Search

Albuminuria is an under-recognized component of chronic kidney disease definition, staging, and prognosis. Guidelines, particularly for hypertension, conflict on recommendations for urine albumin-to-creatinine ratio (ACR) measurement. Separately among 1 344 594 adults with diabetes and 2 334 461 nondiabetic adults with hypertension from the chronic kidney disease Prognosis Consortium, we assessed ACR testing, estimated the prevalence and incidence of ACR ≥30 mg/g and developed risk models for ACR ≥30 mg/g. The ACR screening rate (cohort range) was 35.1% (12.3%–74.5%) in diabetes and 4.1% (1.3%–20.7%) in hypertension. Screening was largely unrelated to the predicted risk of prevalent albuminuria. The median prevalence of ACR ≥30 mg/g across cohorts was 32.1% in diabetes and 21.8% in hypertension. Higher systolic blood pressure was associated with a higher prevalence of albuminuria (odds ratio [95% CI] per 20 mm Hg in diabetes, 1.50 [1.42–1.60]; in hypertension, 1.36 [1.28–1.45]). The ratio of undetected (due to lack of screening) to detected ACR ≥30 mg/g was estimated at 1.8 in diabetes and 19.5 in hypertension. Among those with ACR

Background and objectives AKI treated with dialysis initiation is a common complication of coronavirus disease 2019 (COVID-19) among hospitalized patients. However, dialysis supplies and personnel are often limited. Design, setting, participants, & measurements Using data from adult patients hospitalized with COVID-19 from five hospitals from the Mount Sinai Health System who were admitted between March 10 and December 26, 2020, we developed and validated several models (logistic regression, Least Absolute Shrinkage and Selection Operator (LASSO), random forest, and eXtreme GradientBoosting [XGBoost; with and without imputation]) for predicting treatment with dialysis or death at various time horizons (1, 3, 5, and 7 days) after hospital admission. Patients admitted to the Mount Sinai Hospital were used for internal validation, whereas the other hospitals formed part of the external validation cohort. Features included demographics, comorbidities, and laboratory and vital signs within 12 hours of hospital admission. Results A total of 6093 patients (2442 in training and 3651 in external validation) were included in the final cohort. Of the different modeling approaches used, XGBoost without imputation had the highest area under the receiver operating characteristic (AUROC) curve on internal validation (range of 0.93–0.98) and area under the precision-recall curve (AUPRC; range of 0.78–0.82) for all time points. XGBoost without imputation also had the highest test parameters on external validation (AUROC range of 0.85–0.87, and AUPRC range of 0.27–0.54) across all time windows. XGBoost without imputation outperformed all models with higher precision and recall (mean difference in AUROC of 0.04; mean difference in AUPRC of 0.15). Features of creatinine, BUN, and red cell distribution width were major drivers of the model’s prediction. Conclusions An XGBoost model without imputation for prediction of a composite outcome of either death or dialysis in patients positive for COVID-19 had the best performance, as compared with standard and other machine learning models. Podcast This article contains a podcast at https://www.asn-online.org/media/podcast/CJASN/2021_07_09_CJN17311120.mp3

Recent case reports suggest that coronavirus disease 2019 (COVID-19) is associated with collapsing glomerulopathy in African Americans with apolipoprotein L1 gene (APOL1) risk alleles; however, it is unclear whether disease pathogenesis is similar to HIV-associated nephropathy. RNA sequencing analysis of a kidney biopsy specimen from a patient with COVID-19–associated collapsing glomerulopathy and APOL1 risk alleles (G1/G1) revealed similar levels of APOL1 and angiotensin-converting enzyme 2 (ACE2) messenger RNA transcripts as compared with 12 control kidney samples downloaded from the GTEx (Genotype-Tissue Expression) Portal. Whole-genome sequencing of the COVID-19–associated collapsing glomerulopathy kidney sample identified 4 indel gene variants, 3 of which are of unknown significance with respect to chronic kidney disease and/or focal segmental glomerulosclerosis. Molecular profiling of the kidney demonstrated activation of COVID-19–associated cell injury pathways such as inflammation and coagulation. Evidence for direct severe acute respiratory syndrome coronavirus 2 infection of kidney cells was lacking, which is consistent with the findings of several recent studies. Interestingly, immunostaining of kidney biopsy sections revealed increased expression of phospho-STAT3 (signal transducer and activator of transcription 3) in both COVID-19–associated collapsing glomerulopathy and HIV-associated nephropathy as compared with control kidney tissue. Importantly, interleukin 6–induced activation of STAT3 may be a targetable mechanism driving COVID-19–associated acute kidney injury.

Purpose Limited mechanical ventilators (MV) during the Coronavirus disease (COVID-19) pandemic have led to the use of non-invasive ventilation (NIV) in hypoxemic patients, which has not been studied well. We aimed to assess the association of NIV versus MV with mortality and morbidity during respiratory intervention among hypoxemic patients admitted with COVID-19. Methods We performed a retrospective multi-center cohort study across 5 hospitals during March–April 2020. Outcomes included mortality, severe COVID-19-related symptoms, time to discharge, and final oxygen saturation (SpO2) at the conclusion of the respiratory intervention. Multivariable regression of outcomes was conducted in all hypoxemic participants, 4 subgroups, and propensity-matched analysis. Results Of 2381 participants with laboratory-confirmed SARS-CoV-2, 688 were included in the study who were hypoxemic upon initiation of respiratory intervention. During the study period, 299 participants died (43%), 163 were admitted to the ICU (24%), and 121 experienced severe COVID-19-related symptoms (18%). Participants on MV had increased mortality than those on NIV (128/154 [83%] versus 171/534 [32%], OR = 30, 95% CI 16–60) with a mean survival of 6 versus 15 days, respectively. The MV group experienced more severe COVID-19-related symptoms [55/154 (36%) versus 66/534 (12%), OR = 4.3, 95% CI 2.7–6.8], longer time to discharge (mean 17 versus 7.1 days), and lower final SpO2 (92 versus 94%). Across all subgroups and propensity-matched analysis, MV was associated with a greater OR of death than NIV. Conclusions NIV was associated with lower respiratory intervention mortality and morbidity than MV. However, findings may be liable to unmeasured confounding and further study from randomized controlled trials is needed to definitively determine the role of NIV in hypoxemic patients with COVID-19. Supplementary Information The online version contains supplementary material available at 10.1007/s15010-021-01633-6.

Aim Predicting progression in diabetic kidney disease (DKD) is critical to improving outcomes. We sought to develop/validate a machine-learned, prognostic risk score (KidneyIntelX™) combining electronic health records (EHR) and biomarkers. Methods This is an observational cohort study of patients with prevalent DKD/banked plasma from two EHR-linked biobanks. A random forest model was trained, and performance (AUC, positive and negative predictive values [PPV/NPV], and net reclassification index [NRI]) was compared with that of a clinical model and Kidney Disease: Improving Global Outcomes (KDIGO) categories for predicting a composite outcome of eGFR decline of ≥5 ml/min per year, ≥40% sustained decline, or kidney failure within 5 years. Results In 1146 patients, the median age was 63 years, 51% were female, the baseline eGFR was 54 ml min−1 [1.73 m]−2, the urine albumin to creatinine ratio (uACR) was 6.9 mg/mmol, follow-up was 4.3 years and 21% had the composite endpoint. On cross-validation in derivation (n = 686), KidneyIntelX had an AUC of 0.77 (95% CI 0.74, 0.79). In validation (n = 460), the AUC was 0.77 (95% CI 0.76, 0.79). By comparison, the AUC for the clinical model was 0.62 (95% CI 0.61, 0.63) in derivation and 0.61 (95% CI 0.60, 0.63) in validation. Using derivation cut-offs, KidneyIntelX stratified 46%, 37% and 17% of the validation cohort into low-, intermediate- and high-risk groups for the composite kidney endpoint, respectively. The PPV for progressive decline in kidney function in the high-risk group was 61% for KidneyIntelX vs 40% for the highest risk strata by KDIGO categorisation (p event for the high-risk group was 41% (p Conclusions KidneyIntelX improved prediction of kidney outcomes over KDIGO and clinical models in individuals with early stages of DKD. Graphical abstract

In April 2020, in light of COVID-19-related blood shortages, the US Food and Drug Administration (FDA) reduced the deferral period for men who have sex with men (MSM) from its previous duration of 1 year to 3 months. Although originally born out of necessity, the decades-old restrictions on MSM donors have been mitigated by significant advancements in HIV screening, treatment, and public education. The severity of the ongoing COVID-19 pandemic—and the urgent need for safe blood products to respond to such crises—demands an immediate reconsideration of the 3-month deferral policy for MSM. We review historical HIV testing and transmission evidence, discuss the ethical ramifications of the current deferral period, and examine the issue of noncompliance with donor deferral rules. We also propose an eligibility screening format that involves an individual risk-based screening protocol and, unlike current FDA guidelines, does not effectively exclude donors on the basis of gender identity or sexual orientation. Our policy proposal would allow historically marginalized community members to participate with dignity in the blood donation process without compromising blood donation and transfusion safety outcomes.

