The University of Pittsburgh researchers have developed an innovative technology, enhanced Detection System for Healthcare Associated Transmission (EDS-HAT). EDS-HAT combines whole genome sequencing (WGS) of bacterial pathogens with machine learning and data mining of electronic health records (EHR) to detect and predict outbreaks of healthcare-associated infections (HAIs) in hospital settings. This system addresses the limitations of traditional outbreak detection methods by providing real-time surveillance and analysis, significantly reducing the number of undetected outbreaks, infections, and associated healthcare costs.
Description
EDS-HAT utilizes a dual approach to enhance the detection of healthcare-associated outbreaks. It integrates WGS for routine surveillance of bacterial pathogens with advanced machine learning algorithms that analyze EHR data to identify the transmission routes responsible for outbreaks. This combined use of WGS and EHR data mining is a novel approach, enabling rapid identification of outbreaks and the implementation of timely interventions to prevent further infections. Additionally, the system is being developed in a "Lite" version (EDS-HAT Lite), which requires less WGS data, making it accessible to a broader range of healthcare facilities.
Applications
• Infection Control
• Healthcare Cost Reduction
• Scalable Solution
Advantages
EDS-HAT represents a significant advancement in the detection and prevention of HAIs. Its ability to detect outbreaks that would otherwise go unnoticed or be detected too late, combined with its integration of WGS and machine learning, sets it apart from traditional methods. By reducing false positives and improving the accuracy of outbreak detection, EDS-HAT enhances patient safety and reduces the economic burden of HAIs on the healthcare system.
Invention Readiness
The prototype for EDS-HAT has been developed and validated through NIH-funded research. The system has demonstrated its effectiveness in identifying serious outbreaks that were not detected by traditional means. Further development and validation activities are ongoing, with plans to expand the system's capabilities and commercialize the technology.
IP Status
Patent pending
