Key points are not available for this paper at this time.
Purpose: Record linkage based on quasi-identifiers remains an important approach as not every data source provides a comprehensive unique identifier. In this study, reasons for the failure of a linkage based on quasi-identifiers were examined. Furthermore, informed algorithms using information on gold-standard links were developed to investigate the potentially achievable linkage quality based on quasi-identifiers. Methods: Linkage algorithms were applied on German claims and cancer registry data using information on gold-standard links. Informed linkage algorithms based on deterministic linkage, logistic regression, random forests, gradient boosting and neural networks were derived and compared. Descriptive analyses were performed to identify reasons for failure of linkage such as discrepancies between data sources. Results: A linkage approach based on gradient boosting performed best and reached a precision of 77%, a recall of 81% and an F*-measure of 64%. Of 641 patients in GePaRD, 8% were not uniquely identifiable using birth year, sex, area of residence, year and quarter of diagnosis, whereas 33% of 42,817 cancer registries patients of Bremen and Lower Saxony were not uniquely identifiable with these quasi-identifiers. Conclusions: Linkage of German claims and cancer registry data based on quasi-identifiers does result in insufficient linkage quality since subjects cannot be uniquely identified. It is advisable to use unique identifiers from a subsample, if available, to derive informed linkage algorithms for the entire sample. In this case the machine learning technique gradient boosting has been found to outperform other methods.
Lendle et al. (Tue,) studied this question.