An artificial intelligence approach for predicting death or organ failure after hospitalization for COVID-19: development of a novel risk prediction tool and comparisons with ISARIC-4C, CURB-65, qSOFA, and MEWS scoring systems.

BACKGROUND: We applied machine learning (ML) algorithms to generate a risk prediction tool [Collaboration for Risk Evaluation in COVID-19 (CORE-COVID-19)] for predicting the composite of 30-day endotracheal intubation, intravenous administration of vasopressors, or death after COVID-19 hospitalization and compared it with the existing risk scores. METHODS: This is a retrospective study of adults hospitalized with COVID-19 from March 2020 to February 2021. Patients, each with 92 variables, and one composite outcome underwent feature selection process to identify the most predictive variables. Selected variables were modeled to build four ML algorithms (artificial neural network, support vector machine, gradient boosting machine, and Logistic regression) and an ensemble model to generate a CORE-COVID-19 model to predict the composite outcome and compared with existing risk prediction scores. The net benefit for clinical use of each model was assessed by decision curve analysis. RESULTS: Of 1796 patients, 278 (15%) patients reached primary outcome. Six most predictive features were identified. Four ML algorithms achieved comparable discrimination (P > 0.827) with c-statistics ranged 0.849-0.856, calibration slopes 0.911-1.173, and Hosmer-Lemeshow P > 0.141 in validation dataset. These 6-variable fitted CORE-COVID-19 model revealed a c-statistic of 0.880, which was significantly (P < 0.04) higher than ISARIC-4C (0.751), CURB-65 (0.735), qSOFA (0.676), and MEWS (0.674) for outcome prediction. The net benefit of the CORE-COVID-19 model was greater than that of the existing risk scores. CONCLUSION: The CORE-COVID-19 model accurately assigned 88% of patients who potentially progressed to 30-day composite events and revealed improved performance over existing risk scores, indicating its potential utility in clinical practice.

Real-World Clinical Practice Among Patients With Bipolar Disorder and Chronic Kidney Disease on Long-term Lithium Therapy.

PURPOSE: Long-term lithium therapy (LTLT) has been associated with chronic kidney disease (CKD). We investigated changes in clinical characteristics, pharmacotherapeutic treatments for medical/psychiatric disorders, and outcomes among patients with bipolar disorder (BD) and CKD on LTLT in a 2-year mirror-image study design. METHODS: Adult BD patients on LTLT for ≥1 year who enrolled in the Mayo Clinic Bipolar Disorder Biobank and developed CKD (stage 3) were included, and our study was approved by the Mayo Clinic Institutional Review Board. The primary outcome was the time to the first mood episode after CKD diagnosis among the lithium (Li) continuers and discontinuers. Cox proportional hazards models were used to estimate the time to the first mood episode. We tested for differences in other medication changes between the Li continuers and discontinuers group using Mantel-Haenszel χ2 tests (linear associations). RESULTS: Of 38 BD patients who developed CKD, 18 (47%) discontinued Li, and the remainder continued (n = 20). The median age of the cohort was 56 years (interquartile range [IQR], 48-67 years), 63.2% were female, and 97.4% were White. As compared with continuers, discontinuers had more psychotropic medication trials (6 [IQR, 4-6] vs 3 [IQR, 2-5], P = 0.02), a higher rate of 1 or more mood episodes (61% vs 10%, P = 0.002), and a higher risk of a mood episode after CKD diagnoses (Hazard Ratio, 8.38; 95% confidence interval, 1.85-38.0 [log-rank P = 0.001]]. CONCLUSIONS: Bipolar disorder patients on LTLT who discontinued Li had a higher risk for relapse and a shorter time to the first mood episode, suggesting a need for more thorough discussion before Li discontinuation after the CKD diagnosis.

Digital health utilities in acute kidney injury management.

