Search

Purpose: Coronavirus disease–2019 (COVID-19) continues to be a global threat and remains a significant cause of hospitalizations. Recent clinical guidelines have supported the use of corticosteroids or remdesivir in the treatment of COVID-19. However, uncertainty remains about which patients are most likely to benefit from treatment with either drug; such knowledge is crucial for avoiding preventable adverse effects, minimizing costs, and effectively allocating resources. This study presents a machine-learning system with the capacity to identify patients in whom treatment with a corticosteroid or remdesivir is associated with improved survival time. Methods: Gradient-boosted decision-tree models used for predicting treatment benefit were trained and tested on data from electronic health records dated between December 18, 2019, and October 18, 2020, from adult patients (age ≥18 years) with COVID-19 in 10 US hospitals. Models were evaluated for performance in identifying patients with longer survival times when treated with a corticosteroid versus remdesivir. Fine and Gray proportional-hazards models were used for identifying significant findings in treated and nontreated patients, in a subset of patients who received supplemental oxygen, and in patients identified by the algorithm. Inverse probability-of-treatment weights were used to adjust for confounding. Models were trained and tested separately for each treatment. Findings: Data from 2364 patients were included, with men comprising slightly more than 50% of the sample; 893 patients were treated with remdesivir, and 1471 were treated with a corticosteroid. After adjustment for confounding, neither corticosteroids nor remdesivir use was associated with increased survival time in the overall population or in the subpopulation that received supplemental oxygen. However, in the populations identified by the algorithms, both corticosteroids and remdesivir were significantly associated with an increase in survival time, with hazard ratios of 0.56 and 0.40, respectively (both, P = 0.04). Implications: Machine-learning methods have the capacity to identify hospitalized patients with COVID-19 in whom treatment with a corticosteroid or remdesivir is associated with an increase in survival time. These methods may help to improve patient outcomes and allocate resources during the COVID-19 crisis., SCOPUS: ar.j, info:eu-repo/semantics/published

Background Immune checkpoint inhibitors and mitogen-activated protein kinase inhibitors have become the standard of care in patients with advanced melanoma bearing V600 mutations. However, little is known about their nephrotoxicity. To date, only two cases of anti-glomerular basement membrane glomerulonephritis after exposure to checkpoint inhibitors have been documented. Herein, we report the first case of a patient with metastatic melanoma who developed linear Immunoglobulin G 3+, Immunoglobulin A 2+, kappa 2+, lambda 1+ anti-glomerular basement membrane glomerulonephritis with negative serology following treatment with checkpoint inhibitors and subsequently mitogen-activated protein kinase inhibitors. Case presentation A 58-year-old Caucasian male was referred to our outpatient nephrology clinic with acute kidney injury and proteinuria. He had received three cycles of ipilimumab and nivolumab for recurrent melanoma positive for the BRAF V600E mutation with metastasis to the lungs. Immunotherapy had been discontinued in the setting of severe adverse effects including dermatitis, colitis, and hepatitis. Because of persistent bilateral lung metastases and left pleural metastases, the patient had been initiated on dabrafenib and trametinib until his presentation to our clinic 6 months later. On presentation, his blood pressure was 172/89 mm/Hg and had 2+ edema bilaterally. His creatinine level was 2.4 mg/dL from a previous normal baseline with a urinary protein-to-creatinine ratio of 2 g/g. His urinalysis showed dysmorphic erythrocytes and red blood cell casts. Serologic testing was negative for antineutrophilic cytoplasmic antibodies, proteinase 3 antigen, myeloperoxidase, and anti-glomerular basement membrane antibody. Complement levels were normal. A renal biopsy showed focal crescentic (2 of 15 glomeruli with cellular crescents), proliferative, and sclerosing glomerulonephritis with diffuse linear staining of glomerular capillary loops dominant for IgG (3+), IgA (2+), kappa (2+), and lambda (1+) minimal changes. He was initiated on oral cyclophosphamide and pulse intravenous methylprednisolone followed by oral prednisone for 6 months, which stabilized his renal function until reinitiation of immunotherapy. Conclusions Acute kidney injury is an increasingly reported adverse effect of both drug classes, mostly affecting the tubulointerstitial compartment and infrequently the glomerulus. Although the biologic effect of these drugs on immune cells is not entirely understood, it is possible that BRAF-induced podocyte injury in combination with direct T-cell-mediated glomerular injury facilitated by checkpoint inhibitors led to the unmasking of cryptic antigens, loss of self-tolerance, and autoimmunity. More importantly, we show that treatment with corticosteroids and cyclophosphamide was able to improve and stabilize our patient’s renal function until the reinitiation of immunotherapy.

