There are few published studies examining cytomorphologic alterations in endothelial cells in human tissue. One fascinating but largely unexplored endothelial morphologic variant is large multinucleated variant endothelial cells (MVECs). To our knowledge, there are no published reports of MVECs identified in the kidney. Here, we present a case series of 4 kidney biopsies from allograft kidneys whose microvasculature contained MVECs. Electron microscopy confirmed the endothelial identity in all cases. A broad immunohistochemical panel used in 1 case was also confirmatory of an endothelial cell origin. All cases occurred in the setting of chronic, active, antibody-mediated rejection, and alternative etiologies, such as viral infections, were excluded. Two patients were positive for concurrent donor-specific antibodies, and 3 of the 4 cases occurred in second kidney allografts. We speculate that MVECs are a rare or often overlooked finding often confused for megakaryocytes and may be associated with chronic endothelial cell injury in the setting of chronic antibody-mediated rejection.

Background

There is a shortage of medical informatics and data science platforms using cloud computing on electronic medical record (EMR) data, and with computing capacity for analyzing big data. We implemented, described, and applied a cloud computing solution utilizing the fast health interoperability resources (FHIR) standardization and state-of-the-art parallel distributed computing platform for advanced analytics.

Methods

We utilized the architecture of the modern predictive analytics platform called Cerner® HealtheDataLab and described the suite of cloud computing services and Apache Projects that it relies on. We validated the platform by replicating and improving on a previous single pediatric institution study/model on readmission and developing a multi-center model of all-cause readmission for pediatric-age patients using the Cerner® Health Facts Deidentified Database (now updated and referred to as the Cerner Real World Data). We retrieved a subset of 1.4 million pediatric encounters consisting of 48 hospitals' data on pediatric encounters in the database based on a priori inclusion criteria. We built and analyzed corresponding random forest and multilayer perceptron (MLP) neural network models using HealtheDataLab.

Results

Using the HealtheDataLab platform, we developed a random forest model and multi-layer perceptron model with AUC of 0.8446 (0.8444, 0.8447) and 0.8451 (0.8449, 0.8453) respectively. We showed the distribution in model performance across hospitals and identified a set of novel variables under previous resource utilization and generic medications that may be used to improve existing readmission models.

Conclusion

Our results suggest that high performance, elastic cloud computing infrastructures such as the platform presented here can be used for the development of highly predictive models on EMR data in a secure and robust environment. This in turn can lead to new clinical insights/discoveries.

BACKGROUND: Menopausal hormone therapy (MHT) is recommended for only five years to treat vasomotor symptoms and vulvovaginal atrophy because of safety concerns with long-term treatment. We investigated the ability of 2,3,4-trihydroxychalcone (2,3,4-THC) to modulate estrogen receptor (ER)-mediated responses in order to find drug candidates that could potentially prevent the adverse effects of long-term MHT treatment. METHODS: Transfection assays, real time-polymerase chain reaction, and microarrays were used to evaluate the effects of 2,3,4-THC on gene regulation. Radioligand binding studies were used to determine if 2,3,4-THC binds to ERα. Cell proliferation was examined in MCF-7 breast cancer cells by using growth curves and flow cytometry. Western blots were used to determine if 2,3,4-THC alters the E2 activation of the MAPK pathway and degradation of ERα. Chromatin immunoprecipitation was used to measure ERα binding to genes. RESULTS: The 2,3,4-THC/E2 combination produced a synergistic activation with ERα on reporter and endogenous genes in human U2OS osteosarcoma cells. Microarrays identified 824 genes that we termed reprogrammed genes because they were not regulated in U2OS-ERα cells unless they were treated with 2,3,4-THC and E2 at the same time. 2,3,4-THC blocked the proliferation of MCF-7 cells by preventing the E2-induced activation of MAPK and c-MYC transcription. The antiproliferative mechanism of 2,3,4-THC differs from selective estrogen receptor modulators (SERMs) because 2,3,4-THC did not bind to the E2 binding site in ERα like SERMs. CONCLUSION: Our study suggests that 2,3,4-THC may represent a new class of ERα modulators that do not act as a direct agonists or antagonists. We consider 2,3,4-THC to be a reprogramming compound, since it alters the activity of ERα on gene regulation and cell proliferation without competing with E2 for binding to ERα. The addition of a reprogramming drug to estrogens in MHT may offer a new strategy to overcome the adverse proliferative effects of estrogen in MHT by reprogramming ERα as opposed to an antagonist mechanism that involves blocking the binding of estrogen to ERα.

