Characteristics and Outcomes of NELL1 Membranous Nephropathy in Lipoic Acid Users and Nonusers.

Introduction: Neural epidermal growth factor like 1 membranous nephropathy (NELL1 MN) is associated with various secondary etiologies. However, previous studies on the frequency of these associations and their impact on outcomes are limited. We report a large multiinstitutional series of patients with NELL1 MN with a focus on secondary associations, pathology findings, and their impact on outcome. Methods: We retrospectively reviewed clinicopathologic features of NELL1 MN from 3 institutions and analyzed clinical and histologic associations with outcome. Results: Of 70 patients, 53% were male with a median age of 66 years; median proteinuria was 5.9 g/d. NELL1 MN was associated with lipoic acid (36%), heavy nonsteroidal antiinflammatory drug (NSAID) use (27%), autoimmune disease (23%), malignancy (10% recent, 23% any), mercury exposure (1%), and 11% had no known secondary association. At median follow-up of 11 months, 72% achieved complete or partial remission. Remission rate was 91% in patients with lipoic acid-associated NELL1 MN and ≥6 months of follow-up. On multivariable analyses, patients with primary NELL1 MN (adjusted odds ratio [OR]: 19.7, P = 0.01) and increasing degree of tubular atrophy and interstitial fibrosis (IFTA) (adjusted OR 1.1, P = 0.01) were less likely to achieve any remission, whereas complete remission (CR) was associated with lipoic acid use (adjusted OR: 10.9, P = 0.04, 95% confidence interval [CI]: 1.2-100) and lesser degrees of IFTA (adjusted OR: 0.79, P = 0.16, 95% CI: 0.66-0.96). Conclusion: Our findings strengthen the association between lipoic acid and NELL1 MN. Furthermore, our findings suggest that discontinuation of lipoic acid without immunosuppression should be considered as the first-line treatment.

Benchmarking clinical risk prediction algorithms with ensemble machine learning for the non-invasive diagnosis of liver fibrosis in NAFLD.

Ensemble machine learning methods, like the superlearner, combine multiple models into a single one to enhance predictive accuracy. Here we explore the potential of the superlearner as a benchmarking tool for clinical risk prediction, illustrating the approach in identifying significant liver fibrosis among patients with non-alcoholic fatty liver disease (NAFLD). We used 23 demographic/clinical variables to train superlearner(s) on data from the NASH-CRN observational study (n=648) and validated models with data from the FLINT trial (n=270) and NHANES participants with NAFLD (n=1244). Comparing the superlearner's performance to existing models (FIB-4, NFS, Forns, APRI, BARD, and SAFE), it exhibited strong discriminative ability in the FLINT and NHANES validation sets, with AUCs of 0.79 (95% CI: 0.73-0.84) and 0.74 (95% CI: 0.68-0.79) respectively. Notably, the SAFE score performed similarly to the superlearner, both of which outperformed FIB-4, APRI, Forns, and BARD scores in the validation datasets. Surprisingly, the superlearner derived from 12 base models matched the performance of one with 90 base models. Overall, the superlearner, being the "best-in-class" ML predictor, excelled in detecting fibrotic NASH, and this approach can be used to benchmark the performance of conventional clinical risk prediction models.

Endometrioid Endometrial RNA Index Predicts Recurrence in Stage I Patients.

PURPOSE: Risk prediction with genomic and transcriptomic data has the potential to improve patient outcomes by enabling clinicians to identify patients requiring adjuvant treatment approaches, while sparing low-risk patients from unnecessary interventions. Endometrioid endometrial carcinoma (EEC) is the most common cancer in women in developed countries, and rates of endometrial cancer are increasing. EXPERIMENTAL DESIGN: We collected a 105-patient case-control cohort of stage I EEC comprised of 45 patients who experienced recurrence less than 6 years after excision, and 60 FIGO grade matched controls without recurrence. We first utilized two RNA based, previously validated machine learning approaches, namely EcoTyper and Complexity Index in Sarcoma (CINSARC). We developed Endometrioid Endometrial RNA Index (EERI) which uses RNA expression data from 46 genes to generate a personalized risk score for each patient. EERI was trained on our 105-patient cohort and tested on a publicly available cohort of 263 stage I EEC patients. RESULTS: EERI was able to predict recurrences with 94% accuracy in the training set and 81% accuracy in the test set. In the test set, patients assigned as EERI high-risk were significantly more likely to experience recurrence (30%) than the EERI low-risk group (1%) with a hazard ratio of 9.9 (95% CI 4.1-23.8, P <0.001). CONCLUSIONS: Tumors with high-risk genetic features may require additional treatment or closer monitoring and are not readily identified using traditional clinicopathologic and molecular features. EERI performs with high sensitivity and modest specificity, which may benefit from further optimization and validation in larger independent cohorts.

