Agreement between individual and neighborhood income measures in patients with colorectal cancer in Canada

Abstract

Introduction: With increasing interest in income-related differences in cancer outcomes, accurate measurement of income is imperative. Misclassification of income can result in wrong conclusions as to the presence of income inequalities. We determined misclassification between individual- and neighborhood-level income and their association with overall survival among colorectal cancer (CRC) patients.

Methods: The Canadian Census Health and Environment Cohorts were used to identify CRC patients diagnosed from 1992 to 2017. We used neighborhood income quintiles from Statistics Canada and created individual income quintiles from the same data sources to be as similar as possible. Agreement between individual and neighborhood income quintiles was measured using cross-tabulations and weighted kappa statistics. Cox proportional hazards and Lin semiparametric hazards models were used to determine the effects of individual and neighborhood income independently and jointly on survival. Analyses were also stratified by rural residence.

Results: A total of 103 530 CRC patients were included in the cohort. There was poor agreement between individual and neighborhood income with only 17% of respondents assigned to the same quintile (weighted kappa = 0.18). Individual income had a greater effect on relative and additive survival than neighborhood income when modeled separately. The interaction between individual and neighborhood income demonstrated that the most at risk for poor survival were those in the lowest individual and neighborhood income quintiles. Misclassification was more likely to occur for patients residing in rural areas.

Conclusion: Cancer researchers should avoid using neighborhood income as a proxy for individual income, especially among patients with cancers with demonstrated inequalities by income.

Figure 1.

Individual income distribution by individual and neighborhood income quintiles (whiskers represent 10th and 90th percentiles as opposed to minimum and maximum values because of data confidentiality). Q = quintiles; CAD = Canadian Dollars.

Figure 2.

Five-year Kaplan–Meier survival by individual and neighborhood income quintiles.