Multidrug-resistant organisms (MDROs), particularly carbapenem-resistant organisms (CROs), are a major cause of healthcare-associated infections (HAIs). Though studies have found multiple interventions addressing MDRO colonization and transmission to be effective at reducing HAIs, implementation has lagged due to questions regarding the most efficacious combination of interventions. As healthcare facilities (e.g., hospitals, long-term care facilities, or outpatient surgical centers and clinics) are part of an interconnected healthcare network, evaluation of an intervention’s impact on transmission and infection must consider the dynamics across the healthcare system. To address remaining knowledge gaps regarding the most effective combinations of intervention strategies, we will build a multi-level model that spans from individual patients to regionally interconnected healthcare facilities. The resulting framework will provide hospital administrators and infection control experts with tools for quantifying individual patient risk factors for colonization and infection and for comparing the potential effectiveness of interventions to control HAIs. The aims of the project are: (1) to develop models to estimate the underlying prevalence and incidence of CROs and predict which patients are at highest risk for colonization and infection with CROs using clinical samples collected during the normal course of care; (2) to utilize hospital-level models to quantify the combinatorial relationship between, and marginal impact of, additional interventions to reduce HAIs; and (3) to build a regional model of a healthcare system to examine the effectiveness of interventions across institutions. Models will start with the patient at the center, utilizing the rich covariate data stored in electronic medical records to develop prediction models based on advanced machine learning. These prediction models will be translatable tools that can be directly incorporated into clinical care to assist clinicians in preventing HAIs. In addition, they will form the foundation of hospital-level models that will allow for detailed examinations of the effectiveness of different combinations of interventions. Hospital-level models will then be embedded in a network of healthcare facilities that accounts for the differing incentives faced by geographically dispersed facilities with variable demographic populations. These models will directly inform CDC guidelines about MDRO prevention and aid clinicians in reducing the risk of HAIs.


Funding Source

Project Period