[Using principal component analysis to increase accuracy of prediction of metabolic syndrome in artificial neural network and logistic regression models]

Background and aims: In modeling process, correlation between covariates causes multicolinearity that may reduce efficiency of the model. This study was aimed to use principal component analysis to eliminate the effect of multicolinearity in logistic regression and neural network models, and to determine its effect on the accuracy of predicting metabolic syndrome in a sample of individuals participating in the Tehran Lipid and Glucose Study

Methods: A total of 347 participants from the Cohort section of the Tehran Lipid and Glucose Study [TLGS] were evaluated. The subjects were free of metabolic syndrome, according to the ATPIII criteria, at the beginning. Logistic regression, logistic regression with principal components, neural network and neural network with principal components models were fitted to the data. The ability of the models in predicting metabolic syndrome was compared using ROC analysis and kappa statistics

Results: The area under receiver operating characteristic [ROC] curve for logistic regression, logistic regression with principal components, neural network and neural network with principal component were estimated as 0.749, 0.790, 0.890 and 0.927 respectively. Sensitivity of the models was calculated as 0.483, 0.435, 0.836 and 0.919 and their specificity as 0.857, 0.919, 0.892 and 0.964 respectively. The kappa statistic for these models was 0.322, 0.386, 0.712 and 0.886 respectively

Conclusion: the study shows that the prediction accuracy of models based on principal components is better than that of models based on primary covariates, so in the presence of multicolinearity, models based on principal components are efficient for predicting metabolic syndrome

[Removal of Cr [VI] from simulated electroplating wastewater by magnetite nanoparticles]

Background and aims: Chromium is considered as one of the important environmental pollutants. There is high concentration of chromium in the wastewater of electroplating industries. Magnetic iron nanoparticles are used to control and eliminate heavy metals from industrial effluents through the mechanisms of adsorption, ion exchange and electro-static forces. The aim of this study was to evaluate the efficiency of magnetic nanoparticles for removal of hexavalent chromium [VI] from simulated electroplating wastewater and the parameters that influence the removal

Methods: The magnetite nanoparticles were prepared by sol-gel method through the addition of bivalent and trivalent iron chloride in the water environment under alkaline conditions. Then the factors influencing this process, including nanoparticle concentration, initial concentration of chromium, pH, mixing rate and retention time were studied .The taguchi method was used to determine sample size and data analysis. Sampling was performed based on sampling protocol

Results: Removal efficiency was increased with significant increasing the mixing speed [P<0.001]. There was a significant reduction in the removal efficiency by increasing the pH and chromium concentration [P<0.001]. The findings of this study showed that in pH 2, 10 mg/L initial chromium concentrationy a dose of 1 g/L synthesized magnetite nanoparticles, 5 minutes retention time and 250 rpm mixing rate, about 82 % of chromium [VI] was removed. In addition, characteristics of nanoparticles including: particles structure, composition, size and zeta potential were determined using analytical devices such as: XRD, XRF, Zeta potential and particle seizer

Conclusion: Magnetite nanoparticles have high competency for removal of chromium [VI] from simulated electroplating wastewater, and removal efficiency is reversely related to pH

[Artificial neural network design for modeling of mixed bivariate outcomes in medical research data]

Mixed outcomes arise when, in a multivariate model, response variables measured on different scales such as binary and continuous. Artificial neural networks [ANN] can be used for modeling in situations where classic models have restricted application when some of their assumptions are not met. In this paper, we propose a method based on ANNs for modeling mixed binary and continuous outcomes. Univariate and bivariate models were evaluated based on two different sets of simulated data. The scaled conjugate gradient [SCG] algorithm was used for optimization. To end the algorithm and finding optimum number of iteration and learning coefficient, mean squared error [MSE] was computed. Predictive accuracy rate criterion was employed for selection of appropriate model. We also used our model in medical data for joint prediction of metabolic syndrome [binary] and HOMA-IR [continues] in Tehran Lipid and Glucose Study [TLGS]. The codes were written in R 2.9.0 and MATLAB 7.6. The predictive accuracy for univariate and bivariate models based on simulated dataset I, where two outcomes associated with a common covariate, were shown to be approximately similar. However, in simulated dataset ?? in which two outcomes associated with different covariates, predictive accuracy in bivariate models were seen to be larger than that of univariate models. It is indicated that the predictive accuracy gain is higher in bivariate model, when the outcomes share a different set of covariates with higher level of correlation between the outcomes

[Comparison of artificial neural network, logistic regression and discriminant analysis methods in prediction of metabolic syndrome]

Artificial neural networks as a modern modeling method have received considerable attention in recent years. The models are used in prediction and classification in situations where classic statistical models have restricted application when some, or all of their assumptions are met. This study is aimed to compare the ability of neural network models to discriminant analysis and logistic regression models in predicting the metabolic syndrome. A total of 347 participants from the cohort of the Tehran Lipid and Glucose Study [TLGS] were studied. The subjects were free of metabolic syndrome at baseling according to the ATPIII criteria. Demographic characteristics, history of coronary artery disease, body mass index, waist, LDL, HDL, total cholesterol, triglycerides, fasting and 2 hours blood sugar, smoking, systolic and diastolic blood pressure were measured at baseline. Incidence of metabolic syndrome after about 3 years of follow up was considered a dependent variable. Logistic regression, discriminant analysis and neural network models were fitted to the data. The ability of the models in predicting metabolic syndrome was compared using ROC analysis and the Kappa statistic, for which, MATLAB software was used. The areas under receiver operating characteristic [ROC] curve for logistic regression, discriminant analysis and artificial neural network models [15: 8:1] and [15:10:10] were estimated as 0.749, 0.739, 0.748 and 0.890 respectively. Sensitivity of models were calculated as 0.483, 0.677, 0.453 and 0.863 and their specificity as 0.857, 0.660, 0.910 and 0.844 respectively. The Kappa statistics for these models were 0.322, 0.363, 0.372 and 0.712 respectively. Results of this study indicate that artificial neural network models perform better than classic statistical models in predicting the metabolic syndrome

Evaluation of chemical quality in 17 brands of Iranian bottled drinking waters

The purpose of study was to evaluate and compare chemical quality of Iranian bottled drinking water reported on manufacturer's labeling and standards. This study was a cross-sectional descriptive study and done during July to December 2008. The bottled mineral water collected from shops randomly were analyzed using all parameters address on manufacturer's labeling and the results were compared with the manufacturers' labeling data, WHO Guideline Values, USEPA Maximum Contaminant Levels and the maximum contaminant levels of drinking water imposed by the Iranian legislation. Statistical analysis on data was done with the Kolmogorov-Smirnov test for normal distribution, the paired t-test to compare the data with manufacturer's labeling and the one-sample t-test to compare with standard and MCL values at P<0.05 of confidence level. The results showed a statistically significant difference with manufacturer's labeling values, however there was no significant difference between the values of magnesium and pH and manufacturers' labeling values [P>0.05]. In addition, ph and calcium values were significantly higher that their proposed values indicated by Iranian National Legislation and international MCLs [P<0.05]. Our results are extremely important for the health supervisory agencies such as Ministry of Health and Institute of Standards and Industrial Research of Iran to have more effective controls on bottled water industries, and to improve periodical the proposed standard values

Supravesical diversion and later undiversion in severe war injuries of the bladder

From 20 patients with bladder injury due to war trauma, three patients were in critical condition because of extensive bladder injury associated with rectosigmoid injury and septicemia. In these three patients, early supravesical diversion was undertaken using ileal conduit. After stabilization of the patients' condition, undiversion was performed successfully, bringing the patients back to their normal voiding condition