Related Experiment Videos
Record linkage strategies, outpatient procedures, and administrative data
1Manitoba Centre for Health Policy and Evaluation, Department of Community Health Sciences, Faculty of Medicine, University of Manitoba, Winnipeg, Canada.
Medical Care
|June 1, 1996
Summary
This study explores record linkage for health researchers, showing successful patient data matching is possible even without identification numbers. It highlights challenges in consistent procedure recording for better health services research.
Area of Science:
- Health Services Research
- Epidemiology
- Health Informatics
Background:
- Modern record linkage offers valuable tools for epidemiologists and health services researchers.
- Understanding different record linkage approaches is crucial for researchers to assess suitability for specific needs.
Purpose of the Study:
- To evaluate the effectiveness of record linkage in connecting hospital abstracts and physician claims.
- To identify challenges in consistent procedure recording within healthcare databases.
- To demonstrate the utility of record linkage for quality control and research expansion.
Main Methods:
- Utilized existing identification numbers as a gold standard for linking hospital abstracts and physician claims.
- Investigated the performance of record linkage with and without available identification numbers.
- Analyzed discrepancies in the recording of coronary angiography in inpatient and outpatient hospital records.
Main Results:
- Achieved successful record linkage (over 95% match rate) even in the absence of identification numbers under certain conditions.
- Identified inconsistencies in the recording of coronary angiography within hospital abstracts.
- Demonstrated the feasibility and utility of the proposed record linkage approach.
Conclusions:
- Record linkage can be a valuable method for health services research and quality control in healthcare.
- Addressing inconsistencies in data recording is essential for accurate record linkage.
- The discussed approach is beneficial for validating procedures across multiple data files.