We have developed a method to longitudinally classify subjects into two or more prognostic groups using longitudinally observed values of markers related to the prognosis. We assume the availability of a training data set where the subjects' allocation into the prognostic group is known. The proposed method proceeds in two steps as described earlier in the literature. First, multivariate linear mixed models are fitted in each prognostic group from the training data set to model the dependence of markers on time and on possibly other covariates. Second, fitted mixed models are used to develop a discrimination rule for future subjects. Our method improves upon existing approaches by relaxing the normality assumption of random effects in the underlying mixed models. Namely, we assume a heteroscedastic multivariate normal mixture for random effects. Inference is performed in the Bayesian framework using the Markov chain Monte Carlo methodology. Software has been written for the proposed method and it is freely available. The methodology is applied to data from the Dutch Primary Biliary Cirrhosis Study.

• MeSH
• Liver Cirrhosis, Biliary drug therapy   MeSH
• Biomarkers analysis   MeSH
• Cholagogues and Choleretics therapeutic use   MeSH
• Discriminant Analysis * MeSH
• Data Interpretation, Statistical * MeSH
• Ursodeoxycholic Acid therapeutic use   MeSH
• Humans MeSH
• Linear Models * MeSH
• Longitudinal Studies MeSH
• Computer Simulation MeSH
• Disease Progression MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Names of Substances
• Biomarkers MeSH
• Cholagogues and Choleretics MeSH
• Ursodeoxycholic Acid MeSH

The objective of this study is the evaluation of the potential of high-throughput direct analysis in real time-high resolution mass spectrometry (DART-HRMS) fingerprinting and multivariate regression analysis in prediction of the extent of acrylamide formation in biscuit samples prepared by various recipes and baking conditions. Information-rich mass spectral fingerprints were obtained by analysis of biscuit extracts for preparation of which aqueous methanol was used. The principal component analysis (PCA) of the acquired data revealed an apparent clustering of samples according to the extent of heat-treatment applied during the baking of the biscuits. The regression model for prediction of acrylamide in biscuits was obtained by partial least square regression (PLSR) analysis of the data matrix representing combined positive and negative ionization mode fingerprints. The model provided a least root mean square error of cross validation (RMSECV) equal to an acrylamide concentration of 5.4 μg kg(-1) and standard error of prediction (SEP) of 14.8 μg kg(-1). The results obtained indicate that this strategy can be used to accurately predict the amounts of acrylamide formed during baking of biscuits. Such rapid estimation of acrylamide concentration can become a useful tool in evaluation of the effectivity of processes aiming at mitigation of this food processing contaminant. However, the robustness this approach with respect to variability in the chemical composition of ingredients used for preparation of biscuits should be tested further.

• Keywords
• Acrylamide, Biscuits, Direct analysis in real time, Mass spectrometry, Multivariate regression analysis,
• MeSH
• Acrylamide analysis   MeSH
• Principal Component Analysis MeSH
• Food Analysis methods   MeSH
• Bread analysis   MeSH
• Mass Spectrometry MeSH
• Linear Models MeSH
• Least-Squares Analysis MeSH
• Multivariate Analysis MeSH
• Tandem Mass Spectrometry MeSH
• Cooking * MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Names of Substances
• Acrylamide MeSH

Field crops represent one of the highest contributions to dietary metal exposure. The aim of this study was to develop specific regression models for the uptake of metals into various field crops and to compare the usability of other available models. We analysed samples of potato, hop, maize, barley, wheat, rape seed, and grass from 66 agricultural sites. The influence of measured soil concentrations and soil factors (pH, organic carbon, content of silt and clay) on the plant concentrations of Cd, Cr, Cu, Mo, Ni, Pb and Zn was evaluated. Bioconcentration factors (BCF) and plant-specific metal models (PSMM) developed from multivariate regressions were calculated. The explained variability of the models was from 19 to 64% and correlations between measured and predicted concentrations were between 0.43 and 0.90. The developed hop and rapeseed models are new in this field. Available models from literature showed inaccurate results, except for Cd; the modelling efficiency was mostly around zero. The use of interaction terms between parameters can significantly improve plant-specific models.