The objective of this review article was to identify and examine current evidence surrounding the potential renoprotective effects of newer antidiabetic agents such as sodium-glucose cotransporter 2 (SGLT-2) inhibitors, glucose-like peptide 1 (GLP-1) agonists, and dipeptidyl peptidase 4 (DPP-4) inhibitors. A literature search of MEDLINE and PubMed (January 2000 to April 2019) was performed using the following search terms: “diabetes treatment,” “renoprotection,” “kidneys,” “SGLT-2 inhibitors,” “GLP-1 receptor agonists,” “DPP-4 inhibitors,” and the drug names in each of those classes as well as any combination of these terms. Literature was excluded if published in a language other than English, performed in nonhuman subjects, did not include patients from the United States, was nonrandomized, or the data were available from poster presentations. There were 11 studies that met the search criteria. The majority of the studies focused on renal outcomes as secondary end points and looked at albuminuria, estimated glomerular filtration rate changes from baseline, urinary albumin-to-creatinine ratio, serum creatinine, and need for renal replacement therapy. There are fewer studies that focused on renal protection as a primary end point. After reviewing the available literature, the use of SGLT-2 inhibitors and GLP-1 agonists in addition to standard of care may be considered in patients with or at risk of developing chronic kidney disease. SGLT-2 inhibitors and GLP-1 agonists should be considered when patients’ diabetes is no longer well controlled with metformin. Other factors such as cost, cardiovascular disease, and other comorbidities may also be taken into consideration when recommending therapy for patients.

Introduction: To date, the effects of hyperkalemia (HK) on the ECG in chronic hemodialysis (HD) patients are inconsistent. No studies examining all of the possible effects of HK on the ECG of HD patients have been performed. We studied the ECGs of 128 consecutive HD patients with acutely clotted grafts or fistulas. ECGs from 46 HK patients with potassium levels ≥5.5 mEq/L were compared to 82 patients with normal potassium (NK) levels < 5.5 mEq/L. Methods: Patients with bundle branch block or cardiac events within 3 months were excluded. There were no differences between HK & NK patients for dialysis duration, causes of ESRD, cardiac disease or serum levels of Na + , Ca 2+ , HCO3, or phosphorus. ECG analysis included: height & width of P waves, T waves in V4 & Lead II, time intervals of PR, QRS, QT, QTc, PR/QT, PR/QTc & slopes of ascending & descending T waves in Lead II & V4. For the first time ever in HK HD patients, the ECG measurements in 32 HK patients were compared to their own NK ECGs obtained 3 to 6 months from the HK event. Results: Univariate analysis between the 46 HK & 82 NK patients showed 4 differences in mean values: V4 T wave height 4.0 vs 2.9mm, Lead II T wave height 2.7 vs. 2.0 mm, & V4 T wave ascending (.03 vs .02) & descending slopes (.04 vs .03). Multivariate analysis for all clinical & ECG findings between HK & NK patients found only the increased height of the T wave in V4 was significant, p Conclusion: Intra-patient comparison of baseline NK to HK ECGs in HD patients confirms the importance of the height of the T wave in Lead V4 to diagnose HK. Shortened width and increased height of T waves in V4 are the most predictive ECG changes of HK.

Therapeutic agents for the novel coronavirus disease 2019 (COVID-19) have been proposed, but evidence supporting their use is limited. A machine learning algorithm was developed in order to identify a subpopulation of COVID-19 patients for whom hydroxychloroquine was associated with improved survival, this population might be relevant for study in a clinical trial. A pragmatic trial was conducted at six United States hospitals. We enrolled COVID-19 patients that were admitted between 10 March and 4 June 2020. Treatment was not randomized. The study endpoint was mortality, discharge was a competing event. Hazard ratios were obtained on the entire population, and on the subpopulation indicated by the algorithm as suitable for treatment. A total of 290 patients were enrolled. In the subpopulation that was identified by the algorithm, hydroxychloroquine was associated with a statistically significant (p = 0.011) increase in survival (adjusted hazard ratio 0.29, 95% confidence interval (CI) 0.11&ndash, 0.75). Adjusted survival among the algorithm indicated patients was 82.6% in the treated arm and 51.2% in the arm not treated. No association between treatment and mortality was observed in the general population. A 31% increase in survival at the end of the study was observed in a population of COVID-19 patients that were identified by a machine learning algorithm as having a better outcome with hydroxychloroquine treatment. Precision medicine approaches may be useful in identifying a subpopulation of COVID-19 patients more likely to be proven to benefit from hydroxychloroquine treatment in a clinical trial.

