Results from simulated data sets: probabilistic record linkage outperforms deterministic record linkage.

OBJECTIVE: To gain insight into the performance of deterministic record linkage (DRL) vs. probabilistic record linkage (PRL) strategies under different conditions by varying the frequency of registration errors and the amount of discriminating power. STUDY DESIGN AND SETTING: A simulation study in which data characteristics were varied to create a range of realistic linkage scenarios. For each scenario, we compared the number of misclassifications (number of false nonlinks and false links) made by the different linking strategies: deterministic full, deterministic N-1, and probabilistic. RESULTS: The full deterministic strategy produced the lowest number of false positive links but at the expense of missing considerable numbers of matches dependent on the error rate of the linking variables. The probabilistic strategy outperformed the deterministic strategy (full or N-1) across all scenarios. A deterministic strategy can match the performance of a probabilistic approach providing that the decision about which disagreements should be tolerated is made correctly. This requires a priori knowledge about the quality of all linking variables, whereas this information is inherently generated by a probabilistic strategy. CONCLUSION: PRL is more flexible and provides data about the quality of the linkage process that in turn can minimize the degree of linking errors, given the data provided.

Regional perinatal mortality differences in the Netherlands; care is the question.

BACKGROUND: Perinatal mortality is an important indicator of health. European comparisons of perinatal mortality show an unfavourable position for the Netherlands. Our objective was to study regional variation in perinatal mortality within the Netherlands and to identify possible explanatory factors for the found differences. METHODS: Our study population comprised of all singleton births (904,003) derived from the Netherlands Perinatal Registry for the period 2000-2004. Perinatal mortality including stillbirth from 22+0 weeks gestation and early neonatal death (0-6 days) was our main outcome measure. Differences in perinatal mortality were calculated between 4 distinct geographical regions North-East-South-West. We tried to explain regional differences by adjustment for the demographic factors maternal age, parity and ethnicity and by socio-economic status and urbanisation degree using logistic modelling. In addition, regional differences in mode of delivery and risk selection were analysed as health care factors. Finally, perinatal mortality was analysed among five distinct clinical risk groups based on the mediating risk factors gestational age and congenital anomalies. RESULTS: Overall perinatal mortality was 10.1 per 1,000 total births over the period 2000-2004. Perinatal mortality was elevated in the northern region (11.2 per 1,000 total births). Perinatal mortality in the eastern, western and southern region was 10.2, 10.1 and 9.6 per 1,000 total births respectively. Adjustment for demographic factors increased the perinatal mortality risk in the northern region (odds ratio 1.20, 95% CI 1.12-1.28, compared to reference western region), subsequent adjustment for socio-economic status and urbanisation explained a small part of the elevated risk (odds ratio 1.11, 95% CI 1.03-1.20). Risk group analysis showed that regional differences were absent among very preterm births (22+0 - 25+6 weeks gestation) and most prominent among births from 32+0 gestation weeks onwards and among children with severe congenital anomalies. Among term births (>or= 37+0 weeks) regional mortality differences were largest for births in women transferred from low to high risk during delivery. CONCLUSION: Regional differences in perinatal mortality exist in the Netherlands. These differences could not be explained by demographic or socio-economic factors, however clinical risk group analysis showed indications for a role of health care factors.

Ignoring dependency between linking variables and its impact on the outcome of probabilistic record linkage studies.

OBJECTIVES This study sought to examine the differences between ignoring (naïve) and incorporating dependency (nonnaïve) among linkage variables on the outcome of a probabilistic record linkage study. DESIGN AND MEASUREMENTS We used the outcomes of a previously developed probabilistic linkage procedure for different registries in perinatal care assuming independence among linkage variables. We estimated the impact of ignoring dependency by re-estimating the linkage weights after constructing a variable that combines the outcomes of the comparison of 2 correlated linking variables. The results of the original naïve and the new nonnaïve strategy were systematically compared for 3 scenarios: the empirical dataset using 9 variables, the empirical dataset using 5 variables, and a simulated dataset using 5 variables. RESULTS The linking weight for agreement on 2 correlated variables among nonmatches was estimated considerably higher in the naïve strategy than in the nonnaïve strategy (16.87 vs. 13.55). Therefore, ignoring dependency overestimates the amount of identifying information if both correlated variables agree. The impact on the number of pairs that was classified differently with both approaches was modest in the situation in which there were many different linking variables but grew substantially with fewer variables. The simulation study confirmed the results of the empirical study and suggests that the number of misclassifications can increase substantially by ignoring dependency under less favorable linking conditions. CONCLUSION Dependency often exists between linking variables and has the potential to bias the outcome of a linkage study. The nonnaïve approach is a straightforward method for creating linking weights that accommodate dependency. The impact on the number of misclassifications depends on the quality and number of linking variables relative to the number of correlated linking variables.

Medical Record Linkage of Anonymous Registries without Validated Sample Linkage of the Dutch Perinatal Registries.

This paper describes the linkage of data from three Dutch Perinatal Registries: the Dutch National Midwife Registry, the Dutch National Obstetrics Registry and the Dutch National Pediatrics Registry, for the year of 2001. All these registries are anonymous and lack a common identifier. We used probabilistic and deterministic record linkage techniques to combine data from the mother, delivery and child involving to the same pregnancy. Records of singleton and twin pregnancies were linked separately. We have developed a probabilistic close method based on maximum likelihood methods to estimate the weights of individual linking variables and the threshold value for the overall weight. Probabilistic linkage identified 80% more links than a full deterministic linkage approach. External validation revealed an error rate of less than 1%. Our method is a flexible and powerful method to link anonymous registries in the absence of a gold standard.