Bayesian Analysis of Lung Cancer Mortality in the Presence of Misclassification

Background: Lung cancer is an important cause of cancer mortality. Mortality is a familiar projection to address the burden of cancers. However, according to Iranian death registry, about 20% of death statistics were still recorded in misclassified categories. The aim of this study was to estimate lung cancer mortality in Iranian population, using Bayesian approach to revise this misclassification.

Methods: We analyzed National death Statistic reported by the Iranian Ministry of Health and Medical Education from 1995 to 2004. Lung cancer [ICD-10; C34] was expressed as the annual mortality rates/100,000 by sex and by age group. The Bayesian approach to correct and account for misclassification effects in Poisson count regression with a beta prior was employed to estimate the mortality rate of lung cancer in age and sex groups.

Results: According to the Bayesian analysis, there were between 20 to 30 percent underreported mortality records in deaths due to lung cancer, and its mortality rate increased through the recent years.

Conclusion: Our findings suggested a substantial undercount of Lung cancer mortality in Iranian population. Therefore, policy makers who determine research and treatment priorities on death rates should pay more attention to this underreported data.