Search

Hepatitis B virus (HBV) is a cause of hepatocellular carcinoma (HCC). Interestingly, this process is not necessarily mediated through cirrhosis and may in fact involve oncogenic processes. Prior studies have suggested specific oncogenic gene expression pathways were affected by viral regulatory proteins. Thus, identifying these genes and associated pathways could highlight predictive factors for HCC transformation and has implications in early diagnosis and treatment.To elucidate HBV oncogenesis in HCC and identify potential therapeutic targets.We employed our Search, Tag, Analyze, Resource platform to conduct a meta-analysis of public data from National Center for Biotechnology Information's Gene Expression Omnibus. We performed meta-analysis consisting of 155 tumor samples compared against 185 adjacent non-tumor samples and analyzed results with ingenuity pathway analysis.Our analysis revealed liver X receptors/retinoid X receptor (RXR) activation and farnesoid X receptor/RXR activation as top canonical pathways amongst others. Top upstream regulators identified included the Ras family gene rab-like protein 6 (RABL6). The role of RABL6 in oncogenesis is beginning to unfold but its specific role in HBV-related HCC remains undefined. Our causal analysis suggests RABL6 mediates pathogenesis of HBV-related HCC through promotion of genes related to cell division, epigenetic regulation, and Akt signaling. We conducted survival analysis that demonstrated increased mortality with higher RABL6 expression. Additionally, homeobox A10 (HOXA10) was a top upstream regulator and was strongly upregulated in our analysis. HOXA10 has recently been demonstrated to contribute to HCC pathogenesisThis meta-analysis describes possible roles of RABL6 and HOXA10 in the pathogenesis of HBV-related HCC. RABL6 and HOXA10 represent potential therapeutic targets and warrant further investigation.

In healthcare, artificial intelligence (AI) technologies have the potential to create significant value by improving time-sensitive outcomes while lowering error rates for each patient. Diagnostic images, clinical notes, and reports are increasingly generated and stored in electronic medical records. This heterogeneous data presenting us with challenges in data analytics and reusability that is by nature has high complexity, thereby necessitating novel ways to store, manage and process, and reuse big data. This presents an urgent need to develop new, scalable, and expandable AI infrastructure and analytical methods that can enable healthcare providers to access knowledge for individual patients, yielding better decisions and outcomes. In this review article, we briefly discuss the nature of data in breast cancer study and the role of AI for generating “smart data” which offer actionable information that supports the better decision for personalized medicine for individual patients. In our view, the biggest challenge is to create a system that makes data robust and smart for healthcare providers and patients that can lead to more effective clinical decision-making, improved health outcomes, and ultimately, managing the healthcare outcomes and costs. We highlight some of the challenges in using breast cancer data and propose the need for an AI-driven environment to address them. We illustrate our vision with practical use cases and discuss a path for empowering the study of breast cancer databases with the application of AI and future directions.

Transcriptional profiling of pre- and post-malignant colorectal cancer (CRC) lesions enable temporal monitoring of molecular events underlying neoplastic progression. However, the most widely used transcriptomic dataset for CRC, TCGA-COAD, is devoid of adenoma samples, which increases reliance on an assortment of disparate microarray studies and hinders consensus building. To address this, we developed a microarray meta-dataset comprising 231 healthy, 132 adenoma, and 342 CRC tissue samples from twelve independent studies. Utilizing a stringent analytic framework, select datasets were downloaded from the Gene Expression Omnibus, normalized by frozen robust multiarray averaging and subsequently merged. Batch effects were then identified and removed by empirical Bayes estimation (ComBat). Finally, the meta-dataset was filtered for low variant probes, enabling downstream differential expression as well as quantitative and functional validation through cross-platform correlation and enrichment analyses, respectively. Overall, our meta-dataset provides a robust tool for investigating colorectal adenoma formation and malignant transformation at the transcriptional level with a pipeline that is modular and readily adaptable for similar analyses in other cancer types., Measurement(s)transcriptome • colorectal cancerTechnology Type(s)microarrayFactor Type(s)gene expressionSample Characteristic - OrganismHomo sapiens Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.14589006