Purpose: Advanced, unresectable pancreatic cancer is often treated with either gemcitabine plus nab-paclitaxel (Gem/NabP) or FOLFIRINOX, although these regimens have never been compared in a head-to-head trial. In this study, we compared these two regimens using Veterans Administration (VA) data and evaluated the use of a novel tumor growth formula to predict outcomes. Methods: We identified 670 Veterans from national VA data with unresected stage II-IV pancreatic adenocarcinoma diagnosed between 2003 and 2016 who were treated with either first-line Gem/NabP or FOLFIRINOX. We compared overall survival (OS) and adverse events by treatment using propensity scores (PS) to account for allocation bias. Using longitudinal CA19-9 biomarker information we then fit the data to a novel tumor growth equation, comparing growth with OS. Results: We found no difference in PS-adjusted (hazard ratio [HR] 1.00; 95% confidence interval [95% CI] 0.84–1.20) or PS-matched (HR: 0.93; 95% CI: 0.76–1.13) OS between the two treatment groups. Tumor growth analysis revealed similar growth parameter values for Gem/NabP and FOLFIRINOX (P = .074 for difference). Conclusions: Gem/NabP appeared noninferior to FOLFIRINOX for survival outcomes for advanced pancreatic adenocarcinoma based on national VA data. Biomarker-based growth equations may be useful for monitoring treatment response and predicting prognosis for pancreatic cancer.

Background/Aims: Acute kidney injury (AKI) in critically ill patients is common, and continuous renal replacement therapy (CRRT) is a preferred mode of renal replacement therapy (RRT) in hemodynamically unstable patients. Prediction of clinical outcomes in patients on CRRT is challenging. We utilized several approaches to predict RRT-free survival (RRTFS) in critically ill patients with AKI requiring CRRT. Methods: We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify patients ≥18 years old with AKI on CRRT, after excluding patients who had ESRD on chronic dialysis, and kidney transplantation. We defined RRTFS as patients who were discharged alive and did not require RRT ≥7 days prior to hospital discharge. We utilized all available biomedical data up to CRRT initiation. We evaluated 7 approaches, including logistic regression (LR), random forest (RF), support vector machine (SVM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), multilayer perceptron (MLP), and MLP with long short-term memory (MLP + LSTM). We evaluated model performance by using area under the receiver operating characteristic (AUROC) curves. Results: Out of 684 patients with AKI on CRRT, 205 (30%) patients had RRTFS. The median age of patients was 63 years and their median Simplified Acute Physiology Score (SAPS) II was 67 (interquartile range 52–84). The MLP + LSTM showed the highest AUROC (95% CI) of 0.70 (0.67–0.73), followed by MLP 0.59 (0.54–0.64), LR 0.57 (0.52–0.62), SVM 0.51 (0.46–0.56), AdaBoost 0.51 (0.46–0.55), RF 0.44 (0.39–0.48), and XGBoost 0.43 (CI 0.38–0.47). Conclusions: A MLP + LSTM model outperformed other approaches for predicting RRTFS. Performance could be further improved by incorporating other data types.

BACKGROUND AND OBJECTIVES: Genetic variants in NAT8, a liver- and kidney-specific acetyltransferase encoding gene, have been associated with eGFR and CKD in European populations. Higher circulating levels of two NAT8-associated metabolites, N-δ-acetylornithine and N-acetyl-1-methylhistidine, have been linked to lower eGFR and higher risk of incident CKD in the Black population. We aimed to expand upon prior studies to investigate associations between rs13538, a missense variant in NAT8, N-acetylated amino acids, and kidney failure in multiple, well-characterized cohorts. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: We conducted analyses among participants with genetic and/or serum metabolomic data in the African American Study of Kidney Disease and Hypertension (AASK; n=962), the Atherosclerosis Risk in Communities (ARIC) study (n=1050), and BioMe, an electronic health record–linked biorepository (n=680). Separately, we evaluated associations between rs13538, urinary N-acetylated amino acids, and kidney failure in participants in the German CKD (GCKD) study (n=1624). RESULTS: Of 31 N-acetylated amino acids evaluated, the circulating and urinary levels of 14 were associated with rs13538 (P

Coronavirus disease 2019 (COVID-19) due to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has had devastating effects worldwide. Patients with kidney failure on dialysis may have a higher risk of worse outcomes. Reports from China found that these patients with SARS-CoV-2 had fewer

Background and objectives Sepsis-associated AKI is a heterogeneous clinical entity. We aimed to agnostically identify sepsis-associated AKI subphenotypes using deep learning on routinely collected data in electronic health records. Design, setting, participants, & measurements We used the Medical Information Mart for Intensive Care III database, which consists of electronic health record data from intensive care units in a tertiary care hospital in the United States. We included patients ≥18 years with sepsis who developed AKI within 48 hours of intensive care unit admission. We then used deep learning to utilize all available vital signs, laboratory measurements, and comorbidities to identify subphenotypes. Outcomes were mortality 28 days after AKI and dialysis requirement. Results We identified 4001 patients with sepsis-associated AKI. We utilized 2546 combined features for K-means clustering, identifying three subphenotypes. Subphenotype 1 had 1443 patients, and subphenotype 2 had 1898 patients, whereas subphenotype 3 had 660 patients. Subphenotype 1 had the lowest proportion of liver disease and lowest Simplified Acute Physiology Score II scores compared with subphenotypes 2 and 3. The proportions of patients with CKD were similar between subphenotypes 1 and 3 (15%) but highest in subphenotype 2 (21%). Subphenotype 1 had lower median bilirubin levels, aspartate aminotransferase, and alanine aminotransferase compared with subphenotypes 2 and 3. Patients in subphenotype 1 also had lower median lactate, lactate dehydrogenase, and white blood cell count than patients in subphenotypes 2 and 3. Subphenotype 1 also had lower creatinine and BUN than subphenotypes 2 and 3. Dialysis requirement was lowest in subphenotype 1 (4% versus 7% [subphenotype 2] versus 26% [subphenotype 3]). The mortality 28 days after AKI was lowest in subphenotype 1 (23% versus 35% [subphenotype 2] versus 49% [subphenotype 3]). After adjustment, the adjusted odds ratio for mortality for subphenotype 3, with subphenotype 1 as a reference, was 1.9 (95% confidence interval, 1.5 to 2.4). Conclusions Utilizing routinely collected laboratory variables, vital signs, and comorbidities, we were able to identify three distinct subphenotypes of sepsis-associated AKI with differing outcomes.

Purpose of Review Type 2 diabetes mellitus (T2DM) is a prevalent disease with the severe clinical implications including myocardial infarction, stroke, and kidney disease. Therapies focusing on glycemic control in T2DM such as biguanides, sulfonylureas, thiazolidinediones, and insulin-based regimens have largely failed to substantially improve cardiovascular and kidney outcomes. We review the recent findings on sodium-glucose co-transporter type 2 (SGLT2) inhibitors which have shown to have beneficial cardiovascular and kidney-related effects.

