Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Short term hospital occupancy prediction.

Steven J Littig1, Mark W Isken

  • 1Improvement Path Systems, Inc., Farmington Hills, MI, USA. littig@improvementpath.com

Health Care Management Science
|February 28, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A tactical multi-week implicit tour scheduling model with applications in healthcare.

Health care management science·2022
Same author

Global patterns and drivers of ecosystem functioning in rivers and riparian zones.

Science advances·2019
Same author

An open source software project for obstetrical procedure scheduling and occupancy analysis.

Health care management science·2010
Same author

Hillmaker: an open source occupancy analysis tool.

Clinical and investigative medicine. Medecine clinique et experimentale·2006
Same author

Collection and preparation of sensor network data to support modeling and analysis of outpatient clinics.

Health care management science·2005
Same author

Data mining to support simulation modeling of patient flow in hospitals.

Journal of medical systems·2002
Same journal

Optimal hospital capacity management during demand surges.

Health care management science·2026
Same journal

Towards optimal valve prescription for transcatheter aortic valve replacement (TAVR) surgery: a machine learning approach.

Health care management science·2026
Same journal

Efficient engagement: opportunities for mobile methadone maintenance in geographically underserved areas.

Health care management science·2026
Same journal

Ahead of the ambulance: Optimizing volunteer training.

Health care management science·2026
Same journal

A novel multi-criteria doctor ranking method considering patient risk attitudes and compensatory relationships.

Health care management science·2026
Same journal

Toward generalizable and interpretable machine learning models in healthcare: Insights from ICU outcome predictions.

Health care management science·2026
See all related articles

This study developed a computerized model for predicting hospital inpatient census, or occupancy, by nursing unit and shift. The model uses statistical predictions at the individual patient level to improve resource management and patient care.

Area of Science:

  • Healthcare Management
  • Operations Research
  • Predictive Analytics

Background:

  • Hospital inpatient census (occupancy) significantly impacts resource allocation, staffing, and patient care quality.
  • Fluctuating occupancy rates present challenges for hospital operations, including bed management and ambulance diversions.
  • Accurate occupancy prediction is crucial for efficient hospital resource utilization and improved patient outcomes.

Purpose of the Study:

  • To develop and evaluate a second-generation computerized model for short-term hospital occupancy prediction.
  • To provide accurate, unit- and shift-specific occupancy forecasts using real hospital data.
  • To compare the predictive accuracy of the new model against various alternative methods.

Main Methods:

  • Development of a comprehensive predictive occupancy model utilizing statistical predictions at the individual patient level.

Related Experiment Videos

  • Implementation and piloting of an early model version in a mid-size community hospital.
  • Testing and validation of the second-generation model using two years of actual hospital data, comparing its accuracy to other predictive techniques.

    • Main Results:

    • The developed model provides short-term occupancy predictions by nursing unit and shift.
    • The second-generation model demonstrates improved accuracy compared to various other predictive methods.
    • Pilot testing of an early version provided valuable insights for model refinement.

    Conclusions:

    • Computerized, data-driven occupancy prediction models can enhance hospital resource management.
    • Accurate short-term occupancy forecasting can positively impact operational efficiency and patient care quality.
    • The developed predictive model offers a valuable tool for hospitals seeking to optimize staffing and bed management.