Time-Series Approaches for Forecasting the Number of Hospital Daily Discharged Inpatients
Abstract
For hospitals where decisions regarding acceptable rates of elective admissions are made in advance based on expected available bed capacity and emergency requests, accurate predictions of inpatient bed capacity are especially useful for capacity reservation purposes. As given, the remaining unoccupied beds at the end of each day, bed capacity of the next day can be obtained by examining the forecasts of the number of discharged patients during the next day. The features of fluctuations in daily discharges like trend, seasonal cycles, special-day effects, and autocorrelation complicate decision optimizing, while time-series models can capture these features well. This research compares three models: a model combining seasonal regression and ARIMA, a multiplicative seasonal ARIMA (MSARIMA) model, and a combinatorial model based on MSARIMA and weighted Markov Chain models in generating forecasts of daily discharges. The models are applied to three years of discharge data of an entire hospital. Several performance measures like the direction of the symmetry value, normalized mean squared error, and mean absolute percentage error are utilized to capture the under- and overprediction in model selection. The findings indicate that daily discharges can be forecast by using the proposed models. A number of important practical implications are discussed, such as the use of accurate forecasts in discharge planning, admission scheduling, and capacity reservation.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Predicting next 48 h discharges is critical for physicians to identify and prioritize patients ready for discharge and for case management teams to accelerate discharge preparations, which ultimately reduces patient burden and direct operating costs in healthcare systems.
“Particularly, predicting next 48 h discharges is critical for physicians to identify and prioritize patients ready for discharge and for case management teams to accelerate discharge preparations, which ultimately reduces patient burden and direct operating costs in healthcare systems43.”
From Integrated multimodal artificial intelligence framework for healthcare applications (2022) · cites this paper as [43]
Cites
Time series forecasting using a hybrid ARIMA and neural network model
Zhang, G. P. (2003) · Neurocomputing · doi:10.1016/s0925-2312(01)00702-0 · Cited by 4,576 · see citing works
Neural Network Ensembles, Cross Validation, and Active Learning
Krogh, A., & Vedelsby, J. (1994) · Cited by 1,838 · see citing works
The M3-Competition: results, conclusions and implications
Makridakis, S., & Hibon, M. (2000) · International Journal of Forecasting · doi:10.1016/s0169-2070(00)00057-1 · Cited by 1,701 · see citing works
‘Horses for Courses’ in demand forecasting
Petropoulos, F., Makridakis, S., Assimakopoulos, V., & Nikolopoulos, K. I. (2014) · European Journal of Operational Research · doi:10.1016/j.ejor.2014.02.036 · Cited by 201 · see citing works
Very short-term wind speed prediction: A new artificial neural network–Markov chain model
Pourmousavi, S. A., & Ardehali, M. M. (2010) · Energy Conversion and Management · doi:10.1016/j.enconman.2010.07.053 · Cited by 189 · see citing works
Channouf, N., L’Ecuyer, P., Ingólfsson, Á., et al. (2006) · Health Care Management Science · doi:10.1007/s10729-006-9006-3 · Cited by 180 · see citing works
Models and Insights for Hospital Inpatient Operations: Time-Dependent ED Boarding Time
Shi, P., Chou, M. C., Dai, J. G., Ding, D., & Sim, J. H. J. (2015) · Management Science · doi:10.1287/mnsc.2014.2112 · Cited by 175 · see citing works
The Impact of Empirical Accuracy Studies on Time Series Analysis and Forecasting
Fildes, R., & Makridakis, S. (1995) · International Statistical Review / Revue Internationale de Statistique · doi:10.2307/1403481 · Cited by 172 · see citing works
First-order Markov chain approach to wind speed modelling
Şahin, A. D., & Şen, Z. (2001) · Journal of Wind Engineering and Industrial Aerodynamics · doi:10.1016/s0167-6105(00)00081-7 · Cited by 156 · see citing works
Markov chain model for turbulent wind speed data
Kantz, H., Holstein, D., Ragwitz, M., et al. (2004) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2004.01.070 · Cited by 125 · see citing works
Forecasting Demand of Emergency Care
Jones, S., Joy, M., & Pearson, J. (2002) · Health Care Management Science · doi:10.1023/a:1020390425029 · Cited by 123 · see citing works
Xu, M., Wong, T. C., & Chin, K. (2012) · Decision Support Systems · doi:10.1016/j.dss.2012.12.019 · Cited by 112 · see citing works
Time Series Forecasts of Emergency Department Patient Volume, Length of Stay, and Acuity
Tandberg, D., & Qualls, C. (1994) · Annals of Emergency Medicine · doi:10.1016/s0196-0644(94)70044-3 · Cited by 110 · see citing works
Short-Term Forecasting of Emergency Inpatient Flow
Abraham, G., Byrnes, G. B., & Bain, C. (2009) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2009.2014565 · Cited by 101 · see citing works
Modelling Variability in Hospital Bed Occupancy
Harrison, G. W., Shafer, A., & Mackay, M. F. (2005) · Health Care Management Science · doi:10.1007/s10729-005-4142-8 · Cited by 93 · see citing works
Short term hospital occupancy prediction
Littig, S. J., & Isken, M. W. (2006) · Health Care Management Science · doi:10.1007/s10729-006-9000-9 · Cited by 66 · see citing works
Choice of Models for the Analysis and Forecasting of Hospital Beds
Mackay, M. F., & Lee, M. (2005) · Health Care Management Science · doi:10.1007/s10729-005-2013-y · Cited by 64 · see citing works
Hospital output forecasts and the cost of empty hospital beds.