Background Early reports indicate that AKI is common among patients with coronavirus disease 2019 (COVID-19) and associated with worse outcomes. However, AKI among hospitalized patients with COVID-19 in the United States is not well described. Methods This retrospective, observational study involved a review of data from electronic health records of patients aged ≥18 years with laboratory-confirmed COVID-19 admitted to the Mount Sinai Health System from February 27 to May 30, 2020. We describe the frequency of AKI and dialysis requirement, AKI recovery, and adjusted odds ratios (aORs) with mortality. Results Of 3993 hospitalized patients with COVID-19, AKI occurred in 1835 (46%) patients; 347 (19%) of the patients with AKI required dialysis. The proportions with stages 1, 2, or 3 AKI were 39%, 19%, and 42%, respectively. A total of 976 (24%) patients were admitted to intensive care, and 745 (76%) experienced AKI. Of the 435 patients with AKI and urine studies, 84% had proteinuria, 81% had hematuria, and 60% had leukocyturia. Independent predictors of severe AKI were CKD, men, and higher serum potassium at admission. In-hospital mortality was 50% among patients with AKI versus 8% among those without AKI (aOR, 9.2; 95% confidence interval, 7.5 to 11.3). Of survivors with AKI who were discharged, 35% had not recovered to baseline kidney function by the time of discharge. An additional 28 of 77 (36%) patients who had not recovered kidney function at discharge did so on posthospital follow-up. Conclusions AKI is common among patients hospitalized with COVID-19 and is associated with high mortality. Of all patients with AKI, only 30% survived with recovery of kidney function by the time of discharge.

Background Data on patients with coronavirus disease 2019 (COVID-19) who return to hospital after discharge are scarce. Characterization of these patients may inform post-hospitalization care. Objective To describe clinical characteristics of patients with COVID-19 who returned to the emergency department (ED) or required readmission within 14 days of discharge. Design Retrospective cohort study of SARS-COV-2-positive patients with index hospitalization between February 27 and April 12, 2020, with ≥ 14-day follow-up. Significance was defined as P < 0.05 after multiplying P by 125 study-wide comparisons. Participants Hospitalized patients with confirmed SARS-CoV-2 discharged alive from five New York City hospitals. Main Measures Readmission or return to ED following discharge. Results Of 2864 discharged patients, 103 (3.6%) returned for emergency care after a median of 4.5 days, with 56 requiring inpatient readmission. The most common reason for return was respiratory distress (50%). Compared with patients who did not return, there were higher proportions of COPD (6.8% vs 2.9%) and hypertension (36% vs 22.1%) among those who returned. Patients who returned also had a shorter median length of stay (LOS) during index hospitalization (4.5 [2.9,9.1] vs 6.7 [3.5, 11.5] days; Padjusted = 0.006), and were less likely to have required intensive care on index hospitalization (5.8% vs 19%; Padjusted = 0.001). A trend towards association between absence of in-hospital treatment-dose anticoagulation on index admission and return to hospital was also observed (20.9% vs 30.9%, Padjusted = 0.06). On readmission, rates of intensive care and death were 5.8% and 3.6%, respectively. Conclusions Return to hospital after admission for COVID-19 was infrequent within 14 days of discharge. The most common cause for return was respiratory distress. Patients who returned more likely had COPD and hypertension, shorter LOS on index-hospitalization, and lower rates of in-hospital treatment-dose anticoagulation. Future studies should focus on whether these comorbid conditions, longer LOS, and anticoagulation are associated with reduced readmissions. Electronic supplementary material The online version of this article (10.1007/s11606-020-06120-6) contains supplementary material, which is available to authorized users.

INTRODUCTION A previous study demonstrated that the surface area-normalized standard Kt/V (SAstdKt/V) was better associated with mortality than standard Kt/V (stdKt/V). This study investigates the association of SAstdKt/V and stdKt/V with mortality, anemia, and hypoalbuminemia in a larger patient cohort with a longer follow-up period. METHODS We included adult patients on thrice-weekly hemodialysis in the USRDS database and excluded amputated patients. StdKt/V and SAstdKt/V were calculated from the available single-pool Kt/V. Patients were categorized into five groups according to their stdKt/V and SAstdKt/V

Despite substantial advances in the study, treatment, and prevention of cardiovascular disease, numerous challenges relating to optimally screening, diagnosing, and managing patients remain. Simultaneous improvements in computing power, data storage, and data analytics have led to the development of new techniques to address these challenges. One powerful tool to this end is machine learning (ML), which aims to algorithmically identify and represent structure within data. Machine learning’s ability to efficiently analyze large and highly complex data sets make it a desirable investigative approach in modern biomedical research. Despite this potential and enormous public and private sector investment, few prospective studies have demonstrated improved clinical outcomes from this technology. This is particularly true in cardiology, despite its emphasis on objective, data-driven results. This threatens to stifle ML’s growth and use in mainstream medicine. We outline the current state of ML in cardiology and outline methods through which impactful and sustainable ML research can occur. Following these steps can ensure ML reaches its potential as a transformative technology in medicine.

Polygenic risk scores (PRS) for coronary artery disease (CAD) identify high-risk individuals more likely to benefit from primary prevention statin therapy. Whether polygenic CAD risk is captured by conventional paradigms for assessing clinical cardiovascular risk remains unclear.This study sought to intersect polygenic risk with guideline-based recommendations and management patterns for CAD primary prevention.A genome-wide CAD PRS was applied to 47,108 individuals across 3 U.S. health care systems. The authors then assessed whether primary prevention patients at high polygenic risk might be distinguished on the basis of greater guideline-recommended statin eligibility and higher rates of statin therapy.Of 47,108 study participants, the mean age was 60 years, and 11,020 (23.4%) had CAD. The CAD PRS strongly associated with prevalent CAD (odds ratio: 1.4 per SD increase in PRS; p 0.0001). High polygenic risk (top 20% of PRS) conferred 1.9-fold odds of developing CAD (p 0.0001). However, among primary prevention patients (n = 33,251), high polygenic risk did not correspond with increased recommendations for statin therapy per the American College of Cardiology/American Heart Association (46.2% for those with high PRS vs. 46.8% for all others, p = 0.54) or U.S. Preventive Services Task Force (43.7% vs. 43.7%, p = 0.99) or higher rates of statin prescriptions (25.0% vs. 23.8%, p = 0.04). An additional 4.1% of primary prevention patients may be recommended for statin therapy if high CAD PRS were considered a guideline-based risk-enhancing factor.Current paradigms for primary cardiovascular prevention incompletely capture a polygenic susceptibility to CAD. An opportunity may exist to improve CAD prevention efforts by integrating both genetic and clinical risk.

PURPOSE OF REVIEW: The universal adoption of electronic health records, improvement in technology, and the availability of continuous monitoring has generated large quantities of healthcare data. Machine learning is increasingly adopted by nephrology researchers to analyze this data in order to improve the care of their patients. RECENT FINDINGS: In this review, we provide a broad overview of the different types of machine learning algorithms currently available and how researchers have applied these methods in nephrology research. Current applications have included prediction of acute kidney disease and chronic kidney disease along with progression of kidney disease. Researchers have demonstrated the ability of machine learning to read kidney biopsy samples, identify patient outcomes from unstructured data, identify subtypes in complex diseases, and discuss the potential benefits on drug discovery. We end with a discussion on the ethics and potential pitfalls of machine learning. SUMMARY: Machine learning provides researchers with the ability to analyze data which was previously inaccessible. While still burgeoning several studies show promising results which will enable researchers to perform larger scale studies and clinicians the ability to provide more personalized care. However, we must ensure that implementation aids providers and does not lead to harm to patients.

