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,5,17]]},"reference":[{"issue":"4","key":"1878_CR1","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1016\/j.annemergmed.2009.03.006","volume":"54","author":"ML McCarthy","year":"2009","unstructured":"McCarthy ML, Zeger SL, Ding R, Levin SR, Desmond JS, Lee J, et al. Crowding delays treatment and lengthens emergency department length of stay, even among high-acuity patients. Ann Emerg Med. 2009;54(4):492-503.e4. https:\/\/doi.org\/10.1016\/j.annemergmed.2009.03.006.","journal-title":"Ann Emerg Med"},{"issue":"12","key":"1878_CR2","doi-asserted-by":"publisher","first-page":"1725","DOI":"10.1016\/j.ajem.2015.08.004","volume":"33","author":"S Jo","year":"2015","unstructured":"Jo S, Jeong T, Jin YH, Lee JB, Yoon J, Park B. ED crowding is associated with inpatient mortality among critically ill patients admitted via the ED: post hoc analysis from a retrospective study. Am J Emerg Med. 2015;33(12):1725\u201331. https:\/\/doi.org\/10.1016\/j.ajem.2015.08.004.","journal-title":"Am J Emerg Med"},{"issue":"3","key":"1878_CR3","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/j.annemergmed.2019.04.012","volume":"74","author":"LM Berg","year":"2019","unstructured":"Berg LM, Ehrenberg A, Florin J, \u00d6stergren J, Discacciati A, G\u00f6ransson KE. Associations between crowding and ten-day mortality among patients allocated lower triage acuity levels without need of acute hospital care on departure from the emergency department. Ann Emerg Med. 2019;74(3):345\u201356. https:\/\/doi.org\/10.1016\/j.annemergmed.2019.04.012.","journal-title":"Ann Emerg Med"},{"issue":"5","key":"1878_CR4","doi-asserted-by":"publisher","first-page":"213","DOI":"10.5694\/j.1326-5377.2006.tb00204.x","volume":"184","author":"DB Richardson","year":"2006","unstructured":"Richardson DB. Increase in patient mortality at 10 days associated with emergency department overcrowding. Med J Aust. 2006;184(5):213\u20136.","journal-title":"Med J Aust"},{"key":"1878_CR5","doi-asserted-by":"publisher","DOI":"10.1080\/20476965.2018.1547348","author":"M Gul","year":"2018","unstructured":"Gul M, Celik E. An exhaustive review and analysis on applications of statistical forecasting in hospital emergency departments. Heal Syst. 2018. https:\/\/doi.org\/10.1080\/20476965.2018.1547348.","journal-title":"Heal Syst"},{"key":"1878_CR6","doi-asserted-by":"publisher","first-page":"110247","DOI":"10.1016\/j.chaos.2020.110247","volume":"139","author":"F Harrou","year":"2020","unstructured":"Harrou F, Dairi A, Kadri F, Sun Y. Forecasting emergency department overcrowding: a deep learning framework. Chaos Solitons Fractals. 2020;139:110247. https:\/\/doi.org\/10.1016\/j.chaos.2020.110247.","journal-title":"Chaos Solitons Fractals"},{"key":"1878_CR7","doi-asserted-by":"publisher","first-page":"45552","DOI":"10.1109\/ACCESS.2021.3066164","volume":"9","author":"AR Sharafat","year":"2021","unstructured":"Sharafat AR, Bayati M. PatientFlowNet: a deep learning approach to patient flow prediction in emergency departments. IEEE Access. 2021;9:45552\u201361.","journal-title":"IEEE Access"},{"issue":"1","key":"1878_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-018-0616-8","volume":"18","author":"L Zhou","year":"2018","unstructured":"Zhou L, Zhao P, Wu D, Cheng C, Huang H. Time series model for forecasting the number of new admission inpatients. BMC Med Inform Decis Mak. 2018;18(1):1\u201311.","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"1878_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-020-01256-1","volume":"20","author":"Y Huang","year":"2020","unstructured":"Huang Y, Xu C, Ji M, Xiang W, He D. Medical service demand forecasting using a hybrid model based on ARIMA and self-adaptive filtering method. BMC Med Inform Decis Mak. 2020;20(1):1\u201314.","journal-title":"BMC Med Inform Decis Mak"},{"issue":"4","key":"1878_CR10","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1016\/j.annemergmed.2014.10.008","volume":"65","author":"A Ekstr\u00f6m","year":"2015","unstructured":"Ekstr\u00f6m A, Kurland L, Farrokhnia N, Castr\u00e9n M, Nordberg M. Forecasting emergency department visits using internet data. Ann Emerg Med. 2015;65(4):436-442.e1. https:\/\/doi.org\/10.1016\/j.annemergmed.2014.10.008.","journal-title":"Ann Emerg Med"},{"key":"1878_CR11","first-page":"57","volume":"260","author":"J Rauch","year":"2019","unstructured":"Rauch J, H\u00fcbner U, Denter M, Babitsch B. Improving the prediction of emergency department crowding: a time series analysis including road traffic flow. Stud Health Technol Inform. 