Objective The aim of this article is to examine characteristics of birth tourism (BT) neonates admitted to a neonatal intensive care unit (NICU). Methods This was a retrospective review over 3 years; BT cases were identified, and relevant perinatal, medical, social, and financial data were collected and compared with 100 randomly selected non-birth tourism neonates. Results A total of 46 BT neonates were identified. They were more likely to be born to older women (34 vs. 29 years; p < 0.001), via cesarean delivery (72 vs. 48%; p = 0.007), and at a referral facility (80 vs. 32%; p < 0.001). BT group had longer hospital stay (15 vs. 7 days; p = 0.02), more surgical intervention (50 vs. 21%; p < 0.001), and higher hospital charges (median $287,501 vs. $103,105; p = 0.003). One-third of BT neonates were enrolled in public health insurance program and four BT neonates (10%) were placed for adoption. Conclusion Families of BT neonates admitted to the NICU face significant challenges. Larger studies are needed to better define impacts on families, health care system, and society.

The COVID-19 pandemic has required greater minute-to-minute urgency of patient treatment in Intensive Care Units (ICUs), rendering the use of Randomized Controlled Trials (RCTs) too slow to be effective for treatment discovery. There is a need for agility in clinical research, and the use of data science to develop predictive models for patient treatment is a potential solution. However, rapidly developing predictive models in healthcare is challenging given the complexity of healthcare problems and the lack of regular interaction between data scientists and physicians. Data scientists can spend significant time working in isolation to build predictive models that may not be useful in clinical environments. We propose the use of an agile data science framework based on the Scrumban framework used in software development. Scrumban is an iterative framework, where in each iteration larger problems are broken down into simple do-able tasks for data scientists and physicians. The two sides collaborate closely in formulating clinical questions and developing and deploying predictive models into clinical settings. Physicians can provide feedback or new hypotheses given the performance of the model, and refinement of the model or clinical questions can take place in the next iteration. The rapid development of predictive models can now be achieved with increasing numbers of publicly available healthcare datasets and easily accessible cloud-based data science tools. What is truly needed are data scientist and physician partnerships ensuring close collaboration between the two sides in using these tools to develop clinically useful predictive models to meet the demands of the COVID-19 healthcare landscape.

Background

Pediatric oncology patients have high rates of hospital readmission but there is a dearth of research into risk factors for unplanned 30-day readmissions among this high-risk population.

Aim

In this study, we built a statistical model to provide insight into risk factors of unplanned readmissions in this pediatric oncology.

Methods

We retrieved 32 667 encounters from 10 418 pediatric patients with a neoplastic condition from 16 hospitals in the Cerner Health Facts Database and built a mixed-effects model with patients nested within hospitals for inference on 75% of the data and reserved the remaining as an independent test dataset.

Results

The mixed-effects model indicated that patients with acute lymphoid leukemia (in relapse), neuroblastoma, rhabdomyosarcoma, or bone/cartilage cancer have increased odds of readmission. The number of cancer medications taken by the patient and the administration of chemotherapy were associated with increased odds of readmission for all cancer types. Wilms Tumor had a significant interaction with administration of chemotherapy, indicating that the risk due to chemotherapy is exacerbated in patients with Wilms Tumor. A second two-way interaction between recent history of chemotherapy treatment and infections was associated with increased odds of readmission. The area under the receiver operator characteristic curve (and corresponding 95% confidence interval) of the mixed-effects model was 0.714 (0.702, 0.725) on the independent test dataset.

Conclusion

Readmission risk in oncology is modified by the specific type of cancer, current and past administration of chemotherapy, and increased health care utilization. Oncology-specific models can provide decision support where model built on other or mixed population has failed.

Background

Cardiovascular and other circulatory system diseases have been implicated in the severity of COVID-19 in adults. This study provides a super learner ensemble of models for predicting COVID-19 severity among these patients.