PURPOSE OF REVIEW: Acute kidney injury (AKI) is a highly prevalent clinical syndrome that substantially impacts patient outcomes. It is accepted by the clinical communities that the management of AKI is time-sensitive. Unfortunately, despite growing proof of its preventability, AKI management remains suboptimal in community, acute care, and postacute care settings. Digital health solutions comprise various tools and models to improve care processes and patient outcomes in multiple medical fields. AKI development, progression, recovery, or lack thereof, offers tremendous opportunities for developing, validating, and implementing digital health solutions in multiple settings. This article will review the definitions and components of digital health, the characteristics of AKI that allow digital health solutions to be considered, and the opportunities and threats in implementing these solutions. RECENT FINDINGS: Over the past two decades, the academic output related to the use of digital health solutions in AKI has exponentially grown. While this indicates the growing interest in the topic, most topics are primarily related to clinical decision support by detecting AKI within hospitals or using artificial intelligence or machine learning technologies to predict AKI within acute care settings. However, recently, projects to assess the impact of digital health solutions in more complex scenarios, for example, managing nephrotoxins among adults of pediatric patients who already have AKI, is increasing. Depending on the type of patients, chosen digital health solution intervention, comparator groups, and selected outcomes, some of these studies showed benefits, while some did not indicate additional gain in care processes or clinical outcomes. SUMMARY: Careful needs assessment, selection of the correct digital health solution, and appropriate clinical validation of the benefits while avoiding additional health disparities are moral, professional, and ethical obligations for all individuals using these healthcare tools, including clinicians, data scientists, and administrators.

Moving toward a contemporary classification of drug-induced kidney disease.

Drug-induced kidney disease (DIKD) accounts for about one-fourth of all cases of acute kidney injury (AKI) in hospitalized patients, especially in critically ill setting. There is no standard definition or classification system of DIKD. To address this, a phenotype definition of DIKD using expert consensus was introduced in 2015. Recently, a novel framework for DIKD classification was proposed that incorporated functional change and tissue damage biomarkers. Medications were stratified into four categories, including "dysfunction without damage," "damage without dysfunction," "both dysfunction and damage," and "neither dysfunction nor damage" using this novel framework along with predominant mechanism(s) of nephrotoxicity for drugs and drug classes. Here, we briefly describe mechanisms and provide examples of drugs/drug classes related to the categories in the proposed framework. In addition, the possible movement of a patient's kidney disease between certain categories in specific conditions is considered. Finally, opportunities and barriers to adoption of this framework for DIKD classification in real clinical practice are discussed. This new classification system allows congruencies for DIKD with the proposed categorization of AKI, offering clarity as well as consistency for clinicians and researchers.

Body temperature and infection in critically ill patients on continuous kidney replacement therapy.

PURPOSE: Continuous kidney replacement therapy (CKRT) is an increasingly common intervention for critically ill patients with kidney failure. Because CKRT affects body temperature, detecting infections in patients on CKRT is challenging. Understanding the relation between CKRT and body temperature may facilitate earlier detection of infection. METHODS: We retrospectively reviewed adult patients (≥ 18 years) admitted to the intensive care unit at Mayo Clinic in Rochester, Minnesota, from December 1, 2006, through November 31, 2015, who required CKRT. We summarized central body temperatures for these patients according to the presence or absence of infection. RESULTS: We identified 587 patients who underwent CKRT during the study period, of whom 365 had infections, and 222 did not have infections. We observed no statistically significant differences in minimum (P = .70), maximum (P = .22), or mean (P = .55) central body temperature for patients on CKRT with infection vs. those without infection. While not on CKRT (before CKRT initiation and after cessation), all three body temperature measurements were significantly higher in patients with infection than in those without infection (all P < .02). CONCLUSION: Body temperature is insufficient to indicate an infection in critically ill patients on CKRT. Clinicians should remain watchful for other signs, symptoms, and indications of infection in patients on CKRT because of expected high infection rates.

Forecasting imminent atrial fibrillation in long-term electrocardiogram recordings.

