CKD Progression Prediction in a Diverse US Population: A Machine-Learning Model.

Rationale & Objective: Chronic kidney disease (CKD) is a major cause of morbidity and mortality. To date, there are no widely used machine-learning models that can predict progressive CKD across the entire disease spectrum, including the earliest stages. The objective of this study was to use readily available demographic and laboratory data from Sonic Healthcare USA laboratories to train and test the performance of machine learning-based predictive risk models for CKD progression. Study Design: Retrospective observational study. Setting & Participants: The study population was composed of deidentified laboratory information services data procured from a large US outpatient laboratory network. The retrospective data set included 110,264 adult patients over a 5-year period with initial estimated glomerular filtration rate (eGFR) values between 15-89 mL/min/1.73 m2. Predictors: Patient demographic and laboratory characteristics. Outcomes: Accelerated (ie, >30%) eGFR decline associated with CKD progression within 5 years. Analytical Approach: Machine-learning models were developed using random forest survival methods, with laboratory-based risk factors analyzed as potential predictors of significant eGFR decline. Results: The 7-variable risk classifier model accurately predicted an eGFR decline of >30% within 5 years and achieved an area under the curve receiver-operator characteristic of 0.85. The most important predictor of progressive decline in kidney function was the eGFR slope. Other key contributors to the model included initial eGFR, urine albumin-creatinine ratio, serum albumin (initial and slope), age, and sex. Limitations: The cohort study did not evaluate the role of clinical variables (eg, blood pressure) on the performance of the model. Conclusions: Our progressive CKD classifier accurately predicts significant eGFR decline in patients with early, mid, and advanced disease using readily obtainable laboratory data. Although prospective studies are warranted, our results support the clinical utility of the model to improve timely recognition and optimal management for patients at risk for CKD progression. Plain-Language Summary: Defined by a significant decrease in estimated glomerular filtration rate (eGFR), chronic kidney disease (CKD) progression is strongly associated with kidney failure. However, to date, there are no broadly used resources that can predict this clinically significant event. Using machine-learning techniques on a diverse US population, this cohort study aimed to address this deficiency and found that a 5-year risk prediction model for CKD progression was accurate. The most important predictor of progressive decline in kidney function was the eGFR slope, followed by the urine albumin-creatinine ratio and serum albumin slope. Although further study is warranted, the results showed that a machine-learning model using readily obtainable laboratory information accurately predicts CKD progression, which may inform clinical diagnosis and management for this at-risk population.

Antibody Duration After Infection From SARS-CoV-2 in the Texas Coronavirus Antibody Response Survey.

Understanding the duration of antibodies to the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus that causes COVID-19 is important to controlling the current pandemic. Participants from the Texas Coronavirus Antibody Response Survey (Texas CARES) with at least 1 nucleocapsid protein antibody test were selected for a longitudinal analysis of antibody duration. A linear mixed model was fit to data from participants (n = 4553) with 1 to 3 antibody tests over 11 months (1 October 2020 to 16 September 2021), and models fit showed that expected antibody response after COVID-19 infection robustly increases for 100 days postinfection, and predicts individuals may remain antibody positive from natural infection beyond 500 days depending on age, body mass index, smoking or vaping use, and disease severity (hospitalized or not; symptomatic or not).

Case Report of Conjunctival Melanoacanthoma.

PURPOSE: The purpose of this study was to describe a case of conjunctival melanoacanthoma, an exceedingly rare condition that has yet to be fully described in the literature. METHODS: Melanoacanthomas are most commonly seen on the skin or oral mucosa and are believed to result from local irritation or trauma. A 34-year-old Hispanic man presented with a painless, solitary, pigmented conjunctival lesion, in addition to bilateral pterygia suggesting chronic solar damage. The lesion was excised and sent for analysis. RESULTS: Histopathologic analysis of tissue samples demonstrated melanocyte proliferation and epithelial dysplasia, yielding a final pathologic diagnosis of conjunctival melanoacanthoma with dysplastic and acantholytic-type features. The patient is being closely followed and has not had recurrence of the lesion. CONCLUSIONS: Only 1 prior case of conjunctival melanoacanthoma has been documented. As such, there is no standard of care regarding appropriate management.

Epstein-Barr-virus-positive large B-cell lymphoma associated with breast implants: an analysis of eight patients suggesting a possible pathogenetic relationship.

Breast implant anaplastic large cell lymphoma (ALCL) is a T-cell neoplasm arising around textured breast implants that was recognized recently as a distinct entity by the World Health Organization. Rarely, other types of lymphoma have been reported in patients with breast implants, raising the possibility of a pathogenetic relationship between breast implants and other types of lymphoma. We report eight cases of Epstein-Barr virus (EBV)-positive large B-cell lymphoma associated with breast implants. One of these cases was invasive, and the other seven neoplasms were noninvasive and showed morphologic overlap with breast implant ALCL. All eight cases expressed B-cell markers, had a non-germinal center B-cell immunophenotype, and were EBV+ with a latency type III pattern of infection. We compared the noninvasive EBV+ large B-cell lymphoma cases with a cohort of breast implant ALCL cases matched for clinical and pathologic stage. The EBV+ large B-cell lymphoma cases more frequently showed a thicker capsule, and more often were associated with calcification and prominent lymphoid aggregates outside of the capsule. The EBV+ B-cell lymphoma cells were more often arranged within necrotic fibrinoid material in a layered pattern. We believe that this case series highlights many morphologic similarities between EBV+ large B-cell lymphoma and breast implant ALCL. The data presented suggest a pathogenetic role for breast implants (as well as EBV) in the pathogenesis of EBV+ large B-cell lymphoma. We also provide some histologic findings useful for distinguishing EBV+ large B-cell lymphoma from breast implant ALCL in this clinical setting.

Prevalence of BRCA mutations in an unselected population of triple-negative breast cancer.

BACKGROUND: This study assessed BRCA1 and BRCA2 mutation prevalence in an unselected cohort of patients with triple-negative breast cancer (BC). METHODS: One hundred ninety-nine patients were enrolled. Triple negativity was defined as <1% estrogen and progesterone staining by immunohistochemistry and HER-2/neu not overexpressed by fluorescence in situ hybridization. Having given consent, patients had BRCA1 and BRCA2 full sequencing and large rearrangement analysis. Mutation prevalence was assessed among the triple-negative BC patients and the subset of patients without a family history of breast/ovarian cancer. Independent pathological review was completed on 50 patients. RESULTS: Twenty-one deleterious BRCA mutations were identified--13 in BRCA1 and 8 in BRCA2 (prevalence, 10.6%). In 153 patients (76.9%) without significant family history (first-degree or second-degree relatives with BC aged <50 years or ovarian cancer at any age), 8 (5.2%) mutations were found. By using prior National Comprehensive Cancer Network (NCCN) guidelines recommending testing for triple-negative BC patients aged <45 years, 4 of 21 mutations (19%) would have been missed. Two of 21 mutations (10%) would have been missed using updated NCCN guidelines recommending testing for triple-negative BC patients aged <60 years. CONCLUSIONS: The observed mutation rate was significantly higher (P = .0005) than expected based on previously established prevalence tables among patients unselected for pathology. BRCA1 mutation prevalence was lower, and BRCA2 mutation prevalence was higher, than previously described. Additional mutation carriers would have met new NCCN testing guidelines, underscoring the value of the updated criteria. Study data suggest that by increasing the age limit to 65 years, all carriers would have been identified.