A Deep Cox Mixture Model Approach to End-Stage Kidney Disease

Persons with end-stage kidney/renal disease (ESKD) require undergoing dialysis or receiving a kidney transplant. Ethnic minority groups are disproportionately affected by ESKD in the United States. Due to the large range of ethnic and socio-economic groups in the United States, the assumption of proportional hazards (PH), which is required for Cox regression, could easily be violated. Hence, a deep Cox mixture (DCM) model is utilized to identify and model latent subpopulations that better satisfy the PH assumption and leverage deep neural networks for improved performance. Data from USRDS on patients with ESKD is analyzed. We found that the DCM model has better performance overall compared to a Cox PH model in terms of Brier score and a time-dependent concordance index. Additionally, the DCM model has better performance for the smaller subpopulations, i.e., race/ethnicity, region of the United States, and rurality of the community the patient belongs.