Augmenting maternal clinical cohort data with administrative laboratory dataset linkages: a validation study

Area of Science:

• Health Informatics
• Data Science in Healthcare
• Bioinformatics

Background:

• Big data and large language models offer potential for improving patient treatment and healthcare management.
• Protecting patient confidentiality is a major challenge when using large-scale administrative healthcare data.
• Augmenting clinical data with administrative laboratory dataset linkages can avoid using sensitive demographic information.

Purpose of the Study:

• To explore an alternative method for examining patient files from a large administrative dataset.
• To link external data to the National Health Laboratory Services (NHLS) database using specimen barcodes.
• To quantify the performance metrics of using specimen barcodes for deterministic data linkages without demographic information.

Main Methods:

• Utilized specimen barcodes associated with laboratory tests for deterministic data linkages.
• Linked external hospital data to the NHLS database.
• Quantified linkage performance metrics on a validation sample of 1200 records.

Main Results:

• Achieved a 95% success rate in linking NHLS data to external hospital data using specimen barcodes.
• Obtained 87% exact matches and 9% matches with typographic correction.
• Identified 5% mismatches or duplicates in the administrative data.

Conclusions:

• Specimen barcodes are a reliable tool for linking large datasets without compromising patient confidentiality.
• This deterministic linkage approach effectively avoids the need for demographic identifiers.
• The high success rate supports the use of specimen barcodes for secure and efficient healthcare data integration.