Suppression of Exosomal PD-L1 Induces Systemic Anti-tumor Immunity and Memory.

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.

Quantifying in situ adaptive immune cell cognate interactions in humans.

Two-photon excitation microscopy (TPEM) has revolutionized the understanding of adaptive immunity. However, TPEM usually requires animal models and is not amenable to the study of human disease. The recognition of antigen by T cells requires cell contact and is associated with changes in T cell shape. We postulated that by capturing these features in fixed tissue samples, we could quantify in situ adaptive immunity. Therefore, we used a deep convolutional neural network to identify fundamental distance and cell-shape features associated with cognate help (cell-distance mapping (CDM)). In mice, CDM was comparable to TPEM in discriminating cognate T cell-dendritic cell (DC) interactions from non-cognate T cell-DC interactions. In human lupus nephritis, CDM confirmed that myeloid DCs present antigen to CD4+ T cells and identified plasmacytoid DCs as an important antigen-presenting cell. These data reveal a new approach with which to study human in situ adaptive immunity broadly applicable to autoimmunity, infection, and cancer.

Interferon gamma constrains type 2 lymphocyte niche boundaries during mixed inflammation.

Allergic immunity is orchestrated by group 2 innate lymphoid cells (ILC2s) and type 2 helper T (Th2) cells prominently arrayed at epithelial- and microbial-rich barriers. However, ILC2s and Th2 cells are also present in fibroblast-rich niches within the adventitial layer of larger vessels and similar boundary structures in sterile deep tissues, and it remains unclear whether they undergo dynamic repositioning during immune perturbations. Here, we used thick-section quantitative imaging to show that allergic inflammation drives invasion of lung and liver non-adventitial parenchyma by ILC2s and Th2 cells. However, during concurrent type 1 and type 2 mixed inflammation, IFNγ from broadly distributed type 1 lymphocytes directly blocked both ILC2 parenchymal trafficking and subsequent cell survival. ILC2 and Th2 cell confinement to adventitia limited mortality by the type 1 pathogen Listeria monocytogenes. Our results suggest that the topography of tissue lymphocyte subsets is tightly regulated to promote appropriately timed and balanced immunity.

Clonal Deletion of Tumor-Specific T Cells by Interferon-γ Confers Therapeutic Resistance to Combination Immune Checkpoint Blockade.

Resistance to checkpoint-blockade treatments is a challenge in the clinic. We found that although treatment with combined anti-CTLA-4 and anti-PD-1 improved control of established tumors, this combination compromised anti-tumor immunity in the low tumor burden (LTB) state in pre-clinical models as well as in melanoma patients. Activated tumor-specific T cells expressed higher amounts of interferon-γ (IFN-γ) receptor and were more susceptible to apoptosis than naive T cells. Combination treatment induced deletion of tumor-specific T cells and altered the T cell repertoire landscape, skewing the distribution of T cells toward lower-frequency clonotypes. Additionally, combination therapy induced higher IFN-γ production in the LTB state than in the high tumor burden (HTB) state on a per-cell basis, reflecting a less exhausted immune status in the LTB state. Thus, elevated IFN-γ secretion in the LTB state contributes to the development of an immune-intrinsic mechanism of resistance to combination checkpoint blockade, highlighting the importance of achieving the optimal magnitude of immune stimulation for successful combination immunotherapy strategies.

Microbial influences on severity and sex bias of systemic autoimmunity.

Commensal microbes have the capacity to affect development and severity of autoimmune diseases. Germ-free (GF) animals have proven to be a fine tool to obtain definitive answers to the queries about the microbial role in these diseases. Moreover, GF and gnotobiotic animals can be used to dissect the complex symptoms and determine which are regulated (enhanced or attenuated) by microbes. These include disease manifestations that are sex biased. Here, we review comparative analyses conducted between GF and Specific-Pathogen Free (SPF) mouse models of autoimmunity. We present data from the B6;NZM-Sle1NZM2410/AegSle2NZM2410/AegSle3NZM2410/Aeg-/LmoJ (B6.NZM) mouse model of systemic lupus erythematosus (SLE) characterized by multiple measurable features. We compared the severity and sex bias of SPF, GF, and ex-GF mice and found variability in the severity and sex bias of some manifestations. Colonization of GF mice with the microbiotas taken from B6.NZM mice housed in two independent institutions variably affected severity and sexual dimorphism of different parameters. Thus, microbes regulate both the severity and sexual dimorphism of select SLE traits. The sensitivity of particular trait to microbial influence can be used to further dissect the mechanisms driving the disease. Our results demonstrate the complexity of the problem and open avenues for further investigations.