Background: Currently, physicians are limited in their ability to provide an accurate prognosis for COVID-19 positive patients. Existing scoring systems have been ineffective for identifying patient decompensation. Machine learning (ML) may offer an alternative strategy. A prospectively validated method to predict the need for ventilation in COVID-19 patients is essential to help triage patients, allocate resources, and prevent emergency intubations and their associated risks. Methods: In a multicenter clinical trial, we evaluated the performance of a machine learning algorithm for prediction of invasive mechanical ventilation of COVID-19 patients within 24 h of an initial encounter. We enrolled patients with a COVID-19 diagnosis who were admitted to five United States health systems between March 24 and May 4, 2020. Results: 197 patients were enrolled in the REspirAtory Decompensation and model for the triage of covid-19 patients: a prospective studY (READY) clinical trial. The algorithm had a higher diagnostic odds ratio (DOR, 12.58) for predicting ventilation than a comparator early warning system, the Modified Early Warning Score (MEWS). The algorithm also achieved significantly higher sensitivity (0.90) than MEWS, which achieved a sensitivity of 0.78, while maintaining a higher specificity (p < 0.05). Conclusions: In the first clinical trial of a machine learning algorithm for ventilation needs among COVID-19 patients, the algorithm demonstrated accurate prediction of the need for mechanical ventilation within 24 h. This algorithm may help care teams effectively triage patients and allocate resources. Further, the algorithm is capable of accurately identifying 16% more patients than a widely used scoring system while minimizing false positive results., SCOPUS: ar.j, info:eu-repo/semantics/published

New treatments, new understanding, and new approaches to translational research are transforming the outlook for patients with kidney diseases. A number of new initiatives dedicated to advancing the field of nephrology-from value-based care to prize competitions-will further improve outcomes of patients with kidney disease. Because of individual nephrologists and kidney organizations in the United States, such as the American Society of Nephrology, the National Kidney Foundation, and the Renal Physicians Association, and international nephrologists and organizations, such as the International Society of Nephrology and the European Renal Association-European Dialysis and Transplant Association, we are beginning to gain traction to invigorate nephrology to meet the pandemic of global kidney diseases. Recognizing the timeliness of this opportunity, the American Society of Nephrology convened a Division Chief Retreat in Dallas, Texas, in June 2019 to address five key issues: (1) asserting the value of nephrology to the health system; (2) productivity and compensation; (3) financial support of faculty's and divisions' educational efforts; (4) faculty recruitment, retention, diversity, and inclusion; and (5) ensuring that fellowship programs prepare trainees to provide high-value nephrology care and enhance attraction of trainees to nephrology. Herein, we highlight the outcomes of these discussions and recommendations to the American Society of Nephrology.

Introduction Acute kidney injury (AKI) is common among hospitalized patients and has a significant impact on morbidity and mortality. Although early prediction of AKI has the potential to reduce adverse patient outcomes, it remains a difficult condition to predict and diagnose. The purpose of this study was to evaluate the ability of a machine learning algorithm to predict for AKI as defined by Kidney Disease: Improving Global Outcomes (KDIGO) stage 2 or 3 up to 48 hours in advance of onset using convolutional neural networks (CNNs) and patient electronic health record (EHR) data. Methods A CNN prediction system was developed to use EHR data gathered during patients’ stays to predict AKI up to 48 hours before onset. A total of 12,347 patient encounters were retrospectively analyzed from the Medical Information Mart for Intensive Care III (MIMIC-III) database. An XGBoost AKI prediction model and the sequential organ failure assessment (SOFA) scoring system were used as comparators. The outcome was AKI onset. The model was trained on routinely collected patient EHR data. Measurements included area under the receiver operating characteristic (AUROC) curve, positive predictive value (PPV), and a battery of additional performance metrics for advance prediction of AKI onset. Results On a hold-out test set, the algorithm attained an AUROC of 0.86 and PPV of 0.24, relative to a cohort AKI prevalence of 7.62%, for long-horizon AKI prediction at a 48-hour window before onset. Conclusion A CNN machine learning-based AKI prediction model outperforms XGBoost and the SOFA scoring system, revealing superior performance in predicting AKI 48 hours before onset, without reliance on serum creatinine (SCr) measurements., Graphical abstract