Objective.Osteoporosis is a growing healthcare burden. By identifying osteoporosis-promoting genetic variations, we can spotlight targets for new pharmacologic therapies that will improve patient outcomes. In this metaanalysis, we analyzed mesenchymal stem cell (MSC) biomarkers in patients with osteoporosis.Methods.We employed our Search Tag Analyze Resource for the Gene Expression Omnibus (STARGEO) platform to conduct a metaanalysis to define osteoporosis pathogenesis. We compared 15 osteoporotic and 14 healthy control MSC samples. We then analyzed the genetic signature in Ingenuity Pathway Analysis.Results.The top canonical pathways identified that were statistically significant included the serine peptidase inhibitor kazal type 1 pancreatic cancer pathway, calcium signaling, pancreatic adenocarcinoma signaling, axonal guidance signaling, and glutamate receptor signaling. Upstream regulators involved in this disease process included ESR1, dexamethasone, CTNNβ1, CREB1, and ERBB2.Conclusion.Although there has been extensive research looking at the genetic basis for inflammatory arthritis, very little literature currently exists that has identified genetic pathways contributing to osteoporosis. Our study has identified several important genes involved in osteoporosis pathogenesis including ESR1, CTNNβ1, CREB1, and ERBB2. ESR1 has been shown to have numerous polymorphisms, which may play a prominent role in osteoporosis. The Wnt pathway, which includes the CTNNβ1 gene identified in our study, plays a prominent role in bone mass regulation. Wnt pathway polymorphisms can increase susceptibility to osteoporosis. Our analysis also suggests a potential mechanism for ERBB2 in osteoporosis through Semaphorin 4D (SEMA4D). Our metaanalysis identifies several genes and pathways that can be targeted to develop new anabolic drugs for osteoporosis treatment.

Early detection plays a key role to enhance the outcome for Coronary Artery Disease. We utilized a big data analytics platform on ∼32,000 patients to trace patients from the first encounter to CAD treatment. There are significant gender-based differences in patients younger than 60 from the time of the first encounter to Coronary Artery Bypass Grafting with a p-value=0.03. This recognition makes significant changes in outcome by avoiding delay in treatment.

A retrospective study at a single academic institution.The purpose of this study is to utilize machine learning to predict hospital length of stay (LOS) and discharge disposition following adult elective spine surgery, and to compare performance metrics of machine learning models to the American College of Surgeon's National Surgical Quality Improvement Program's (ACS NSQIP) prediction calculator.A total of 3678 adult patients undergoing elective spine surgery between 2014 and 2019, acquired from the electronic health record.Patients were divided into three stratified cohorts: cervical degenerative, lumbar degenerative, and adult spinal deformity groups. Predictive variables included demographics, body mass index, surgical region, surgical invasiveness, surgical approach, and comorbidities. Regression, classification trees, and least absolute shrinkage and selection operator (LASSO) were used to build predictive models. Validation of the models was conducted on 16% of patients (N=587), using area under the receiver operator curve (AUROC), sensitivity, specificity, and correlation. Patient data were manually entered into the ACS NSQIP online risk calculator to compare performance. Outcome variables were discharge disposition (home vs. rehabilitation) and LOS (days).Of 3678 patients analyzed, 51.4% were male (n=1890) and 48.6% were female (n=1788). The average LOS was 3.66 days. In all, 78% were discharged home and 22% discharged to rehabilitation. Compared with NSQIP (Pearson R2=0.16), the predictions of poisson regression (R2=0.29) and LASSO (R2=0.29) models were significantly more correlated with observed LOS (P=0.025 and 0.004, respectively). Of the models generated to predict discharge location, logistic regression yielded an AUROC of 0.79, which was statistically equivalent to the AUROC of 0.75 for NSQIP (P=0.135).The predictive models developed in this study can enable accurate preoperative estimation of LOS and risk of rehabilitation discharge for adult patients undergoing elective spine surgery. The demonstrated models exhibited better performance than NSQIP for prediction of LOS and equivalent performance to NSQIP for prediction of discharge location.

