Utility Mobile

Controlling Hospital Acquired Infections


Global Infectious Disease Institute

Hospital-acquired infections (HAIs) due to Clostridioides difficile and multidrug-resistant organisms (MDROs) such as carbapenem-resistant Enterobacteriaceae (CRE) pose a significant burden to modern healthcare systems. According to the Centers for Disease Control and Prevention (CDC), one in twenty five hospital patients are infected with at least one healthcare acquired infection (HAI) on any given day. 

The overall goal of this project is to develop methods for prediction of incidence rates and patient risk to HAIs and evaluate interventions to control their spread. The mechanisms of HAI transmission and antimicrobial resistance are very complex, and the available data are sparse and noisy. Therefore, risk prediction and evaluation of interventions cannot be done by simple statistical models restricted to one hospital.

We will develop an in-silico framework with the following specific aims: (1) build a detailed agent based model (ABM) for HAI transmission in hospitals to identify key driving factors and estimate the relative impact of hospital operational characteristics, (2) develop advanced machine learning methods for prediction of HAI incidence rate within a hospital, and the risk of individual patients becoming colonized or infected, and (3) study the socio-economic factors involved in HAI transmission, through infection control measures across hospitals in a patient sharing network, and within the community.


This project has just started, and we are working with the SOM team members on collecting data on patients from the UVA hospital. We have also started developing simulation models of HAIs.



Professor of Computer Science, School of Engineering and Applied Science


Professor of Public Health Sciences, School of Medicine

Other Team Members

Costi Sifri | Professor and Director of Hospital Epidemiology | University of Virginia