Podocyte injury at young age causes premature senescence and worsens glomerular aging.

As life expectancy continues to rise, age-related diseases are becoming more prevalent. For example, proteinuric glomerular diseases typified by podocyte injury have worse outcomes in the elderly compared with young patients. However, the reasons are not well understood. We hypothesized that injury to nonaged podocytes induces senescence, which in turn augments their aging processes. In primary cultured human podocytes, injury induced by a cytopathic antipodocyte antibody, adriamycin, or puromycin aminonucleoside increased the senescence-related genes CDKN2A (p16INK4a/p14ARF), CDKN2D (p19INK4d), and CDKN1A (p21). Podocyte injury in human kidney organoids was accompanied by increased expression of CDKN2A, CDKN2D, and CDKN1A. In young mice, experimental focal segmental glomerulosclerosis (FSGS) induced by adriamycin and antipodocyte antibody increased the glomerular expression of p16, p21, and senescence-associated ß-galactosidase (SA-ß-gal). To assess the long-term effects of early podocyte injury-induced senescence, we temporally followed young mice with experimental FSGS through adulthood (12 m of age) and middle age (18 m of age). p16 and Sudan black staining were higher at middle age in mice with earlier FSGS compared with age-matched mice that did not get FSGS when young. This was accompanied by lower podocyte density, reduced canonical podocyte protein expression, and increased glomerular scarring. These results are consistent with injury-induced senescence in young podocytes, leading to increased senescence of podocytes by middle age accompanied by lower podocyte lifespan and health span.NEW & NOTEWORTHY Glomerular function is decreased by aging. However, little is known about the molecular mechanisms involved in age-related glomerular changes and which factors could contribute to a worse glomerular aging process. Here, we reported that podocyte injury in young mice and culture podocytes induced senescence, a marker of aging, and accelerates glomerular aging when compared with healthy aging mice.

Prospective observational study to validate a next-generation sequencing blood RNA signature to predict early kidney transplant rejection.

The objective of this study was to validate the performance of Tutivia, a peripheral blood gene expression signature, in predicting early acute rejection (AR) post-kidney transplant. Recipients of living or deceased donor kidney transplants were enrolled in a nonrandomized, prospective, global, and observational study (NCT04727788). The main outcome was validation of the area under the curve (AUC) of Tutivia vs serum creatinine at biopsy alone, or Tutivia + serum creatinine at biopsy. Of the 151 kidney transplant recipients, the mean cohort age was 53 years old, and 64% were male. There were 71% (107/151) surveillance/protocol biopsies and 29% (44/151) for-cause biopsies, with a 31% (47/151) overall rejection rate. Tutivia (AUC 0.69 [95% CI: 0.59-0.77]) and AUC of Tutivia + creatinine at biopsy (0.68 [95% CI: 0.59-0.77]) were greater than the AUC of creatinine at biopsy alone (0.51.4 [95% CI: 0.43-0.60]). Applying a model cut-off of 50 (scale 0-100) generated a high- and low-risk category for AR with a negative predictive value of 0.79 (95% CI: 0.71-0.86), a positive predictive value of 0.60 (95% CI: 0.45-0.74), and an odds ratio of 5.74 (95% CI: 2.63-12.54). Tutivia represents a validated noninvasive approach for clinicians to accurately predict early AR, beyond the current standard of care.

Promises, Pitfalls, and Clinical Applications of Artificial Intelligence in Pediatrics.

Artificial intelligence (AI) broadly describes a branch of computer science focused on developing machines capable of performing tasks typically associated with human intelligence. Those who connect AI with the world of science fiction may meet its growing rise with hesitancy or outright skepticism. However, AI is becoming increasingly pervasive in our society, from algorithms helping to sift through airline fares to substituting words in emails and SMS text messages based on user choices. Data collection is ongoing and is being leveraged by software platforms to analyze patterns and make predictions across multiple industries. Health care is gradually becoming part of this technological transformation, as advancements in computational power and storage converge with the rapid expansion of digitized medical information. Given the growing and inevitable integration of AI into health care systems, it is our viewpoint that pediatricians urgently require training and orientation to the uses, promises, and pitfalls of AI in medicine. AI is unlikely to solve the full array of complex challenges confronting pediatricians today; however, if used responsibly, it holds great potential to improve many aspects of care for providers, children, and families. Our aim in this viewpoint is to provide clinicians with a targeted introduction to the field of AI in pediatrics, including key promises, pitfalls, and clinical applications, so they can play a more active role in shaping the future impact of AI in medicine.