The study of precision medicine that measures the effects of social, cultural, and environmental influences on health is essential to improve health outcomes. Race is a social concept used historically to divide, track, control populations, and reinforce social hierarchies. Beyond genetics, race is also a surrogate for other socioeconomic factors affecting patient outcomes. Our data analytics study aims to analyze the Electronic Medical Record (EMR) to study patients of different races in diagnosing and treating Coronary Artery Disease (CAD). We found no race discrepancies at the University of California San Francisco Medical Centers. This study opens several new hypotheses for further research in this crucial field.

The development of an ontology facilitates the organization of the variety of concepts used to describe different terms in different resources. The proposed ontology will facilitate the study of cardiothoracic surgical education and data analytics in electronic medical records (EMR) with the standard vocabulary.

Our objective was to develop deep learning models with chest radiograph data to predict healthcare costs and classify top-50% spenders. 21,872 frontal chest radiographs were retrospectively collected from 19,524 patients with at least 1-year spending data. Among the patients, 11,003 patients had 3 years of cost data, and 1678 patients had 5 years of cost data. Model performances were measured with area under the receiver operating characteristic curve (ROC-AUC) for classification of top-50% spenders and Spearman ρ for prediction of healthcare cost. The best model predicting 1-year (N=21,872) expenditure achieved ROC-AUC of 0.806 [95% CI, 0.793-0.819] for top-50% spender classification and ρ of 0.561 [0.536-0.586] for regression. Similarly, for predicting 3-year (N=12,395) expenditure, ROC-AUC of 0.771 [0.750-0.794] and ρ of 0.524 [0.489-0.559]; for predicting 5-year (N=1,779) expenditure ROC-AUC of 0.729 [0.667-0.729] and ρ of 0.424 [0.324-0.529]. Our deep learning model demonstrated the feasibility of predicting health care expenditure as well as classifying top 50% healthcare spenders at 1, 3, and 5 year(s), implying the feasibility of combining deep learning with information-rich imaging data to uncover hidden associations that may allude physicians. Such a model can be a starting point of making an accurate budget in reimbursement models in healthcare industries.

Supplemental Digital Content is available in the text., Background. Early prediction of whether a liver allograft will be utilized for transplantation may allow better resource deployment during donor management and improve organ allocation. The national donor management goals (DMG) registry contains critical care data collected during donor management. We developed a machine learning model to predict transplantation of a liver graft based on data from the DMG registry. Methods. Several machine learning classifiers were trained to predict transplantation of a liver graft. We utilized 127 variables available in the DMG dataset. We included data from potential deceased organ donors between April 2012 and January 2019. The outcome was defined as liver recovery for transplantation in the operating room. The prediction was made based on data available 12–18 h after the time of authorization for transplantation. The data were randomly separated into training (60%), validation (20%), and test sets (20%). We compared the performance of our models to the Liver Discard Risk Index. Results. Of 13 629 donors in the dataset, 9255 (68%) livers were recovered and transplanted, 1519 recovered but used for research or discarded, 2855 were not recovered. The optimized gradient boosting machine classifier achieved an area under the curve of the receiver operator characteristic of 0.84 on the test set, outperforming all other classifiers. Conclusions. This model predicts successful liver recovery for transplantation in the operating room, using data available early during donor management. It performs favorably when compared to existing models. It may provide real-time decision support during organ donor management and transplant logistics.

Background: Cardiovascular Disease (CVD) and Coronary Artery Disease (CAD) in particular, is one of the leading causes of death, morbidity, and mortality in the United States. Notably, women continue to have worse outcomes than men. The causes of these discrepancies have yet to be fully elucidated. The main objective of this study is to detect gender discrepancies in outcome using data analytics to risk stratify ~ 32,000 patients with CAD of the total 960,129 patients treated at UCSF Medical Center during an eight years. As an implementation of clinical care, this study’s long-term goal is to improve precision diagnosis and ultimately management of CAD for both early detection and identification of patients at risk for rapid progression of the disease.Methods: We designed and implemented a multidimensional framework to trace patients from admission through treatment as a path of events. The time between events for a similar set of paths was calculated. Then the average waiting time for each step of the treatment was calculated for men and women. Finally, we applied statistical analysis to determine differences in time between diagnosis and treatment steps for men and women.Discussions: There were statistically significant gender-based differences in the common path of diagnosis and treatment of patients with CAD. The average time for women from the first visit to diagnostic Cardiac Catheterization was more than 2 months than for men (358.77 vs. 291.83 days). By contrast, the average time from diagnostic Cardiac Catheterization to treatment Cardiac Catheterization and Coronary Artery Bypass Grafting (CABG) was not significant. Women with CAD requiring revascularization have a significantly longer interval between their first physician encounter indicative of CVD and their first diagnostic cardiac catheterization compared to men. Avoiding the delay in diagnosis and treatment will provide a better outcome for patients at risk.

