Qureshi, Fawad

Abstract Background Serum chloride derangement is common in critically ill patients requiring continuous renal replacement therapy (CRRT). We aimed to assess the association between serum chloride levels before and during CRRT with mortality. Methods This is a retrospective cohort study of critically ill patients receiving CRRT for acute kidney injury from December 2006 through November 2015 in a tertiary referral hospital in the United States. We used logistic regression to assess serum chloride before and mean serum chloride during CRRT as predictors for 90 days mortality after CRRT initiation. The normal reference range for serum chloride was 99–108 mmol/L. Results Of 1282 eligible patients, 25%, 50%, and 25% had hypochloremia, normochloremia, and hyperchloremia, respectively. The adjusted odds ratio for 90 days mortality in patients with hypochloremia before CRRT was 1.82 (95% CI 1.29–2.55). During CRRT, 4%, 70%, 26% of patients had mean serum chloride in the hypochloremia, normochloremia, and hyperchloremia range, respectively. The adjusted odds ratio for 90 days mortality in patients with mean serum chloride during CRRT in the hypochloremia range was 2.96 (95% CI 1.43–6.12). Hyperchloremia before and during CRRT was not associated with mortality. The greater serum chloride range during CRRT was associated with increased mortality (OR 1.29; 95% CI 1.13–1.47 per 5 mmol/L increase). Conclusion Hypochloremia before and during CRRT is associated with higher mortality.

AbstractIntroductionWe aimed to assess the association between serum potassium and mortality in patients receiving continuous renal replacement therapy (CRRT).MethodsWe studied 1279 acute kidney injury patients receiving CRRT in a tertiary referral hospital in the United States. We used logistic regression to assess the association of serum potassium before CRRT and mean serum potassium during CRRT with 90‐day mortality after CRRT initiation, using serum potassium 4.0–4.4 mmol/L as reference group.ResultsBefore CRRT, there was a U‐shaped association between serum potassium and 90‐day mortality. There was a significant increase in mortality when serum potassium before CRRT was ≤3.4 and ≥4.5 mmol/L. During CRRT, progressively increased mortality was noted when mean serum potassium was ≥4.5 mmol/L. The odds ratio of 90‐day mortality was significantly higher when mean serum potassium was ≥4.5 mmol/L.ConclusionHypokalemia and hyperkalemia before CRRT and hyperkalemia during CRRT predicts 90‐day mortality.

Background: The objectives of this study were to classify patients with serum magnesium derangement on hospital admission into clusters using unsupervised machine learning approach and to evaluate the mortality risks among these distinct clusters. Methods: Consensus cluster analysis was performed based on demographic information, principal diagnoses, comorbidities, and laboratory data in hypomagnesemia (serum magnesium ≤ 1.6 mg/dL) and hypermagnesemia cohorts (serum magnesium ≥ 2.4 mg/dL). Each cluster’s key features were determined using the standardized mean difference. The associations of the clusters with hospital mortality and one-year mortality were assessed. Results: In hypomagnesemia cohort (n = 13,320), consensus cluster analysis identified three clusters. Cluster 1 patients had the highest comorbidity burden and lowest serum magnesium. Cluster 2 patients had the youngest age, lowest comorbidity burden, and highest kidney function. Cluster 3 patients had the oldest age and lowest kidney function. Cluster 1 and cluster 3 were associated with higher hospital and one-year mortality compared to cluster 2. In hypermagnesemia cohort (n = 4671), the analysis identified two clusters. Compared to cluster 1, the key features of cluster 2 included older age, higher comorbidity burden, more hospital admissions primarily due to kidney disease, more acute kidney injury, and lower kidney function. Compared to cluster 1, cluster 2 was associated with higher hospital mortality and one-year mortality. Conclusion: Our cluster analysis identified clinically distinct phenotypes with differing mortality risks in hospitalized patients with dysmagnesemia. Future studies are required to assess the application of this ML consensus clustering approach to care for hospitalized patients with dysmagnesemia.