Molecular architecture of proliferative lupus nephritis as elucidated using 50-plex imaging mass cytometry proteomics.

Due to unique advantages that allow high-dimensional tissue profiling, we postulated imaging mass cytometry (IMC) may shed novel insights on the molecular makeup of proliferative lupus nephritis (LN). This study interrogates the spatial expression profiles of 50 target proteins in LN and control kidneys. Proliferative LN glomeruli are marked by podocyte loss with immune infiltration dominated by CD45RO+, HLA-DR+ memory CD4 and CD8 T-cells, and CD163+ macrophages, with similar changes in tubulointerstitial regions. Macrophages are the predominant HLA-DR expressing antigen presenting cells with little expression elsewhere, while macrophages and T-cells predominate cellular crescents. End-stage sclerotic glomeruli are encircled by an acellular fibro-epithelial Bowman's space surrounded by immune infiltrates, all enmeshed in fibronectin. Proliferative LN also shows signs indicative of epithelial to mesenchymal plasticity of tubular cells and parietal epithelial cells. IMC enabled proteomics is a powerful tool to delineate the spatial architecture of LN at the protein level.

Mouse Homologue of Human HLA-DO Does Not Preempt Autoimmunity but Controls Murine Gammaherpesvirus MHV68.

H2-O (human HLA-DO) is a relatively conserved nonclassical MHC class II (MHCII)-like molecule. H2-O interaction with human HLA-DM edits the repertoire of peptides presented to TCRs by MHCII. It was long hypothesized that human HLA-DM inhibition by H2-O provides protection from autoimmunity by preventing binding of the high-affinity self-peptides to MHCII. The available evidence supporting this hypothesis, however, was inconclusive. A possibility still remained that the effect of H2-O deficiency on autoimmunity could be better revealed by using H2-O-deficient mice that were already genetically predisposed to autoimmunity. In this study, we generated and used autoimmunity-prone mouse models for systemic lupus erythematosus and organ-specific autoimmunity (type 1 diabetes and multiple sclerosis) to definitively test whether H2-O prevents autoimmune pathology. Whereas our data failed to support any significance of H2-O in protection from autoimmunity, we found that it was critical for controlling a γ-herpesvirus, MHV68. Thus, we propose that H2-O editing of the MHCII peptide repertoire may have evolved as a safeguard against specific highly prevalent viral pathogens.

2',3',4'-Trihydroxychalcone changes estrogen receptor α regulation of genes and breast cancer cell proliferation by a reprogramming mechanism.

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.

Quantification of Glomerular Structural Lesions: Associations With Clinical Outcomes and Transcriptomic Profiles in Nephrotic Syndrome.

RATIONALE & OBJECTIVE: The current classification system for focal segmental glomerulosclerosis (FSGS) and minimal change disease (MCD) does not fully capture the complex structural changes in kidney biopsies nor the clinical and molecular heterogeneity of these diseases. STUDY DESIGN: Prospective observational cohort study. SETTING & PARTICIPANTS: 221 MCD and FSGS patients enrolled in the Nephrotic Syndrome Study Network (NEPTUNE). EXPOSURE: The NEPTUNE Digital Pathology Scoring System (NDPSS) was applied to generate scores for 37 glomerular descriptors. OUTCOME: Time from biopsy to complete proteinuria remission, time from biopsy to kidney disease progression (40% estimated glomerular filtration rate [eGFR] decline or kidney failure), and eGFR over time. ANALYTICAL APPROACH: Cluster analysis was used to group patients with similar morphologic characteristics. Glomerular descriptors and patient clusters were assessed for associations with outcomes using adjusted Cox models and linear mixed models. Messenger RNA from glomerular tissue was used to assess differentially expressed genes between clusters and identify genes associated with individual descriptors driving cluster membership. RESULTS: Three clusters were identified: X (n = 56), Y (n = 68), and Z (n = 97). Clusters Y and Z had higher probabilities of proteinuria remission (HRs of 1.95 [95% CI, 0.99-3.85] and 3.29 [95% CI, 1.52-7.13], respectively), lower hazards of disease progression (HRs of 0.22 [95% CI, 0.08-0.57] and 0.11 [95% CI, 0.03-0.45], respectively), and lower loss of eGFR over time compared with X. Cluster X had 1,920 genes that were differentially expressed compared with Y+Z; these reflected activation of pathways of immune response and inflammation. Six descriptors driving the clusters individually correlated with clinical outcomes and gene expression. LIMITATIONS: Low prevalence of some descriptors and biopsy at a single time point. CONCLUSIONS: The NDPSS allows for categorization of FSGS/MCD patients into clinically and biologically relevant subgroups, and uncovers histologic parameters associated with clinical outcomes and molecular signatures not included in current classification systems.

