ABSTRACT Despite recent progress in reducing the incidence of healthcare-associated infections (HAIs), the Centers for Disease Control and Prevention estimated that 722,000 HAIs occurred in U.S. acute care hospitals in 2011, resulting in 75,000 deaths. Current methods for detecting outbreaks in hospitals are rudimentary and likely to miss some outbreaks altogether and result in substantial delays in detection of others. There are two major developments in healthcare that have the potential to revolutionize how healthcare associated outbreaks of bacterial pathogens are identified and controlled in hospitals. First, the Affordable Care Act mandates use of the electronic medical record (EMR), which has led to its widespread use in healthcare. Second, the costs of bacterial whole genome sequencing (WGS) have declined substantially, which is making its use by infection programs increasingly feasible. In this application, we propose to establish and evaluate the impact of the Enhanced Detection System for Healthcare Association Transmission (EDS-HAT) at the University of Pittsburgh Medical Center (UPMC). EDS-HAT uses a combination of WGS and analysis of the EMR for enhanced outbreak detection. Our specific aims are to 1a): Determine the utility of EDS-HAT to identify HAT that is not identified through routine infection prevention practice, 1b): Improve the efficiency and reduce the cost of EDS-HAT by using the EMR to restrict the use of WGS, 2a): Measure reductions in HAIs following implementation of EDS-HAT, and 2b): Estimate the number of infections and deaths prevented and healthcare costs averted by EDS-HAT. For Aim 1a, EDS-HAT will be performed retrospectively while routine infection prevention practice (requests for molecular typing when an outbreak is suspected) continues, thus allowing a direct comparison of the two approaches. For Aim 1b, we will improve the efficiency and reduce the cost of EDS-HAT by using machine learning and data mining of the EMR to select isolates for WGS. For Aim 2a, we will monitor changes in HAI rates both before and after implementation of EDS-HAT in real time, which will occur at the beginning of year 3. Finally, for Aim 2b, we will perform clinical and budget impact analyses to determine the overall impact of EDS-HAT. To accomplish these aims, we have assembled a team with expertise in infectious diseases, outbreak investigation, infection prevention, microbial genomics and genomic epidemiology, machine learning and data mining, economic analysis and modeling, epidemiology, and biostatistics. EDS-HAT will likely lead to substantial reductions in infections, deaths, and healthcare costs and can serve as a model for how HAT is detected in hospitals.