Pauly, M. V., & Wilson, P. M. (1986) · PubMed · Cited by 53 · see citing works
Practical experience with bed occupancy management and planning systems: an Australian view
Mackay, M. F. (2001) · Health Care Management Science · doi:10.1023/a:1009653716457 · Cited by 45 · see citing works
A Model-Based Approach to the Analysis of Patterns of Length of Stay in Institutional Long-Term Care
Xie, H., Chaussalet, T., & Millard, P. H. (2006) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2005.863820 · Cited by 40 · see citing works
Modeling and forecasting hospital patient movements: Univariate and multiple time series approaches
Lin, W. T. (1989) · International Journal of Forecasting · doi:10.1016/0169-2070(89)90087-3 · Cited by 38 · see citing works
Forecasting medical cost inflation rates: A model comparison approach
Cao, Q., Ewing, B. T., & Thompson, M. A. (2012) · Decision Support Systems · doi:10.1016/j.dss.2011.12.012 · Cited by 25 · see citing works
A dual hybrid forecasting model for support of decision making in healthcare management
Purwanto, P., Eswaran, C., & Logeswaran, R. (2012) · Advances in Engineering Software · doi:10.1016/j.advengsoft.2012.07.006 · Cited by 19 · see citing works
A decision support system for hospital bed assignment.
Clerkin, D., Fos, P. J., & Pétry, F. (1995) · PubMed · Cited by 15 · see citing works
SDM95-Reducing Aggregate Care Team Costs Through Optimal Patient Placement
Ledersnaider, D. L., & Channon, B. (1998) · JONA The Journal of Nursing Administration · doi:10.1097/00005110-199810000-00010 · Cited by 10 · see citing works
PMC1 FORECASTING WITH TIME SERIES MODELS TO EXAMINE THE AVAILABILITY OF INPATIENT BEDS
Cerrito, P., & Cerrito, J. (2007) · Value in Health · doi:10.1016/s1098-3015(10)69100-0 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Integrated multimodal artificial intelligence framework for healthcare applications
Soenksen, L. R., Ma, Y., Zeng, C., Boussioux, L., Villalobos Carballo, K., Na, L., Wiberg, H. M., Li, M. L., Fuentes, I., & Bertsimas, D. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00689-4 · Cited by 380 · see citing works
“Particularly, predicting next 48 h discharges is critical for physicians to identify and prioritize patients ready for discharge and for case management teams to accelerate discharge preparations, which ultimately reduces patient burden and direct operating costs in healthcare systems 43 .”
Background
- Authors
- Zhu, T., Luo, L., Zhang, X., Shi, Y., & Shen, W.
- Affiliations
- Sichuan University (CN)
- West China Hospital of Sichuan University (CN)
- Venue
- IEEE Journal of Biomedical and Health Informatics
- Published
- 2017-03
- Volume
- 21
- Issue
- 2
- Pages
- 515-526
- ISSN
- 2168-2194 (ISSN-L)
- 2168-2208
- OpenAlex
- W2342545017
- Cited by
- 68
- References
- 26
- Citations by year
- 2026: 1 · 2025: 8 · 2024: 9 · 2023: 5 · 2022: 8 · 2021: 8 · 2020: 11 · 2019: 7 · 2018: 8 · 2017: 3
- FWCI
- 6.32
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Journal of Biomedical and Health Informatics (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Natural Science Foundation of China
- Research on big data-driven resource management of whole society in environment and smart health care (71532007)
- Resource dispatching and optimizing research in medical service (71131006)
- Design of Sichuan Medicare payments based on patients’ medical value maximization and big data (2015ZR0097)
- Hospital resource planning and control optimizing based on patients’ demand (71172197)
- Topics
- Health Sciences › Health Professions › Emergency Medical Services › Healthcare Operations and Scheduling Optimization
- Social Sciences › Decision Sciences › Management Science and Operations Research › Forecasting Techniques and Applications
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Keywords
- capacity reservation, elective admissions, seasonal ARIMA, weighted Markov chain, discharge planning, time series forecasting
- MeSH terms
- Bed Occupancy, Forecasting, Hospital Bed Capacity, Humans, Markov Chains, Patient Discharge, Regression Analysis, Time Factors, Models, Statistical
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