Background: Lactic acidosis is a heterogeneous condition with multiple underlying causes and associated outcomes. The use of multi-dimensional patient data to subtype lactic acidosis can personalize patient care. Machine learning consensus clustering may identify lactic acidosis subgroups with unique clinical profiles and outcomes. Methods: We used the Medical Information Mart for Intensive Care III database to abstract electronic medical record data from patients admitted to intensive care units (ICU) in a tertiary care hospital in the United States. We included patients who developed lactic acidosis (defined as serum lactate ≥ 4 mmol/L) within 48 h of ICU admission. We performed consensus clustering analysis based on patient characteristics, comorbidities, vital signs, organ supports, and laboratory data to identify clinically distinct lactic acidosis subgroups. We calculated standardized mean differences to show key subgroup features. We compared outcomes among subgroups. Results: We identified 1919 patients with lactic acidosis. The algorithm revealed three best unique lactic acidosis subgroups based on patient variables. Cluster 1 (n = 554) was characterized by old age, elective admission to cardiac surgery ICU, vasopressor use, mechanical ventilation use, and higher pH and serum bicarbonate. Cluster 2 (n = 815) was characterized by young age, admission to trauma/surgical ICU with higher blood pressure, lower comorbidity burden, lower severity index, and less vasopressor use. Cluster 3 (n = 550) was characterized by admission to medical ICU, history of liver disease and coagulopathy, acute kidney injury, lower blood pressure, higher comorbidity burden, higher severity index, higher serum lactate, and lower pH and serum bicarbonate. Cluster 3 had the worst outcomes, while cluster 1 had the most favorable outcomes in terms of persistent lactic acidosis and mortality. Conclusions: Consensus clustering analysis synthesized the pattern of clinical and laboratory data to reveal clinically distinct lactic acidosis subgroups with different outcomes.

Background: Lactic acidosis is the most common cause of anion gap metabolic acidosis in the intensive care unit (ICU), associated with poor outcomes including mortality. We sought to compare machine learning (ML) approaches versus logistic regression analysis for prediction of mortality in lactic acidosis patients admitted to the ICU. Methods: We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify ICU adult patients with lactic acidosis (serum lactate ≥4 mmol/L). The outcome of interest was hospital mortality. We developed prediction models using four ML approaches consisting of random forest (RF), decision tree (DT), extreme gradient boosting (XGBoost), artificial neural network (ANN), and statistical modeling with forward stepwise logistic regression using the testing dataset. We then assessed model performance using area under the receiver operating characteristic curve (AUROC), accuracy, precision, error rate, Matthews correlation coefficient (MCC), F1 score, and assessed model calibration using the Brier score, in the independent testing dataset. Results: Of 1919 lactic acidosis ICU patients, 1535 and 384 were included in the training and testing dataset, respectively. Hospital mortality was 30%. RF had the highest AUROC at 0.83, followed by logistic regression 0.81, XGBoost 0.81, ANN 0.79, and DT 0.71. In addition, RF also had the highest accuracy (0.79), MCC (0.45), F1 score (0.56), and lowest error rate (21.4%). The RF model was the most well-calibrated. The Brier score for RF, DT, XGBoost, ANN, and multivariable logistic regression was 0.15, 0.19, 0.18, 0.19, and 0.16, respectively. The RF model outperformed multivariable logistic regression model, SOFA score (AUROC 0.74), SAP II score (AUROC 0.77), and Charlson score (AUROC 0.69). Conclusion: The ML prediction model using RF algorithm provided the highest predictive performance for hospital mortality among ICU patient with lactic acidosis.