BACKGROUND: Despite the morbidity associated with acute atrial fibrillation (AF), no models currently exist to forecast its imminent onset. We sought to evaluate the ability of deep learning to forecast the imminent onset of AF with sufficient lead time, which has important implications for inpatient care. METHODS: We utilized the Physiobank Long-Term AF Database, which contains 24-h, labeled ECG recordings from patients with a history of AF. AF episodes were defined as ≥5 min of sustained AF. Three deep learning models incorporating convolutional and transformer layers were created for forecasting, with two models focusing on the predictive nature of sinus rhythm segments and AF epochs separately preceding an AF episode, and one model utilizing all preceding waveform as input. Cross-validated performance was evaluated using area under time-dependent receiver operating characteristic curves (AUC(t)) at 7.5-, 15-, 30-, and 60-min lead times, precision-recall curves, and imminent AF risk trajectories. RESULTS: There were 367 AF episodes from 84 ECG recordings. All models showed average risk trajectory divergence of those with an AF episode from those without ∼15 min before the episode. Highest AUC was associated with the sinus rhythm model [AUC = 0.74; 7.5-min lead time], though the model using all preceding waveform data had similar performance and higher AUCs at longer lead times. CONCLUSIONS: In this proof-of-concept study, we demonstrated the potential utility of neural networks to forecast the onset of AF in long-term ECG recordings with a clinically relevant lead time. External validation in larger cohorts is required before deploying these models clinically.

Discrepancy between perceptions and acceptance of clinical decision support Systems: implementation of artificial intelligence for vancomycin dosing.

BACKGROUND: Artificial intelligence (AI) tools are more effective if accepted by clinicians. We developed an AI-based clinical decision support system (CDSS) to facilitate vancomycin dosing. This qualitative study assesses clinicians' perceptions regarding CDSS implementation. METHODS: Thirteen semi-structured interviews were conducted with critical care pharmacists, at Mayo Clinic (Rochester, MN), from March through April 2020. Eight clinical cases were discussed with each pharmacist (N = 104). Following initial responses, we revealed the CDSS recommendations to assess participants' reactions and feedback. Interviews were audio-recorded, transcribed, and summarized. RESULTS: The participants reported considerable time and effort invested daily in individualizing vancomycin therapy for hospitalized patients. Most pharmacists agreed that such a CDSS could favorably affect (N = 8, 62%) or enhance (9, 69%) their ability to make vancomycin dosing decisions. In case-based evaluations, pharmacists' empiric doses differed from the CDSS recommendation in most cases (88/104, 85%). Following revealing the CDSS recommendations, we noted 78% (69/88) discrepant doses. In discrepant cases, pharmacists indicated they would not alter their recommendations. The reasons for declining the CDSS recommendation were general distrust of CDSS, lack of dynamic evaluation and in-depth analysis, inability to integrate all clinical data, and lack of a risk index. CONCLUSION: While pharmacists acknowledged enthusiasm about the advantages of AI-based models to improve drug dosing, they were reluctant to integrate the tool into clinical practice. Additional research is necessary to determine the optimal approach to implementing CDSS at the point of care acceptable to clinicians and effective at improving patient outcomes.

Pharmacist-provider collaborative visits after hospital discharge in a comprehensive acute kidney injury survivor model.

BACKGROUND: Postdischarge follow-up in primary care is an opportunity for pharmacists to re-evaluate medication use in acute kidney injury (AKI) survivors. Of the emerging AKI survivor care models described in literature, only one involved a pharmacist with limited detail about the direct impact. OBJECTIVE: This study aimed to describe pharmacist contributions to a comprehensive postdischarge AKI survivorship program in primary care (the AKI in Care Transitions [ACT] program). METHODS: The ACT program was piloted from May to December of 2021 at Mayo Clinic as a bundled care strategy for patients who survived an episode of AKI and were discharged home without the need for hemodialysis. Patients received education and care coordination from nurses before discharge and later completed postdischarge laboratory assessment and clinician follow-up in primary care. During the follow-up encounter, patients completed a 30-minute comprehensive medication management visit with a pharmacist focusing on AKI survivorship considerations. Medication therapy recommendations were communicated to a collaborating primary care provider (PCP) before a separate 30-minute visit with the patient. PCPs had access to clinical decision support with evidence-based post-AKI care recommendations. Medication-related issues were summarized descriptively. RESULTS: Pharmacists made 28 medication therapy recommendations (median 3 per patient, interquartile range 2-3) and identified 14 medication discrepancies for the 11 patients who completed the pilot program, and 86% of the medication therapy recommendations were acted on by the PCP within 7 days. Six recommendations were made to initiate renoprotective medications, and 5 were acted on (83%). CONCLUSION: During the pilot phase of a multifaceted transitional care program for AKI survivors, pharmacists' successfully identified and addressed multiple medication therapy problems, including for renally active drugs. These results demonstrate the potential for pharmacist-provider collaborative visits in primary care to improve safe and effective medication use in AKI survivors.

