Examining Final-Administered Medication as a Measure of Data Quality: A Comparative Analysis of Death Data with the Central Cancer Registry in Republic of Korea

SIMPLE SUMMARY: Death represents the definitive endpoint for a patient; therefore, it is crucial to determine an accurate date of death. This study aims to examine the final-administered medication in a gold standard cohort that assesses death data accuracy. By utilizing electronic health records from a single medical institution and the Korean Central Cancer Registry, we establish the gold standard as patients who died in the hospital after the implementation of electronic health records, with a difference of 0 or 1 day between the final hospital visit/discharge and death. We calculate the similarity of the terminal medication between the gold standard and cohorts using cosine similarity. The findings reveal a positive correlation between mortality rates and similarities of the final-administered medication. This study introduces the potential of the last administered medication as a novel data quality measure of death data when the date of death differs between datasets. ABSTRACT: Death is a crucial outcome in retrospective cohort studies, serving as a criterion for analyzing mortality in a database. This study aimed to assess the quality of extracted death data and investigate the potential of the final-administered medication as a variable to quantify accuracy for the validation dataset. Electronic health records from both an in-hospital and the Korean Central Cancer Registry were used for this study. The gold standard was established by examining the differences between the dates of in-hospital deaths and cancer-registered deaths. Cosine similarity was employed to quantify the final-administered medication similarities between the gold standard and other cohorts. The gold standard was determined as patients who died in the hospital after 2006 and whose final hospital visit/discharge date and death date differed by 0 or 1 day. For all three criteria—(a) cancer stage, (b) cancer type, and (c) type of final visit—there was a positive correlation between mortality rates and the similarities of the final-administered medication. This study introduces a measure that can provide additional accurate information regarding death and differentiates the reliability of the dataset.