BACKGROUND: Pregnancy-related AKI (PR-AKI) is increasing in the United States. PR-AKI is associated with adverse maternal outcomes. Disparities in racial/ethnic differences in PR-AKI by race have not been studied. METHODS: This was a retrospective cohort study using the National Inpatient Sample (NIS) from 2005 to 2015. We identified patients who were admitted for a pregnancy-related diagnosis using the Neomat variable provided by the NIS database that indicates the presence of a maternal or neonatal diagnosis code or procedure code. PR-AKI was identified using ICD codes. Survey logistic regression was used for multivariable analysis adjusting for age, medical comorbidities, socioeconomic factors, and hospital/admission factors. RESULTS: From 48,316,430 maternal hospitalizations, 34,001 (0.07%) were complicated by PR-AKI. Hospitalizations for PR-AKI increased from 3.5/10,000 hospitalizations in 2005 to 11.8/10,000 hospitalizations in 2015 with the largest increase seen in patients aged ≥35 and black patients. PR-AKI was associated with higher odds of miscarriage (adjusted odds ratio [aOR], 1.64; 95% CI, 1.34 to 2.07) and mortality (aOR, 1.53; 95% CI, 1.25 to 1.88). After adjustment for age, medical comorbidities, and socioeconomic factors, blacks were more likely than whites to develop PR-AKI (aOR, 1.17; 95% CI, 1.04 to 1.33). On subgroup analyses in hospitalizations of patients with PR-AKI, blacks and Hispanics were more likely to have preeclampsia/eclampsia compared with whites (aOR, 1.29; 95% CI, 1.01 to 1.65; and aOR, 1.69; 95% CI, 1.23 to 2.31, respectively). Increased odds of mortality in PR-AKI compared with whites were only seen in black patients (aOR, 1.61; 95% CI, 1.02 to 2.55). CONCLUSIONS: The incidence of PR-AKI has increased and the largest increase was seen in older patients and black patients. PR-AKI is associated with miscarriages, adverse discharge from hospital, and mortality. Black and Hispanic patients with PR-AKI were more likely to have adverse outcomes than white patients. Further research is needed to identify factors contributing to these discrepancies.

Symptoms are common in patients on maintenance hemodialysis but identification is challenging. New informatics approaches including natural language processing (NLP) can be utilized to identify symptoms from narrative clinical documentation. Here we utilized NLP to identify seven patient symptoms from notes of maintenance hemodialysis patients of the BioMe Biobank and validated our findings using a separate cohort and the MIMIC-III database. NLP performance was compared for symptom detection with International Classification of Diseases (ICD)-9/10 codes and the performance of both methods were validated against manual chart review. From 1034 and 519 hemodialysis patients within BioMe and MIMIC-III databases, respectively, the most frequently identified symptoms by NLP were fatigue, pain, and nausea/vomiting. In BioMe, sensitivity for NLP (0.85 - 0.99) was higher than for ICD codes (0.09 - 0.59) for all symptoms with similar results in the BioMe validation cohort and MIMIC-III. ICD codes were significantly more specific for nausea/vomiting in BioMe and more specific for fatigue, depression, and pain in the MIMIC-III database. A majority of patients in both cohorts had four or more symptoms. Patients with more symptoms identified by NLP, ICD, and chart review had more clinical encounters. NLP had higher specificity in inpatient notes but higher sensitivity in outpatient notes and performed similarly across pain severity subgroups. Thus, NLP had higher sensitivity compared to ICD codes for identification of seven common hemodialysis-related symptoms, with comparable specificity between the two methods. Hence, NLP may be useful for the high-throughput identification of patient-centered outcomes when using electronic health records.

We explored rates of premature births and neonatal intensive care unit (NICU) admissions at the Mount Sinai Hospital after the implementation of COVID-19 lockdown measures (March 16, 2020) and phase one reopening (June 8, 2020), comparing them to those of the same time periods from 2012-2019. Mount Sinai Hospital is in New York City (NYC), an early epicenter of COVID-19 in the United States, which was heavily impacted by the pandemic during the study period. Among 43,963 singleton births, we observed no difference in either outcome after the implementation of lockdown measures when compared to the same trends in prior years (p=0.09-0.35). Of interest, we observed a statistically significant decrease in premature births after NYC phase one reopening compared to those of the same time period in 2012-2019 across all time windows (p=0.0028-0.049), and a statistically significant decrease in NICU admissions over the largest time window (2.75 months) compared to prior years (p=0.0011).

The burden of advanced chronic kidney disease (CKD) falls disproportionately on minorities including African Americans (AAs) and Hispanic Americans (HAs) with admixed ancestry. Even though APOL1 high-risk genotypes increase risk of kidney disease, their penetrance is incomplete, indicating that the modification of APOL1 high risk may be polygenic. For this study, we used three multi-ethnic cohorts with APOL1 high risk genotypes and calculated a multi-ethnic PRS using publicly available summary statistics. We show that CKD risk is significantly modified by a multi-ethnic polygenic risk score. Standardizing population screening for CKD by including APOL1 high-risk genotypes and polygenic risk score may improve risk stratification and outcomes.

ImportancePassive and non-invasive identification of SARS-CoV-2 infection remains a challenge. Widespread use of wearable devices represents an opportunity to leverage physiological metrics and fill this knowledge gap.ObjectiveTo determine whether a machine learning model can detect SARS-CoV-2 infection from physiological metrics collected from wearable devices.DesignA multicenter observational study enrolling health care workers with remote follow-up.SettingSeven hospitals from the Mount Sinai Health System in New York CityParticipantsEligibility criteria included health care workers who were ≥18 years, employees of one of the participating hospitals, with at least an iPhone series 6, and willing to wear an Apple Watch Series 4 or higher. We excluded participants with underlying autoimmune/inflammatory diseases, and medications known to interfere with autonomic function. We enrolled participants between April 29th, 2020, and March 2nd, 2021, and followed them for a median of 73 days (range, 3-253 days). Participants provided patient-reported outcome measures through a custom smartphone application and wore an Apple Watch, collecting heart rate variability and heart rate data, throughout the follow-up period.ExposureParticipants were exposed to SARS-CoV-2 infection over time due to ongoing community spread.Main Outcome and MeasureThe primary outcome was SARS-CoV-2 infection, defined as ±7 days from a self-reported positive SARS-CoV-2 nasal PCR test.ResultsWe enrolled 407 participants with 49 (12%) having a positive SARS-CoV-2 test during follow-up. We examined five machine-learning approaches and found that gradient-boosting machines (GBM) had the most favorable 10-CV performance. Across all testing sets, our GBM model predicted SARS-CoV-2 infection with an average area under the receiver operating characteristic (auROC)=85% (Confidence Interval 83-88%). The model was calibrated to improve sensitivity over specificity, achieving an average sensitivity of 76% (CI ±∼4%) and specificity of 84% (CI ±∼0.4%). The most important predictors included parameters describing the circadian HRV mean (MESOR) and peak-timing (acrophase), and age.Conclusions and RelevanceWe show that a tree-based ML algorithm applied to physiological metrics passively collected from a wearable device can identify and predict SARS-CoV2 infection. Utilizing physiological metrics from wearable devices may improve screening methods and infection tracking.

Background Despite advances in cardiovascular disease and risk factor management, mortality from ischemic heart failure (HF) in patients with coronary artery disease (CAD) remains high. Given the partial role of genetics in HF and lack of reliable risk stratification tools, we developed and validated a polygenic risk score for HF in patients with CAD, which we term HF‐PRS. Methods and Results Using summary statistics from a recent genome‐wide association study for HF, we developed candidate PRSs in the Mount Sinai Bio Me CAD patient cohort (N=6274) by using the pruning and thresholding method and LDPred. We validated the best score in the Penn Medicine BioBank (N=7250) and performed a subgroup analysis in a high‐risk cohort who had undergone coronary catheterization. We observed a significant association between HF‐PRS score and ischemic HF even after adjusting for evidence of obstructive CAD in patients of European ancestry in both Bio Me (odds ratio [OR], 1.14 per SD; 95% CI, 1.05–1.24; P =0.003) and Penn Medicine BioBank (OR, 1.07 per SD; 95% CI, 1.01–1.13; P =0.016). In European patients with CAD in Penn Medicine BioBank who had undergone coronary catheterization, individuals in the top 10th percentile of PRS had a 2‐fold increased odds of ischemic HF (OR, 2.0; 95% CI, 1.1–3.7; P =0.02) compared with the bottom 10th percentile. Conclusions A PRS for HF enables risk stratification in patients with CAD. Future prospective studies aimed at demonstrating clinical utility are warranted for adoption in the patient setting.