A crucial factor in Big Data is to take advantage of available data and use that for discovery, hypothesis generation, and testing the hypothesis. When it comes to chronic diseases, worldwide, women continue to have poorer outcomes than men. The causes of these discrepancies have yet to be fully elucidated. Personalized medicine has transformed the way we identify and manage health-related issues. The big difference between traditional assessment of a situation and personalized medicine is the reliance of the multidimensional data (e.g., demographic, genetics) to make decisions about a treatment for individual patients. Predictive modeling with electronic health record (EHR) data is anticipated to drive personalized medicine and improve health care quality in general. Deep learning models could be used in a wide variety of predictive problems and settings in health care. In this chapter, we describe the role of big data analytics, machine learning, deep learning, and personalized medicine to improve women’s health. Then we describe a summary of use cases from our research group at UCSF School of Medicine and Mayo Clinic Healthcare Delivery and Informatics that shows big-scale advanced data analytics to improve women’s health in dermatology, cardiology, and breast cancer.

Opal is the first published example of a full-stack platform infrastructure for an implementation science designed for ML in anesthesia that solves the problem of leveraging ML for clinical decision support. Users interact with a secure online Opal web application to select a desired operating room (OR) case cohort for data extraction, visualize datasets with built-in graphing techniques, and run in-client ML or extract data for external use. Opal was used to obtain data from 29,004 unique OR cases from a single academic institution for pre-operative prediction of post-operative acute kidney injury (AKI) based on creatinine KDIGO criteria using predictors which included pre-operative demographic, past medical history, medications, and flowsheet information. To demonstrate utility with unsupervised learning, Opal was also used to extract intra-operative flowsheet data from 2995 unique OR cases and patients were clustered using PCA analysis and k-means clustering. A gradient boosting machine model was developed using an 80/20 train to test ratio and yielded an area under the receiver operating curve (ROC-AUC) of 0.85 with 95% CI [0.80–0.90]. At the default probability decision threshold of 0.5, the model sensitivity was 0.9 and the specificity was 0.8. K-means clustering was performed to partition the cases into two clusters and for hypothesis generation of potential groups of outcomes related to intraoperative vitals. Opal’s design has created streamlined ML functionality for researchers and clinicians in the perioperative setting and opens the door for many future clinical applications, including data mining, clinical simulation, high-frequency prediction, and quality improvement.

Highlights • Early age of onset of cannabis use among adolescents is associated with increased likelihood of poor cognitive function and mental health. • Persistent cannabis use is associated with decreased academic performance scores. • Racial disparities exist among adolescent cannabis users as well as the negative sequalae associated with cannabis use in this group. • Adolescents from states with medical marijuana laws were less likely to use marijuana in the past 30 days. • Mitigation methods associated with COVID-19 could directly impact cannabis use and mental health among adolescents., Given varying state-level laws regarding cannabis use, the objective of the review was to summarize contemporary literature on the relationship between adolescent cognitive function and academic performance with cannabis use. Frequency and quantity of cannabis use were associated with decreased functional connectivity of the brain. Earlier age at cannabis initiation and more frequent use was associated with poorer executive control and academic performance. Social determinants such as minimal parental monitoring, peer use and low social cohesion were associated with more frequent adolescent use. Race/ethnicity and residence were other factors influencing cannabis use. To prevent cannabis use disorders among adolescents, interventions should aim to prevent early initiation that can lead to chronic use in youth who may be more at risk.