Extraglomerular immune complex deposition in lupus nephritis.

BACKGROUND: Lupus nephritis (LN) is a common manifestation and a major cause of morbidity and mortality in systemic lupus erythematosus (SLE) patients. It is characterized by glomerular and often extraglomerular immune complex deposition. PURPOSE: Given the emerging importance of the tubulointerstitial compartment, we conducted a retrospective study of 78 LN biopsies to enumerate the spectrum of extraglomerular immune complex deposition that can be observed in lupus nephritis by electron microscopy and to identify possible clinical or pathologic correlates. RESULTS: The presence of tubulointerstitial immune complex deposition often accompanied interstitial inflammation, but some discrepancies were also seen. CONCLUSIONS: As target antigens are identified, correlation with glomerular, tubulointerstitial, and vascular immune complex deposition will be of increasing interest.

Local complement factor H protects kidney endothelial cell structure and function.

Factor H (FH) is a critical regulator of the alternative complement pathway and its deficiency or mutation underlie kidney diseases such as dense deposit disease. Since vascular dysfunction is an important facet of kidney disease, maintaining optimal function of the lining endothelial cells is important for vascular health. To investigate the molecular mechanisms that are regulated by FH in endothelial cells, FH deficient and sufficient mouse kidney endothelial cell cultures were established. Endothelial FH deficiency resulted in cytoskeletal remodeling, increased angiogenic potential, loss of cellular layer integrity and increased cell proliferation. FH reconstitution prevented these FH-dependent proliferative changes. Respiratory flux analysis showed reduced basal mitochondrial respiration, ATP production and maximal respiratory capacity in FH deficient endothelial cells, while proton leak remained unaltered. Similar changes were observed in FH deficient human glomerular endothelial cells indicating the translational potential of these studies. Gene expression analysis revealed that the FH-dependent gene changes in mouse kidney endothelial cells include significant upregulation of genes involved in inflammation and the complement system. The transcription factor nuclear factor-kB, that regulates many biological processes, was translocated from the cytoplasm to the nucleus in the absence of FH. Thus, our studies show the functional relevance of intrinsic FH in kidney endothelial cells in man and mouse.

Cellular aspects of the pathogenesis of lupus nephritis.

PURPOSE OF REVIEW: Lupus nephritis is a common severe manifestation of systemic lupus erythematosus. Despite recent advances in therapeutics and understanding of its pathogenesis, there are still substantial unmet needs. This review discusses recent discoveries in these areas, especially the role of tubulointerstitial inflammation (TII) in lupus nephritis. RECENT FINDINGS: Non-white ethnicity is still a major risk and poor prognostic factor in lupus nephritis. TII and fibrosis have been found to be associated with worse renal outcome but the current lupus nephritis treatment guidelines and trials are based on the degree of glomerular inflammation. In combination with mycophenolate mofetil, a B-cell-targeted therapy (belimumab) and a calcineurin inhibitor (voclosporin) have shown efficacy in recent lupus nephritis trials. However, response rates have been modest. While lupus glomerulonephritis results from immune complex deposition derived from systemic autoantibodies, TII arises from complex processes associated with in situ adaptive cell networks. These include local antibody production, and cognate or antigen-induced interactions between T follicular helper cells, and likely other T-cell populations, with antigen presenting cells including B cells, myeloid dendritic cells and plasmacytoid dendritic cells. SUMMARY: Better understanding of the pathogenesis of TII will identify novel therapeutic targets predicted to improve outcomes in our patients with lupus nephritis.

Discordance between immunofluorescence and immunohistochemistry C4d staining and outcomes following heart transplantation.