Treatment Effect of Percutaneous Coronary Intervention in Dialysis Patients With ST-Elevation Myocardial Infarction.

RATIONALE & OBJECTIVE: Patients receiving maintenance dialysis have higher mortality after primary percutaneous coronary intervention (pPCI) than patients not receiving dialysis. Whether pPCI confers a benefit to patients receiving dialysis that is similar to that which occurs in lower-risk groups remains unknown. We compared the effect of pPCI on in-hospital outcomes among patients hospitalized for ST-elevation myocardial infarction (STEMI) and receiving maintenance dialysis with the effect among patients hospitalized for STEMI but not receiving dialysis. STUDY DESIGN: Retrospective cohort study. SETTING & PARTICIPANTS: We used the National Inpatient Sample (2016-2018) and included all adult hospitalizations with a primary diagnosis of STEMI. PREDICTORS: Primary exposure was PCI. Confounders included dialysis status, demographics, insurance, household income, comorbidities, and the elective nature of the admission. OUTCOME: In-hospital mortality, stroke, acute kidney injury, new dialysis requirement, vascular complications, gastrointestinal bleeding, blood transfusion, mechanical ventilation, palliative care, and discharge destination. ANALYTICAL APPROACH: The average treatment effect (ATE) of pPCI was estimated using propensity score matching independently within the group receiving dialysis and the group not receiving dialysis to explore whether the effect is modified by dialysis status. Additionally, the average marginal effect (AME) was calculated accounting for the clustering within hospitals. RESULTS: Among hospitalizations, 4,220 (1.07%) out of 413,500 were for patients receiving dialysis. The dialysis cohort was older (65.2 ± 12.2 vs 63.4 ± 13.1, P < 0.001), had a higher proportion of women (42.4% vs 30.6%, P < 0.001) and more comorbidities, and had a lower proportion of White patients (41.1% vs 71.7%, P < 0.001). Patients receiving dialysis were less likely to undergo angiography (73.1% vs 85.4%, P < 0.001) or pPCI (57.5% vs 79.8%, P < 0.001). Primary PCI was associated with lower mortality in patients receiving dialysis (15.7% vs 27.1%, P < 0.001) as well as in those who were not (5.0% vs 17.4%, P < 0.001). The ATE on mortality did not differ significantly (P interaction = 0.9) between patients receiving dialysis (-8.6% [95% CI, -15.6% to -1.6%], P = 0.02) and those who were not (-8.2% [95% CI, -8.8% to -7.5%], P < 0.001). The AME method showed similar results among patients receiving dialysis (-9.4% [95% CI, -14.8% to -4.0%], P < 0.001) and those who were not (-7.9% [95% CI, -8.5% to -7.4%], P < 0.001) (P interaction = 0.6). Both the ATE and AME were comparable for other in-hospital outcomes in both groups. LIMITATIONS: Administrative data, lack of pharmacotherapy and long-term outcome data, and residual confounding. CONCLUSIONS: Compared with conservative management, pPCI for STEMI was associated with comparable reductions in short-term mortality among patients irrespective of their receipt of maintenance dialysis.

Nephrotoxin Exposure in the 3 Years following Hospital Discharge Predicts Development or Worsening of Chronic Kidney Disease among Acute Kidney Injury Survivors.

INTRODUCTION: Survivors of acute kidney injury (AKI) are at high risk of progression to chronic kidney disease (CKD), for which drugs may be a modifiable risk factor. METHODS: We conducted a population-based cohort study of Olmsted County, MN residents who developed AKI while hospitalized between January 1, 2006, and December 31, 2014, using Rochester Epidemiology Project data. Adults with a hospitalization complicated by AKI who survived at least 90 days after AKI development were included. Medical records were queried for prescription of potentially nephrotoxic medications over the 3 years after discharge. The primary outcome was de novo or progressive CKD defined by either a new diagnosis code for CKD or ≥30% decline in estimated glomerular filtration rate from baseline. The composite of CKD, AKI readmission, or death was also evaluated. RESULTS: Among 2,461 AKI survivors, 2,140 (87%) received a potentially nephrotoxic medication during the 3 years following discharge. When nephrotoxic medication use was analyzed in a time-dependent fashion, those actively prescribed at least one of these drugs experienced a significantly higher risk of de novo or progressive CKD (HR 1.38: 95% CI: 1.24, 1.54). Similarly, active potentially nephrotoxic medication use predicted a greater risk of the composite endpoint of CKD, AKI readmission, or death within 3 years of discharge (HR 1.41: 95% CI: 1.28, 1.56). CONCLUSION: In this population-based cohort study, AKI survivors actively prescribed one or more potentially nephrotoxic medications were at significantly greater risk for de novo or progressive CKD. An opportunity exists to reassess nephrotoxin appropriateness following an AKI episode to improve patient outcomes.