Interviewer biases in medical survey data: The example of blood pressure measurements.

Health agencies rely upon survey-based physical measures to estimate the prevalence of key global health indicators such as hypertension. Such measures are usually collected by nonhealthcare worker personnel and are potentially subject to measurement error due to variations in interviewer technique and setting, termed "interviewer effects." In the context of physical measurements, particularly in low- and middle-income countries, interviewer-induced biases have not yet been examined. Using blood pressure as a case study, we aimed to determine the relative contribution of interviewer effects on the total variance of blood pressure measurements in three large nationally representative health surveys from the Global South. We utilized 169,681 observations between 2008 and 2019 from three health surveys (Indonesia Family Life Survey, National Income Dynamics Study of South Africa, and Longitudinal Aging Study in India). In a linear mixed model, we modeled systolic blood pressure as a continuous dependent variable and interviewer effects as random effects alongside individual factors as covariates. To quantify the interviewer effect-induced uncertainty in hypertension prevalence, we utilized a bootstrap approach comparing subsamples of observed blood pressure measurements to their adjusted counterparts. Our analysis revealed that the proportion of variation contributed by interviewers to blood pressure measurements was statistically significant but small: ∼0.24--2.2% depending on the cohort. Thus, hypertension prevalence estimates were not substantially impacted at national scales. However, individual extreme interviewers could account for measurement divergences as high as 12%. Thus, highly biased interviewers could have important impacts on hypertension estimates at the subdistrict level.

Representation of Real-World Adults With Chronic Kidney Disease in Clinical Trials Supporting Blood Pressure Treatment Targets.

BACKGROUND: Little is known about how well trial participants with chronic kidney disease (CKD) represent real-world adults with CKD. We assessed the population representativeness of clinical trials supporting the 2021 Kidney Disease: Improving Global Outcomes blood pressure (BP) guidelines in real-world adults with CKD. METHODS AND RESULTS: Using a cross-sectional analysis, we identified patients with CKD who met the guideline definition of hypertension based on use of antihypertensive medications or sustained systolic BP ≥120 mm Hg in 2019 in the Veterans Affairs and Kaiser Permanente of Southern California. We applied the eligibility criteria from 3 BP target trials, SPRINT (Systolic Pressure Intervention Trial), ACCORD (Action to Control Cardiovascular Risk in Diabetes), and AASK (African American Study of Kidney Disease), to estimate the proportion of adults with a systolic BP above the guideline-recommended target and the proportion who met eligibility criteria for ≥1 trial. We identified 503 480 adults in the Veterans Affairs and 73 412 adults in Kaiser Permanente of Southern California with CKD and hypertension in 2019. We estimated 79.7% in the Veterans Affairs and 87.3% in the Kaiser Permanente of Southern California populations had a systolic BP ≥120 mm Hg; only 23.8% [23.7%-24.0%] in the Veterans Affairs and 20.8% [20.5%-21.1%] in Kaiser Permanente of Southern California were trial-eligible. Among trial-ineligible patients, >50% met >1 exclusion criteria. CONCLUSIONS: Major BP target trials were representative of fewer than 1 in 4 real-world adults with CKD and hypertension. A large proportion of adults who are at risk for cardiovascular morbidity from hypertension and susceptible to adverse treatment effects lack relevant treatment information.

Antineutrophil Cytoplasmic Antibody-Associated Vasculitis with Active Kidney Involvement in the United States: 2016-2020.