• Keywords
• Field crops, Heavy metals, Linear regression, Plant uptake, Prediction models,
• MeSH
• Brassica rapa chemistry   MeSH
• Food Contamination MeSH
• Zea mays chemistry   MeSH
• Soil Pollutants analysis   MeSH
• Environmental Monitoring methods   statistics & numerical data   MeSH
• Multivariate Analysis MeSH
• Triticum chemistry   MeSH
• Soil chemistry   MeSH
• Regression Analysis MeSH
• Models, Theoretical * MeSH
• Metals, Heavy analysis   MeSH
• Crops, Agricultural chemistry   MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Geographicals
• Czech Republic MeSH
• Names of Substances
• Soil Pollutants MeSH
• Soil MeSH
• Metals, Heavy MeSH

BACKGROUND: This study examines the associations of fatty acids (FAs) in plasma phosphatidylcholine (PC) with the anthropometrical and biochemical characteristic of patients with metabolic syndrome (MetS)-related traits. METHODS: We analyzed the FA profiles of PC in 300 persons with MetS-related traits (152 M/148F, mean age 46.9 ± 9.0 years) and in 70 healthy controls of the same age using a balanced men/women ratio and gas-liquid chromatography. Multivariate linear regression analysis was performed to determine the coefficients of determination (R2) using FA proportions of the mentioned proband characteristics. RESULTS: The FA composition of PC in patients with MetS traits was only associated with waist circumference (R2 = 0.27), waist-to-hip ratio (WHR; R2 = 0.41), body fat percentage (R2 = 0.62), and fat mass (R2 = 0.29). Positive associations were found for dihomo-γ-linolenic (DGLA), palmitic, stearic (SA), α-linolenic (ALA), and eicosapentaenoic acids, whereas negative associations were found for linoleic (LA), oleic, and docosapentaenoic acids. Palmitoleic acid (POA) was positively associated with waist circumference but negatively with fat percentage. In controls, significant associations were found for waist circumference (R2 = 0.51), WHR (R2 = 0.53), body fat percentage (R2 = 0.60), and fat mass (R2 = 0.34). DGLA and saturated FA (SFA) were positively associated, whereas docosahexaenoic, adrenic, and cis-vaccenic acids were negatively associated. The study group differed from controls as follows: lower concentrations of LA and total n-6 FA, higher indices of delta-9-desaturase and delta-6 desaturase activity and higher proportions of POA, SA, ALA, DGLA, and SFA. CONCLUSIONS: We found significant associations (R2 >0.25) of FA in plasma PC with adiposity in middle-aged persons with MetS-related traits, but not with metabolic indices.

• Keywords
• anthropometric variables, de novo lipogenesis, fatty acids, multivariate linear regression analysis, phosphatidylcholine,
• MeSH
• Adiposity * MeSH
• Anthropometry MeSH
• Chromatography, Liquid MeSH
• Adult MeSH
• Phosphatidylcholines blood   MeSH
• Insulin Resistance MeSH
• Middle Aged MeSH
• Humans MeSH
• Linear Models MeSH
• Lipids blood   MeSH
• Fatty Acids blood   MeSH
• Metabolic Syndrome blood   MeSH
• Multivariate Analysis MeSH
• Waist Circumference MeSH
• Pilot Projects MeSH
• Waist-Hip Ratio MeSH
• Cross-Sectional Studies MeSH
• Regression Analysis MeSH
• Stearoyl-CoA Desaturase metabolism   MeSH
• Case-Control Studies MeSH
• Check Tag
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Male MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Names of Substances
• Phosphatidylcholines MeSH
• Lipids MeSH
• Fatty Acids MeSH
• Stearoyl-CoA Desaturase MeSH

In comparison with analytical tools, bioassays provide higher sensitivity and more complex evaluation of environmental samples and are indispensable tools for monitoring increasing in anthropogenic pollution. Nevertheless, the disadvantage in cellular assays stems from the material variability used within the assays, and an interlaboratory adaptation does not usually lead to satisfactory test sensitivities. The aim of this study was to evaluate the influence of material variability on CXCL12 secretion by T47D cells, the outcome of the CXCL-test (estrogenic activity assay). For this purpose, the cell line sources, sera suppliers, experimental and seeding media, and the amount of cell/well were tested. The multivariable linear model (MLM), employed as an innovative approach in this field for parameter evaluation, identified that all the tested parameters had significant effects. Knowledge of the contributions of each parameter has permitted step-by-step optimization. The most beneficial approach was seeding 20,000 cells/well directly in treatment medium and using DMEM for the treatment. Great differences in both basal and maximal cytokine secretions among the three tested cell lines and different impacts of each serum were also observed. Altogether, both these biologically based and highly variable inputs were additionally assessed by MLM and a subsequent two-step evaluation, which revealed a lower variability and satisfactory reproducibility of the test. This analysis showed that not only parameter and procedure optimization but also the evaluation methodology must be considered from the perspective of interlaboratory method adaptation. This overall methodology could be applied to all bioanalytical methods for fast multiparameter and accurate analysis.

