Abstract
The goal of this study is to explore and evaluate the use of a hybrid ARIMA-SVR approach to forecast daily radiology emergency patient flow. Owing to the fact that emergency patient flow is highly uncertain and dynamic, the forecasting problem is regarded as a complicated task. As the emergency patient flow may have both linear and nonlinear patterns, this paper presents a hybrid ARIMA-SVR approach, which hybridizes autoregressive integrated moving average (ARIMA) model and support vector regression (SVR) model to predict emergency patient arrivals. The proposed model is applied to 4 years of daily emergency visits data in the radiology department of a large hospital to justify the performance of the hybrid model against single models. The MAPE, RMSE and MAE of the hybrid model are 7.02%, 19.20 and 14.97, respectively. Furthermore, the hybrid model achieves better prediction performance than its competitors because it can capture the linear and nonlinear patterns simultaneously. Experimental results indicate that the proposed hybrid ARIMA-SVR approach is a promising alternative for forecasting emergency patient flow. These findings are beneficial for efficient patient flow management and scheduling decisions optimization.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Aboagye-Sarfo P, Mai Q, Sanfilippo FM, Preen DB, Stewart LM, Fatovich DM (2015) A comparison of multivariate and univariate time series approaches to modelling and forecasting emergency department demand in Western Australia. J Biomed Inform 57:62–73
Abraham G, Byrnes GB, Bain CA (2009) Short-term forecasting of emergency inpatient flow. IEEE Trans Inf Technol Biomed 13(3):380–383
Afilal M, Yalaoui F, Dugardin F, Amodeo L, Laplanche D, Blua P (2016) Forecasting the emergency department patients flow. J Med Syst 40(7):175
Alafeef M, Fraiwan M (2018) On the diagnosis of idiopathic Parkinson’s disease using continuous wavelet transform complex plot. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-018-1014-x
Aye GC, Balcilar M, Gupta R, Majumdar A (2015) Forecasting aggregate retail sales: the case of South Africa. Int J Prod Econ 160:66–79
Bergs J, Heerinckx P, Verelst S (2013) Knowing what to expect, forecasting monthly emergency department visits: a time-series analysis. Int Emerg Nurs 22(2):112–115
Bi X, Ma H, Li JH, Ma YL, Chen DY (2018) A positive and unlabeled learning framework based on extreme learning machine for drug-drug interactions discovery. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-018-0960-7
Box GEP, Jenkins GM (1971) Time series analysis: forecasting and control. J Oper Res Soc 22(2):199–201
Chan EW, Taylor SE, Marriott J, Barger B (2010) An intervention to encourage ambulance paramedics to bring patients’ own medications to the ED: impact on medications brought in and prescribing errors. Emerg Med Australas 22(2):151–158
Che JX, Wang JZ (2010) Short-term electricity prices forecasting based on support vector regression and auto-regressive integrated moving average modeling. Energy Convers Manag 51(10):1911–1917
Chen KY (2011) Combining linear and nonlinear model in forecasting tourism demand. Expert Syst Appl 38(8):10368–10376
Chen T (2018) An innovative fuzzy and artificial neural network approach for forecasting yield under an uncertain learning environment. J Ambient Intell Humaniz Comput 9(4):1013–1025. https://doi.org/10.1007/s12652-017-0504-6
Cui RM, Gallino S, Moreno A, Zhang DJ (2017) The operational value of social media information. Prod Oper Manag. https://doi.org/10.1111/poms.12707
Ekström A, Kurland L, Farrokhnia N, Castrén M, Nordberg M (2015) Forecasting emergency department visits using Internet data. Ann Emerg Med 65(4):436–442
Ganesh SS, Arulmozhivarman P, Tatavarti VSNR (2018) Prediction of PM2.5 using an ensemble of artificial neural networks and regression models. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-018-0801-8
Han YZ, Deng Y (2018) A hybrid intelligent model for assessment of critical success factors in high-risk emergency system. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-018-0882-4
Huang JF, Carmeli B, Mandelbaum A (2015) Control of patient flow in emergency departments, or multiclass queues with deadlines and feedback. Oper Res 63(4):892–908
Izabel M, Shakoor H, Nelson G (2013) Forecasting daily emergency department visits using calendar variables and ambient temperature readings. Acad Emerg Med 20(8):769–777
Jiang Y, Zhang T, Gou Y, He LL, Bai HT, Hu CQ (2018) High-resolution temperature and salinity model analysis using support vector regression. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-018-0896-y
