BackgroundWe present a method utilizing Healthcare Cost and Utilization Project (HCUP) dataset for predicting disease risk of individuals based on their medical diagnosis history. The presented methodology may be incorporated in a variety of applications such as risk management, tailored health communication and decision support systems in healthcare.MethodsWe employed the National Inpatient Sample (NIS) data, which is publicly available through Healthcare Cost and Utilization Project (HCUP), to train random forest classifiers for disease prediction. Since the HCUP data is highly imbalanced, we employed an ensemble learning approach based on repeated random sub-sampling. This technique divides the training data into multiple sub-samples, while ensuring that each sub-sample is fully balanced. We compared the performance of support vector machine (SVM), bagging, boosting and RF to predict the risk of eight chronic diseases.ResultsWe predicted eight disease categories. Overall, the RF ensemble learning method outperformed SVM, bagging and boosting in terms of the area under the receiver operating characteristic (ROC) curve (AUC). In addition, RF has the advantage of computing the importance of each variable in the classification process.ConclusionsIn combining repeated random sub-sampling with RF, we were able to overcome the class imbalance problem and achieve promising results. Using the national HCUP data set, we predicted eight disease categories with an average AUC of 88.79%.

Phytochemicals such as alkaloids, flavonoids, pigments, phenolics, terpenoids, steroids and essential oils are a large group of plant-derived compounds commonly found in diets high in fruits, vegetables, beans and cereals. Plant remedies are closely linked to the maintenance of good health in the cultural heritage of many countries. Despite the potential benefits to health and performance as noted in various terrestrial animals, the use of phytochemicals in fish farming has rarely been investigated. Fish culture is under pressure to decrease the use of synthetic antibiotics and chemotherapeutics because of the risk caused to humans by chemical residues in food and by antibiotic resistance being passed on to human pathogens. Consequently, efforts are being made to exploit plants, plant extracts or natural plant compounds as potential alternatives to synthetic chemicals for the stimulation of immune responses and disease resistance in fish. The phytochemicals contained in herbs may enhance the innate immune system and possess antimicrobial capabilities that may be of immense use in fish culture without causing any environmental and ⁄ or hazardous problems. Most phytochemicals are redox active molecules that have anti-oxidant characteristics that may improve the general physiological condition of fish. This review discusses the results emanating from different studies related to the in vivo application of plants and ⁄ or phytochemicals in fish in relation to immunostimulation, antipathogenic and antistress activities. Special emphasis is given to the use of Chinese and Indian herbs as immunostimulants in different finfish species during culture and as antibacterial agents against Aeromonas hydrophila.

There is a constant need to increase productivity in aquaculture, particularly to improve growth rate, feed utilization as well as stress resistance of fish. Because of consumer concerns and strict regulations in many countries, the use of synthetic chemicals, hormones and antibiotics is becoming unviable and natural compounds are more acceptable to the public. A wide variety of chemical compounds are found in plants, and many of them have been shown to have beneficial effects on appetite, growth and the immune status of fish acting through different mechanisms. Phytochemicals contained in herbs may enhance the innate immune system, possess antimicrobial capabilities, and are redox active molecules with antioxidant characteristics that may help to improve the general physiological condition of fish. Many studies have discussed the values of phytochemicals as feed additives. Another paramount concern related to phytochemicals is their endocrine modulator effect that can be applied both in aquaculture targeting the production of table fish and the growing sector of ornamental fish production. Different mechanisms such as the effects at the steroid receptor level, effects on steroid synthesis, distribution and excretion, actions on the hypothalamuspituitary-gonad axis, as well as indirect mechanisms including thyroid and growth hormone disruption have been postulated for the reproductive endocrine disruption in fish populations by phytochemicals. This paper reviews the results of a great number of studies focusing on phytochemicals such as essential oils, saponins, flavonoids and phytosterols discussing their effects on productive traits and the putative mechanism of action.

Most plants engage in symbioses with mycorrhizal fungi in soils and net consequences for plants vary widely from mutualism to parasitism. However, we lack a synthetic understanding of the evolutionary and ecological forces driving such variation for this or any other nutritional symbiosis. We used meta-analysis across 646 combinations of plants and fungi to show that evolutionary history explains substantially more variation in plant responses to mycorrhizal fungi than the ecological factors included in this study, such as nutrient fertilization and additional microbes. Evolutionary history also has a different influence on outcomes of ectomycorrhizal versus arbuscular mycorrhizal symbioses; the former are best explained by the multiple evolutionary origins of ectomycorrhizal lifestyle in plants, while the latter are best explained by recent diversification in plants; both are also explained by evolution of specificity between plants and fungi. These results provide the foundation for a synthetic framework to predict the outcomes of nutritional mutualisms.

