Evaluating Privacy-Preserving Record Linkage in Merging Cancer Registry Data and Electronic Health Records.

Area of Science:

• Health Informatics
• Biostatistics
• Oncology Research

Background:

• Clinical data utility is often limited by fragmented patient records across disparate sources.
• Privacy-preserving record linkage (PPRL) offers a solution to integrate data while protecting patient confidentiality.
• Effective linkage is crucial for comprehensive patient data analysis in research.

Purpose of the Study:

• To evaluate the performance of PPRL in merging cancer registry data with electronic health records (EHRs).
• To assess the accuracy and reliability of the data linkage process for oncology research.
• To demonstrate that enhanced data integration can be achieved without compromising patient privacy.

Main Methods:

• Utilized two distinct datasets: electronic health record (EHR) extracts and Missouri Cancer Registry (MCR) records.
• Performed validation exercises including an audit by the MCR.
• Employed multiple matching algorithms for a comparative evaluation of record linkage performance.

Main Results:

• The study demonstrated substantial matching performance between the two data sources.
• High recall and precision rates were achieved, indicating effective data linkage.
• The PPRL process proved successful in integrating disparate clinical data.

Conclusions:

• The refined data linkage process significantly enhances research capabilities in oncology.
• Reliable data integration for clinical research is achievable through PPRL.
• The methodology supports improved patient data utility without compromising privacy.