Invited Talk 2
Time: 11:00 - 12:00 AM CDT
Speaker: Semhar Michael, PhD, Associate Professor of Statistics, South Dakota State University
Title: Survival Score Development and Geographic Trends in End-Stage Kidney Disease
Abstract: This study aimed to develop and validate survival scores for patients with end-stage kidney disease (ESKD) using a mixture cure model (MCM). Additionally, the research aimed to examine geographic variations in ESKD outcomes across the United States. This study used a United States Renal Data System (USRDS) dataset that contains people with incident ESKD from 2000 through 2020, including those on dialysis or who had at least one transplant. Many variables, including demographic and comorbid factors, were included within an MCM. This MCM was used to develop seven survival scores that would be summarized geographically. These survival scores are presented using maps of the United States and validated against clinical measurements from the USRDS dataset. Several spatial survival trends across the United States were observed, which could be validated using the USRDS data and current literature. The Appalachian and Great Plains regions of the United States contained individuals who had lower survival rates. Conversely, individuals residing in Southern California, the Southeast, and the Texas-Mexico border had higher survivability rates. Most of these findings aligned with previous studies. Furthermore, many of the trends could be explained by both the coefficient estimates of the MCM and the characteristics of the individuals living in each region. For example, the MCM coefficient estimates found Hispanics to have a higher survivability than their non-Hispanic counterparts, which aligned with the predominantly Hispanic-populated area of the Texas-Mexico border. Lastly, serum creatinine, a USRDS variable not used within the MCM, was found to have a moderately positive, linear relationship with the survival scores developed. The MCM-based survival scores were successfully validated using both geographic trends and clinical variables, reinforcing the model’s reliability in estimating ESKD outcomes. These survival scores can serve as valuable tools for clinicians and policymakers seeking to better understand and address geographic and demographic gaps in ESKD survival, ultimately informing targeted interventions and resource allocation strategies.
Bio: Dr. Michael earned a B.S. in Applied Mathematics from the University of Asmara, Eritrea, an M.Sc. in Mathematics from the University of North Dakota, and a Ph.D. in Applied Statistics from the University of Alabama. Dr. Michael's research focuses on computational statistics, with an emphasis on unsupervised learning and latent variable modeling through finite mixture models. Her applied work spans several areas of science, such as health and forensic science. Her research has been published in peer-reviewed journals, presented at national and international conferences, and has received national recognition through paper awards. Dr. Michael has secured funding to support her research from multiple national agencies.