BACKGROUND Racial disparities in health care are well documented in the United States. As machine learning methods become more common in health care settings, it is important to ensure that these methods do not contribute to racial disparities through biased predictions or differential accuracy across racial groups. OBJECTIVE The goal of the research was to assess a machine learning algorithm intentionally developed to minimize bias in in-hospital mortality predictions between white and nonwhite patient groups. METHODS Bias was minimized through preprocessing of algorithm training data. We performed a retrospective analysis of electronic health record data from patients admitted to the intensive care unit (ICU) at a large academic health center between 2001 and 2012, drawing data from the Medical Information Mart for Intensive Care–III database. Patients were included if they had at least 10 hours of available measurements after ICU admission, had at least one of every measurement used for model prediction, and had recorded race/ethnicity data. Bias was assessed through the equal opportunity difference. Model performance in terms of bias and accuracy was compared with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score II (SAPS II), and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE). RESULTS The machine learning algorithm was found to be more accurate than all comparators, with a higher sensitivity, specificity, and area under the receiver operating characteristic. The machine learning algorithm was found to be unbiased (equal opportunity difference 0.016, P=.20). APACHE was also found to be unbiased (equal opportunity difference 0.019, P=.11), while SAPS II and MEWS were found to have significant bias (equal opportunity difference 0.038, P=.006 and equal opportunity difference 0.074, P CONCLUSIONS This study indicates there may be significant racial bias in commonly used severity scoring systems and that machine learning algorithms may reduce bias while improving on the accuracy of these methods.

Rationale and objectivesAcute kidney injury (AKI) is common among hospitalized patients and has a significant impact on morbidity and mortality. While early prediction of AKI has the potential to reduce adverse patient outcomes, it remains a difficult condition to predict and diagnose. The purpose of this study was to evaluate the ability of a machine learning algorithm to predict for AKI KDIGO Stage 2 or 3 up to 72 hours in advance of onset using convolutional recurrent neural nets (CNN) and patient Electronic Health Record (EHR) data.MethodsA CNN prediction system was developed to continuously and automatically monitor for incipient AKI. 7122 patient encounters were retrospectively analyzed from the Medical Information Mart for Intensive Care III (MIMIC-III) database.New Predictors and Established PredictorsNew predictor - CNN machine learning-based AKI prediction model. Established predictors - XGBoost AKI prediction model and the Sequential Organ Failure Assessment (SOFA) scoring system.OutcomesAKI onset.Analytical ApproachThe model was trained on routinely-collected patient EHR data. Measurements included Area Under the Receiver Operating Characteristic (AUROC) curve, positive predictive value (PPV), and a battery of additional performance metrics for 72 hour advance prediction of AKI onset.ResultsOn a hold-out test set, the algorithm attained an AUROC of 0.85 and PPV of 0.25, relative to a cohort AKI prevalence of 5.21%, for long-horizon AKI prediction at a 72-hour window prior to onset.ConclusionsA CNN machine learning-based AKI prediction model outperforms XGBoost and the SOFA scoring system, demonstrating superior performance in predicting acute kidney injury 72 hours prior to onset, without reliance on changes in serum creatinine.

Background Racial disparities in health care are well documented in the United States. As machine learning methods become more common in health care settings, it is important to ensure that these methods do not contribute to racial disparities through biased predictions or differential accuracy across racial groups. Objective The goal of the research was to assess a machine learning algorithm intentionally developed to minimize bias in in-hospital mortality predictions between white and nonwhite patient groups. Methods Bias was minimized through preprocessing of algorithm training data. We performed a retrospective analysis of electronic health record data from patients admitted to the intensive care unit (ICU) at a large academic health center between 2001 and 2012, drawing data from the Medical Information Mart for Intensive Care–III database. Patients were included if they had at least 10 hours of available measurements after ICU admission, had at least one of every measurement used for model prediction, and had recorded race/ethnicity data. Bias was assessed through the equal opportunity difference. Model performance in terms of bias and accuracy was compared with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score II (SAPS II), and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE). Results The machine learning algorithm was found to be more accurate than all comparators, with a higher sensitivity, specificity, and area under the receiver operating characteristic. The machine learning algorithm was found to be unbiased (equal opportunity difference 0.016, P=.20). APACHE was also found to be unbiased (equal opportunity difference 0.019, P=.11), while SAPS II and MEWS were found to have significant bias (equal opportunity difference 0.038, P=.006 and equal opportunity difference 0.074, P Conclusions This study indicates there may be significant racial bias in commonly used severity scoring systems and that machine learning algorithms may reduce bias while improving on the accuracy of these methods.