Validation of cardiogenic shock phenotypes in a mixed cardiac intensive care unit population.

BACKGROUND: Proposed phenotypes have recently been identified in cardiogenic shock (CS) populations using unsupervised machine learning clustering methods. We sought to validate these phenotypes in a mixed cardiac intensive care unit (CICU) population of patients with CS. METHODS: We included Mayo Clinic CICU patients admitted from 2007 to 2018 with CS. Agnostic K means clustering was used to assign patients to three clusters based on admission values of estimated glomerular filtration rate, bicarbonate, alanine aminotransferase, lactate, platelets, and white blood cell count. In-hospital mortality and 1-year mortality were analyzed using logistic regression and Cox proportional-hazards models, respectively. RESULTS: We included 1498 CS patients with a mean age of 67.8 ± 13.9 years, and 37.1% were females. The acute coronary syndrome was present in 57.3%, and cardiac arrest was present in 34.0%. Patients were assigned to clusters as follows: Cluster 1 (noncongested), 603 (40.2%); Cluster 2 (cardiorenal), 452 (30.2%); and Cluster 3 (hemometabolic), 443 (29.6%). Clinical, laboratory, and echocardiographic characteristics differed across clusters, with the greatest illness severity in Cluster 3. Cluster assignment was associated with in-hospital mortality across subgroups. In-hospital mortality was higher in Cluster 3 (adjusted odds ratio [OR]: 2.6 vs. Cluster 1 and adjusted OR: 2.0 vs. Cluster 2, both p < 0.001). Adjusted 1-year mortality was incrementally higher in Cluster 3 versus Cluster 2 versus Cluster 1 (all p < 0.01). CONCLUSIONS: We observed similar phenotypes in CICU patients with CS as previously reported, identifying a gradient in both in-hospital and 1-year mortality by cluster. Identifying these clinical phenotypes can improve mortality risk stratification for CS patients beyond standard measures.

Associations of Vasopressor Requirements With Echocardiographic Parameters After Out-of-Hospital Cardiac Arrest.

BACKGROUND: Post-arrest hypotension is common after out of hospital cardiac arrest (OHCA) and many patients resuscitated after OHCA will require vasopressors. We sought to determine the associations between echocardiographic parameters and vasopressor requirements in OHCA patients. METHODS: We retrospectively analyzed adult patients with OHCA treated with targeted temperature management between December 2005 and September 2016 who underwent a transthoracic echocardiogram (TTE). Categorical variables were compared using 2-tailed Fisher's exact and Pearson's correlation coefficients and variance (r2) values were used to assess relationships between continuous variables. RESULTS: Among 217 included patients, the mean age was 62 ± 12 years, including 74% males. The arrest was witnessed in 90%, the initial rhythm was shockable in 88%, and 58% received bystander CPR. At the time of TTE, 41% of patients were receiving vasopressors; this group of patients was older, had greater severity of illness, higher inpatient mortality and left ventricular ejection fraction (LVEF) was modestly lower (36.8 ± 17.1% vs. 41.4 ± 16.4%, P = 0.04). Stroke volume, cardiac power output and left ventricular stroke work index correlated with number of vasopressors (Pearson r -0.24 to -0.34, all P < 0.002), but the correlation with LVEF was weak (Pearson r -0.13, P = 0.06). CONCLUSIONS: In patients after OHCA, left ventricular systolic dysfunction was associated with the need for vasopressors, and Doppler TTE hemodynamic parameters had higher correlation coefficients compared with vasopressor requirements than LVEF. This emphasizes the complex nature of shock after OHCA, including pathophysiologic processes not captured by TTE assessment alone.

