Association of statin use after renal replacement therapy with mortality in patients with dialysis-requiring acute kidney injury.

BACKGROUND: Statin use before hospitalization or after discharge increased the survival rates of patients with dialysis-requiring acute kidney injury. This study aimed to investigate whether statin use during hospitalization period after renal replacement therapy is associated with reduced mortality in patients with dialysis-requiring acute kidney injury. METHODS: This retrospective cohort study was conducted using the Medical Information Mart for Intensive Care IV database between 2008 and 2019. We compared 1-year mortality in patients with dialysis-requiring acute kidney injury with and without exposure to statin during hospitalization period after renal replacement therapy. The secondary outcome was in-hospital mortality. RESULTS: Among 1035 patients with dialysis-requiring acute kidney injury, only 24.9% of the participants received statin therapy during hospitalization after renal replacement therapy. During the 1-year follow-up, 127 of 258 statin users (49.2%) and 541 of 777 statin nonusers (69.6%) died. The risk of 1-year mortality and in-hospital mortality of statin users was 54% lower [hazard ratio (HR) = 0.46; 95% confidence interval (CI) = 0.37 to 0.56, P < 0.001] and 59% lower HR = 0.41, 95% CI = 0.32 to 0.53, P < 0.001), respectively. CONCLUSION: For patients with dialysis-requiring acute kidney injury, statin therapy during hospitalization period after renal replacement therapy was associated with decreased 1-year mortality and in-hospital mortality.

Predicting hyperkalemia in patients with advanced chronic kidney disease using the XGBoost model.

BACKGROUND: Hyperkalemia is a common complication of chronic kidney disease (CKD). Hyperkalemia is associated with mortality, CKD progression, hospitalization, and high healthcare costs in patients with CKD. We developed a machine learning model to predict hyperkalemia in patients with advanced CKD at an outpatient clinic. METHODS: This retrospective study included 1,965 advanced CKD patients between January 1, 2010, and December 31, 2020 in Taiwan. We randomly divided all patients into the training (75%) and testing (25%) datasets. The primary outcome was to predict hyperkalemia (K+ > 5.5 mEq/L) in the next clinic vist. Two nephrologists were enrolled in a human-machine competition. The area under the receiver operating characteristic curves (AUCs), sensitivity, specificity, and accuracy were used to evaluate the performance of XGBoost and conventional logistic regression models with that of these physicians. RESULTS: In a human-machine competition of hyperkalemia prediction, the AUC, PPV, and accuracy of the XGBoost model were 0.867 (95% confidence interval: 0.840-0.894), 0.700, and 0.933, which was significantly better than that of our clinicians. There were four variables that were chosen as high-ranking variables in XGBoost and logistic regression models, including hemoglobin, the serum potassium level in the previous visit, angiotensin receptor blocker use, and calcium polystyrene sulfonate use. CONCLUSIONS: The XGBoost model provided better predictive performance for hyperkalemia than physicians at the outpatient clinic.

Predicting Mortality Using Machine Learning Algorithms in Patients Who Require Renal Replacement Therapy in the Critical Care Unit.

Background: General severity of illness scores are not well calibrated to predict mortality among patients receiving renal replacement therapy (RRT) for acute kidney injury (AKI). We developed machine learning models to make mortality prediction and compared their performance to that of the Sequential Organ Failure Assessment (SOFA) and HEpatic failure, LactatE, NorepInephrine, medical Condition, and Creatinine (HELENICC) scores. Methods: We extracted routinely collected clinical data for AKI patients requiring RRT in the MIMIC and eICU databases. The development models were trained in 80% of the pooled dataset and tested in the rest of the pooled dataset. We compared the area under the receiver operating characteristic curves (AUCs) of four machine learning models (multilayer perceptron [MLP], logistic regression, XGBoost, and random forest [RF]) to that of the SOFA, nonrenal SOFA, and HELENICC scores and assessed calibration, sensitivity, specificity, positive (PPV) and negative (NPV) predicted values, and accuracy. Results: The mortality AUC of machine learning models was highest for XGBoost (0.823; 95% confidence interval [CI], 0.791−0.854) in the testing dataset, and it had the highest accuracy (0.758). The XGBoost model showed no evidence of lack of fit with the Hosmer−Lemeshow test (p > 0.05). Conclusion: XGBoost provided the highest performance of mortality prediction for patients with AKI requiring RRT compared with previous scoring systems.

