Simultaneous disease mapping and hot spot detection with application to childhood obesity surveillance from electronic health records

TL;DR

This paper introduces a novel statistical method leveraging electronic health records to simultaneously map childhood obesity prevalence and detect hot spots, aiding targeted public health interventions.

Contribution

It develops a penalized multilevel generalized linear model with an efficient algorithm for joint disease mapping and hot spot detection from EHR data.

Findings

Superior performance in simulations

Effective application to Wisconsin EHR data

Identifies meaningful obesity hot spots

Abstract

Electronic health records (EHRs) have become a platform for data-driven surveillance on a granular level in recent years. In this paper, we make use of EHRs for early prevention of childhood obesity. The proposed method simultaneously provides smooth disease mapping and outlier information for obesity prevalence, which are useful for raising public awareness and facilitating targeted intervention. More precisely, we consider a penalized multilevel generalized linear model. We decompose regional contribution into smooth and sparse signals, which are automatically identified by a combination of fusion and sparse penalties imposed on the likelihood function. In addition, we weigh the proposed likelihood to account for the missingness and potential non-representativeness arising from the EHR data. We develop a novel alternating minimization algorithm, which is computationally efficient, easy to implement, and guarantees convergence. Simulation studies demonstrate superior performance of the proposed method. Finally, we apply our method to the University of Wisconsin Population Health Information Exchange database.