Evaluating a Prediction-Driven Targeting Strategy for Reducing the Transmission of Multidrug-Resistant Organisms

Sean L. Barnes (), Miranda Myers (), Clare Rock (), Daniel J. Morgan (), Lisa Pineles (), Kerri A. Thom () and Anthony D. Harris ()
Additional contact information
Sean L. Barnes: Department of Decision, Operations and Information Technologies, Robert H. Smith School of Business, University of Maryland, College Park, Maryland 20742;
Miranda Myers: Department of Decision, Operations and Information Technologies, Robert H. Smith School of Business, University of Maryland, College Park, Maryland 20742;
Clare Rock: Division of Infectious Diseases, Johns Hopkins University School of Medicine, Baltimore, Maryland 21205;
Daniel J. Morgan: Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore, Maryland 21201
Lisa Pineles: Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore, Maryland 21201
Kerri A. Thom: Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore, Maryland 21201
Anthony D. Harris: Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore, Maryland 21201

INFORMS Journal on Computing, 2020, vol. 32, issue 4, 912-929

Abstract: The transmission of multidrug-resistant organisms (MDROs) in the healthcare setting is an ongoing challenge affecting at least 2 million patients in the United States each year via infection and leading to over 20,000 deaths. Many mathematical models have been developed to approximate MDRO transmission dynamics, focusing most often on evaluating the impact of various infection-control strategies. However, although the insights derived from these studies are useful, the models do not typically have the ability to support decision making for infection-control practitioners in real time. In this study, we design a detailed agent-based model of MDRO transmission—focusing on methicillin-resistant Staphylococcus aureus in the intensive care unit setting—and validate its transmission dynamics using data collected during a multisite randomized, controlled trial. We leverage this model to develop and evaluate the effectiveness of a prediction-driven approach for targeting patients for contact precautions (i.e., requiring all visiting healthcare workers to wear personal protective equipment) in a simulated intensive care unit based on their daily likelihood of becoming colonized by the organism. We show that we can predict these outcomes with moderate to high accuracy across a broad range of scenarios and that these predictions can be used to efficiently target patients for intervention and, ultimately, to reduce the overall acquisition rate in the unit.

Keywords: agent-based modeling; simulation; machine learning; healthcare epidemiology (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1287/ijoc.2019.0916 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:orijoc:v:32:y:4:i:2020:p:912-929

Access Statistics for this article

More articles in INFORMS Journal on Computing from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().