Background Improper control on reactive oxygen species (ROS) elimination process and formation of free radicals causes tissue dysfunction. Pineal hormone melatonin is considered a potent regulator of such oxidative damage in different vertebrates. Aim of the current communication is to evaluate the levels of oxidative stress and ROS induced damage, and amelioration of oxidative status through melatonin induced activation of signaling pathways. Hepatocytes were isolated from adult Labeo rohita and exposed to H2O2 at three different doses (12.5, 25 and 50 µM) to observe peroxide induced damage in fish hepatocytes. Melatonin (25, 50 and 100 μg/ml) was administered against the highest dose of H2O2. Enzymatic and non-enzymatic antioxidants such as malondialdehyde (MDA), superoxide dismutase (SOD), catalase (CAT) and glutathione (GSH) was measured spectrophotometrically. Expression level of heat shock proteins (HSP70 and HSP90), HSPs-associated signaling molecules (Akt, ERK, cytosolic and nuclear NFkB), and melatonin receptor was also measured by western blotting analysis.ResultsH2O2 induced oxidative stress significantly altered (P < 0.05) MDA and GSH level, SOD and CAT activity, and up regulated HSP70 and HSP90 expression in carp hepatocytes. Signaling proteins exhibited differential modulation as revealed from their expression patterns in H2O2-exposed fish hepatocytes, in comparison with control hepatocytes. Melatonin treatment of H2O2-stressed fish hepatocytes restored basal cellular oxidative status in a dose dependent manner. Melatonin was observed to be inducer of signaling process by modulation of signaling molecules and melatonin receptor.ConclusionsThe results suggest that exogenous melatonin at the concentration of 100 µg/ml is required to improve oxidative status of the H2O2-stressed fish hepatocytes. In H2O2 exposed hepatocytes, melatonin modulates expression of HSP70 and HSP90 that enable the hepatocytes to become stress tolerant and survive by altering the actions of ERK, Akt, cytosolic and nuclear NFkB in the signal transduction pathways. Study also confirms that melatonin could act through melatonin receptor coupled to ERK/Akt signaling pathways. This understanding of the mechanism by which melatonin regulates oxidative status in the stressed hepatocytes may initiate the development of novel strategies for hepatic disease therapy in future.

Variable selection for high dimensional data has recently received a great deal of attention. However, due to the complex structure of the likelihood, only limited developments have been made for time-to-event data where censoring is present. In this paper, we propose a Bayesian variable selection scheme for a Bayesian semiparametric survival model for right censored survival data sets. A special shrinkage prior on the coefficients corresponding to the predictor variables is used to handle cases when the explanatory variables are of very high-dimension. The shrinkage prior is obtained through a scale mixture representation of Normal and Gamma distributions. Our proposed variable selection prior corresponds to the well known lasso penalty. The likelihood function is based on the Cox proportional hazards model framework, where the cumulative baseline hazard function is modeled a priori by a gamma process. We assign a prior on the tuning parameter of the shrinkage prior and adaptively control the sparsity of our model. The primary use of the proposed model is to identify the important covariates relating to the survival curves. To implement our methodology, we have developed a fast Markov chain Monte Carlo algorithm with an adaptive jumping rule. We have successfully applied our method on simulated data sets under two different settings and real microarray data sets which contain right censored survival time. The performance of our Bayesian variable selection model compared with other competing methods is also provided to demonstrate the superiority of our method. A short description of the biological relevance of the selected genes in the real data sets is provided, further strengthening our claims.

Hepatocellular carcinoma (HCC) is one of the most aggressive cancers and is the third leading cause of all cancer-related death. Limited noninvasive biomarkers are available for HCC detection. Early detection is the key in improving the survival of HCC patients. In this study, we tested the hypothesis that serum miRNAs can be used as a potential biomarker for HCC. Quantitative RT-PCR for miRNA analysis was performed using 70 serum samples. Receiver operating characteristic analysis was performed to measure the prognostic power of the miRNAs. The miRNA expression level was also measured from liver biopsy samples. Our study revealed that two miRNAs, miR-30e and miR-223, were expressed at significantly lower levels (P < 0.003) in the sera of HCC patients compared with healthy volunteers. Furthermore, expression of these miRNAs was compared between sera from chronic liver disease and sera from HCC patients. miR-30e and miR-223 expression was significantly lower in HCC sera compared with sera from chronic liver disease patients. Both miRNA expression levels were lower in HCC liver biopsy specimens compared with normal liver RNA. Taken together, our results suggested that serum miR-30e and miR-223 are useful biomarkers of HCC, irrespective of etiology, and deserve further study for their diagnostic value.

Regularization plays a critical role in modern statistical research, especially in high-dimensional variable selection problems. Existing Bayesian methods usually assume independence between variables a priori. In this article, we propose a novel Bayesian approach, which explicitly models the dependence structure through a graph Laplacian matrix. We also generalize the graph Laplacian to allow both positively and negatively correlated variables. A prior distribution for the graph Laplacian is then proposed, which allows conjugacy and thereby greatly simplifies the computation. We show that the proposed Bayesian model leads to proper posterior distribution. Connection is made between our method and some existing regularization methods, such as Elastic Net, Lasso, Octagonal Shrinkage and Clustering Algorithm for Regression (OSCAR) and Ridge regression. An efficient Markov Chain Monte Carlo method based on parameter augmentation is developed for posterior computation. Finally, we demonstrate the method through several simulation studies and an application on a real data set involving key performance indicators of electronics companies.