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

Predicting inpatient costs with admitting clinical data

W M Tierney1, J F Fitzgerald, M E Miller

  • 1Department of Medicine, Indiana University School of Medicine, Indianapolis.

Medical Care
|January 1, 1995
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

Bowel and bladder outcomes in patients with anorectal malformations and sacral agenesis: a retrospective cohort study.

Pediatric surgery international·2026
Same author

Inactivation of the bacterial pathogens Staphylococcus pseudintermedius and Acinetobacter baumannii by butanoic acid.

Journal of applied microbiology·2018
Same author

Health Informatics Standards: A View From Mid-America.

Yearbook of medical informatics·2016
Same author

Preface.

Environmental monitoring and assessment·2013
Same author

Transanal endoscopic microsurgery for rectal carcinoids: the largest reported United States experience.

Colorectal disease : the official journal of the Association of Coloproctology of Great Britain and Ireland·2011
Same author

A characterization of local LOINC mapping for laboratory tests in three large institutions.

Methods of information in medicine·2010

Predicting hospital costs using electronic medical records and diagnosis-related groups (DRGs) can help target high-cost patients. Early clinical data significantly improves cost prediction accuracy for hospital cost-containment programs.

Area of Science:

  • Health Economics
  • Medical Informatics
  • Healthcare Management

Background:

  • Hospital cost-containment programs require cost-effective strategies.
  • Identifying high-cost physicians and patients is crucial for program success.
  • Predicting hospital costs necessitates accounting for case mix and early patient identification.

Purpose of the Study:

  • To develop and validate statistical models for predicting hospital costs.
  • To assess the utility of clinical data from electronic medical records (EMRs) for cost prediction.
  • To evaluate the contribution of diagnosis-related groups (DRGs) and discretionary clinical data to cost prediction accuracy.

Main Methods:

  • Retrospective analysis of 2,355 patients admitted to an urban teaching hospital.

Related Experiment Videos

  • Development of predictive models using EMR data, including clinical, demographic, and discretionary variables.
  • Validation of models on a separate subset of patients to assess generalizability.

    • Main Results:

    • Diagnosis-related groups (DRGs) explained 16-24% of cost variance; adding discretionary data substantially increased predictive power.
    • Clinical data gathered within 24 hours of admission improved cost prediction accuracy.
    • Models using all data types showed the lowest underestimation of true costs (10-13%).

    Conclusions:

    • Clinical data from EMRs are valuable for adjusting for case mix and identifying high-cost patients.
    • Early identification of high-cost patients enables targeted cost-containment interventions.
    • Integrating comprehensive clinical data into predictive models enhances hospital cost management strategies.