Background: We aimed to cluster patients with acute kidney injury at hospital admission into clinically distinct subtypes using an unsupervised machine learning approach and assess the mortality risk among the distinct clusters. Methods: We performed consensus clustering analysis based on demographic information, principal diagnoses, comorbidities, and laboratory data among 4289 hospitalized adult patients with acute kidney injury at admission. The standardized difference of each variable was calculated to identify each cluster’s key features. We assessed the association of each acute kidney injury cluster with hospital and one-year mortality. Results: Consensus clustering analysis identified four distinct clusters. There were 1201 (28%) patients in cluster 1, 1396 (33%) patients in cluster 2, 1191 (28%) patients in cluster 3, and 501 (12%) patients in cluster 4. Cluster 1 patients were the youngest and had the least comorbidities. Cluster 2 and cluster 3 patients were older and had lower baseline kidney function. Cluster 2 patients had lower serum bicarbonate, strong ion difference, and hemoglobin, but higher serum chloride, whereas cluster 3 patients had lower serum chloride but higher serum bicarbonate and strong ion difference. Cluster 4 patients were younger and more likely to be admitted for genitourinary disease and infectious disease but less likely to be admitted for cardiovascular disease. Cluster 4 patients also had more severe acute kidney injury, lower serum sodium, serum chloride, and serum bicarbonate, but higher serum potassium and anion gap. Cluster 2, 3, and 4 patients had significantly higher hospital and one-year mortality than cluster 1 patients (p < 0.001). Conclusion: Our study demonstrated using machine learning consensus clustering analysis to characterize a heterogeneous cohort of patients with acute kidney injury on hospital admission into four clinically distinct clusters with different associated mortality risks.

AbstractPeritoneal–mediastinal communication is a rare complication of peritoneal dialysis (PD). We report the first case of peritoneal–mediastinal communication complication in a 36‐year‐old Caucasian man on continuous cycler peritoneal dialysis (CCPD) after undergoing cardiac surgery. He developed end‐stage kidney disease (ESKD) due to calcineurin inhibitor nephrotoxicity and BK virus nephropathy in the setting of prior heart transplantation. He was initially started on intermittent hemodialysis (iHD) and was switched to CCPD 1 year later. He presented with increased drainage from his sternal incision site and reduced ultrafiltration. A contrast‐enhanced chest computed tomography scan revealed an anterior chest wall subcutaneous fluid collection. He was found to have a peritoneal–mediastinal communication intraoperatively. He was successfully managed with “low‐volume” PD by using reduced fill volumes for all his exchanges and did not require transition to iHD. He also had no vascular access options because of multiple prior thromboses, which would have made transitioning to iHD not feasible. This case further highlights the complex management of an ESKD patient who cannot do iHD and only do low‐volume PD because of a surgical complication and the need for a multidisciplinary approach to ensure appropriate patient care.

Background: This study aimed to determine the rates of inpatient palliative care service use and assess the impact of palliative care service use on in-hospital treatments and resource utilization in hospital admissions for hepatorenal syndrome. Methods: Using the National Inpatient Sample, hospital admissions with a primary diagnosis of hepatorenal syndrome were identified from 2003 through 2014. The primary outcome of interest was the temporal trend and predictors of inpatient palliative care service use. Logistic and linear regression was performed to assess the impact of inpatient palliative care service on in-hospital treatments and resource use. Results: Of 5571 hospital admissions for hepatorenal syndrome, palliative care services were used in 748 (13.4%) admissions. There was an increasing trend in the rate of palliative care service use, from 3.3% in 2003 to 21.1% in 2014 (p < 0.001). Older age, more recent year of hospitalization, acute liver failure, alcoholic cirrhosis, and hepatocellular carcinoma were predictive of increased palliative care service use, whereas race other than Caucasian, African American, and Hispanic and chronic kidney disease were predictive of decreased palliative care service use. Although hospital admission with palliative care service use had higher mortality, palliative care service was associated with lower use of invasive mechanical ventilation, blood product transfusion, paracentesis, renal replacement, vasopressor but higher DNR status. Palliative care services reduced mean length of hospital stay and hospitalization cost. Conclusion: Although there was a substantial increase in the use of palliative care service in hospitalizations for hepatorenal syndrome, inpatient palliative care service was still underutilized. The use of palliative care service was associated with reduced resource use.