Summary ParagraphTwo years into the SARS-CoV-2 pandemic, the post-acute sequelae of infection are compounding the global health crisis. Often debilitating, these sequelae are clinically heterogeneous and of unknown molecular etiology. Here, a transcriptome-wide investigation of this new condition was performed in a large cohort of acutely infected patients followed clinically into the post-acute period. Gene expression signatures of post-acute sequelae were already present in whole blood during the acute phase of infection, with both innate and adaptive immune cells involved. Plasma cells stood out as driving at least two distinct clusters of sequelae, one largely dependent on circulating antibodies against the SARS-CoV-2 spike protein and the other antibody-independent. Altogether, multiple etiologies of post-acute sequelae were found concomitant with SARS-CoV-2 infection, directly linking the emergence of these sequelae with the host response to the virus.

Polygenic risk scores (PRS) summarize genetic liability to a disease at the individual level, and the aim is to use them as biomarkers of disease and poor outcomes in real-world clinical practice. To date, few studies have assessed the prognostic value of PRS relative to standards of care. Schizophrenia (SCZ), the archetypal psychotic illness, is an ideal test case for this because the predictive power of the SCZ PRS exceeds that of most other common diseases. Here, we analyzed clinical and genetic data from two multi-ethnic cohorts totaling 8,541 adults with SCZ and related psychotic disorders, to assess whether the SCZ PRS improves the prediction of poor outcomes relative to clinical features captured in a standard psychiatric interview. For all outcomes investigated, the SCZ PRS did not improve the performance of predictive models, an observation that was generally robust to divergent case ascertainment strategies and the ancestral background of the study participants. The inclusion of polygenic risk scores does not improve the performance of standard-of-care predictive models of disease outcomes in patients with psychosis.

Rationale & Objective Outcomes of patients hospitalized with coronavirus disease 2019 (COVID-19) and acute kidney injury (AKI) are not well understood. The goal of this study was to investigate the survival and kidney outcomes of these patients. Study Design Retrospective cohort study. Setting & Participants Patients (aged ≥18 years) hospitalized with COVID-19 at 13 hospitals in metropolitan New York between March 1, 2020, and April 27, 2020, followed up until hospital discharge. Exposure AKI. Outcomes Primary outcome: in-hospital death. Secondary outcomes: requiring dialysis at discharge, recovery of kidney function. Analytical Approach Univariable and multivariable time-to-event analysis and logistic regression. Results Among 9,657 patients admitted with COVID-19, the AKI incidence rate was 38.4/1,000 patient-days. Incidence rates of in-hospital death among patients without AKI, with AKI not requiring dialysis (AKI stages 1-3), and with AKI receiving dialysis (AKI 3D) were 10.8, 31.1, and 37.5/1,000 patient-days, respectively. Taking those without AKI as the reference group, we observed greater risks for in-hospital death for patients with AKI 1-3 and AKI 3D (HRs of 5.6 [95% CI, 5.0-6.3] and 11.3 [95% CI, 9.6-13.1], respectively). After adjusting for demographics, comorbid conditions, and illness severity, the risk for death remained higher among those with AKI 1-3 (adjusted HR, 3.4 [95% CI, 3.0-3.9]) and AKI 3D (adjusted HR, 6.4 [95% CI, 5.5-7.6]) compared with those without AKI. Among patients with AKI 1-3 who survived, 74.1% achieved kidney recovery by the time of discharge. Among those with AKI 3D who survived, 30.6% remained on dialysis at discharge, and prehospitalization chronic kidney disease was the only independent risk factor associated with needing dialysis at discharge (adjusted OR, 9.3 [95% CI, 2.3-37.8]). Limitations Observational retrospective study, limited to the NY metropolitan area during the peak of the COVID-19 pandemic. Conclusions AKI in hospitalized patients with COVID-19 was associated with significant risk for death., Graphical abstract

Supplemental Digital Content is available in the text., OBJECTIVES: Critically ill patients with coronavirus disease 2019 have variable mortality. Risk scores could improve care and be used for prognostic enrichment in trials. We aimed to compare machine learning algorithms and develop a simple tool for predicting 28-day mortality in ICU patients with coronavirus disease 2019. DESIGN: This was an observational study of adult patients with coronavirus disease 2019. The primary outcome was 28-day inhospital mortality. Machine learning models and a simple tool were derived using variables from the first 48 hours of ICU admission and validated externally in independent sites and temporally with more recent admissions. Models were compared with a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 using the area under the receiver operating characteristic curve and calibration. SETTING: Sixty-eight U.S. ICUs. PATIENTS: Adults with coronavirus disease 2019 admitted to 68 ICUs in the United States between March 4, 2020, and June 29, 2020. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The study included 5,075 patients, 1,846 (36.4%) of whom died by day 28. eXtreme Gradient Boosting had the highest area under the receiver operating characteristic curve in external validation (0.81) and was well-calibrated, while k-nearest neighbors were the lowest performing machine learning algorithm (area under the receiver operating characteristic curve 0.69). Findings were similar with temporal validation. The simple tool, which was created using the most important features from the eXtreme Gradient Boosting model, had a significantly higher area under the receiver operating characteristic curve in external validation (0.78) than the Sequential Organ Failure Assessment score (0.69), National Early Warning Score (0.60), and CURB-65 (0.65; p < 0.05 for all comparisons). Age, number of ICU beds, creatinine, lactate, arterial pH, and Pao2/Fio2 ratio were the most important predictors in the eXtreme Gradient Boosting model. CONCLUSIONS: eXtreme Gradient Boosting had the highest discrimination overall, and our simple tool had higher discrimination than a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 on external validation. These models could be used to improve triage decisions and clinical trial enrichment.

Aims Clinical scoring systems for pulmonary embolism (PE) screening have low specificity and contribute to computed tomography pulmonary angiogram (CTPA) overuse. We assessed whether deep learning models using an existing and routinely collected data modality, electrocardiogram (ECG) waveforms, can increase specificity for PE detection. Methods and results We create a retrospective cohort of 21 183 patients at moderate- to high suspicion of PE and associate 23 793 CTPAs (10.0% PE-positive) with 320 746 ECGs and encounter-level clinical data (demographics, comorbidities, vital signs, and labs). We develop three machine learning models to predict PE likelihood: an ECG model using only ECG waveform data, an EHR model using tabular clinical data, and a Fusion model integrating clinical data and an embedded representation of the ECG waveform. We find that a Fusion model [area under the receiver-operating characteristic curve (AUROC) 0.81 ± 0.01] outperforms both the ECG model (AUROC 0.59 ± 0.01) and EHR model (AUROC 0.65 ± 0.01). On a sample of 100 patients from the test set, the Fusion model also achieves greater specificity (0.18) and performance (AUROC 0.84 ± 0.01) than four commonly evaluated clinical scores: Wells’ Criteria, Revised Geneva Score, Pulmonary Embolism Rule-Out Criteria, and 4-Level Pulmonary Embolism Clinical Probability Score (AUROC 0.50–0.58, specificity 0.00–0.05). The model is superior to these scores on feature sensitivity analyses (AUROC 0.66–0.84) and achieves comparable performance across sex (AUROC 0.81) and racial/ethnic (AUROC 0.77–0.84) subgroups. Conclusion Synergistic deep learning of ECG waveforms with traditional clinical variables can increase the specificity of PE detection in patients at least at moderate suspicion for PE.

Diabetic kidney disease (DKD) is considered partially hereditary, but the genetic factors underlying disease remain largely unknown. A key barrier to our understanding stems from its heterogeneity, and likely polygenic etiology. Proteinuric and non-proteinuric DKD are two sub-classes of DKD, defined by high urinary albumin-to-creatinine ratio (UACR) and low creatinine estimated glomerular filtration rate (eGFR). Prior genome-wide association studies (GWAS) have identified multiple loci associated with eGFR and UACR. We aimed to combine summary statistics from previous GWAS’ for eGFR and UACR in one prediction model and associate it with DKD prevalence. We then tested this using genetic data from 18,841 individuals diagnosed with type 2 diabetes in UK Biobank. We computed two genome-wide polygenic risk scores (GPS) aggregating effects of common variants associated with the two measurements, eGFR and UACR. We show that including both GPS’ in a single model confers significant improvement in comparison with the single GPS model generated from GWAS summary statistics for DKD. We also find in replication analysis in 5,389 individuals in the multi-ethnic BioMe Biobank, that although the combined model had consistent direction of association, the lowest performance was in individuals with recent African ancestry. In summary, we show that joint modeling of polygenic associations of eGFR and UACR is more significantly associated with DKD than individual modeling as well as a GPS comprised of only DKD summary statistics and may be used to gain insights into biology and progression. However, efforts should be made to develop and validate polygenic approaches in diverse populations.

