Renal Replacement Therapy in Patients With Acute Decompensated Pulmonary Hypertension Admitted to the Intensive Care Unit

Background: Pulmonary arterial hypertension and chronic thromboemholic pulmonary hypertension (PH) are characterized hemodynamically by pre-capillary PH. Acute worsening of systemic congestion and/or reduced right ventricular flow output in patients with pre-capillary PH characterizes an episode of acute decompensated PH. Acute kidney injury (AKI) is a common complication in this population and those patients frequently use renal replacement therapy (RRT). Predictors and timing for RRT in acute decompensated PH are unknown and mortality of patients who require this therapy is high. We hypothesize that AKI and hypervolemia are associated with use of RRT during episodes of acute decompensated PH in patients with pre-capillary PH requiring intensive care unit (ICU) admission. Aim: Explore variables associated with RRT use, develop a decision tree model to predict use of RRT in acute decompensated PH and analyze ICU, in-hospital and 90-days mortality in this population. Materials and methods: Multicenter retrospective cohort study including patients with pulmonary arterial hypertension and chronic thromboembolic PH with unplanned admission in the ICU for acute decompensated PH. Acute decompensated PH was defined by acute right ventricular failure leading to low cardiac output and elevated right ventricle filling pressures. We employed two multivariable logistic regression models using directed acyclic graphs to identify confounders. Unadjusted and adjusted odds ratios and 95% confidence intervals were used to measure the association between variables and RRT use. Results: Some 73 patients were included, 16.4% (n=12) of patients required RRT during ICU stay. In the univariate analysis, right atrial pressure (RAP) on last right heart catheterization, and creatinine upon ICU admission were associated with use of RRT and were included in the multivariable model and in the decision tree model. The decision tree model based on RAP and creatinine showed sensitivity of 58.3% and specificity of 100% with area under the receiver operating characteristic curve of 0.81 for predicting RRT use in the ICU. In-hospital mortality and 90-days mortality of patients who used RRT were higher than in patients that did not use RRT (75.0% vs. 34.4%, p < 0.01 and 83.3% vs. 42.6%, p = 0.01, respectively). Conclusion: The decision tree model based on creatinine upon admission and RAP, which is a surrogate of hypervolemia, can identify patients at risk for RRT. Increased ICU, in-hospital, and 90-days mortality were observed in patients with acute decompensated PH who used RRT in the ICU.