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

Machine-Learning Algorithms to Code Public Health Spending Accounts.

Eoghan S Brady1, Jonathon P Leider2, Beth A Resnick2

  • 11 Department of Population, Family and Reproductive Health, School of Public Health, Johns Hopkins University, Baltimore, MD, USA.

Public Health Reports (Washington, D.C. : 1974)
|April 1, 2017
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

Building Career Capital Through Service: A Qualitative Study of Public Health Corps Members' Skill Development and Professional Growth.

Journal of public health management and practice : JPHMP·2026
Same author

Attainment of Public Health Degrees in the Governmental Public Health Workforce in 2024.

American journal of public health·2026
Same author

Preventability of Severe Maternal Morbidity: A Scoping Review of the Literature in High-Income Countries.

American journal of perinatology·2026
Same author

The toll of tobacco: smoking-attributable health spending in South Korea, 2014-2024. National claims evidence for cost recovery.

The Lancet regional health. Western Pacific·2026
Same author

Comparative performance of risk prediction models for kidney disease: an external validation using 0.5 million UK Biobank participants.

BMC nephrology·2026
Same author

Adverse selection or beneficial selection in dual western medicine-traditional Chinese medicine insurance markets.

Social science & medicine (1982)·2026

Machine learning algorithms offer a faster, cheaper alternative to manual classification of public health expenditures. These tools can efficiently analyze large datasets, aiding policymakers in understanding public health spending.

Area of Science:

  • Public Health Informatics
  • Health Services Research
  • Computational Health Science

Background:

  • Government public health expenditure data requires extensive manual effort for analysis.
  • Policy makers need summarized data for informed decision-making.
  • Current methods are time-consuming and costly.

Purpose of the Study:

  • To compare machine learning algorithms against manual classification of public health expenditures.
  • To assess if machine learning can provide a more efficient alternative.
  • To evaluate the performance of machine learning in classifying public health spending.

Main Methods:

  • Utilized machine learning algorithms to replicate manual classification of state public health expenditures.
  • Employed standardized categories from the Foundational Public Health Services model.
Keywords:
health financemachine learningpublic health

Related Experiment Videos

  • Trained 9 algorithms on a dataset of 147,280 expenditure records (2000-2013).
  • Measured performance using recall, precision, and coverage rates.

    • Main Results:

    • The random forests algorithm achieved 84% recall and 91% precision.
    • An ensemble of 6+ algorithms met the 90% recall target.
    • The ensemble method retained 93% coverage, leaving only 7% unclassified.

    Conclusions:

    • Machine learning presents a time- and cost-saving method for estimating US public health spending.
    • Standardized categories facilitate parsing of public health expenditures.
    • ML tools can enhance comparability across organizations and evaluate resource allocation.