Introduction: Antineutrophil cytoplasmic antibody (ANCA)-associated vasculitis (AAV) and its subtypes, granulomatosis with polyangiitis (GPA), microscopic polyangiitis (MPA), and eosinophilic GPA (EGPA), frequently present with acute kidney injury and can often lead to kidney failure, even with successful induction therapy. Few contemporary, nationally representative studies have described hospital complications of AAV. Methods: Using data from the 2016-2020 National Inpatient Sample, a nationally representative database, we identified hospitalizations from adults with a new diagnosis of AAV (subtype or unspecified) and an inpatient kidney biopsy during the index hospitalization. We described baseline characteristics, associated inpatient procedures and complications, and compared lengths of stay and costs by geographic region, hospital characteristics, and AAV subtype. Results: We identified an average of 1,329 cases of hospitalized AAV with a concurrent kidney biopsy per year over the 5-year period. More than 50% were not designated as having a specific subtype, likely owing to delays in documentation of histopathology. Kidney involvement was severe as the majority of patients developed acute kidney injury, and the proportion of patients who required inpatient dialysis was approximately 24%. Approximately 20% of patients developed hypoxia. Inpatient plasmapheresis was delivered to 20.4% and 20.6% of patients with GPA and MPA, respectively. There were no clinically meaningful or statistically significant differences in adjusted length of stay or inpatient costs among AAV subtypes. Admission in the Midwest region was associated with shorter hospital stays and lower costs than that in the Northeast, South, or West regions of the USA (adjusted p = 0.007 and <0.001, respectively). Conclusion: AAV with acute kidney involvement remains a challenging, high-risk condition. Maintaining a high index of suspicion and a low threshold for kidney biopsy should help ameliorate short- and long-term complications.

Quantitative assessment of glomerular basement membrane collagen IV α chains in paraffin sections from patients with focal segmental glomerulosclerosis and Alport gene variants.

Focal segmental glomerulosclerosis (FSGS) lesions have been linked to variants in COL4A3/A4/A5 genes, which are also mutated in Alport syndrome. Although it could be useful for diagnosis, quantitative evaluation of glomerular basement membrane (GBM) type IV collagen (colIV) networks is not widely used to assess these patients. To do so, we developed immunofluorescence imaging for collagen α5(IV) and α1/2(IV) on kidney paraffin sections with Airyscan confocal microscopy that clearly distinguishes GBM collagen α3α4α5(IV) and α1α1α2(IV) as two distinct layers, allowing quantitative assessment of both colIV networks. The ratios of collagen α5(IV):α1/2(IV) mean fluorescence intensities (α5:α1/2 intensity ratios) and thicknesses (α5:α1/2 thickness ratios) were calculated to represent the levels of collagen α3α4α5(IV) relative to α1α1α2(IV). The α5:α1/2 intensity and thickness ratios were comparable across all 11 control samples, while both ratios were significantly and markedly decreased in all patients with pathogenic or likely pathogenic Alport COL4A variants, supporting validity of this approach. Thus, with further validation of this technique, quantitative measurement of GBM colIV subtype abundance by immunofluorescence, may potentially serve to identify the subgroup of patients with FSGS lesions likely to harbor pathogenic COL4A variants who could benefit from genetic testing.

Matrix viscoelasticity promotes liver cancer progression in the pre-cirrhotic liver.

Type 2 diabetes mellitus is a major risk factor for hepatocellular carcinoma (HCC). Changes in extracellular matrix (ECM) mechanics contribute to cancer development1,2, and increased stiffness is known to promote HCC progression in cirrhotic conditions3,4. Type 2 diabetes mellitus is characterized by an accumulation of advanced glycation end-products (AGEs) in the ECM; however, how this affects HCC in non-cirrhotic conditions is unclear. Here we find that, in patients and animal models, AGEs promote changes in collagen architecture and enhance ECM viscoelasticity, with greater viscous dissipation and faster stress relaxation, but not changes in stiffness. High AGEs and viscoelasticity combined with oncogenic ß-catenin signalling promote HCC induction, whereas inhibiting AGE production, reconstituting the AGE clearance receptor AGER1 or breaking AGE-mediated collagen cross-links reduces viscoelasticity and HCC growth. Matrix analysis and computational modelling demonstrate that lower interconnectivity of AGE-bundled collagen matrix, marked by shorter fibre length and greater heterogeneity, enhances viscoelasticity. Mechanistically, animal studies and 3D cell cultures show that enhanced viscoelasticity promotes HCC cell proliferation and invasion through an integrin-ß1-tensin-1-YAP mechanotransductive pathway. These results reveal that AGE-mediated structural changes enhance ECM viscoelasticity, and that viscoelasticity can promote cancer progression in vivo, independent of stiffness.

