UNSTRUCTURED
Objectives: We address the real-world challenges of missing data and matching field selection in linking medical records by evaluating the extent to which incorporating the missing-at-random assumption in the Fellegi-Sunter model and using data-driven selected fields improve patient matching accuracy using real-world use cases.
Methods: We adapted the Fellegi-Sunter model to accommodate missing data using the missing-at-random assumption and compared the adaptation to the common strategy of treating missing values as disagreement, with matching fields specified by experts or selected by data-driven methods. We used four use cases, each containing a random sample of record pairs with match status ascertained by manual reviews. Use cases included health information exchange (HIE) record deduplication, linkage of public health registry records to HIE, linkage of Social Security Death Master File records to HIE, and deduplicating newborn screening records, which represent real-world clinical and public health scenarios. Matching performance was evaluated using sensitivity, specificity, positive predictive value, negative predictive value, and F-score.
Results: Incorporating the missing-at-random assumption in the Fellegi-Sunter model maintained or improved F-scores whether matching fields were expert-specified or selected by data-driven methods. Combining the missing-at-random assumption and data-driven fields optimized F-scores in the four use cases.
Conclusions: Missing-at-random is a reasonable assumption in real-world record linkage applications: it maintains or improves F-scores regardless of whether matching fields are expert-specified or data-driven. Data-driven selection of fields coupled with MAR achieves the best overall performance, which can be especially useful in privacy-preserving record linkage.