Session 5 : Challenges and Opportunities of Combining Clinical Datasets with Social Determinants of Health Datasets in Machine Learning: Application to Determining the Risk of Mortality in End Stage Kidney Disease

Presentation Type

Invited

Student

No

Track

Health Care Application

Abstract

Social determinants of health (SDOH) are non-medical factors that influence health outcomes. Common SDOH factors include income, education, safe housing, transportation, polluted air and water, access to health care, and access to healthy food. In an effort to reduce health disparities and more accurately predict outcomes of care, it is important to incorporate SDOH variables with clinical findings. This presentation will discuss various challenges to combining clinical datasets, such as electronic health records or clinical registries, with SDOH datasets along with suggestions to reduce bias in artificial intelligence (AI)/machine learning (ML) algorithms aimed at predicting risk for outcomes of care.

The status of a current SDSU project with the National Institutes of Health (NIH) under the “Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity,” program, or AIM-AHEAD, will be shared. This project uses machine learning to assist in identifying disparities in health outcomes for populations affected by end-stage kidney disease. The SDSU project includes partners from the University of Nebraska Medical Center, Dakota State University, Auburn University, Avera Health, and other researchers and clinicians in and outside of South Dakota.

Start Date

2-7-2025 11:00 AM

End Date

2-7-2025 12:00 PM

This document is currently not available here.

Share

COinS
 
Feb 7th, 11:00 AM Feb 7th, 12:00 PM

Session 5 : Challenges and Opportunities of Combining Clinical Datasets with Social Determinants of Health Datasets in Machine Learning: Application to Determining the Risk of Mortality in End Stage Kidney Disease

Dakota A & C (Room 250)

Social determinants of health (SDOH) are non-medical factors that influence health outcomes. Common SDOH factors include income, education, safe housing, transportation, polluted air and water, access to health care, and access to healthy food. In an effort to reduce health disparities and more accurately predict outcomes of care, it is important to incorporate SDOH variables with clinical findings. This presentation will discuss various challenges to combining clinical datasets, such as electronic health records or clinical registries, with SDOH datasets along with suggestions to reduce bias in artificial intelligence (AI)/machine learning (ML) algorithms aimed at predicting risk for outcomes of care.

The status of a current SDSU project with the National Institutes of Health (NIH) under the “Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity,” program, or AIM-AHEAD, will be shared. This project uses machine learning to assist in identifying disparities in health outcomes for populations affected by end-stage kidney disease. The SDSU project includes partners from the University of Nebraska Medical Center, Dakota State University, Auburn University, Avera Health, and other researchers and clinicians in and outside of South Dakota.