Reducing oral health disparities in children using predictive analytics and mathematical modeling - Project Summary Tooth decay is the most common chronic disease among U.S. children.2,3 Despite efforts to increase utilization among minority populations by improving coverage for dental insurance via Medicaid and Children’s Health Insurance Program (CHIP), large oral health disparities remain with Black and Hispanic children having the poorest oral health of any racial groups in the US.5-8 In addition to lack of access to recommended care, individual health behaviors (e.g., poor dietary and oral hygiene) and community- and provider-related structural factors also contribute to the high risk of severe dental caries in minority populations.6,9 State Medicaid and CHIP dental programs are encouraged to consider strategies to reduce oral health disparities in their delivery system improvement efforts,6 however, they are challenged with improving quality and reducing quality disparities among high-need beneficiaries in a cost-effective way.6 Steps toward successful program improvements include the ability to validly measure the value of care (defined by both health outcomes and costs) delivered to their beneficiaries, as well as incorporating racial/ethnic disparities in the assessment. There is a critical gap in our understanding of the influence of race/ethnicity and its interaction with multilevel risk factors on disparities in quality and oral health outcomes. The scientific objective of this research plan is to study multilevel determinants of oral health and disparities in quality of dental care and assess the value of improving care and eliminating racial/ethnic disparities in quality. In Aim 1, we will develop a risk prediction model of severe dental caries by applying machine-learning based survival analysis4,10 on electronic health record (EHR) data to understand the influence of race/ethnicity on progression of severe caries and explore heterogenous treatment effects of dental care. In Aim 2, we will analyze individual-level claims in Medicaid Analytic eXtract (MAX) data combined with multiple data sources to comprehensively measure racial/ethnic disparities in overall quality of dental care, using evidence-based quality indicators, and identify modifiable structural risk factors creating disparities. In Aim 3, incorporating results from Aims 1 and 2, a microsimulation model of severe caries, integrating individual-level data with data on key contextual factors, will be developed and used to assess the cost-effectiveness and value of improvements in care stemming from dental quality measures and eliminating racial/ethnic disparities in quality. Findings from this study will support decision-making by policymakers and stakeholders, and will form the basis of an R01 application to study novel strategies that target underserved and vulnerable populations. This research plan is complemented by a career development plan that builds on the applicant’s background in health policy and decision science. Specifically, this career development plan outlines new training in three areas: (1) oral health epidemiology, (2) health disparities research, and (3) advanced analytics methods. The combined research and training plan will prepare the applicant for a successful independent research career identifying, evaluating, and implementing multilevel interventions to reduce racial/ethnic disparities in oral health.
