Gastroenterology and Hepatology from Bed to Bench

Abstract

Aim: The aim of this study was to investigate the impact of diabetes and hypertension on colorectal cancer (CRC) mortality.

Background: One of the methodology in epidemiological studies is to use self-report questionnaires to gather data, this is the easiest and cheapest method but involves with misclassification bias. We use robust Bayesian adjustment to correct this bias.

Methods: One of the methodology in epidemiological studies is to use self-report questionnaires to gather data, this is the easiest and cheapest method but involves with misclassification bias. We use robust Bayesian adjustment to correct this bias.

Results: The effect size with ignorance misclassification bias was 0.78 for diabetes and 0.94 for hypertension respectively which both of them were not significant. After adjusting the misclassification and performing the robust Bayesian analysis, we arrived at region (0.27, 3.4) for OR of diabetes and (0.21, 2.31) for hypertension.

Conclusion: our study demonstrated that diabetes and hypertension increase the risk of mortality in CRC patients, using robust Bayesian analysis and misclassification in diagnosis these two exposure could change or confound the results of this association