Heterogeneous Treatment Effects of Intensive Glycemic Control on Kidney Microvascular Outcomes and Mortality in ACCORD.

SIGNIFICANCE STATEMENT: Identifying and quantifying treatment effect variation across patients is the fundamental challenge of precision medicine. Here we quantify heterogeneous treatment effects of intensive glycemic control in the Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial, considering three outcomes of interest-a composite kidney outcome (driven by macroalbuminuria), all-cause mortality, and first assisted hypoglycemic event. We demonstrate that the effects of intensive glycemic control vary with risk of kidney failure, as predicted by the kidney failure risk equation (KFRE). Participants at highest risk of kidney failure gain the largest absolute kidney benefit of intensive glycemic control but also experience the largest absolute risk of death and hypoglycemic events. Our findings illustrate the value of identifying clinically meaningful treatment heterogeneity, particularly when treatments have different effects on multiple end points. OBJECTIVE: Clear criteria to individualize glycemic targets in patients with type II diabetes are lacking. In this post hoc analysis of the ACCORD, we evaluate whether the KFRE can identify patients for whom intensive glycemic control confers more benefit in preventing kidney microvascular outcomes. RESEARCH DESIGN AND METHODS: We divided the ACCORD trial population into quartiles on the basis of 5-year kidney failure risk using the KFRE. We estimated conditional treatment effects within each quartile and compared them with the average treatment effect in the trial. The treatment effects of interest were the 7-year restricted mean survival time (RMST) differences between intensive and standard glycemic control arms on ( 1 ) time-to-first development of severely elevated albuminuria or kidney failure and ( 2 ) all-cause mortality. RESULTS: We found evidence that the effect of intensive glycemic control on kidney microvascular outcomes and all-cause mortality varies with baseline risk of kidney failure. Patients with elevated baseline risk of kidney failure derived the most from intensive glycemic control in reducing kidney microvascular outcomes (7-year RMST difference of 114.8 [95% confidence interval 58.1 to 176.4] versus 48.4 [25.3 to 69.6] days in the entire trial population) However, this same patient group also experienced a shorter time to death (7-year RMST difference of -56.7 [-100.2 to -17.5] v. -23.6 [-42.2 to -6.6] days). CONCLUSIONS: We found evidence of heterogenous treatment effects of intensive glycemic control on kidney microvascular outcomes in ACCORD as a function of predicted baseline risk of kidney failure. Patients with higher kidney failure risk experienced the most pronounced reduction in kidney microvascular outcomes but also experienced the highest risk of all-cause mortality.

The Association of Class I and II Human Leukocyte Antigen Serotypes With End-Stage Kidney Disease Due to Membranoproliferative Glomerulonephritis and Dense Deposit Disease.