Despite having excellent prognosis when detected early, colorectal cancer (CRC) remains a leading cause of cancer-related deaths globally. Barriers to screening reduces compliance and negatively impacts patient outcomes, necessitating alternatives. A blood-based approach provides a more convenient and accessible modality, but serum markers are lacking. Using a meta-transcriptomics approach, we identified Fibroblast Growth Factor 19 (FGF19), an enteroendocrine FGF responsible for bile acid (BA) homeostasis, as an attractive CRC marker. However, whether FGF19 is aberrantly secreted into blood by colorectal tumors or induces endocrine-like paraneoplastic effects is unknown. To assess the strength of FGF19 as a CRC biomarker, expression data from the Genotype-Tissue Expression consortium (GTEx), The Cancer Genome Atlas (TCGA-COADREAD), and our curated Meta-dataset (E-MTAB-10089) were downloaded and analyzed for associations with prognostic indicators. Next, in silico FGF19 expression profiles were validated in vitro using a panel of five CRC cell lines via western blot with secretion quantitated by sandwich ELISA. To determine whether colorectal tumors contribute FGF19 to circulation, subcutaneous xenografts of HCT116 and Colo201 cells were established in four male and female NOD Scid gamma (NSG) mice. Tumor volume, as well as serum and urine FGF19 were assessed weekly over a 36-day period. Following euthanasia, murine liver and ileal tissue were processed for downstream mRNA and bile acid quantification. To determine if malignant FGF19 exerts paraneoplastic effects RNA sequencing was performed on hepatic mRNA using the Illumina NovaSeq 6000 system. Reads were processed, aligned, mapped, and analyzed for differential expression and functional enrichment using an integrated informatics pipeline implemented in R. Meta-transcriptomics revealed that ectopic overexpression of FGF19 was highly indicative of CRC and associated with unfavorable prognostic indicators including disease progression, treatment failure, and poor survival. In vitro testing recapitulated in silico findings, showing that that four out of five CRC cell lines constitutively express and secrete FGF19. We also readily detected FGF19 in serum and urine of mice harboring xenografts derived from Colo201, but not HCT116, cells. Moreover, circulating FGF19 levels increased with tumor size and exerted paraneoplastic effects on liver tissue such as suppression of BA synthesis, dysregulation of cholesterol metabolism, and induction of pre-neoplasia. In summary, we describe FGF19 as a putative serum CRC biomarker that exerts novel endocrine-like paraneoplastic effects on the liver. Study limitations included the lack of FGF19 quantification in CRC patient blood, in vivo experimentation using two different cell lines, and gender-related batch effects identified by RNA sequencing. Citation Format: Michael Walter Rohr, Jordan Beardsley, Sai Preethi Nakkina, Dexter Hadley, Deborah Altomare. FGF19 is a novel serum colorectal cancer biomarker that exerts endocrine paraneoplastic effects on hepatic tissue [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 2689.

