Missing data imputation and multilevel conditional autoregressive modeling of spatial end-stage renal disease incidence

End-stage renal disease has many adverse complications associated with it and accounted for a 41.8% increase in reported incidence from 2000–2019 in the United States. The adjusted mortality rate among Medicare beneficiaries with chronic kidney disease aged 66 years or older was more than twice as high (103.9 per 1000 person-years) in 2020 compared to those without the disease (47.9 per 1000), according to the United States Renal Data System. This article analyzes the incidence of end-stage renal disease in Florida in 2019 using a hierarchical Conditional Autoregressive model under a Bayesian framework at both the Zip Code Tabulation Area and facility levels. The effects of certain social factors and health indicators on the standardized hospitalization ratio of dialysis facilities are quantified. Additionally, kidney research data being collected in the form of electronic health records poses statistical challenges due to missing data, which can reduce the validity of the results. Therefore, we introduce a novel method to impute missing spatial data using spatial state space modeling. The outcomes of this study offer potentially valuable insights for policymakers aiming to develop strategies that enhance healthcare and service quality for disadvantaged populations.