Accuracy of a probabilistic record-linkage methodology used to track blood donors in the Mortality Information System database

The probabilistic record linkage (PRL) is based on a likelihood score that measures the degree of similarity of several matching variables. Screening test results for different diseases are available for the blood donor population. In this paper, we describe the accuracy of a PRL process used to track blood donors from the Fundacao Pro-Sangue (FPS) in the Mortality Information System (SIM), in order that future studies might determine the blood donor's cause of death. The databases used for linkage were SIM and the database made up of individuals that were living (200 blood donors in 2007) and dead (196 from the Hospital das Clinicas de Sao Paulo that died in 2001-2005). The method consists of cleaning and linking the databases using three blocking steps comparing the variables "Name/Mother's Name/Date of Birth" to determine a cut-off score. For a cut-off score of 7.06, the sensitivity and specificity of the method is 94.4% (95% CI: 90.0-97.0) and 100% (95% CI: 98.0-100.0), respectively. This method can be used in studies that aim to track blood donors from the FPS database in SIM.