Objectives Classifying hospital admissions into various acute myocardial infarction phenotypes in electronic health records (EHRs) is a challenging task with strong research implications that remains unsolved. To our knowledge, this study is the first study to design and validate phenotyping algorithms using cardiac catheterizations to identify not only patients with a ST-elevation myocardial infarction (STEMI), but the specific encounter when it occurred. Materials and Methods We design and validate multi-modal algorithms to phenotype STEMI on a multicenter EHR containing 5.1 million patients and 115 million patient encounters by using discharge summaries, diagnosis codes, electrocardiography readings, and the presence of cardiac catheterizations on the encounter. Results We demonstrate that robustly phenotyping STEMIs by selecting discharge summaries containing “STEM” has the potential to capture the most number of STEMIs (positive predictive value [PPV] = 0.36, N = 2110), but that addition of a STEMI-related International Classification of Disease (ICD) code and cardiac catheterizations to these summaries yields the highest precision (PPV = 0.94, N = 952). Discussion and Conclusion In this study, we demonstrate that the incorporation of percutaneous coronary intervention increases the PPV for detecting STEMI-related patient encounters from the EHR.

Federated learning is a technique for training predictive models without sharing patient-level data, thus maintaining data security while allowing inter-institutional collaboration. We used federated learning to predict acute kidney injury within three and seven days of admission, using demographics, comorbidities, vital signs, and laboratory values, in 4029 adults hospitalized with COVID-19 at five sociodemographically diverse New York City hospitals, between March-October 2020. Prediction performance of federated models was generally higher than single-hospital models and was comparable to pooled-data models. In the first use-case in kidney disease, federated learning improved prediction of a common complication of COVID-19, while preserving data privacy.

KidneyIntelX is a composite risk score incorporating biomarkers and clinical variables for predicting progression of prevalent diabetic kidney disease (DKD). The change of this score over time in response to SGLT2 inhibitors and how these changes associate with future kidney outcomes is unknown. We measured soluble Tumor Necrosis Factor Receptor 1 (sTNFR-1), soluble Tumor Necrosis Factor Receptor 2 (sTNFR-2), and Kidney Injury Molecule (KIM-1) on banked samples from CANVAS trial participants with baseline DKD (eGFR In conclusion, CANA treatment reduced KidneyIntelX risk scores. Changes in the KidneyIntelX score from baseline to 1 year predict future risk of DKD progression whether they resulted from kidney protection afforded by SGLT2i therapy, or decline in kidney function caused by disease progression. Disclosure D. W. Lam: None. G. N. Nadkarni: Advisory Panel; Self; Renalytix AI plc., Consultant; Self; AstraZeneca, Renalytix AI plc., Variant Bio, Research Support; Self; Renalytix AI plc., Stock/Shareholder; Self; Renalytix AI plc. B. Neal: Advisory Panel; Self; Abbott, Janssen Pharmaceuticals, Inc., Novartis Pharmaceuticals Corporation, Pfizer Inc., Roche Pharma, Servier Laboratories, Research Support; Self; Janssen Pharmaceuticals, Inc., Merck Schering Plough, Roche Pharma, Servier Laboratories. K. W. Mahaffey: Consultant; Self; Abbott, Amgen Inc., Anthos, AstraZeneca, Baim Institute for Clinical Research, Bayer Healthcare Pharmaceuticals Inc., Boehringer Ingelheim Pharmaceuticals, Inc., CSL Behring, Elsevier, Inova, Intermountain Health, Johnson & Johnson, Medscape, Mount Sinai, Mundipharma International, MyoKardia, National Institutes of Health, Novartis Pharmaceuticals Corporation, Novo Nordisk, Otsuka America Pharmaceutical, Inc., Portola Pharmaceuticals, Inc., Regeneron Pharmaceuticals Inc., SmartMedics, Theravance Biopharma, Research Support; Self; Afferent, AHA, Amgen Inc., Apple, AstraZeneca, Bayer Healthcare Pharmaceuticals Inc., Cardiva Medical, Inc, Eidos, Ferring Pharmaceuticals Inc., Gilead Sciences, Inc., Google, Johnson & Johnson, Luitpold Pharmaceuticals, Inc., Medtronic, Merck & Co., Inc., National Institutes of Health, Novartis Pharmaceuticals Corporation, Sanifit, Sanofi, St. Jude Medical. N. Rosenthal: Employee; Self; Janssen Research & Development, LLC. M. K. Hansen: Employee; Self; Janssen Pharmaceuticals, Inc. H. L. Heerspink: Consultant; Self; AbbVie Inc., Astellas Pharma Inc., AstraZeneca, Bayer AG, Boehringer Ingelheim International GmbH, Chinook, CSL Behring, Fresenius Medical Care, Gilead Sciences, Inc., Janssen Research & Development, LLC, Merck & Co., Inc., Mitsubishi Corporation Life Sciences Limited, Mundipharma International, Novo Nordisk, Retrophin, Inc., Research Support; Self; AbbVie Inc., AstraZeneca, Boehringer Ingelheim International GmbH, Janssen Research & Development, LLC. S. Coca: Advisory Panel; Self; Akebia Therapeutics, Inc., Bayer AG, Boehringer Ingelheim International GmbH, Consultant; Self; CHF Solutions, Relypsa Inc., Renalytix AI plc., Takeda Pharmaceutical Co., Research Support; Self; inRegen, XORTX Therapeutics Inc., Stock/Shareholder; Self; Renalytix AI plc.

Objective Electronic health record (EHR) systems contain structured data (such as diagnostic codes) and unstructured data (clinical documentation). Clinical insights can be derived from analyzing both. The use of natural language processing (NLP) algorithms to effectively analyze unstructured data has been well demonstrated. Here we examine the utility of NLP for the identification of patients with non-alcoholic fatty liver disease, assess patterns of disease progression, and identify gaps in care related to breakdown in communication among providers. Materials and Methods All clinical notes available on the 38,575 patients enrolled in the Mount Sinai BioMe cohort were loaded into the NLP system. We compared analysis of structured and unstructured EHR data using NLP, free-text search, and diagnostic codes with validation against expert adjudication. We then used the NLP findings to measure physician impression of progression from early-stage NAFLD to NASH or cirrhosis. Similarly, we used the same NLP findings to identify mentions of NAFLD in radiology reports that did not persist into clinical notes. Results Out of 38,575 patients, we identified 2,281 patients with NAFLD. From the remainder, 10,653 patients with similar data density were selected as a control group. NLP outperformed ICD and text search in both sensitivity (NLP: 0.93, ICD: 0.28, text search: 0.81) and F2 score (NLP: 0.92, ICD: 0.34, text search: 0.81). Of 2281 NAFLD patients, 673 (29.5%) were believed to have progressed to NASH or cirrhosis. Among 176 where NAFLD was noted prior to NASH, the average progression time was 410 days. 619 (27.1%) NAFLD patients had it documented only in radiology notes and not acknowledged in other forms of clinical documentation. Of these, 170 (28.4%) were later identified as having likely developed NASH or cirrhosis after a median 1057.3 days. Discussion NLP-based approaches were more accurate at identifying NAFLD within the EHR than ICD/text search-based approaches. Suspected NAFLD on imaging is often not acknowledged in subsequent clinical documentation. Many such patients are later found to have more advanced liver disease. Analysis of information flows demonstrated loss of key information that could have been used to help prevent the progression of early NAFLD (NAFL) to NASH or cirrhosis. Conclusion For identification of NAFLD, NLP performed better than alternative selection modalities. It then facilitated analysis of knowledge flow between physician and enabled the identification of breakdowns where key information was lost that could have slowed or prevented later disease progression.

Ethnic disparities in health outcomes exist among multiple complex diseases especially cardiovascular disease, hypertension, and kidney disease. Recent discoveries in genetics have taught us that these disparities go beyond environmental and socioeconomic factors. The discovery of ethnic-specific risk variants in the Apolipoprotein L1 (APOL1) gene on chromosome 22 seen only in individuals of recent African ancestry explains a large proportion of kidney disease disparities. In addition, recent large-scale genotype-phenotype association studies have identified associations with cardiovascular disease and hypertension. This review aims to review the recent literature in this field and point toward future directions for research.