Association between predialysis creatinine and mortality in acute kidney injury patients requiring dialysis.

BACKGROUND: Creatinine is widely used to estimate renal function, but this is not practical in critical illness. Low creatinine has been associated with mortality in many clinical settings. However, the associations between predialysis creatinine level, Sepsis-related Organ Failure Assessment (SOFA) score, fluid overload, and mortality in acute kidney injury patients receiving dialysis therapy (AKI-D) has not been fully addressed. METHODS: We extracted data for AKI-D patients in the eICU and MIMIC databases. We conducted a retrospective observational cohort study using the eICU dataset. The study cohort was divided into the high-creatine group and the low-creatinine group by the median value (4 mg/dL). The baseline patient information included demographic data, laboratory tests, medications, and comorbid conditions. The independent association of creatinine level with 30-day mortality was examined using multivariate logistic regression analysis. In sensitivity analyses, the associations between creatinine, SOFA score, and mortality were analyzed in patients with or without fluid overload. We also carried out an external validity using the MIMIC dataset. RESULTS: In all 1,600 eICU participants, the 30-day mortality rate was 34.2%. The crude overall mortality rate in the low-creatinine group (44.9%) was significantly higher than that in the high-creatinine group (21.9%; P < 0.001). In the fully adjusted models, the low-creatinine group was associated with a higher risk of 30-day mortality (odds ratio, 1.77; 95% confidence interval, 1.29-2.42; P < 0.001) compared with the high-creatinine group. The low-creatinine group had higher SOFA and nonrenal SOFA scores. In sensitivity analyses, the low-creatinine group had a higher 30-day mortality rate with regard to the BMI or albumin level. Fluid overloaded patients were associated with a significantly worse survival in the low-creatinine group. The results were consistent when assessing the external validity using the MIMIC dataset. CONCLUSIONS: In patients with AKI-D, lower predialysis creatinine was associated with increased mortality risk. Moreover, the mortality rate was substantially higher in patients with lower predialysis creatinine with concomitant elevation of fluid overload status.

Association of Self-Rated Health With Functional Limitations in Patients With CKD.

RATIONALE & OBJECTIVE: In patients with chronic kidney disease (CKD), self-rated health ("In general, how do you rate your health?") is associated with mortality. The association of self-rated health with functional status is unknown. We evaluated the association of limitations in activities of daily living (ADLs) with self-rated health and clinical correlates in a cohort of patients with CKD stages 1-5. STUDY DESIGN: Prospective cohort study. SETTING & PARTICIPANTS: Patients with CKD at a nephrology outpatient clinic in western Pennsylvania. OUTCOME: Patients participated in a survey assessing their self-rated health (5-point Likert scale) and physical (ambulation, dressing, shopping) and cognitive (executive and memory) ADLs. Adjusted analysis was performed using logistic regression models. ANALYTICAL APPROACH: Logistic regression was conducted to examine the adjusted association of 3 dependent variables (sum of total, physical, and cognitive ADL limitations) with self-rated health (independent variable of interest). RESULTS: The survey was completed by 1,268 participants (mean age, 60 years; 49% females, and 74% CKD stages 3-5), of which 41% reported poor-to-fair health. Overall, 35.9% had at least 1 physical ADL limitation, 22.1% had at least 1 cognitive ADL limitation, and 12.5% had at least 3 ADL limitations. Ambulation was the most frequently reported limitation and was more common in patients reporting poor-to-fair self-rated health compared with those with good-to-excellent self-rated health (58.1% vs 17.4%, P < 0.001). In our fully adjusted model, poor-to-fair self-rated health was strongly associated with limitations in at least 3 ADLs (total ADL) [OR 8.29 (95% CI, 5.23-13.12)]. There was no significant association of eGFR with ADL limitations. LIMITATIONS: Selection bias due to optional survey completion, residual confounding, and use of abbreviated (as opposed to full) ADL questionnaires. CONCLUSIONS: Poor-to-fair self-rated health is strongly associated with physical ADL limitations in patients with CKD. Future studies should evaluate whether self-rated health questions may be useful for identifying patients who can benefit from additional evaluation and treatment of functional limitations to improve patient-centered outcomes.