Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Aug 13;28(9):1977-1981.
doi: 10.1093/jamia/ocab089.

Practical development and operationalization of a 12-hour hospital census prediction algorithm

Alexander J Ryu  1 , Santiago Romero-Brufau  2 , Narges Shahraki  3 , Jiawei Zhang  4 , Ray Qian  5 , Thomas C Kingsley  1
Affiliations

Practical development and operationalization of a 12-hour hospital census prediction algorithm

Alexander J Ryu et al. J Am Med Inform Assoc. .

Abstract

Hospital census prediction has well-described implications for efficient hospital resource utilization, and recent issues with hospital crowding due to CoVID-19 have emphasized the importance of this task. Our team has been leading an institutional effort to develop machine-learning models that can predict hospital census 12 hours into the future. We describe our efforts at developing accurate empirical models for this task. Ultimately, with limited resources and time, we were able to develop simple yet useful models for 12-hour census prediction and design a dashboard application to display this output to our hospital's decision-makers. Specifically, we found that linear models with ElasticNet regularization performed well for this task with relative 95% error of +/- 3.4% and that this work could be completed in approximately 7 months.

Keywords: forecasting; hospital census; inpatient; machine learning.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.
Hourly census over 4 representative weeks. Two cyclical patterns are apparent: 1 daily, 1 weekly. Red line—actual adult acute census. Blue line—predicted adult acute census.
Figure 2.
Figure 2.
Mockup of hospital census dashboard application. Home screen view.
See this image and copyright information in PMC

References

    1. Huang Y, Xu C, Ji M, et al.Medical service demand forecasting using a hybrid model based on ARIMA and self-adaptive filtering method. BMC Med Inform Decis Mak 2020; 20 (1). doi:10.1186/s12911-020-01256-1. - PMC - PubMed
    1. Zinouri N, Taaffe KM, Neyens DM.. Modelling and forecasting daily surgical case volume using time series analysis. Heal Syst 2018; 7: 111–9. - PMC - PubMed
    1. Koestler DC, Ombao H, Bender J.. Ensemble-based methods for forecasting census in hospital units. BMC Med Res Methodol 2013; 13 (1): 1–12. - PMC - PubMed
    1. Garrison GM, Pecina JL.. Using the M/G/∞ queueing model to predict inpatient family medicine service census and resident workload. Health Informatics J 2016; 22 (3): 429–39. - PubMed
    1. Broyles JR, Cochran JK, Montgomery DC.. A statistical Markov chain approximation of transient hospital inpatient inventory. Eur J Oper Res 2010; 207 (3): 1645–57.

Publication types