In recent years, there has been a marked decline in applicants to United States nephrology programs ([1][1]). Although a multipronged approach is clearly needed to increase interest in nephrology, it is important that we ensure that our applicants/future colleagues are treated in the most fair and

Background:We identified two boys with type 3 renal tubular acidosis (RTA) and growth hormone deficiency and we sought to differentiate them from children with classic type 1 distal RTA.Methods:We reviewed all children Results:All children with type 1 RTA reached the 5th percentile or higher on CDC growth charts within 2 years of alkali therapy. Their mean height standard deviation score (SDS) improved from −1.4 to −0.6 SDS and their mean mid-parental height (MPH) SDS improved from −0.6 to 0 SDS after 2 years. In contrast, the boys with growth hormone deficiency had a height SDS of −1.4 and −2.4 SDS after 2 years of alkali and the MPH SDS were both −2.6 SDS after 2 years of alkali therapy. Growth hormone therapy accelerated their growth to normal levels and led to long-term correction of RTA.Conclusions:A child with type 1 RTA whose height response after 2 years of alkali therapy is inadequate should undergo provocative growth hormone testing.

Transplanting a kidney from a hepatitis B surface antigen (HBsAg)-positive donor to an HBsAg-negative recipient who is naturally immune has been successful in countries endemic for hepatitis B virus (HBV). However, in most of these cases, the donors were deceased. We present a report of a successful HBsAg-discordant kidney transplantation in the United States; in this case, a living donor kidney was transplanted to a vaccinated recipient. The wife of a 58-year-old HBsAg-negative man volunteered to donate a kidney to her husband. She had chronic hepatitis B but undetectable HBV DNA. She tested positive for HBsAg and antibody to hepatitis B core antigen, but hepatitis B e antigen was undetectable. The recipient failed to develop an antibody response to 3 doses of intramuscular recombinant HBV vaccine given in consecutive months. Immunity was induced by using biweekly intradermal vaccine. However, antibody titer tapered to

Although acute kidney injury (AKI) is common in heart failure, yet the impact of the onset, timing, and duration of AKI on short-term outcomes is not well studied. AKI was defined as an increase in serum creatinine SCr of ≥0.3 mg/dl or 1.5 times relative to the admission and further categorized as transient AKI (T-AKI: SCr returning to within 10% of baseline); sustained AKI (S-AKI: those with at least 72 hours of hospital stay and did not meet T-AKI); and unknown duration AKI (U-AKI: those with less than 72 hours stay and did not meet T-AKI). Reference category was no AKI (stable or0.3 mg/dl change in SCr). The main outcome was 30-day all-cause hospital readmission. Unadjusted and adjusted association between AKI category of interest and main outcome was represented as percent and relative risks with 95% CIs. Statistical significance was set at an alpha of 0.05. From the Cerner Health Facts sample, 14,017 of 22,059 available subjects met the eligibility criteria. Approximately, 19.2% of our sample met the primary outcome. Compared with no AKI (readmission rate of 17.7%; 95% CI 16.4% to 18.9%), the adjusted rate of readmission was highest in patients with S-AKI (22.8%, 95% CI 20.8% to 24.8%; p0.001), followed by 20.2% (95% CI 17.5% to 22.8%; p = 0.05) in T-AKI patients. Compared with no AKI, the adjusted relative risk of 30-day readmission was 1.29 (95% CI 1.17 to 1.42), 1.14 (95% CI 1.00 to 1.31), and 1.12 (95% CI, 1.01 to 1.26) in S-AKI, T-AKI, and U-AKI, respectively. In conclusion, both sustained AKI and patients with transient elevation still remain at a higher risk of readmission within 30 days. Future studies should focus on examining process-of-care after discharge in patients with different patterns of AKI.

Its routine use is not supported at this time, but there is evidence to suggest giving it to patients with baseline renal dysfunction.

Rhabdomyolysis is an uncommon but life-threatening adverse effect of simvastatin therapy. A 73-year-old male on chronic simvastatin therapy received azithromycin for acute bronchitis. He presented with weakness of all extremities with a significant increase in creatinine phosphokinase levels and acute kidney injury. Simvastatin was stopped and supportive therapy with intravenous saline and bicarbonate was initiated. The serum creatinine and creatine phosphokinase returned to baseline in the next 7 days. Two months later, simvastatin was resumed without any recurrence of symptoms. Our case report highlights the rare description of rhabdomyolysis caused by a drug interaction between simvastatin with azithromycin.