DATA RECORD MATCHING ALGORITHMS FOR LONGITUDINAL PATIENT LEVEL DATABASES

摘要

A method is provided for assigning longitudinal linking tags to de~identifiedpatient data records by matching the patient data records with reference datarecords. The de-identified patient data records may include both encrypted andnon~ encrypted data attributes. Different possible subsets of the dataattributes are categorized in a hierarchy of levels. Subsets of data fieldvalues are compared with the reference data records one level at a time. Uponsuccessful comparison or matching of a subset of data field values, alongitudinal linking tag associated with a matched reference data record isassigned to de-identified data record is assigned. When a match is not found,a new longitudinal linking tag is created and assigned to the de-identifieddata record. The new tag and corresponding data record attributes are thenadded to the reference data for future matching operations.