Stratifying individuals into non-alcoholic fatty liver disease risk levels using time series machine learning models.

Non-alcoholic fatty liver disease (NAFLD) affects 25% of the population worldwide, and its prevalence is anticipated to increase globally. While most NAFLD patients are asymptomatic, NAFLD may progress to fibrosis, cirrhosis, cardiovascular disease, and diabetes. Research reports, with daunting results, show the challenge that NAFLD's burden causes to global population health. The current process for identifying fibrosis risk levels is inefficient, expensive, does not cover all potential populations, and does not identify the risk in time. Instead of invasive liver biopsies, we implemented a non-invasive fibrosis assessment process calculated from clinical data (accessed via EMRs/EHRs). We stratified patients' risks for fibrosis from 2007 to 2017 by modeling the risk in 5579 individuals. The process involved time-series machine learning models (Hidden Markov Models and Group-Based Trajectory Models) profiled fibrosis risk by modeling patients' latent medical status resulted in three groups. The high-risk group had abnormal lab test values and a higher prevalence of chronic conditions. This study can help overcome the inefficient, traditional process of detecting fibrosis via biopsies (that are also medically unfeasible due to their invasive nature, the medical resources involved, and costs) at early stages. Thus longitudinal risk assessment may be used to make population-specific medical recommendations targeting early detection of high risk patients, to avoid the development of fibrosis disease and its complications as well as decrease healthcare costs.

Improvement in the Prediction of Coronary Heart Disease Risk by Using Artificial Neural Networks.

BACKGROUND AND OBJECTIVES: Cardiovascular diseases, such as coronary heart disease (CHD), are the main cause of mortality and morbidity worldwide. Although CHD cannot be entirely predicted by classic risk factors, it is preventable. Therefore, predicting CHD risk is crucial to clinical cardiology research, and the development of innovative methods for predicting CHD risk is of great practical interest. The Framingham risk score (FRS) is one of the most frequently implemented risk models. However, recent advances in the field of analytics may enhance the prediction of CHD risk beyond the FRS. Here, we propose a model based on an artificial neural network (ANN) for predicting CHD risk with respect to the Framingham Heart Study (FHS) dataset. The performance of this model was compared to that of the FRS. METHODS: A sample of 3066 subjects from the FHS offspring cohort was subjected to an ANN. A multilayer perceptron ANN architecture was used and the lift, gains, receiver operating characteristic (ROC), and precision-recall predicted by the ANN were compared with those of the FRS. RESULTS: The lift and gain curves of the ANN model outperformed those of the FRS model in terms of top percentiles. The ROC curve showed that, for higher risk scores, the ANN model had higher sensitivity and higher specificity than those of the FRS model, although its area under the curve (AUC) was lower. For the precision-recall measures, the ANN generated significantly better results than the FRS with a higher AUC. CONCLUSIONS: The findings suggest that the ANN model is a promising approach for predicting CHD risk and a good screening procedure to identify high-risk subjects.

Non-alcoholic Fatty Liver and Liver Fibrosis Predictive Analytics: Risk Prediction and Machine Learning Techniques for Improved Preventive Medicine.

Non-alcoholic fatty liver disease (NAFLD) is the most common liver disease worldwide, with a prevalence of 20%-30% in the general population. NAFLD is associated with increased risk of cardiovascular disease and may progress to cirrhosis with time. The purpose of this study was to predict the risks associated with NAFLD and advanced fibrosis on the Fatty Liver Index (FLI) and the 'NAFLD fibrosis 4' calculator (FIB-4), to enable physicians to make more optimal preventive medical decisions. A prospective cohort of apparently healthy volunteers from the Tel Aviv Medical Center Inflammation Survey (TAMCIS), admitted for their routine annual health check-up. Data from the TAMCIS database were subjected to machine learning classification models to predict individual risk after extensive data preparation that included the computation of independent variables over several time points. After incorporating the time covariates and other key variables, this technique outperformed the predictive power of current popular methods (an improvement in AUC above 0.82). New powerful factors were identified during the predictive process. The findings can be used for risk stratification and in planning future preventive strategies based on lifestyle modifications and medical treatment to reduce the disease burden. Interventions to prevent chronic disease can substantially reduce medical complications and the costs of the disease. The findings highlight the value of predictive analytic tools in health care environments. NAFLD constitutes a growing burden on the health system; thus, identification of the factors related to its incidence can make a strong contribution to preventive medicine.

Lung Based Engineered Micro-Pancreas Sustains Human Beta Cell Survival and Functionality.

The whole world has been affected by a dramatically increasing prevalence of diabetes. Today, the etiology of both type 1 and type 2 diabetes is thought to revolve around the dysfunction of ß-cells, the insulin producing cells of the body. Within the pharmaceutical industry, the evaluation of new drugs for diabetes treatment is mostly done using cell lines or rodent islets and depends solely on the assessment of static insulin secretion. However, the use of cell lines or rodent islets is limiting lack of similarity of the human islet cells, leading to a constrain of the predictive value regarding the clinical potential of newly developed drugs. To overcome this issue, we developed an Engineered Micro-Pancreas as a unique platform for drug discovery. The Engineered Micro Pancreas is composed of (i) an organ-derived micro-scaffold, specifically a decellularized porcine lung-derived micro-scaffold and (ii) cadaveric islets seeded thereon. The Engineered Micro Pancreas remained viable and maintained insulin secretion in vitro for up to three months. The quantities of insulin were comparable to those secreted by freshly isolated human islets and therefore hold the potential for real-time and metabolic physiology mimicking drug screening.

