The existence of standard-biased mortality ratios due to death certificate misclassification - a simulation study based on a true story

Abstract

Background: Mortality statistics are used to compare health status of populations; optimally, they base on individual death certificates. However, determining cause of death is error-prone. E.g. cardiovascular disease (CVD) death determination is characterized by sensitivity (SE) and specificity (SP) lower than 85%. Furthermore, differential misclassification may be present in case of homogenous target populations. We investigate the bias of standardized mortality ratios (SMR), based on real-world data.

Methods: CVD mortality of 6378 ethnic German repatriates was assessed and the SMR calculated. Non-differential age-dependent misclassification was introduced into data by scenarios of equal SE and SP in a range of 0.7 to 0.85. The bias between originally reported and actual SMR was calculated for each pair of values. Additionally, four differential misclassification scenarios were simulated, reflecting two extreme scenarios of both quality criteria varied in the cohort but fixed to either higher or lower in the reference, and two scenarios of crossed criteria values.

Results: In case of non-differential misclassification the bias is always towards the null-hypothesis. The lowest bias was 13.5% (SE, SP = 0.85 constantly), the maximum bias was 40% (SP = 0.7). However, in case of differential misclassification the observed SMR can be on the wrong track. If SP is high but SE low in the cohort, negative bias up to -10% can occur. In case SE is low but SP is high in the reference, the bias remains always positive. In the opposite case plus SP is high in the cohort, the bias can reach -30%.

Conclusion: SMR values are always biased due to the diagnostic test character of death determination. In majority of epidemiological studies the bias should be towards the null-hypothesis (non-differential misclassification). However, caution is needed in case of differential misclassification, possibly experienced in studies on homogenous subgroups, and in large prospective cohorts with specifically trained personnel.

Fig. 1

Scenario A) non-differential misclassification; < 70 years SE, SP = 0.85; ≥70 years SE = [0.7, 0.85], SP = [0.7, 0.85]; applied to mortality data of a cohort of migrants in Augsburg, Germany

Fig. 2

Scenario B1) differential misclassification; <70 years SE, SP = 0.85; ≥70 years cohort SE = [0.7, 0.85], SP = [0.7, 0.85], reference SE, SP = 0.85; applied to mortality data of a cohort of migrants in Augsburg, Germany

Fig. 3

Scenario B2) differential misclassification; <70 years SE, SP = 0.85; ≥70 years cohort SE = [0.7, 0.85], SP = [0.7, 0.85], reference SE, SP = 0.7; applied to mortality data of a cohort of migrants in Augsburg, Germany

Fig. 4

Scenario B3) differential misclassification; <70 years SE, SP = 0.85; ≥70 years cohort SE = [0.7, 0.85], SP = [0.7, 0.85], reference SE = 0.7, SP = 0.85; applied to mortality data of a cohort of migrants in Augsburg, Germany

Fig. 5

Scenario B4) differential misclassification; <70 years SE, SP = 0.85; ≥70 years cohort SE = [0.7, 0.85], SP = [0.7, 0.85], reference SE = 0.85, SP = 0.7; applied to mortality data of a cohort of migrants in Augsburg, Germany