Linking Hospital and Aged Care Data
Author Information
Author(s): Karmel Rosemary, Gibson Diane
Primary Institution: Australian Institute of Health and Welfare
Hypothesis
Can event-based record linkage effectively connect hospital and residential aged care data without using names or unique identifiers?
Conclusion
Event-based record linkage can successfully link hospital and residential aged care data, providing a useful tool for analyzing transitions between these sectors.
Supporting Evidence
- 3% of hospital separations for older people involve transfers to residential aged care.
- 50% of residential aged care admissions come from hospitals.
- Event-based matching can reduce false matches as event rates decline.
Takeaway
This study shows a way to connect hospital and aged care records without using names, which helps understand how older people move between these services.
Methodology
The study developed a statistical model for event-based matching using demographic data and event dates to link hospital and aged care records.
Potential Biases
Potential for false matches due to similar demographic characteristics among different individuals.
Limitations
The accuracy of the linkage depends on the quality of the demographic data and the assumptions made about birth date distributions.
Participant Demographics
Focus on individuals aged 65 and over in Australia.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website