Functional Blood Progenitor Markers in Developing Human Liver Progenitors.

In the early fetal liver, hematopoietic progenitors expand and mature together with hepatoblasts, the liver progenitors of hepatocytes and cholangiocytes. Previous analyses of human fetal livers indicated that both progenitors support each other's lineage maturation and curiously share some cell surface markers including CD34 and CD133. Using the human embryonic stem cell (hESC) system, we demonstrate that virtually all hESC-derived hepatoblast-like cells (Hep cells) transition through a progenitor stage expressing CD34 and CD133 as well as GATA2, an additional hematopoietic marker that has not previously been associated with human hepatoblast development. Dynamic expression patterns for CD34, CD133, and GATA2 in hepatoblasts were validated in human fetal livers collected from the first and second trimesters of gestation. Knockdown experiments demonstrate that each gene also functions to regulate hepatic fate mostly in a cell-autonomous fashion, revealing unprecedented roles of fetal hematopoietic progenitor markers in human liver progenitors.

Human Pluripotent Stem Cells: Myths and Future Realities for Liver Cell Therapy.

The severe shortage of organ donors for treating patients with liver disease has prompted in vitro efforts to produce the main functional cells of the liver: hepatocyte-like cells (Hep cells). We consider the key challenges posed by various stem cell technologies and liver pathologies for developing clinically useful Hep cells.

The mesenchymal transcription factor SNAI-1 instructs human liver specification.

Epithelial-mesenchymal transition (EMT) and the mesenchymal-epithelial transition (MET) are processes required for embryo organogenesis. Liver develops from the epithelial foregut endoderm from which the liver progenitors, hepatoblasts, are specified. The migrating hepatoblasts acquire a mesenchymal phenotype to form the liver bud. In mid-gestation, hepatoblasts mature into epithelial structures: the hepatocyte cords and biliary ducts. While EMT has been associated with liver bud formation, nothing is known about its contribution to hepatic specification. We previously established an efficient protocol from human embryonic stem cells (hESC) to generate hepatic cells (Hep cells) resembling the hepatoblasts expressing alpha-fetoprotein (AFP) and albumin (ALB). Here we show that Hep cells express both epithelial (EpCAM and E-cadherin) and mesenchymal (vimentin and SNAI-1) markers. Similar epithelial and mesenchymal hepatoblasts were identified in human and mouse fetal livers, suggesting a conserved interspecies phenotype. Knock-down experiments demonstrated the importance of SNAI-1 in Hep cell hepatic specification. Moreover, ChIP assays revealed direct binding of SNAI-1 in the promoters of AFP and ALB genes consistent with its transcriptional activator function in hepatic specification. Altogether, our hESC-derived Hep cell cultures reveal the dual mesenchymal and epithelial phenotype of hepatoblast-like cells and support the unexpected transcriptional activator role of SNAI-1 in hepatic specification.

Predicting 30-day readmissions with preadmission electronic health record data.

BACKGROUND: Readmission prevention should begin as early as possible during the index admission. Early identification may help target patients for within-hospital readmission prevention interventions. OBJECTIVES: To develop and validate a 30-day readmission prediction model using data from electronic health records available before the index admission. RESEARCH DESIGN: Retrospective cohort study of admissions between January 1 and March 31, 2010. SUBJECTS: Adult enrollees of Clalit Health Services, an integrated delivery system, admitted to an internal medicine ward in any hospital in Israel. MEASURES: All-cause 30-day emergency readmissions. A prediction score based on before admission electronic health record and administrative data (the Preadmission Readmission Detection Model-PREADM) was developed using a preprocessing variable selection step with decision trees and neural network algorithms. Admissions with a recent prior hospitalization were excluded and automatically flagged as "high-risk." Selected variables were entered into multivariable logistic regression, with a derivation (two-thirds) and a validation cohort (one-third). RESULTS: The derivation dataset comprised 17,334 admissions, of which 2913 (16.8%) resulted in a 30-day readmission. The PREADM includes 11 variables: chronic conditions, prior health services use, body mass index, and geographical location. The c-statistic was 0.70 in the derivation set and of 0.69 in the validation set. Adding length of stay did not change the discriminatory power of the model. CONCLUSIONS: The PREADM is designed for use by health plans for early high-risk case identification, presenting discriminatory power better than or similar to that of previously reported models, most of which include data available only upon discharge.

Endoderm generates endothelial cells during liver development.

