Estimating area deprivation effects on mortality using evolutionary algorithm

The exact nature of the association between thecontext of the local area and local health outcomes is unknown. We investigated whether areas geographically close but divergentin terms of deprivation have greater inequality in health thanthose where deprivation is similar across neighbouring localities. In order to disaggregate the strong correlation between the deprivationof a target area and that of its surrounding areas, we usedprincipal component analysis to create the measure of deprivationinequality. Through application of Evolutionary Algorithm (EA), our study compared three models with the different combinationsof variables, e.g., DSR and IMD, DSR, IMD and ALD or DSR, IMD, ALD and PC2 to produce the evidence that neighbouringdeprivation strongly influences the health outcomes. The resultshows the strong effect of neighbouring deprivation inequalityin estimating mortality. It suggests that increased deprivationinequality is associated with increased mortality.