Development and testing of prediction models for end stage kidney disease patient nonadherence to renal replacement treatment regimens utilizing big data and healthcare informatics

In patients with end stage kidney disease (ESKD), renal replacement therapy assumes some functions of the diseased kidney and is required to sustain life. Hemodialysis (HD) is the primary modality for treatment of ESKD and includes treatments to filter the body´s toxins from the blood three times per week. It has been shown that nonadherence with dialysis treatment regimens is associated with increased morbidity and mortality, even with missing one routine session of HD [1][2]. We aimed to utilize clinical and nonclinical data sources to develop predictive models (PMs) that identify patients with a high probability of not attending their HD treatments within the following week.