Determine an optimal cut-point in presence of competing risks to categorize a continuous distribution: An application in studying outcomes of patients with cirrhosis listed for liver transplantation

Abstract

Introduction Whether non-selective beta-blockers (NSBBs) are deleterious in patients with end-stage cirrhosis and refractory ascites has been widely debated. We hypothesized that only the subset of patients on the liver transplant waiting list who had impaired cardiac performance would be at increased risk of mortality if receiving NSBBs. Methods This study included 584 consecutive patients with cirrhosis evaluated for transplantation between 1999 and 2014. All patients had right heart catheterization with hemodynamic measurements at evaluation. Fifty percent received NSBBs. Refractory ascites was present in 33%. Cardiac performance was assessed by left ventricular stroke work index (LVSWI). Waiting list mortality without liver transplantation was explored using competing risk analysis trough Fine & Gray regression model. As describe in Contal et al. and Woo et al., we used the maximally selected rank statistic methods to determine an optimal cutpoint for a quantitative covariate with competing risks. There is no package available for this method so we implemented an R function and codes and description of the method are available in GitHub ( https://github.com/PManchon/Cutoff-Gray_DEBRC-Bichat ). Results LVSWI was significantly lower in patients with refractory ascites. In multivariate analysis using competing risk, refractory ascites, NSBBs (yes/no) and LVSWI (quantitative) were associated with waiting list mortality in the whole population, with a statistically significant interaction between NSBBs and LVSWI. To create a composite variable to ensure interpretability of the result we determine an optimal cutpoint for LVSWI. The most discriminant value was 64.1 g-m/m2 (corresponding to the maximally Gray statistic standardized at 0.86). In the final model, refractory ascites (subdistribution hazard ratio: 1.52; 95% CI: 1.01–2.28; P = 0.0083) and treatment by NSBBs with LVSWI Conclusion This study suggests that compromised cardiac performance is more common in patients with refractory ascites and that NSBBs are deleterious in cirrhotic patients with compromised cardiac performance. These results highlight the prognostic value of cardiac function in patients with end-stage cirrhosis.