BACKGROUND: Capillary deposition of C4d is an important marker of antibody-mediated rejection (AMR) following heart transplantation (HT). There are two immunopathologic assay methods for detecting C4d: frozen-tissue immunofluorescence (IF) and paraffin immunohistochemistry (IHC). The clinical significance of discrepancy between the results of IF and IHC has not been understood. METHODS AND RESULTS: We reviewed 2187 biopsies from 142 HT recipients who had biopsies with assessment of both IF and IHC staining. Among them, 103 (73%) patients had negative IF and IHC C4d staining (Negative Group) and 32 (23%) patients had positive IF but negative IHC staining (Discordant Group). At the time of positive biopsy, 6 (19%) Discordant patients had graft dysfunction, compared to 5 (5%) Negative patients (p = .022). Cumulative incidence of cellular rejection at 1 year was comparable (31% vs. 29%, p = .46); however, cumulative incidence of AMR was significantly higher in the Discordant group (21% vs. 4%, p = .004). Overall 1-year survival was comparable (90% vs. 96%, p = .24); however, freedom from heart failure (HF) was significantly lower in the Discordant group (70% vs. 96%, p < .001). CONCLUSION: The Discordant group showed higher rates of graft dysfunction, AMR and HF admission than the Negative group.

Myeloperoxidase immunohistochemical staining can identify glomerular endothelial cell injury in dense deposit disease.

BACKGROUND: Previous studies have demonstrated residual complement-mediated deposits in repeat kidney biopsies of C3 glomerulopathies (C3G) (dense deposit disease (DDD) and C3 glomerulonephritis) following eculizumab treatment, despite some clinical improvement. With residual complement deposition, it is difficult to determine whether there is a reduced complement-mediated endothelial cell injury. We validated that myeloperoxidase (MPO) immunohistochemical staining identified glomerular endothelial cell injury in crescentic glomerulonephritis and C3G. CASE (DIAGNOSIS/TREATMENT): We report that MPO staining in the glomerular endothelium of the post-treatment kidney biopsy was significantly reduced after 3 years of eculizumab treatment and clinical improvement in a 5-year-old boy with initial DDD and secondary crescent formation. CONCLUSION: We find that immunostaining for MPO is a useful method to compare glomerular endothelial injury in C3G following eculizumab treatment. This finding also supports the notion that eculizumab, a C5 blocker, may not mainly block C3 deposits in the glomeruli but significantly blocks final activation of the complement cascade, thus reducing glomerular endothelial cell injury.

Chronic Microangiopathy Due to DCR-MYC, a Myc-Targeted Short Interfering RNA.

Thrombotic microangiopathy (TMA) is an emerging complication of oncologic therapy. Cancer-related causes of renal endothelial cell damage include cytotoxic chemotherapies, radiation given for myeloablation, and direct involvement of renal vasculature by tumor cells. Another class of therapeutic agents that has been implicated in TMA is the vascular endothelial growth factor (VEGF) pathway inhibitors, including the anti-VEGF monoclonal antibody bevacizumab and the VEGF receptor tyrosine kinase inhibitor sunitinib. These TMAs have been termed type II cancer drug-induced TMA and are distinguished from those associated with some cytotoxic chemotherapies (ie, type I) in that they are not dose dependent and patients are more likely to demonstrate some recovery of kidney function. Determination of the cause of TMA in oncologic patients often presents a significant challenge because patients frequently receive multiple chemotherapeutic agents simultaneously and clinicopathologic features often demonstrate substantial overlap, regardless of cause. We present a case of TMA with predominantly chronic features in a 70-year-old patient being treated for adenoid cystic carcinoma of the breast with a single agent, a short interfering RNA targeted against Myc (DCR-MYC).

A New Paradigm for Renal Thrombotic Microangiopathy.

Thrombotic microangiopathy (TMA) is characterized by thrombocytopenia and microangiopathic hemolytic anemia, results from acute and/or chronic endothelial cell injury, and often manifests with kidney dysfunction. TMA can be observed in a wide spectrum of clinical scenarios, which includes but is not limited to thrombotic thrombocytopenic purpura, hemolytic uremic syndrome, severe (malignant) hypertension, preeclampsia/eclampsia, antiphospholipid antibody syndrome, scleroderma renal crisis, drug toxicities, or metabolic disorders. These different conditions are impossible to distinguish based solely on the pathologic findings, necessitating correlation with clinical and laboratory data. For both treating physicians and pathologists, the absence of specific pathologic features for a particular etiology or association with TMA remains a great source of frustration and confusion that currently accompanies this complex topic. In this review, we introduce a new paradigm for TMA that coalesces around the important contribution of the complement system, which has potential implications for therapeutic management, disease recurrence in the kidney allograft, and genetic risks to family members.

HealtheDataLab - a cloud computing solution for data science and advanced analytics in healthcare with application to predicting multi-center pediatric readmissions.

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.