Background: The pathogenesis of sickle cell disease (SCD) and its complications have been well characterized down to the molecular level. However, there remains a relative dearth of disease modifying therapies that reduce the frequency and number of vas-occlusive crises, hospitalizations, and deaths. Recent advancements in utilizing hydroxyurea and L-glutamine, which both impact unique disease pathways, should pave way for the identification of other molecular pathways as ideal drug targets. In this regard, our meta-analysis serves to identify key genes and associated pathways that are differentially expressed in SC patients. Methods: We employed our STARGEO platform to tag samples from the NCBI Gene Expression Omnibus and performed meta-analysis to compare SC and healthy control transcriptomes. For the meta-analysis, we tagged 285 peripheral blood samples from SC patients and 86 samples from healthy subjects as a control. We then analyzed the signature in Ingenuity Pathway Analysis to elucidate top disease functions from our analysis. Results: From our meta-analysis, we identified iron homeostasis signaling, NRF2-mediated oxidative stress response, cell senescence, and pyrimidine interconversion/biosynthesis as top canonical pathways that were upregulated in the peripheral blood samples from SC patients. Top upstream regulators included membrane associated protein and transporter ABCB6, non-coding RNY3, and erythroid maturation transcription factors GATA1, KLF1, and HIPK2 (with predicted activation). The most upregulated genes included inflammatory modulators RNF182 and IFI27, the latter of which has been shown to inhibit vascular endothelial growth and repair. Several membrane-associated protein coding genes such as GYPA, RAP1GAP, and PAQR9 were also upregulated in the SC samples. RAP1GAP is known to modulate neutrophil cell adhesion and homing while PAQR9 has roles in regulating protein quality control: a role also seen in similarly upregulated YOD1, a deubiquitinating enzyme involved in trafficking of misfolded proteins. Expectedly, also upregulated were HBBP1 and SOX6, which regulate globin genes and have been shown to silence γ-globin expression. Lastly, SLC6A19, the neutral amino acid transporter mutated in Hartnup disease, was also upregulated. Of the downregulated genes, WASF3, a member of the Wiskott-Aldrich syndrome protein family, has been linked to poor survival in many malignancies, including AML and CMML, but has not previously been linked to SCD pathogenesis. ENKUR was also downregulated and has been annotated as a tethering protein to cation channels as well as linked to pathways involving vascular leakage. SIGLEC10, which binds to vascular adhesion proteins, is a key suppressor of inflammatory responses to damage; it's downregulation along with ELAPOR1, a transmembrane protein involved in cellular response to stress, was also observed. Finally, based off the focus genes in our analysis we identified several networks with most being involved in amino acid metabolism, cellular assembly, function, and maintenance, hematological disease, and organismal injury. The top pathway is illustrated in Figure 1. Conclusions: Our study illustrates differentially expressed gene activity in SCD consistent with known pathophysiology such as immune response, endothelial damage and adherence, heme metabolism, and globin regulation. We also showed evidence of genes not previously studied in SCD, which may have novel roles such as those part of the ubiquitin-proteasome system like YOD1 and RNF182. Additionally, while some genes in our analysis like EKLF and GAT1 have been shown to enhance δ-globin expression, paving way for possible drug therapies for B-hemoglobinopathies, others like IFI27, PAQR9, RAP1GAP, ENKUR, SIGLEC10, WASF3, and SOX9 have yet to be studied as mediators of disease pathogenesis in SCD. A target to SOX9, a known suppressor of γ-globin, or ABCB6, a known modulator of erythroid cell shape and hydration, have particularly promising potential as disease modifying therapies. Finally, HIPK2, HBBP1, and SLC6A19 have previously been shown to have intriguing effects on hydroxyurea dosing and responsivity in SC patients and may also be candidate target molecules to enhance existing therapies. These data identify potential candidate pathways for mechanistic studies seeking to confirm a causative role in the pathogenesis of sickle cell disease. Disclosures No relevant conflicts of interest to declare.

Hepatitis C is a leading cause of chronic liver disease and hepatocellular carcinoma (HCC). Understanding the evolution and biology of HCC among HCV patients may lead to novel therapeutic avenues and risk stratification.Using meta-analysis platform STARGEO, we performed two separate meta-analyses as follows: 357 HCV-related HCC tumor samples with 220 adjacent non-tumor samples and 92 HCV-related cirrhotic liver samples with 53 healthy liver samples as a control. Then, we analyzed the signature in Ingenuity Pathway Analysis.HCV cirrhosis analysis demonstrated LPS/IL-1 mediated inhibition of RXR function, LXR/RXR activation, sirtuin signaling, IL-10 signaling and hepatic fibrosis/stellate cell activation as top canonical pathways. IL1β, TNF, and TGF-β1 were top upstream regulators. Cellular morphologic and signaling changes were noted through the up-regulation of RGS1/2, WNT receptor FZD7, the TGF-β1-induced gap junction gene GJA1, and the zinc finger transcription factor repressor SNAI2. Apoptosis was inhibited through the down-regulation of OMA1. Metabolic dysfunction was noted through the down-regulation of SCLY and CBS. HCV-related HCC analysis showed FXR/RXR and LXR/RXR signaling, LPS/IL1-mediated inhibition of RXR activation, and melatonin degradation as top canonical pathways.Our results suggest that the genetic changes in the setting of chronic HCV infection predispose patients to developing HCC.

