Profiling Dialysis Facilities for Adverse Recurrent Events

• Activity Number: 506 - Categorical Data
• Type: Contributed
• Date/Time: Wednesday, July 31, 2019 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Danh V Nguyen* and Jason P Estes and Yanjun Chen and Damla Senturk and Connie M Rhee and Esra Kurum and Amy S You and Elani Streja and Kamyar Kalantar-Zadeh
• Companies: University of California At Irvine and Research, Pratt & Whitney and UC Irvine and UCLA and UC Irvine and UC Riverside and UC Irvine and UC Irvine and UC Irvine
• Keywords: profiling; recurrent events; Poisson regression; Negative binomial; dialysis

Abstract

Profiling analysis aims to evaluate health care providers, such as hospitals or dialysis facilities, with respect to a patient outcome. Previous methods have considered binary outcomes, such as 30-day hospital readmission. For the unique population of dialysis patients, regular blood works are required to evaluate effectiveness of treatment and avoid adverse events, including dialysis inadequacy, imbalance mineral levels, and anemia among others. For example, anemic events (when hemoglobin levels exceeds normative range) are recurrent and common for patients on dialysis. Thus, we propose high-dimensional Poisson and negative binomial regression models for rate/count outcomes and introduce a standardized event ratio measure to compare the event rate at a specific facility relative to a chosen normative standard, typically defined as a national rate. Our proposed estimation and inference procedures overcome the challenge of high-dimensional parameters for thousands of dialysis facilities. Also, we investigate how overdispersion affects inference in the context of profiling analysis. The proposed methods are illustrated with profiling dialysis facilities for recurrent anemia events.