Privacy-preserving record linkage using Bloom filters

Abstract

BackgroundCombining multiple databases with disjunctive or additional information on the same person is occurring increasingly throughout research. If unique identification numbers for these individuals are not available, probabilistic record linkage is used for the identification of matching record pairs. In many applications, identifiers have to be encrypted due to privacy concerns.MethodsA new protocol for privacy-preserving record linkage with encrypted identifiers allowing for errors in identifiers has been developed. The protocol is based on Bloom filters on q-grams of identifiers.ResultsTests on simulated and actual databases yield linkage results comparable to non-encrypted identifiers and superior to results from phonetic encodings.ConclusionWe proposed a protocol for privacy-preserving record linkage with encrypted identifiers allowing for errors in identifiers. Since the protocol can be easily enhanced and has a low computational burden, the protocol might be useful for many applications requiring privacy-preserving record linkage.

Estupro e gravidez de meninas de até 13 anos no Brasil: características e implicações na saúde gestacional, parto e nascimento

“…The cases were correlated using a Bloom filter 14 . The following variables were used for pairing between the databases: name of patient in the SINAN and name of mother in the SINASC, date of birth of the patient in the SINAN and date of birth of the mother in the SI-NASC and municipality of residence in the two systems.…”

Privacy‐preserving record linkage

“…The idea of Bloom filter based PPRL was suggested by Schnell et al (2009). The method is based on the idea of splitting an identifier into substrings of length 2 (bigrams) and mapping the bigrams by HMACs to a binary vector.…”

“…For the mapping of each bigram Schnell et al (2009) proposed the use of several different HMACs for each bigram. The combination of a bit-vector with hash functions is called Bloom filters in computer science (Bloom 1970).…”

“…In the standard Bloom filters used for PPRL (Schnell et al 2009) the k hash functions are based on the double hashing scheme…”

Privacy-Preserving Record Linkage

“…The question of non-exact matching is partially addressed in [5,6,34]. These works in essence compute similarity scores for pairs of records via a reduction to a secure set intersection protocol.…”