Prediction of All-Cause Mortality in End-Stage Kidney Disease Patients Using Social Determinants of Health: A Machine Learning Framework

Presentation Type

Poster

Student

Yes

Track

Health Care Application

Abstract

End-stage kidney disease (ESKD) is the irreversible and final stage of chronic kidney disease in which the kidneys lose their ability to function independently. Patients at this stage require dialysis or kidney transplant to survive. This debilitating disease impacted over 800,000 U.S. residents in 2023 according to the United Stated Renal Data System (USRDS). By combining social determinants of health with patient-specific factors, we can better understand how both non-medical and clinical characteristics influence patient survival outcomes. In this study, we propose a machine learning framework to predict ESKD patient all-cause mortality by the end of a follow-up period. A dataset from the USRDS including patients admitted in 2015 and tracked until August 2021 was analyzed. We also integrate community-level data from the Agency for Healthcare and Research Quality (AHRQ) Social Determinants of Health Database. Variable screening techniques and expert feedback were employed to select significant features for predicting all-cause mortality in ESKD patients. Multiple machine learning models were developed, and model performance was evaluated using various metrics. This study presents a novel approach to investigating all-cause mortality in ESKD patients, considering the relationship between a comprehensive set of social determinants of health and survival outcomes. Our framework can help public health professionals identify key factors driving all-cause mortality in ESKD patients, facilitating them to address areas of need and provide resources to support these areas.

ACKNOWLEDGMENTS: The research reported in this abstract was supported by South Dakota State University, AIM-AHEAD Coordinating Center, award number OTA-21-017, and was, in part, funded by the National Institutes of Health Agreement No. 1OT2OD032581. The work is solely the responsibility of the authors and does not necessarily represent the official view of AIM-AHEAD or the National Institutes of Health. The data reported here have been supplied by the United States Renal Data System (USRDS). The interpretation and reporting of these data are the responsibility of the author(s) and in no way should be seen as an official policy or interpretation of the U.S. government.

Start Date

2-7-2025 1:00 PM

End Date

2-7-2025 2:30 PM

This document is currently not available here.

Share

COinS
 
Feb 7th, 1:00 PM Feb 7th, 2:30 PM

Prediction of All-Cause Mortality in End-Stage Kidney Disease Patients Using Social Determinants of Health: A Machine Learning Framework

Volstorff A

End-stage kidney disease (ESKD) is the irreversible and final stage of chronic kidney disease in which the kidneys lose their ability to function independently. Patients at this stage require dialysis or kidney transplant to survive. This debilitating disease impacted over 800,000 U.S. residents in 2023 according to the United Stated Renal Data System (USRDS). By combining social determinants of health with patient-specific factors, we can better understand how both non-medical and clinical characteristics influence patient survival outcomes. In this study, we propose a machine learning framework to predict ESKD patient all-cause mortality by the end of a follow-up period. A dataset from the USRDS including patients admitted in 2015 and tracked until August 2021 was analyzed. We also integrate community-level data from the Agency for Healthcare and Research Quality (AHRQ) Social Determinants of Health Database. Variable screening techniques and expert feedback were employed to select significant features for predicting all-cause mortality in ESKD patients. Multiple machine learning models were developed, and model performance was evaluated using various metrics. This study presents a novel approach to investigating all-cause mortality in ESKD patients, considering the relationship between a comprehensive set of social determinants of health and survival outcomes. Our framework can help public health professionals identify key factors driving all-cause mortality in ESKD patients, facilitating them to address areas of need and provide resources to support these areas.

ACKNOWLEDGMENTS: The research reported in this abstract was supported by South Dakota State University, AIM-AHEAD Coordinating Center, award number OTA-21-017, and was, in part, funded by the National Institutes of Health Agreement No. 1OT2OD032581. The work is solely the responsibility of the authors and does not necessarily represent the official view of AIM-AHEAD or the National Institutes of Health. The data reported here have been supplied by the United States Renal Data System (USRDS). The interpretation and reporting of these data are the responsibility of the author(s) and in no way should be seen as an official policy or interpretation of the U.S. government.