Accuracy of probabilistic record linkage in the assessment of high-complexity cardiology procedures

Abstract

Objective: To evaluate the viability of a probabilistic record linkage strategy to identify patients who underwent complex cardiology procedures among the total deceased population.

Methods: The processing cost was estimated based on 1,672 records of patients undergoing coronary artery bypass grafting that were compared with all death records in Brazil in 2005. The accuracy of the linkage strategy was based on the probabilistic linkage of 99 hospital admissions records of patients, with known vital status, who underwent cardiac surgery at a single cardiology institute, with the death records of the state of Rio de Janeiro, Southeastern Brazil, in 2005. Linkage was conducted in four stages: standardizing the databases, blocking, matching, and rating peers. Blocking in five steps was used, with blocking keys formed by a combination of variables such as Soundex codes for the first and last names, sex, and year of birth. The variables used for matching were "full name" with the use of Levenshtein distance and "birth date".

Results: The second and fifth blocking steps resulted in the largest number of formed pairs and the largest processing times for the matching. The fourth step required a lower processing cost. In the accuracy study, after five blocking steps, the sensitivity of the linkage was 90.6%, and the specificity was 100%.

Conclusions: The probabilistic strategy used has high accuracy and can be used in studies of the effectiveness of high-complexity, high-cost cardiology procedures.