• Keywords
• T47D, cytokine CXCL12/SDF1, estrogenic activity cellular assay, material variability, multivariate linear model (MLM),
• MeSH
• Biological Assay MeSH
• Cell Line MeSH
• Water Pollutants, Chemical * MeSH
• Estrogens * toxicity   MeSH
• Estrone MeSH
• Linear Models MeSH
• Environmental Monitoring methods   MeSH
• Reproducibility of Results MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Names of Substances
• Water Pollutants, Chemical * MeSH
• Estrogens * MeSH
• Estrone MeSH

Functional connectivity (FC) analysis is a prominent approach to analyzing fMRI data, especially acquired under the resting state condition. The commonly used linear correlation FC measure bears an implicit assumption of Gaussianity of the dependence structure. If only the marginals, but not all the bivariate distributions are Gaussian, linear correlation consistently underestimates the strength of the dependence. To assess the suitability of linear correlation and the general potential of nonlinear FC measures, we present a framework for testing and estimating the deviation from Gaussianity by means of comparing mutual information in the data and its Gaussianized counterpart. We apply this method to 24 sessions of human resting state fMRI. For each session, matrix of connectivities between 90 anatomical parcel time series is computed using mutual information and compared to results from its multivariate Gaussian surrogate that conserves the correlations but cancels any nonlinearity. While the group-level tests confirmed non-Gaussianity in the FC, the quantitative assessment revealed that the portion of mutual information neglected by linear correlation is relatively minor-on average only about 5% of the mutual information already captured by the linear correlation. The marginality of the non-Gaussianity was confirmed in comparisons using clustering of the parcels-the disagreement between clustering obtained from mutual information and linear correlation was attributable to random error. We conclude that for this type of data, practical relevance of nonlinear methods trying to improve over linear correlation might be limited by the fact that the data are indeed almost Gaussian.

• MeSH
• Algorithms MeSH
• Adult MeSH
• Fourier Analysis MeSH
• Oxygen blood   MeSH
• Humans MeSH
• Linear Models MeSH
• Magnetic Resonance Imaging * MeSH
• Young Adult MeSH
• Neural Pathways physiology   MeSH
• Normal Distribution MeSH
• Rest physiology   MeSH
• Cluster Analysis MeSH
• Software MeSH
• Check Tag
• Adult MeSH
• Humans MeSH
• Young Adult MeSH
• Male MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Names of Substances
• Oxygen MeSH

Recently developed methods of longitudinal discriminant analysis allow for classification of subjects into prespecified prognostic groups using longitudinal history of both continuous and discrete biomarkers. The classification uses Bayesian estimates of the group membership probabilities for each prognostic group. These estimates are derived from a multivariate generalised linear mixed model of the biomarker's longitudinal evolution in each of the groups and can be updated each time new data is available for a patient, providing a dynamic (over time) allocation scheme. However, the precision of the estimated group probabilities differs for each patient and also over time. This precision can be assessed by looking at credible intervals for the group membership probabilities. In this paper, we propose a new allocation rule that incorporates credible intervals for use in context of a dynamic longitudinal discriminant analysis and show that this can decrease the number of false positives in a prognostic test, improving the positive predictive value. We also establish that by leaving some patients unclassified for a certain period, the classification accuracy of those patients who are classified can be improved, giving increased confidence to clinicians in their decision making. Finally, we show that determining a stopping rule dynamically can be more accurate than specifying a set time point at which to decide on a patient's status. We illustrate our methodology using data from patients with epilepsy and show how patients who fail to achieve adequate seizure control are more accurately identified using credible intervals compared to existing methods.