Organogenesis requires expansion of the embryonic vascular plexus that migrates into developing organs through a process called angiogenesis. Mesodermal progenitors are thought to derive endothelial cells (ECs) that contribute to both embryonic vasculogenesis and the subsequent organ angiogenesis. Here, we demonstrate that during development of the liver, which is an endoderm derivative, a subset of ECs is generated from FOXA2+ endoderm-derived fetal hepatoblast progenitor cells expressing KDR (VEGFR2/FLK-1). Using human and mouse embryonic stem cell models, we demonstrate that KDR+FOXA2+ endoderm cells developing in hepatic differentiation cultures generate functional ECs. This introduces the concept that ECs originate not exclusively from mesoderm but also from endoderm, supported in Foxa2 lineage-tracing mouse embryos by the identification of FOXA2+ cell-derived CD31+ ECs that integrate the vascular network of developing fetal livers.

Hepatic cells derived from induced pluripotent stem cells of pigtail macaques support hepatitis C virus infection.

The narrow species tropism of hepatitis C virus (HCV) limits animal studies. We found that pigtail macaque (Macaca nemestrina) hepatic cells derived from induced pluripotent stem cells support the entire HCV life cycle, although infection efficiency was limited by defects in the HCV cell entry process. This block was overcome by either increasing occludin expression, complementing the cells with human CD81, or infecting them with a strain of HCV with less restricted requirements for CD81. Using this system, we can modify viral and host cell genetics to make pigtail macaques a suitable, clinically relevant model for the study of HCV infection.

KDR identifies a conserved human and murine hepatic progenitor and instructs early liver development.

Understanding the fetal hepatic niche is essential for optimizing the generation of functional hepatocyte-like cells (hepatic cells) from human embryonic stem cells (hESCs). Here, we show that KDR (VEGFR2/FLK-1), previously assumed to be mostly restricted to mesodermal lineages, marks a hESC-derived hepatic progenitor. hESC-derived endoderm cells do not express KDR but, when cultured in media supporting hepatic differentiation, generate KDR+ hepatic progenitors and KDR- hepatic cells. KDR+ progenitors require active KDR signaling both to instruct their own differentiation into hepatic cells and to non-cell-autonomously support the functional maturation of cocultured KDR- hepatic cells. Analysis of human fetal livers suggests that similar progenitors are present in human livers. Lineage tracing in mice provides in vivo evidence of a KDR+ hepatic progenitor for fetal hepatoblasts, adult hepatocytes, and adult cholangiocytes. Altogether, our findings reveal that KDR is a conserved marker for endoderm-derived hepatic progenitors and a functional receptor instructing early liver development.

Generation of functional hepatic cells from pluripotent stem cells.

Liver diseases affect millions of people worldwide, especially in developing country. According to the American Liver Foundation, nearly 1 in every 10 Americans suffers from some form of liver disease. Even though, the liver has great ability to self-repair, in end-stage liver diseases including fibrosis, cirrhosis, and liver cancer induced by viral hepatitis and drugs, the liver regenerative capacity is exhausted. The only successful treatment for chronic liver failure is the whole liver transplantation. More recently, some clinical trials using hepatocyte transplantation have shown some clinical improvement for metabolic liver diseases and acute liver failure. However, the shortage of donor livers remains a life-threatening challenge in liver disease patients. To overcome the scarcity of donor livers, hepatocytes generated from embryonic stem cell or induced pluripotent stem cell differentiation cultures could provide an unlimited supply of such cells for transplantation. This review provides an updated summary of hepatic differentiation protocols published so far, with a characterization of the hepatic cells generated in vitro and their ability to regenerate damaged livers in vivo following transplantation in pre-clinical liver deficient mouse models.

A boost of BMP4 accelerates the commitment of human embryonic stem cells to the endothelial lineage.

Embryoid bodies (EBs) generated during differentiation of human embryonic stem cells (hESCs) contain vascular-like structures, suggesting that commitment of mesoderm progenitors into endothelial cells occurs spontaneously. We showed that bone morphogenetic protein 4 (BMP4), an inducer of mesoderm, accelerates the peak expression of CD133/kinase insert domain-containing receptor (KDR) and CD144/KDR. Because the CD133(+)KDR(+) population could represent endothelial progenitors, we sorted them at day 7 and cultured them in endothelial medium. These cells were, however, unable to differentiate into endothelial cells. Under standard conditions, the CD144(+)KDR(+) population represents up to 10% of the total cells at day 12. In culture, these cells, if sorted, give rise to a homogeneous population with a morphology typical of endothelial cells and express endothelial markers. These endothelial cells derived from the day 12 sorted population were functional, as assessed by different in vitro assays. When EBs were stimulated by BMP4, the CD144(+)KDR(+) peak was shifted to day 7. Most of these cells, however, were CD31(-), becoming CD31(+) in culture. They then expressed von Willebrand factor and were functional. This suggests that, initially, the BMP4-boosted day 7, CD144(+)KDR(+)CD31(-) population represents immature endothelial cells that differentiate into mature endothelial cells in culture. The expression of OCT3/4, a marker of immaturity for hESCs decreases during EB differentiation, decreasing faster following BMP4 induction. We also show that BMP4 inhibits the global expression of GATA2 and RUNX1, two transcription factors involved in hemangioblast formation, at day 7 and day 12.