Cardiovascular disease (CVD) is the major cause of death in the United State and other countries

The identification of novel disease associations using big-data for patient care has had limited success. In this study, we created a longitudinal disease network of traced readmissions (disease trajectories), merging data from over 10.4 million inpatients through the Healthcare Cost and Utilization Project, which allowed the representation of disease progression mapping over 300 diseases. From these disease trajectories, we discovered an interesting association between schizophrenia and rhabdomyolysis, a rare muscle disease (incidence P-value 9.54E-15). We validated this association by using independent electronic medical records from over 830,000 patients at the University of California, San Francisco (UCSF) medical center. A case review of 29 rhabdomyolysis incidents in schizophrenia patients at UCSF demonstrated that 62% are idiopathic, without the use of any drug known to lead to this adverse event, suggesting a warning to physicians to watch for this unexpected risk of schizophrenia. Large-scale analysis of disease trajectories can help physicians understand potential sequential events in their patients.

Allograft rejection is a major concern in kidney transplantation. Inflammatory processes in patients with kidney allografts involve various patterns of immune cell recruitment and distributions. Lymphoid aggregates (LAs) are commonly observed in patients with kidney allografts and their presence and localization may correlate with severity of acute rejection. Alongside with other markers of inflammation, LAs assessment is currently performed by pathologists manually in a qualitative way, which is both time consuming and far from precise. Here we present the first automated method of identifying LAs and measuring their densities in whole slide images of transplant kidney biopsies. We trained a deep convolutional neural network based on U-Net on 44 core needle kidney biopsy slides, monitoring loss on a validation set (n=7 slides). The model was subsequently tested on a hold-out set (n=10 slides). We found that the coarse pattern of LAs localization agrees between the annotations and predictions, which is reflected by high correlation between the annotated and predicted fraction of LAs area per slide (Pearson R of 0.9756). Furthermore, the network achieves an auROC of 97.78 ± 0.93% and an IoU score of 69.72 ± 6.24 % per LA-containing slide in the test set. Our study demonstrates that a deep convolutional neural network can accurately identify lymphoid aggregates in digitized histological slides of kidney. This study presents a first automatic DL-based approach for quantifying inflammation marks in allograft kidney, which can greatly improve precision and speed of assessment of allograft kidney biopsies when implemented as a part of computer-aided diagnosis system.

333 Background: Hepatitis B is a cause of hepatocellular carcinoma (HCC) globally, irrespective of viral loads. Interestingly, this process is not necessarily mediated through cirrhosis and may in fact involve oncogenic processes. Prior studies have suggested specific oncogenic gene expression pathways affected by viral regulatory proteins. Thus, identifying these genes and associated pathways could highlight predictive factors for HCC transformation, and has implications in early diagnosis and treatment. Methods: We employed our Search, Tag, Analyze, Resource (STARGEO) platform to conduct a meta-analysis of public data from NCBI's Gene Expression Omnibus. We performed meta-analysis consisting of 155 tumor samples compared against 185 adjacent non-tumor samples. We present the results from the meta-analysis in Ingenuity Pathway Analysis. Results:Our analysis revealed LXR/RXR activation, LPS-IL-1 mediation inhibition of RXR, and FXR/RXR activation as top canonical pathways amongst others. Top upstream regulators identified included the Ras family gene RABL6. The role of RABL6 in oncogenesis is beginning to unfold but its specific role in HBV-related HCC remains undefined. Our causal analysis suggests RABL6 mediates pathogenesis of HBV-related HCC through promotion of genes related to cell division, epigenetic regulation, and Akt signaling. Additionally, HOXA10 was a top upstream regulator and was strongly upregulated in our analysis. While described in other cancer, HOXA10 has not been well documented in HBV-related HCC and our causal analysis suggests it mediates pathogenesis through downregulation of tumor suppressors and its protective effect from oxidative stress. Conclusions: This meta-analysis describes possible role of viral regulatory proteins such as RABL6 and HOXA10 in the pathogenesis of HBV -related HCC. Further prospective studies are needed to confirm our findings.