Modifications to residential neighbourhood characteristics and risk of 79 common health conditions: a prospective cohort study

Abstract

Background: Observational studies have identified a link between unfavourable neighbourhood characteristics and increased risk of morbidity, but it is unclear whether changes in neighbourhoods affect future disease risk. We used a data-driven approach to assess the impact of neighbourhood modification on 79 health outcomes.

Methods: In this prospective cohort study, we used pooled, individual-level data from two Finnish cohort studies: the Health and Social Support study and the Finnish Public Sector study. Neighbourhood characteristics (mean educational level, median income, and employment rate of residents, and neighbourhood green space) and individual lifestyle factors of community-dwelling individuals were assessed at baseline (at different waves starting between 1998 and 2013). We repeated assessment of neighbourhood characteristics and lifestyle factors approximately 5 years from each baseline assessment, after which follow-up began for health conditions diagnosed according to the WHO International Classification of Diseases for 79 common health conditions using linkage to electronic health records. We used Cox proportional hazard regression models to compute adjusted hazard ratios (HRs) of incident disease associated with neighbourhood characteristics and changes in neighbourhood characteristics over time and logistic regression analysis to compute adjusted odds of association between changes in neighbourhood characteristics and individual lifestyle factors.

Findings: 114 786 individuals (87 012 [75·8%] women; mean age 44·4 years [SD 11·1]) had complete data and were included in this cohort study. During 1·17 million person-years at risk, we recorded 164 368 new-onset health conditions and 3438 deaths. Favourable changes in neighbourhood characteristics were associated with reduced risk of all-cause mortality and incidence of 19 specific health conditions. Unfavourable changes were correspondingly associated with increased risk of mortality and 27 specific health conditions. Among participants who did not move residence during the observation period, relative to individuals who continually lived in disadvantaged neighbourhoods, those who experienced favourable modifications in neighbourhood characteristics had a lower risk of future diabetes (HR 0·84, 95% CI 0·75-0·93), stroke (0·49, 0·29-0·83), skin disease (0·72, 0·53-0·97), and osteoarthritis (0·87, 0·77-0·99). Living in a neighbourhood with improving characteristics was also associated with improvements in individual-level health-related lifestyle factors. Among participants who lived in advantaged residential environments at baseline, unfavourable changes in neighbourhood characteristics were associated with an increased risk of diabetes, stroke, skin disease, and osteoarthritis compared with individuals who lived in advantaged neighbourhoods throughout the study period.

Interpretation: Favourable modifications to residential neighbourhoods showed robust, longitudinal associations with a range of improvements in health outcomes, including improved health behaviours and reduced risk of cardiometabolic, infectious, and orthopaedic conditions.

Funding: UK Medical Research Council, US National Institute on Aging, NordForsk, and Academy of Finland.

Figure 1

Association of favourable change in neighbourhood characteristics with subsequent health outcomes in participants residing in disadvantaged neighbourhoods at baseline* HR=hazard ratio. *HRs are adjusted for age, sex, education, and cohort.

Figure 2

Association of unfavourable change in neighbourhood characteristics with subsequent health outcomes in participants residing in advantaged neighbourhoods at baseline* HR=hazard ratio. *HRs are adjusted for age, sex, education, and cohort.

Figure 3

Association of change in neighbourhood characteristics with subsequent health outcomes among participants with no change in residential address during the 5-year exposure period HR=hazard ratio. *Adjusted for age, sex, education, and cohort. †Adjusted for age, sex, education, marital status, population density in the neighbourhood, place of residence (urban vs rural), and being in employment during the 5-year exposure period.