A Web-Based, Hospital-Wide Health Care-Associated Bloodstream Infection Surveillance and Classification System:...

Area of Science:

• Medical Informatics
• Infectious Disease Surveillance
• Health Care Quality Improvement

Background:

• Traditional health care-associated infection surveillance is resource-intensive and prone to human error.
• Effective surveillance is crucial for infection prevention and control programs.

Purpose of the Study:

• To develop and evaluate an automated system for health care-associated bloodstream infection (HABSI) surveillance and classification.
• To compare the performance of the automated system against conventional infection control personnel (ICP)-based surveillance.

Main Methods:

• A web-based automated surveillance system was developed and integrated into a hospital's medical information system.
• The system was designed to automatically detect and classify HABSIs in a large teaching hospital.

Main Results:

• The automated system demonstrated a strong correlation with ICP-detected HABSIs, both by department (r=.999) and time (r=.941).
• Performance metrics were excellent: sensitivity (98.16%), specificity (99.96%), positive predictive value (95.81%), and negative predictive value (99.98%).
• The automated system reduced the average delay in HABSI case confirmation by 29 days.

Conclusions:

• The developed system provides reliable and objective data for HABSI quality indicators.
• Automated surveillance significantly improves upon the timeliness and efficiency of conventional methods.
• This technology enhances infection prevention efforts by providing faster, more accurate HABSI data.