Background Glomerular endothelial dysfunction and neoangiogenesis have long been implicated in the pathogenesis of diabetic kidney disease (DKD). However, the specific molecular pathways contributing to these processes in the early stages of DKD are not well understood. Our recent transcriptomic profiling of glomerular endothelial cells identified a number of proangiogenic genes that were upregulated in diabetic mice, including leucine-rich α -2-glycoprotein 1 (LRG1). LRG1 was previously shown to promote neovascularization in mouse models of ocular disease by potentiating endothelial TGF- β /activin receptor-like kinase 1 (ALK1) signaling. However, LRG1’s role in the kidney, particularly in the setting of DKD, has been unclear. Methods We analyzed expression of LRG1 mRNA in glomeruli of diabetic kidneys and assessed its localization by RNA in situ hybridization. We examined the effects of genetic ablation of Lrg1 on DKD progression in unilaterally nephrectomized, streptozotocin-induced diabetic mice at 12 and 20 weeks after diabetes induction. We also assessed whether plasma LRG1 was associated with renal outcome in patients with type 2 diabetes. Results LRG1 localized predominantly to glomerular endothelial cells, and its expression was elevated in the diabetic kidneys. LRG1 ablation markedly attenuated diabetes-induced glomerular angiogenesis, podocyte loss, and the development of diabetic glomerulopathy. These improvements were associated with reduced ALK1-Smad1/5/8 activation in glomeruli of diabetic mice. Moreover, increased plasma LRG1 was associated with worse renal outcome in patients with type 2 diabetes. Conclusions These findings identify LRG1 as a potential novel pathogenic mediator of diabetic glomerular neoangiogenesis and a risk factor in DKD progression.

Importance: Primary open-angle glaucoma presents with increased prevalence and a higher degree of clinical severity in populations of African ancestry compared with European or Asian ancestry. Despite this, individuals of African ancestry remain understudied in genomic research for blinding disorders.Objectives: To perform a genome-wide association study (GWAS) of African ancestry populations and evaluate potential mechanisms of pathogenesis for loci associated with primary open-angle glaucoma.Design, Settings, and Participants: A 2-stage GWAS with a discovery data set of 2320 individuals with primary open-angle glaucoma and 2121 control individuals without primary open-angle glaucoma. The validation stage included an additional 6937 affected individuals and 14 917 unaffected individuals using multicenter clinic- and population-based participant recruitment approaches. Study participants were recruited from Ghana, Nigeria, South Africa, the United States, Tanzania, Britain, Cameroon, Saudi Arabia, Brazil, the Democratic Republic of the Congo, Morocco, Peru, and Mali from 2003 to 2018. Individuals with primary open-angle glaucoma had open iridocorneal angles and displayed glaucomatous optic neuropathy with visual field defects. Elevated intraocular pressure was not included in the case definition. Control individuals had no elevated intraocular pressure and no signs of glaucoma.Exposures: Genetic variants associated with primary open-angle glaucoma.Main Outcomes and Measures: Presence of primary open-angle glaucoma. Genome-wide significance was defined as P < 5 × 10−8 in the discovery stage and in the meta-analysis of combined discovery and validation data.Results: A total of 2320 individuals with primary open-angle glaucoma (mean [interquartile range] age, 64.6 [56-74] years; 1055 [45.5%] women) and 2121 individuals without primary open-angle glaucoma (mean [interquartile range] age, 63.4 [55-71] years; 1025 [48.3%] women) were included in the discovery GWAS. The GWAS discovery meta-analysis demonstrated association of variants at amyloid-β A4 precursor protein-binding family B member 2 (APBB2; chromosome 4, rs59892895T>C) with primary open-angle glaucoma (odds ratio [OR], 1.32 [95% CI, 1.20-1.46]; P = 2 × 10−8). The association was validated in an analysis of an additional 6937 affected individuals and 14 917 unaffected individuals (OR, 1.15 [95% CI, 1.09-1.21]; P < .001). Each copy of the rs59892895*C risk allele was associated with increased risk of primary open-angle glaucoma when all data were included in a meta-analysis (OR, 1.19 [95% CI, 1.14-1.25]; P = 4 × 10−13). The rs59892895*C risk allele was present at appreciable frequency only in African ancestry populations. In contrast, the rs59892895*C risk allele had a frequency of less than 0.1% in individuals of European or Asian ancestry.Conclusions and Relevance: In this genome-wide association study, variants at the APBB2 locus demonstrated differential association with primary open-angle glaucoma by ancestry. If validated in additional populations this finding may have implications for risk assessment and therapeutic strategies.

Gut bacterial microbiota is altered in patients with advanced renal disease and those on dialysis. However, it is not clear yet what bacterial composition changes are due to the renal insufficiency per se, and what are in result of the accompanying interventions and comorbid conditions. Most studies analyzed diabetic nephropathy, hypertensive nephropathy, and glomerulonephritis patients which might have directly influenced the microbiome regardless of alterations in renal function. We present in this report changes in gut bacterial microbiota in a highly selected group of patients with strict inclusion criteria to eliminate the effects of the confounding factors on the microbiome composition. We conducted multiple analysis approaches according to participants’ renal function to further understand microbiome alteration in different degrees of renal insufficiency. An interesting group of bacteria showed a step-wise change in relative abundance in response to the three groups’ analysis. These bacteria either decreased or increased from mild, moderate to severe renal insufficiency indicating strong and direct effects of the uremic milieu on its relative abundance. We also ran a sensitivity analysis that took into account an assembly of the significant taxa observed in an approach to investigate whether these taxa can fully explain the separation noted between the groups. We determined the projected metabolic pathways altered according to the gut microbiota composition changes. This report not only delineates with a higher certainty the effects of alteration in renal function on the microbiome, but also explores the possible role of dysbiosis on comorbid conditions through alterations in the projected metabolic pathways. Impact statement The heterogeneity of the renal disease, therapeutic interventions, and the original cause of the renal failure, all directly affect the microbiota. We delineate in this report the direct effect of decreased renal function on the bacterial composition following stringent criteria to eliminate the possibilities of other confounding factors and dissect the direct effects of the uremic milieu. We analyzed the microbiome following three different approaches to further evaluate the effects of mild, moderate and advanced renal insufficiency on the microbiome. We also present here a detailed functional analysis of the projected altered pathways secondary to changes in the microbiome composition.

Variation in hospital mortality has been described for coronavirus disease 2019 (COVID-19), but the factors that explain these differences remain unclear.Our objective was to utilize a large, nationally representative dataset of critically ill adults with COVID-19 to determine which factors explain mortality variability.In this multicenter cohort study, we examined adults hospitalized in intensive care units with COVID-19 at 70 United States hospitals between March and June 2020. The primary outcome was 28-day mortality. We examined patient-level and hospital-level variables. Mixed-effects logistic regression was used to identify factors associated with interhospital variation. The median odds ratio (OR) was calculated to compare outcomes in higher- vs. lower-mortality hospitals. A gradient boosted machine algorithm was developed for individual-level mortality models.A total of 4,019 patients were included, 1537 (38%) of whom died by 28 days. Mortality varied considerably across hospitals (0-82%). After adjustment for patient- and hospital-level domains, interhospital variation was attenuated (OR decline from 2.06 [95% CI, 1.73-2.37] to 1.22 [95% CI, 1.00-1.38]), with the greatest changes occurring with adjustment for acute physiology, socioeconomic status, and strain. For individual patients, the relative contribution of each domain to mortality risk was: acute physiology (49%), demographics and comorbidities (20%), socioeconomic status (12%), strain (9%), hospital quality (8%), and treatments (3%).There is considerable interhospital variation in mortality for critically ill patients with COVID-19, which is mostly explained by hospital-level socioeconomic status, strain, and acute physiologic differences. Individual mortality is driven mostly by patient-level factors. This article is open access and distributed under the terms of the Creative Commons Attribution Non-Commercial No Derivatives License 4.0 (http://creativecommons.org/licenses/by-nc-nd/4.0/).