Trends in Therapy and Outcomes Associated With Respiratory Failure in Patients Admitted to the Cardiac Intensive Care Unit.

PURPOSE: To describe the epidemiology, outcomes, and temporal trends of respiratory failure in the cardiac intensive care unit (CICU). MATERIALS AND METHODS: Retrospective cohort analysis of 2,986 unique Mayo Clinic CICU patients from 2007 to 2018 with respiratory failure. Temporal trends were analyzed, along with hospital and 1-year mortality. Multivariable logistic regression was used to determine adjusted hospital mortality trends. RESULTS: The prevalence of respiratory failure in the CICU increased from 15% to 38% during the study period (P < 0.001 for trend). Among patients with respiratory failure, the utilization of invasive ventilation decreased and noninvasive ventilation modalities increased over time. Hospital mortality and 1-year mortality were 24% and 54%, respectively, with variation according to the type of respiratory support (highest among patients receiving invasive ventilation alone: 35% and 46%, respectively). Hospital mortality was highest among patients with concomitant cardiac arrest and/or shock (52% for patients with both). Hospital mortality decreased in the overall population from 35% to 25% (P < 0.001 for trend), but was unchanged among patients receiving positive-pressure ventilation. CONCLUSIONS: The prevalence of respiratory failure in CICU more than doubled during the last decade. The use of noninvasive respiratory support increased, while overall mortality declined over time. Cardiac arrest and shock accounted for the majority of deaths. Further research is needed to optimize the outcomes of high-risk CICU patients with respiratory failure.

In adults with hypertension, more- vs. less-intensive BP-lowering treatment reduces orthostatic hypotension.

SOURCE CITATION: Juraschek SP, Hu JR, Cluett JL, et al. Effects of intensive blood pressure treatment on orthostatic hypotension: a systematic review and individual participant-based meta-analysis. Ann Intern Med. 2020. [Epub ahead of print.] 32909814.

Simultaneous Use of Hypertonic Saline and IV Furosemide for Fluid Overload: A Systematic Review and Meta-Analysis.

OBJECTIVES: To evaluate the efficacy of the simultaneous hypertonic saline solution and IV furosemide (HSS+Fx) for patients with fluid overload compared with IV furosemide alone (Fx). DATA SOURCES: Electronic databases (MEDLINE, EMBASE, CENTRAL, Cochrane Database of Systematic Reviews, PsycINFO, Scopus, and WOS) were searched from inception to March 2020. STUDY SELECTION: Randomized controlled trials on the use of HSS+Fx in adult patients with fluid overload versus Fx were included. DATA EXTRACTION: Data were collected on all-cause mortality, hospital length of stay, heart failure-related readmission, along with inpatient weight loss, change of daily diuresis, serum creatinine, and 24-hour urine sodium excretion from prior to post intervention. Pooled analysis with random effects models yielded relative risk or mean difference with 95% CIs. DATA SYNTHESIS: Eleven randomized controlled trials comprising 2,987 acute decompensated heart failure patients were included. Meta-analysis demonstrated that HSS+Fx was associated with lower all-cause mortality (relative risk, 0.55; 95% CI, 0.46-0.67; p < 0.05; I2 = 12%) and heart failure-related readmissions (relative risk, 0.50; 95% CI, 0.33-0.76; p < 0.05; I2 = 61%), shorter hospital length of stay (mean difference, -3.28 d; 95% CI, -4.14 to -2.43; p < 0.05; I2 = 93%), increased daily diuresis (mean difference, 583.87 mL; 95% CI, 504.92-662.81; p < 0.05; I2 = 76%), weight loss (mean difference, -1.76 kg; 95% CI, -2.52 to -1.00; p < 0.05; I2 = 57%), serum sodium change (mean difference, 6.89 mEq/L; 95% CI, 4.98-8.79; p < 0.05; I2 = 95%), and higher 24-hour urine sodium excretion (mean difference, 61.10 mEq; 95% CI, 51.47-70.73; p < 0.05; I2 = 95%), along with decreased serum creatinine (mean difference, -0.46 mg/dL; 95% CI, -0.51 to -0.41; p < 0.05; I2 = 89%) when compared with Fx. The Grading of Recommendation, Assessment, Development, and Evaluation certainty of evidence ranged from low to moderate. CONCLUSIONS: Benefits of the HSS+Fx over Fx were observed across all examined outcomes in acute decompensated heart failure patients with fluid overload. There is at least moderate certainty that HSS+Fx is associated with a reduction in mortality in patients with acute decompensated heart failure. Factors associated with a successful HSS+Fx utilization are still unknown. Current evidence cannot be extrapolated to other than fluid overload states in acute decompensated heart failure.

