Updated Diabetes Dataset for the manuscript "<b>Spatial epidemiology of diabetes in Ghana: identifying regional hotspots and socioeconomic predictors for targeted interventions</b>"

Background: Diabetes is a global health concern, yet its spatial and spatiotemporal distribution in Ghana remains poorly characterized.

Aim: Identify hotspots and coldspots, estimate the relative risk of diabetes and determine predictors in Ghana for targeted interventions.

Methods: We analyzed national diabetes cases from 2018 to 2022 using data from the District Health Information Management System (DHIMS). Incidence rates (per 1,000 population) were estimated and smoothed via Empirical Bayesian methods. Spatial dependence and clustering were assessed using Global Moran’s I, Local Indicators of Spatial Association (LISA), and Getis–Ord statistics, while space–time clusters were identified with SaTScan. Bivariate LISA examined spatial associations with key determinants, and relative risk was estimated using Bayesian spatial and spatiotemporal models. Gradient Boosting, supported by SHapley Additive exPlanations (SHAP), quantified the importance and contribution of regional predictors to diabetes burden.