RATIONALE & OBJECTIVE: Membranoproliferative glomerulonephritis (MPGN), encompassing several distinct diseases, is a rare but significant cause of kidney failure in the United States. The potential etiologies of MPGN are unclear, but prior studies have suggested dysregulation of the alternative complement pathway and, recently, autoimmunity as potential mechanisms driving MPGN pathogenesis. In this study, we examined HLA associations with end-stage kidney disease (ESKD) due to MPGN and dense deposit disease (DDD) in a large racially and ethnically diverse US-based cohort. STUDY DESIGN: Case-control study. SETTING & PARTICIPANTS: Using US Renal Data System (USRDS) and United Network for Organ Sharing (UNOS) data, we identified 3,424 patients with kidney failure due to MPGN and 263 due to DDD. We matched patients to kidney donor controls on designated race and ethnicity in a 1:15 ratio. EXPOSURE: 58 class I and II HLA serotypes. OUTCOME: Case-control status. ANALYTICAL APPROACH: For each disease cohort, univariable and multivariable logistic regression analyses were used to investigate associations between the disease and 58 HLA serotypes. In subgroup analyses, we investigated HLA associations in White and Black patients. We also studied antiglomerular basement membrane (anti-GBM) nephritis as a positive-control outcome. We applied a Bonferroni correction to account for multiple comparisons. RESULTS: Eighteen serotypes were significantly associated with the odds of having MPGN in univariable analyses, with DR17 having the strongest association (odds ratio [OR], 1.55 [95% CI, 1.44-1.68], P=4.33e-28). No significant associations were found between any HLA serotype and DDD. Designated race-specific analyses showed comparable findings. We recapitulated known HLA associations in anti-GBM nephritis. LIMITATIONS: Reliance on HLA serotypes (rather than genotype), lack of biopsy-confirmed diagnoses. CONCLUSIONS: HLA-DR17 is associated with ESKD due to MPGN in a racially and ethnically diverse cohort. The strength of association was similar in White and Black patients, suggesting a role in the pathogenesis of MPGN. No HLA associations were observed in patients with DDD. PLAIN-LANGUAGE SUMMARY: Prior studies have suggested dysregulation of the alternative complement pathway as a potential etiology of membranoproliferative glomerulonephritis (MPGN), but recent evidence from a British White population has implicated an autoimmune mechanism in MPGN pathogenesis. We investigated HLA associations between MPGN and dense deposit disease (DDD) in a large racially and ethnically diverse cohort of patients. We found that HLA-DR17 is associated with end-stage kidney disease (ESKD) due to MPGN in both White and Black patients. By contrast, no significant HLA associations with ESKD due to DDD were identified. These results suggest a role for autoimmunity in some cases of MPGN and highlight differences in the disease etiology of MPGN compared with DDD.

S100 Protein Expression in Primary and Metastatic Neuroendocrine Neoplasms: A Specific Marker of Pancreatic Origin.

Neuroendocrine neoplasms can arise in a wide variety of anatomic sites including the gastrointestinal tract, pancreas, and lung, among others. Here, we report on the expression of S100 protein in a tissue microarray composed of 919 distinct primary and metastatic neuroendocrine neoplasms from 548 patients. S100 protein is a commonly used marker in many laboratories for the identification of neural and melanocytic neoplasms and occasionally used in the workup for neuroendocrine neoplasms when the diagnosis of paraganglioma is being considered. We show that strong S100 protein expression is highly specific to well-differentiated neuroendocrine tumors of pancreatic origin. This finding suggests potential diagnostic utility of this marker in cases of tumors of unknown origin, and emphasizes that S100 protein expression should not be an unexpected finding in neuroendocrine tumors of pancreatic origin.

Expert Discussion on Challenges in C3G Diagnosis: A Podcast Article on Best Practices in Kidney Biopsies.

Complement 3 glomerulopathy (C3G) is an ultra-rare, progressive kidney disease resulting from dysregulation of the alternative complement pathway. Clinical presentation of C3G is heterogeneous and definitive diagnosis relies on kidney biopsy and immunofluorescence staining. The term C3G encompasses two subgroups, dense deposit disease and C3 glomerulonephritis, distinguished via electron microscopy. In this podcast article, the authors discuss the challenges associated with C3G diagnosis and the central role of kidney biopsy. Using an illustrative case study, key histological observations are described, and best practices are discussed from the perspectives of a nephrologist and a nephropathologist. Podcast Audio (MP4 141866 KB).

Wilms Tumor: An Unexpected Diagnosis in Adult Patients.

CONTEXT.­: Wilms tumor (WT) in adult patients is rare and has historically been a diagnostic and therapeutic conundrum, with limited data available in the literature. OBJECTIVE.­: To provide detailed diagnostic features, molecular profiling, and patient outcomes in a multi-institutional cohort of adult WT patients. DESIGN.­: We identified and retrospectively examined 4 adult WT cases. RESULTS.­: Two patients presented with metastatic disease, and diagnoses were made on fine-needle aspiration of their renal masses. The aspirates included malignant primitive-appearing epithelioid cells forming tubular rosettes and necrosis, and cell blocks demonstrated triphasic histology. In the remaining 2 cases, patients presented with localized disease and received a diagnosis on resection, with both patients demonstrating an epithelial-predominant morphology. Tumor cells in all cases were patchy variable positive for PAX8 and WT1 immunohistochemistry. Next-generation sequencing identified alterations previously reported in pediatric WT in 3 of 4 cases, including mutations in ASXL1 (2 of 4), WT1 (1 of 4), and the TERT promoter (1 of 4), as well as 1q gains (1 of 4); 1 case showed no alterations. Three patients were treated with pediatric chemotherapy protocols; during follow up (range, 26-60 months), 1 patient died of disease. CONCLUSIONS.­: WT is an unexpected and difficult entity to diagnose in adults and should be considered when faced with a primitive-appearing renal or metastatic tumor. Molecular testing may help exclude other possibilities but may not be sensitive or specific because of the relatively large number of driver mutations reported in WT.