Incidence of Serum Creatinine Monitoring and Outpatient Visit Follow-Up among Acute Kidney Injury Survivors after Discharge: A Population-Based Cohort Study.

INTRODUCTION: Acute kidney injury (AKI) affects 20% of hospitalized patients and worsens outcomes. To limit complications, post-discharge follow-up and kidney function testing are advised. The objective of this study was to evaluate the frequency of follow-up after discharge among AKI survivors. METHODS: This was a population-based cohort study of adult Olmsted County residents hospitalized with an episode of stage II or III AKI between 2006 and 2014. Those dismissed from the hospital on dialysis, hospice, or who died within 30 days after discharge were excluded. The frequency and predictors of follow-up, defined as an outpatient serum creatinine (SCr) level or an in-person healthcare visit after discharge were described. RESULTS: In the 627 included AKI survivors, the 30-day cumulative incidence of a follow-up outpatient SCr was 80% (95% confidence interval [CI]: 76% and 83%), a healthcare visit was 82% (95% CI: 79 and 85%), or both was 70% (95% CI: 66 and 73%). At 90 days and 1 year after discharge, the cumulative incidences of meeting both follow-up criteria rose to 82 and 91%, respectively. Independent predictors of receiving both an outpatient SCr assessment and healthcare visit within 30 days included lower estimated glomerular filtration rate at discharge, higher comorbidity burden, longer length of hospitalization, and greater maximum AKI severity. Age, sex, race/ethnicity, education level, and socioeconomic status did not predict follow-up. CONCLUSIONS: Among patients with moderate to severe AKI, 30% did not have follow-up with a SCr and healthcare visit in the 30-day post-discharge interval. Follow-up was associated with higher acuity of illness rather than demographic or socioeconomic factors.

Long-term lithium therapy and risk of chronic kidney disease in bipolar disorder: A historical cohort study.

AIMS: Long-term lithium therapy (LTLT) has been associated with kidney insufficiency in bipolar disorder (BD). We aimed to investigate the risk factors of chronic kidney disease (CKD) development and progression among BD patients receiving LTLT. METHODS: We included adult patients with BD on LTLT (≥1 year) who were enrolled in the Mayo Clinic Bipolar Biobank, Rochester, Minnesota. We reviewed electronic medical records to extract information related to lithium therapy and kidney-related data to assess changes in the estimated glomerular filtration rate (eGFR). CKD severity was assessed based on eGFR. RESULTS: Among 154 patients who received LTLT, 41 patients (27%) developed CKD, of whom 20 (49%) patients continued lithium (continuers) and 19 (46%) discontinued it (discontinuers). The median time to stage 3 CKD development was 21.7 years from the start of Li treatment. Type-2 diabetes mellitus and benzodiazepine use were independent predictors for CKD development in the survival analysis, after controlling for age. The subsequent CKD progression rate did not differ between continuers and discontinuers (mean GFR 48.6 vs. 44.1, p = 0.13) at the end of follow-up duration (mean duration: 3.5 ± 4.4 years for continuers and 4.9 ± 5.3 years for discontinuers). CONCLUSION: CKD was observed in one fourth of patients with BD receiving LTLT. There was no significant difference in the progression of CKD among Li continuers versus discontinuers, at the mean follow-up duration of 4.2 years, after the CKD diagnosis. Progression of CKD could be influenced by existing comorbidities and may not necessarily be due to lithium alone.

Subtyping Hyperchloremia among Hospitalized Patients by Machine Learning Consensus Clustering.