2019;260:57\u201364.","journal-title":"Stud Health Technol Inform"},{"key":"1878_CR12","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.ajem.2021.04.075","volume":"48","author":"Q Cheng","year":"2021","unstructured":"Cheng Q, Tanik N, Scott C, Liu Y, Platts-mills TF, Ziya S. American journal of emergency medicine forecasting emergency department hourly occupancy using time series analysis. Am J Emerg Med. 2021;48:177\u201382. https:\/\/doi.org\/10.1016\/j.ajem.2021.04.075.","journal-title":"Am J Emerg Med"},{"key":"1878_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.orhc.2019.01.002","volume":"21","author":"W Whitt","year":"2019","unstructured":"Whitt W, Zhang X. Forecasting arrivals and occupancy levels in an emergency department. Oper Res Health Care. 2019;21:1\u201318. https:\/\/doi.org\/10.1016\/j.orhc.2019.01.002.","journal-title":"Oper Res Health Care"},{"key":"1878_CR14","doi-asserted-by":"publisher","first-page":"103375","DOI":"10.1016\/j.compbiomed.2019.103375","volume":"112","author":"B Remeseiro","year":"2019","unstructured":"Remeseiro B, Bolon-Canedo V. A review of feature selection methods in medical applications. Comput Biol Med. 2019;112:103375. https:\/\/doi.org\/10.1016\/j.compbiomed.2019.103375.","journal-title":"Comput Biol Med"},{"key":"1878_CR15","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.cmpb.2017.11.003","volume":"154","author":"S Jiang","year":"2018","unstructured":"Jiang S, Chin KS, Tsui KL. A universal deep learning approach for modeling the flow of patients under different severities. Comput Methods Programs Biomed. 2018;154:191\u2013203. https:\/\/doi.org\/10.1016\/j.cmpb.2017.11.003.","journal-title":"Comput Methods Programs Biomed"},{"key":"1878_CR16","unstructured":"Finnish Meteorological Institute Open Weather Data. 2020 [cited 2020 Feb 2]. Available from: https:\/\/www.ilmatieteenlaitos.fi\/avoin-data."},{"key":"1878_CR17","unstructured":"University of Helsinki Almanac Office. 2020 [cited 2020 Jul 20]. Available from: https:\/\/almanakka.helsinki.fi\/en\/."},{"key":"1878_CR18","unstructured":"Google Trends. 2020 [cited 2020 Jun 7]. Available from: https:\/\/www.google.com\/trends."},{"key":"1878_CR19","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1016\/j.procs.2019.01.026","volume":"148","author":"R Khaldi","year":"2019","unstructured":"Khaldi R, El AA, Chiheb R. Forecasting of weekly patient visits to emergency department: real case study. Procedia Comput Sci. 2019;148:532\u201341. https:\/\/doi.org\/10.1016\/j.procs.2019.01.026.","journal-title":"Procedia Comput Sci"},{"issue":"1","key":"1878_CR20","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.ijforecast.2019.04.014","volume":"36","author":"S Makridakis","year":"2020","unstructured":"Makridakis S, Spiliotis E, Assimakopoulos V. The M4 Competition: 100,000 time series and 61 forecasting methods. Int J Forecast. 2020;36(1):54\u201374. https:\/\/doi.org\/10.1016\/j.ijforecast.2019.04.014.","journal-title":"Int J Forecast"},{"key":"1878_CR21","unstructured":"Hyndman RJ, Athanasopoulos G. Forecasting: principles and practice. OTexts. OTexts: Melbourne, Australia; 2018. Available from: https:\/\/otexts.com\/fpp2\/."},{"issue":"3","key":"1878_CR22","first-page":"1","volume":"26","author":"RJ Hyndman","year":"2008","unstructured":"Hyndman RJ, Khandakar Y. Automatic time series forecasting: the forecast package for R. J Stat Softw. 2008;26(3):1\u201322.","journal-title":"J Stat Softw"},{"key":"1878_CR23","unstructured":"Smith TG et al. pmdarima: ARIMA estimators for Python. 2017. Available from: http:\/\/www.alkaline-ml.com\/pmdarima."},{"issue":"1","key":"1878_CR24","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L. Random forests. Mach Learn. 2001;45(1):5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324.","journal-title":"Mach Learn"},{"key":"1878_CR25","first-page":"281","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra J, Bengio Y. Random search for hyper-parameter optimization. J Mach Learn Res. 2012;13:281\u2013305.","journal-title":"J Mach Learn Res"},{"key":"1878_CR26","unstructured":"Haykin S, Haykin SS. Adaptive filter theory. Pearson: 2014. Available from: https:\/\/books.google.ae\/books?id=J4GRKQEACAAJ."},{"key":"1878_CR27","first-page":"1","volume":"13","author":"C Morley","year":"2018","unstructured":"Morley C, Unwin M, Peterson GM, Stankovich J, Kinsman L. Emergency department crowding: a systematic review of causes, consequences and solutions. PLoS ONE. 2018;13:1\u201342.","journal-title":"PLoS ONE"},{"key":"1878_CR28","unstructured":"Lim B, Ar\u0131k S, Loeff N, Pfister T. Temporal fusion transformers for interpretable multi-horizon time series forecasting. arXiv. 2019;(Bryan Lim):1\u201327."}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-022-01878-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-022-01878-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-022-01878-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T05:04:36Z","timestamp":1652763876000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-022-01878-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,17]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["1878"],"URL":"https:\/\/doi.org\/10.1186\/s12911-022-01878-7","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,17]]},"assertion":[{"value":"15 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Institutional approval was obtained from Pirkamaa hospital district (code R19565). According to Finnish Medical Research Act, no ethics committee review is needed for retrospective observational studies. For this reason no ethics committee approval was obtained.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"NO is a shareholder of Unitary Healthcare Ltd. which has developed patient logistics system currently used in the study emergency department. JT, FL and AR are shareholders of Aika Analytics Ltd. which is a company specialized in time series forecasting. Other authors do not have competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"134"}}