Residential elevation and its effects on hypertension incidence among older adults living at low altitudes: a prospective cohort study

Background: Research on the relationship between residential altitude and hypertension incidence has been inconclusive. Evidence at low altitudes (i.e., <1,500 m) is scarce, let alone in older adults, a population segment with the highest hypertension prevalence. Thus, the objective of this study is to determine whether hypertension risk may be affected by altitude in older adults living at low altitudes. Methods: This prospective cohort study collected data from the Chinese Longitudinal Healthy Longevity Survey (CLHLS). We selected 6,548 older adults (>= 65 years) without hypertension at baseline (2008) and assessed events by the follow-up surveys done in 2011, 2014, and 2018 waves. The mean altitude of 613 residential units (county or district) in which the participants resided was extracted from the Digital Elevation Model (DEM) of the National Aeronautics and Space Administration (NASA) and was accurate to within 30 m. The Cox regression model with penalized splines examined the linear or nonlinear link between altitude and hypertension. A random-effects Cox regression model was used to explore the linear association between altitude and hypertension. Results: The overall rate of incident hypertension was 8.6 per 100-person years. The median altitude was 130.0m (interquartile range [IQR] = 315.5 m). We observed that the exposure-response association between altitude and hypertension incidence was not linear. The shape of the exposure-response curve showed that three change points existed. Hypertension risk increased from the lowest to the first change point (247.1 m) and slightly fluctuated until the last change point (633.9 m). The risk decreased above the last change point. According to the categories stratified by the change points, altitude was only significantly associated with hypertension risk (hazard ratio [HR] = 1.003; 95% confidence interval [CI] = 1.002-1.005) under the first change point (247.1 m) after adjusting for related covariates. Conclusion: Our study found that the association between altitude and hypertension risk might not be linear. We hope the further study can be conducted to confirm the generality of our findings.