Challenges in IgA Nephropathy Management: An Era of Complement Inhibition.

IgA nephropathy (IgAN) is the most common glomerular disease worldwide, with an estimated annual incidence of 25 per million adults. Despite optimized supportive care, some patients fail to achieve disease control and suffer progressive deterioration of kidney function. In this subpopulation of patients, the Kidney Disease: Improving Global Outcomes 2021 guidelines recommend consideration of corticosteroids; however, their use is associated with significant side effects. Ongoing clinical trials are expected to identify corticosteroid-sparing therapies to help improve treatment and prognosis for patients with IgAN. It has been well-documented that the complement system plays a significant role in IgAN pathogenesis, and several complement inhibitors are now entering late-stage clinical development. This review evaluates what we know about the role of complement in the pathophysiology of IgAN and considers how the availability of targeted complement inhibitors may impact future clinical practice. Key knowledge gaps are evaluated, and research opportunities are recommended to help guide clinical decision-making and optimize patient outcomes. Such gaps include evaluating the relative contribution of the alternative and lectin pathways to disease pathogenesis, and the importance of determining the dominant pathway driving IgAN progression. Continued research into the staining of complement proteins in kidney biopsies and identifying targeted biomarkers to assess disease progression and treatment responses will also be needed to support the implementation of newer therapies in clinical practice. Considering the future horizons for enhancing the care of patients with IgAN, tackling the outstanding challenges now will help prepare for the best possible future outcomes.

Treatment and Control of Hypertension Among Adults With Chronic Kidney Disease, 2011 to 2019.

BACKGROUND: Hypertension frequently accompanies chronic kidney disease (CKD) as etiology and sequela. We examined contemporary trends in hypertension treatment and control in a national sample of adults with CKD. METHODS: We evaluated 5% cross-sectional samples of adults with CKD between 2011 and 2019 in the Veterans Health Administration. We defined CKD as a sustained estimated glomerular filtration rate value <60 mL/min per 1.73 m2 or a urine albumin-to-creatinine ratio ≥30 mg/g. The main outcomes were blood pressure (BP) control, defined as a systolic BP <140 mm Hg and a diastolic BP <90 mm Hg based on the mean of monthly BP measurements, and prescriptions for antihypertensive medications. RESULTS: The annual samples ranged between n=22 110 and n=33 039 individuals, with a mean age of 72 years, 96% of whom were men. Between 2011 and 2014, the age-adjusted proportion of adults with controlled BP declined from 78.0% to 72.2% (P value for linear trend, <0.001), reached a nadir of 71.0% in 2015, and then increased to 72.9% by 2019 (P value for linear trend, <0.001). Among adults with BP above goal, the age-adjusted proportion who did not receive antihypertensive treatment increased throughout the decade from 18.8% to 21.6%, and the age-adjusted proportion who received ≥3 antihypertensive medications decreased from 41.8% to 36.3%. Prescriptions for first-line antihypertensive agents also decreased. CONCLUSIONS: Among adults with CKD treated in the Veterans Health Administration, the proportion with controlled BP declined between 2011 and 2015 followed by a modest increase, coinciding with fewer prescriptions for antihypertensive medications.

Benchmarking clinical risk prediction algorithms with ensemble machine learning: An illustration of the superlearner algorithm for the non-invasive diagnosis of liver fibrosis in non-alcoholic fatty liver disease.