Jin H, Wang HY, Gong C, Liu LX (2018) A study on the influencing factors of consumer information-seeking behavior in the context of ambient intelligence. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-018-1005-y
Jones SS, Evans RS, Allen TL, Thomas A, Haug PJ, Welch SJ, Snow GL (2009) A multivariate time series approach to modeling and forecasting demand in the emergency department. J Biomed Inform 42(1):123–139
Krogh A, Vedelsby J (1994) Neural network ensembles, cross validation and active learning. In: International Conference on Neural Information Processing Systems, pp 231–238
Lee YS, Tong LI (2011) Forecasting time series using a methodology based on autoregressive integrated moving average and genetic programming. Knowl Based Syst 24(1):66–72
Liu ZL, Hajiali M, Torabi A, Ahmadi B, Simoes R (2018) Novel forecasting model based on improved wavelet transform, informative feature selection, and hybrid support vector machine on wind power forecasting. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-018-0886-0
Luo L, Luo L, Zhang XL, He XL (2017a) Hospital daily outpatient visits forecasting using a combinatorial model based on ARIMA and SES models. BMC Health Serv Res 17(1):469
Luo L, Zhou Y, Han BT, Li JL (2017b) An optimization model to determine appointment scheduling window for an outpatient clinic with patient no-shows. Health Care Manag Sci. https://doi.org/10.1007/s10729-017-9421-7
Niroomand S, Bazyar A, Alborzi M, Miami H, Mahmoodirad A (2018) A hybrid approach for multi-criteria emergency center location problem considering existing emergency centers with interval type data: a case study. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-018-0804-5
Prabukumar M, Agilandeeswari L, Ganesan K (2017) An intelligent lung cancer diagnosis system using cuckoo search optimization and support vector machine classifier. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-017-0655-5
Qin MJ, Li ZH, Du ZH (2017) Red tide time series forecasting by combining ARIMA and deep belief network. Knowl Based Syst 125:39–52
Sen P, Roy M, Pal P (2016) Application of ARIMA for forecasting energy consumption and GHG emission: a case study of an Indian pig iron manufacturing organization. Energy 116:1031–1038
Vapnik VN (1995) The nature of statistical learning theory. Springer, New York
Wang L, Wang ZG, Qu H, Liu S (2018) Optimal forecast combination based on neural networks for time series forecasting. Appl Soft Comput 66:1–17
Wargon M, Guidet B, Hoang TD, Hejblum G (2009) A systematic review of models for forecasting the number of emergency department visits. Emerg Med J 26(6):395–399
Wiler JL, Bolandifar E, Griffey RT, Poirier RF, Olsen T (2013) An emergency department patient flow model based on queueing theory principles. Acad Emerg Med 20(9):939–946
Wu LJ, Cao GH (2016) Seasonal SVR with FOA algorithm for single-step and multi-step ahead forecasting in monthly inbound tourist flow. Knowl Based Syst 110(Supplement C):157–166
Wu CH, Tzeng GH, Lin RH (2009) A Novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression. Expert Syst Appl 36(3):4725–4735
Xiong T, Li CG, Bao YK, Hu ZY, Zhang L (2015) A combination method for interval forecasting of agricultural commodity futures prices. Knowl Based Syst 77(C):92–102
Xu M, Wong TC, Chin KS (2013) Modeling daily patient arrivals at emergency department and quantifying the relative importance of contributing variables using artificial neural network. Decis Support Syst 54(3):1488–1498
Yolcu U, Egrioglu E, Aladag CH (2013) A new linear and nonlinear artificial neural network model for time series forecasting. Decis Support Syst 54(3):1340–1347
Zhang GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50(1):159–175
Zhu T, Luo L, Zhang XL, Shi YK, Shen WW (2017) Time series approaches for forecasting the number of hospital daily discharged inpatients. IEEE J Biomed Health Inform 21(2):515–526
Acknowledgements
The authors gratefully acknowledge the support from the radiology department and the department of operations management of WCH. This work is sponsored by the Nature Science Foundation of China (Grant Nos. 71532007, 71131006, 71172197, 71673011 and 71273036), Central University Fund of Sichuan University (Grant No. skgt201202), and Key Research and Development Plan of Science and Technology Department of Sichuan Province (Grant Nos. 2017GZ0315 and 2017GZ0333).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, Y., Luo, L., Yang, J. et al. A hybrid ARIMA-SVR approach for forecasting emergency patient flow. J Ambient Intell Human Comput 10, 3315–3323 (2019). https://doi.org/10.1007/s12652-018-1059-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-018-1059-x