Method

The COVID-19 Dataset of the Cerner Real-World Data was used for this study. Data on adult patients (18 years or older) with cardiovascular diseases between 2017 and 2019 were retrieved and a total of 13 of these conditions were identified. Among these patients, 33,042 admitted with positive diagnoses for COVID-19 between March 2020 and June 2020 (from 59 hospitals) were identified and selected for this study. A total of 14 statistical and machine learning models were developed and combined into a more powerful super learning model for predicting COVID-19 severity on admission to the hospital.

Result

LASSO regression, a full extreme gradient boosting model with tree depth of 2, and a full logistic regression model were the most predictive with cross-validated AUROCs of 0.7964, 0.7961, and 0.7958 respectively. The resulting super learner ensemble model had a cross validated AUROC of 0.8006 (range: 0.7814, 0.8163). The unbiased AUROC of the super learner model on an independent test set was 0.8057 (95% CI: 0.7954, 0.8159).

Conclusion

Highly predictive models can be built to predict COVID-19 severity of patients with cardiovascular and other circulatory conditions. Super learning ensembles will improve individual and classical ensemble models significantly.

The incidence of early stage renal cell carcinoma (RCC) is increasing and observational studies have shown equivalent oncological outcomes of partial versus radical nephrectomy for stage I tumours. Population studies suggest that compared with radical nephrectomy, partial nephrectomy is associated with decreased mortality and a lower rate of postoperative decline in kidney function. However, rates of chronic kidney disease (CKD) in patients who have undergone nephrectomy might be higher than in the general population. The risks of new-onset or accelerated CKD and worsened survival after nephrectomy might be linked, as kidney insufficiency is a risk factor for cardiovascular disease and mortality. Nephron-sparing approaches have, therefore, been proposed as the standard of care for patients with type 1a tumours and as a viable option for those with type 1b tumours. However, prospective data on the incidence of de novo and accelerated CKD after cancer nephrectomy is lacking, and the only randomized trial to date was closed prematurely. Intrinsic abnormalities in non-neoplastic kidney parenchyma and comorbid conditions (including diabetes mellitus and hypertension) might increase the risks of CKD and RCC. More research is needed to better understand the risk of CKD post-nephrectomy, to develop and validate predictive scores for risk-stratification, and to optimize patient management.

Abstract

Technological breakthroughs, together with the rapid growth of medical information and improved data connectivity, are creating dramatic shifts in the health care landscape, including the field of developmental and behavioral pediatrics. While medical information took an estimated 50 years to double in 1950, by 2020, it was projected to double every 73 days. Artificial intelligence (AI)-powered health technologies, once considered theoretical or research-exclusive concepts, are increasingly being granted regulatory approval and integrated into clinical care. In the United States, the Food and Drug Administration has cleared or approved over 160 health-related AI-based devices to date. These trends are only likely to accelerate as economic investment in AI health care outstrips investment in other sectors. The exponential increase in peer-reviewed AI-focused health care publications year over year highlights the speed of growth in this sector. As health care moves toward an era of intelligent technology powered by rich medical information, pediatricians will increasingly be asked to engage with tools and systems underpinned by AI. However, medical students and practicing clinicians receive insufficient training and lack preparedness for transitioning into a more AI-informed future. This article provides a brief primer on AI in health care. Underlying AI principles and key performance metrics are described, and the clinical potential of AI-driven technology together with potential pitfalls is explored within the developmental and behavioral pediatric health context.

PD-L1 on the surface of tumor cells binds its receptor PD-1 on effector T cells, thereby suppressing their activity. Antibody blockade of PD-L1 can activate an anti-tumor immune response leading to durable remissions in a subset of cancer patients. Here, we describe an alternative mechanism of PD-L1 activity involving its secretion in tumor-derived exosomes. Removal of exosomal PD-L1 inhibits tumor growth, even in models resistant to anti-PD-L1 antibodies. Exosomal PD-L1 from the tumor suppresses T cell activation in the draining lymph node. Systemically introduced exosomal PD-L1 rescues growth of tumors unable to secrete their own. Exposure to exosomal PD-L1-deficient tumor cells suppresses growth of wild-type tumor cells injected at a distant site, simultaneously or months later. Anti-PD-L1 antibodies work additively, not redundantly, with exosomal PD-L1 blockade to suppress tumor growth. Together, these findings show that exosomal PD-L1 represents an unexplored therapeutic target, which could overcome resistance to current antibody approaches.