Record linkage of healthcare insurance claims

Abstract

Limitations of current record linkage techniques include difficulty in handling large and heterogeneous data sets, low sensitivity in deterministic matching, the necessity to provide a priori weights for probabilistic matching, low computational efficiency, and complex software. This paper provides a detailed description of a method developed for purposes of linking records of individuals across time and geography. The procedure for record-linkage consists of three major components: data standardization, weight estimation, and matching. The proposed method was designed to incorporate a combination of exact and probabilistic matching techniques. The procedure was validated using convergent, divergent, and criterion- validity measures. The authors feel that the procedure outlined in this paper is a first step in addressing the current trend toward larger and more complex databases.