Automated Data Extraction for Influenza Monitoring in Australia
Author Information
Author(s): Gösta TH Liljeqvist, Michael Staff, Michele Puech, Hans Blom, Siranda Torvaldsen
Primary Institution: NSW Public Health Officer Training Program, New South Wales Department of Health
Hypothesis
Can syndromic ILI data be extracted automatically from routine GP data?
Conclusion
Automated data extraction from routine GP records offers a means to gather data without introducing any additional work for the practitioner.
Supporting Evidence
- The Canning Flu Tool identified seasonal trends in ILI both retrospectively and in near real-time.
- The sensitivity of the tool was 96.3% and the specificity was 99.7%.
- The GP surveillance tool produced a more robust signal than the existing PHREDSS system.
Takeaway
This study shows that we can use computers to automatically collect information about flu-like illnesses from doctors' records, making it easier to track flu trends.
Methodology
The study adapted a software program for automated data extraction from GP records and compared ILI data from GP practices with emergency department data.
Potential Biases
The sensitivity of the tool might be lower in practices using certain medical record software that encrypts progress notes.
Limitations
The study was conducted in a metropolitan area with relatively high socioeconomic status, limiting generalizability.
Participant Demographics
The study involved eight GP sites in a metropolitan area of Sydney, Australia.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website