BackgroundRapid evaluation of left and right ventricular function using deep learning (DL) on electrocardiograms (ECG) can assist diagnostic workflow. However, DL tools to estimate right ventricular (RV) function do not exist, while ones to estimate left ventricular (LV) function are restricted to quantification of very low LV function only.ObjectivesThis study sought to develop deep learning models capable of comprehensively quantifying left and right ventricular dysfunction from ECG data in a large, diverse population.MethodsA multi-center study was conducted with data from five New York City hospitals; four for internal testing and one serving as external validation. We created novel DL models to classify Left Ventricular Ejection Fraction (LVEF) into categories derived from the latest universal definition of heart failure, estimate LVEF through regression, and predict a composite outcome of either RV systolic dysfunction or RV dilation.ResultsWe obtained echocardiogram LVEF estimates for 147,636 patients paired to 715,890 ECGs. We used Natural Language Processing (NLP) to extract RV size and systolic function information from 404,502 echocardiogram reports paired to 761,510 ECGs for 148,227 patients.For LVEF classification in internal testing, Area Under Curve (AUC) at detection of LVEF50% was 0.94 (95% CI:0.94-0.94), 0.82 (0.81-0.83), and 0.89 (0.89-0.89) respectively. For external validation, these results were 0.94 (0.94-0.95), 0.73 (0.72-0.74) and 0.87 (0.87-0.88). For regression, the mean absolute error was 5.84% (5.82-5.85) for internal testing, and 6.14% (6.13-6.16) in external validation. For prediction of the composite RV outcome, AUC was 0.84 (0.84-0.84) in both internal testing and external validation.ConclusionsDL on ECG data can be utilized to create inexpensive screening, diagnostic, and predictive tools for both LV/RV dysfunction. Such tools may bridge the applicability of ECGs and echocardiography, and enable prioritization of patients for further interventions for either sided failure progressing to biventricular disease.

This study sought to develop DL models capable of comprehensively quantifying left and right ventricular dysfunction from ECG data in a large, diverse population.Rapid evaluation of left and right ventricular function using deep learning (DL) on electrocardiograms (ECGs) can assist diagnostic workflow. However, DL tools to estimate right ventricular (RV) function do not exist, whereas those to estimate left ventricular (LV) function are restricted to quantification of very low LV function only.A multicenter study was conducted with data from 5 New York City hospitals: 4 for internal testing and 1 serving as external validation. We created novel DL models to classify left ventricular ejection fraction (LVEF) into categories derived from the latest universal definition of heart failure, estimate LVEF through regression, and predict a composite outcome of either RV systolic dysfunction or RV dilation.We obtained echocardiogram LVEF estimates for 147,636 patients paired to 715,890 ECGs. We used natural language processing (NLP) to extract RV size and systolic function information from 404,502 echocardiogram reports paired to 761,510 ECGs for 148,227 patients. For LVEF classification in internal testing, area under curve (AUC) at detection of LVEF ≤40%, 40% LVEF ≤50%, and LVEF50% was 0.94 (95% CI: 0.94-0.94), 0.82 (95% CI: 0.81-0.83), and 0.89 (95% CI: 0.89-0.89), respectively. For external validation, these results were 0.94 (95% CI: 0.94-0.95), 0.73 (95% CI: 0.72-0.74), and 0.87 (95% CI: 0.87-0.88). For regression, the mean absolute error was 5.84% (95% CI: 5.82%-5.85%) for internal testing and 6.14% (95% CI: 6.13%-6.16%) in external validation. For prediction of the composite RV outcome, AUC was 0.84 (95% CI: 0.84-0.84) in both internal testing and external validation.DL on ECG data can be used to create inexpensive screening, diagnostic, and predictive tools for both LV and RV dysfunction. Such tools may bridge the applicability of ECGs and echocardiography and enable prioritization of patients for further interventions for either sided failure progressing to biventricular disease.

Summary Robust phenotyping of patients from electronic health records (EHRs) at scale is a challenge in clinical informatics. Here, we introduce Phe2vec, an automated framework for disease phenotyping from EHRs based on unsupervised learning and assess its effectiveness against standard rule-based algorithms from Phenotype KnowledgeBase (PheKB). Phe2vec is based on pre-computing embeddings of medical concepts and patients' clinical history. Disease phenotypes are then derived from a seed concept and its neighbors in the embedding space. Patients are linked to a disease if their embedded representation is close to the disease phenotype. Comparing Phe2vec and PheKB cohorts head-to-head using chart review, Phe2vec performed on par or better in nine out of ten diseases. Differently from other approaches, it can scale to any condition and was validated against widely adopted expert-based standards. Phe2vec aims to optimize clinical informatics research by augmenting current frameworks to characterize patients by condition and derive reliable disease cohorts., Highlights • Automated framework for disease phenotyping from electronic health records • Unsupervised learning to identify cohorts for any disease of interest • Comparable or superior performance with that of widely adopted expert-based standards, The bigger picture Electronic health record (EHR)-based research is central to fulfill the vision of personalized medicine. However, due to EHRs being structured for billing purposes, reliably identifying patients with a phenotype of interest in a clinical data warehouse is difficult. Phe2vec uses unsupervised learning to derive medical concept embeddings and build phenotype definitions to identify patient cohorts. Pre-training embeddings leads to a flexible solution which is applicable to any disease by simply defining a seed concept. This method showed performance comparable or superior to that of other widely adopted EHR phenotyping approaches. Phe2vec aims to contribute to the next generation of clinical systems that use machine learning to effectively support clinicians in their activities. These systems capable of scaling to a large number of diseases, patients, and health data promise to offer a more holistic way to examine disease complexity and to improve clinical practice and medical research., De Freitas et al. present Phe2vec, an automated framework for disease phenotyping based on unsupervised learning. Phe2vec derives embeddings of medical concepts from electronic health records and uses them to define phenotypes and measure the association between diseases and patients. The authors demonstrate the method's effectiveness via comparison with both rule-based algorithms and standard automated methods. Phe2vec can be used to identify patient cohorts by simply specifying a seed concept associated to any disease of interest.

Traditional Machine Learning (ML) models have had limited success in predicting Coronoavirus-19 (COVID-19) outcomes using Electronic Health Record (EHR) data partially due to not effectively capturing the inter-connectivity patterns between various data modalities. In this work, we propose a novel framework that utilizes relational learning based on a heterogeneous graph model (HGM) for predicting mortality at different time windows in COVID-19 patients within the intensive care unit (ICU). We utilize the EHRs of one of the largest and most diverse patient populations across five hospitals in major health system in New York City. In our model, we use an LSTM for processing time varying patient data and apply our proposed relational learning strategy in the final output layer along with other static features. Here, we replace the traditional softmax layer with a Skip-Gram relational learning strategy to compare the similarity between a patient and outcome embedding representation. We demonstrate that the construction of a HGM can robustly learn the patterns classifying patient representations of outcomes through leveraging patterns within the embeddings of similar patients. Our experimental results show that our relational learning-based HGM model achieves higher area under the receiver operating characteristic curve (auROC) than both comparator models in all prediction time windows, with dramatic improvements to recall.

Schizophrenia (SCZ) is the archetypal severe mental illness and one of the most deeply characterized human genetic traits. Like most common diseases SCZ is highly polygenic, and as such its genetic liability can be summarized at the individual level by a polygenic risk score (PRS). Polygenic risk scores are a cornerstone of the precision medicine vision, as it is widely anticipated they will come to serve as biomarkers of disease and poor outcomes in real-world clinical practice. However, to date, few studies have assessed their actual prognostic value relative to current standards-of-care. SCZ is an ideal test case towards this end because the predictive power of the SCZ PRS exceeds that of most other common diseases. Here, we analyzed clinical and genetic data from two multi-ethnic cohorts totaling 8,541 adults with SCZ and related psychotic disorders, assessing whether the SCZ PRS improves poor outcome prediction relative to clinical features captured in a standard psychiatric interview. For all outcomes investigated, the SCZ PRS did not improve the performance of predictive models, an observation that was generally robust to divergent case definitions and ancestral backgrounds of study participants. These findings demonstrate the limited potential of even the most powerful contemporary polygenic risk scores as a tool for individualized outcome prediction.