Background and Aims: Ensemble machine learning (ML) methods can combine many individual models into a single 'super' model using an optimal weighted combination. Here we demonstrate how an underutilized ensemble model, the superlearner, can be used as a benchmark for model performance in clinical risk prediction. We illustrate this by implementing a superlearner to predict liver fibrosis in patients with non-alcoholic fatty liver disease (NAFLD). Methods: We trained a superlearner based on 23 demographic and clinical variables, with the goal of predicting stage 2 or higher liver fibrosis. The superlearner was trained on data from the Non-alcoholic steatohepatitis - clinical research network observational study (NASH-CRN, n=648), and validated using data from participants in a randomized trial for NASH ('FLINT' trial, n=270) and data from examinees with NAFLD who participated in the National Health and Nutrition Examination Survey (NHANES, n=1244). We compared the performance of the superlearner with existing models, including FIB-4, NFS, Forns, APRI, BARD and SAFE. Results: In the FLINT and NHANES validation sets, the superlearner (derived from 12 base models) discriminates patients with significant fibrosis from those without well, with AUCs of 0.79 (95% CI: 0.73-0.84) and 0.74 (95% CI: 0.68-0.79). Among the existing scores considered, the SAFE score performed similarly to the superlearner, and the superlearner and SAFE scores outperformed FIB-4, APRI, Forns, and BARD scores in the validation datasets. A superlearner model derived from 12 base models performed as well as one derived from 90 base models. Conclusions: The superlearner, thought of as the "best-in-class" ML prediction, performed better than most existing models commonly used in practice in detecting fibrotic NASH. The superlearner can be used to benchmark the performance of conventional clinical risk prediction models.

Liver Pathology After Hematopoietic Stem Cell Transplantation.

Hematopoietic stem cell transplantation is used to treat a variety of hematologic malignancies and autoimmune conditions. The immunosuppressive medications as well as other therapies used both before and after transplantation leave patients susceptible to a wide spectrum of complications, including liver injury. Causes for liver damage associated with stem cell transplantation include sinusoidal obstruction syndrome, graft-versus-host disease, iron overload, and opportunistic infection. Here, the authors review the clinical and pathological findings of these etiologies of liver injury and provide a framework for diagnosis.

Heterogeneous treatment effects of intensive glycemic control on kidney microvascular outcomes in ACCORD.

Objective: Clear criteria to individualize glycemic targets are lacking. In this post-hoc analysis of the Action to Control Cardiovascular Risk in Diabetes trial (ACCORD), we evaluate whether the kidney failure risk equation (KFRE) can identify patients who disproportionately benefit from intensive glycemic control on kidney microvascular outcomes. Research design and methods: We divided the ACCORD trial population in quartiles based on 5-year kidney failure risk using the KFRE. We estimated conditional treatment effects within each quartile and compared them to the average treatment effect in the trial. The treatment effects of interest were the 7-year restricted-mean-survival-time (RMST) differences between intensive and standard glycemic control arms on (1) time-to-first development of severely elevated albuminuria or kidney failure and (2) all-cause mortality. Results: We found evidence that the effect of intensive glycemic control on kidney microvascular outcomes and all-cause mortality varies with baseline risk of kidney failure. Patients with elevated baseline risk of kidney failure benefitted the most from intensive glycemic control on kidney microvascular outcomes (7-year RMST difference of 115 v. 48 days in the entire trial population) However, this same patient group also experienced shorter times to death (7-year RMST difference of -57 v. -24 days). Conclusions: We found evidence of heterogenous treatment effects of intensive glycemic control on kidney microvascular outcomes in ACCORD as a function of predicted baseline risk of kidney failure. Patients with higher kidney failure risk experienced the most pronounced benefits of treatment on kidney microvascular outcomes but also experienced the highest risk of all-cause mortality.

A Case Report of Mediastinal Teratoma in a Pediatric Patient With Nephrotic Syndrome: Paraneoplastic Syndrome or Incidental Finding?

A 12-year-old female presented with weight gain, edema, and shortness of breath. Laboratory and urine studies confirmed nephrotic syndrome and presence of a mediastinal mass, identified as a mature teratoma after resection. Nephrotic syndrome persisted despite resection and renal biopsy confirmed minimal change disease, which ultimately responded to steroid treatment. She had two relapses of nephrotic syndrome after vaccination administration, both of which occurred within eight months of tumor resection and were responsive to steroids. Autoimmune and infectious workup for other causes of nephrotic syndrome was negative. This is the first reported case of nephrotic syndrome associated with mediastinal teratoma.