Background and Objectives: Despite the association between hyperchloremia and adverse outcomes, mortality risks among patients with hyperchloremia have not consistently been observed among all studies with different patient populations with hyperchloremia. The objective of this study was to characterize hyperchloremic patients at hospital admission into clusters using an unsupervised machine learning approach and to evaluate the mortality risk among these distinct clusters. Materials and Methods: We performed consensus cluster analysis based on demographic information, principal diagnoses, comorbidities, and laboratory data among 11,394 hospitalized adult patients with admission serum chloride of >108 mEq/L. We calculated the standardized mean difference of each variable to identify each cluster's key features. We assessed the association of each hyperchloremia cluster with hospital and one-year mortality. Results: There were three distinct clusters of patients with admission hyperchloremia: 3237 (28%), 4059 (36%), and 4098 (36%) patients in clusters 1 through 3, respectively. Cluster 1 was characterized by higher serum chloride but lower serum sodium, bicarbonate, hemoglobin, and albumin. Cluster 2 was characterized by younger age, lower comorbidity score, lower serum chloride, and higher estimated glomerular filtration (eGFR), hemoglobin, and albumin. Cluster 3 was characterized by older age, higher comorbidity score, higher serum sodium, potassium, and lower eGFR. Compared with cluster 2, odds ratios for hospital mortality were 3.60 (95% CI 2.33-5.56) for cluster 1, and 4.83 (95% CI 3.21-7.28) for cluster 3, whereas hazard ratios for one-year mortality were 4.49 (95% CI 3.53-5.70) for cluster 1 and 6.96 (95% CI 5.56-8.72) for cluster 3. Conclusions: Our cluster analysis identified three clinically distinct phenotypes with differing mortality risks in hospitalized patients with admission hyperchloremia.

Prediction of Vancomycin Levels Using Cystatin C in Overweight and Obese Patients: a Retrospective Cohort Study of Hospitalized Patients.

The use of the kidney function biomarker cystatin C (cysC) can improve the accuracy of vancomycin dosing for target trough attainment in nonobese patients. It is unknown whether cysC can also improve vancomycin target trough attainment in overweight and obese patients. We conducted a retrospective observational study of overweight or obese hospitalized adults with stable renal function administered intravenous vancomycin between January 2011 and July 2019. Linear regression models were used to predict initial steady-state vancomycin troughs using several factors, including various cysC- and serum creatinine (SCr)-based estimates of kidney function. We compared the predicted proportion of patients within the target trough range (10 to 20 mg/liter) using the derived models to that observed from usual care. Of the 200 included patients, the mean trough level was 15 ± 6.3 mg/liter. The optimal model to predict the initial trough included both cysC and SCr (R2 = 0.48) rather than either biomarker alone. This model predicted that 79% (95% confidence interval [CI], 73% to 85%) of troughs could be between 10 and 20 mg/liter compared to the 62% observed in clinical practice (P < 0.001), a 1.3-fold increase. This study is the first to examine the role of cysC in predicting vancomycin levels in an exclusively overweight or obese population. While dosing models based on cysC appear promising in this setting, prospective validation is needed.

Neuropathology of COVID-19: a spectrum of vascular and acute disseminated encephalomyelitis (ADEM)-like pathology.

We report the neuropathological findings of a patient who died from complications of COVID-19. The decedent was initially hospitalized for surgical management of underlying coronary artery disease. He developed post-operative complications and was evaluated with chest imaging studies. The chest computed tomography (CT) imaging results were indicative of COVID-19 and he was subsequently tested for SARS-CoV-2, which was positive. His condition worsened and he died after more than 2 weeks of hospitalization and aggressive treatment. The autopsy revealed a range of neuropathological lesions, with features resembling both vascular and demyelinating etiologies. Hemorrhagic white matter lesions were present throughout the cerebral hemispheres with surrounding axonal injury and macrophages. The subcortical white matter had scattered clusters of macrophages, a range of associated axonal injury, and a perivascular acute disseminated encephalomyelitis (ADEM)-like appearance. Additional white matter lesions included focal microscopic areas of necrosis with central loss of white matter and marked axonal injury. Rare neocortical organizing microscopic infarcts were also identified. Imaging and clinical reports have demonstrated central nervous system complications in patients' with COVID-19, but there is a gap in our understanding of the neuropathology. The lesions described in this case provide insight into the potential parainfectious processes affecting COVID-19 patients, which may direct clinical management and ongoing research into the disease. The clinical course of the patient also illustrates that during prolonged hospitalizations neurological complications of COVID may develop, which are particularly difficult to evaluate and appreciate in the critically ill.