Session 2: Development of a Machine Learning and Computational Method to Identify Geographic and Racial Disparities in End-Stage Kidney Disease
Presentation Type
Oral
Student
No
Track
Health Care Application
Abstract
End-stage kidney disease (ESKD) disproportionately affects Hispanic and American Indian (AI) persons with prevalence rates more than double of White persons. Furthermore, all-cause mortality is significantly higher for Hispanic and AI. The increased prevalence and mortality rates can be attributed to the higher level of health disparities caused by social determinants of health (SDOH). We are developing machine learning and computational models based on patient-level ESKD data at zip code or county level paired with SDOH data to predict the risk of mortality among Hispanic and AI persons with ESRD in South Dakota who have varying socio-demographic characteristics. The primary impact of our study is the development of a fair and unbiased identifier mortality risk that will provide the opportunity for healthcare providers and policymakers to mitigate the health disparities among Hispanic and AI persons with ESKD in South Dakota that can be applied to other geographies using our model. The purpose of this presentation is to provide an overview of this NIH-funded project and to more broadly discuss how SDOH and non-biomedical indicators can be used to generate risk scores and target interventions to address SDOH at an individual level.
Start Date
2-6-2024 9:50 AM
End Date
2-6-2024 10:50 AM
Session 2: Development of a Machine Learning and Computational Method to Identify Geographic and Racial Disparities in End-Stage Kidney Disease
Dakota Room 250 A/C
End-stage kidney disease (ESKD) disproportionately affects Hispanic and American Indian (AI) persons with prevalence rates more than double of White persons. Furthermore, all-cause mortality is significantly higher for Hispanic and AI. The increased prevalence and mortality rates can be attributed to the higher level of health disparities caused by social determinants of health (SDOH). We are developing machine learning and computational models based on patient-level ESKD data at zip code or county level paired with SDOH data to predict the risk of mortality among Hispanic and AI persons with ESRD in South Dakota who have varying socio-demographic characteristics. The primary impact of our study is the development of a fair and unbiased identifier mortality risk that will provide the opportunity for healthcare providers and policymakers to mitigate the health disparities among Hispanic and AI persons with ESKD in South Dakota that can be applied to other geographies using our model. The purpose of this presentation is to provide an overview of this NIH-funded project and to more broadly discuss how SDOH and non-biomedical indicators can be used to generate risk scores and target interventions to address SDOH at an individual level.