• Keywords
• allocation scheme, credible intervals, longitudinal discriminant analysis,
• MeSH
• Bayes Theorem * MeSH
• Discriminant Analysis MeSH
• Epilepsy diagnosis   therapy   MeSH
• Remission Induction MeSH
• Classification methods   MeSH
• Humans MeSH
• Linear Models MeSH
• Longitudinal Studies MeSH
• Multivariate Analysis MeSH
• Computer Simulation MeSH
• Probability * MeSH
• Prognosis MeSH
• Decision Making MeSH
• Sensitivity and Specificity MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH

The hyoid bone is characterized by sexually dimorphic features, enabling it to occasionally be used in the sex determination aspect of establishing the biological profile in skeletal remains. Based on a sample of 298 fused and non-fused hyoid bones, the present paper compares several methodological approaches to sexing human hyoid bones in order to test the legitimacy of osteometrics-based linear discriminant equations and to explore the potentials of symbolic regression and methods of geometric morphometrics. In addition, two sets of published predictive models, one of which originated in an indigenous population, were validated on the studied sample. The results showed that the hyoid shape itself is a moderate sex predictor and a combination of linear measurements is a better representation of sex-related differences. The symbolic regression was shown to exceed the predictive powers of linear discriminant function analysis when two models based on a logistic and step regression reached 96% of correctly classified cases. There was a positive correlation between discriminant scores and an individual's age as the sex assessment was highly skewed in favour of males. This suggests that the human hyoid undergoes age-related modifications which facilitates determination of male bones and complicates determination of females in older individuals. The validation of discriminant equations by Komenda and Černý (1990) and Kindschud et al. (2010) revealed that there are marked inter-population and inter-sample differences which lessened the power to correctly determine female hyoid bones.

• Keywords
• Geometric morphometrics, Hyoid bone, Linear discriminant function analysis, Sex determination, Symbolic regression,
• MeSH
• Analysis of Variance MeSH
• Discriminant Analysis MeSH
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Linear Models MeSH
• Young Adult MeSH
• Multivariate Analysis MeSH
• Observer Variation MeSH
• Hyoid Bone anatomy & histology   MeSH
• Reproducibility of Results MeSH
• Aged, 80 and over MeSH
• Aged MeSH
• Software MeSH
• Forensic Anthropology MeSH
• Sex Determination by Skeleton methods   MeSH
• Imaging, Three-Dimensional MeSH
• Check Tag
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Young Adult MeSH
• Male MeSH
• Aged, 80 and over MeSH
• Aged MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

To characterize the source contributions of chemicals of emerging concern (CECs) from different aquatic environments of Taiwan, we collected water samples from different aquatic systems, which were screened for 30 pharmaceuticals and illicit drugs. The total estimated mass loadings of CECs were 23.1 g/d in southern aquatic systems and 133 g/d in central aquatic systems. We developed an analytical framework combining pollutant fingerprinting, hierarchical cluster analysis (HCA), and principal component analysis with multiple linear regression (PCA-MLR) to infer the pharmaco-signature and source contributions of CECs. Based on this approach, we estimate source contributions of 62.2% for domestic inputs, 16.9% for antibiotics application, and 20.9% for drug abuse/medication in southern aquatic system, compared with 47.3% domestic, 35.1% antibiotic, and 17.6% drug abuse/medication inputs to central aquatic systems. The proposed pharmaco-signature method provides initial insights into the profile and source apportionment of CECs in complex aquatic systems, which are of importance for environmental management.

• Keywords
• Emerging contaminants, Fingerprinting, Mass loading, Risk quotient, Source apportionment,
• MeSH
• Principal Component Analysis MeSH
• Water Pollutants, Chemical analysis   chemistry   MeSH
• Linear Models MeSH
• Environmental Monitoring methods   MeSH
• Multivariate Analysis MeSH
• Wastewater chemistry   MeSH
• Rivers chemistry   MeSH
• Quality Control MeSH
• Cluster Analysis MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Geographicals
• Taiwan MeSH
• Names of Substances
• Water Pollutants, Chemical MeSH
• Waste Water MeSH

Although the modern instrumentation enables for the increased amount of data to be delivered in shorter time, computer-assisted spectra analysis is limited by the intelligence and by the programmed logic tool applications. Proposed tutorial covers all the main steps of the data processing which involve the chemical model building, from calculating the concentration profiles and, using spectra regression, fitting the protonation constants of the chemical model to multiwavelength and multivariate data measured. Suggested diagnostics are examined to see whether the chemical model hypothesis can be accepted, as an incorrect model with false stoichiometric indices may lead to slow convergence, cyclization or divergence of the regression process minimization. Diagnostics concern the physical meaning of unknown parameters beta(qr) and epsilon(qr), physical sense of associated species concentrations, parametric correlation coefficients, goodness-of-fit tests, error analyses and spectra deconvolution, and the correct number of light-absorbing species determination. All of the benefits of spectrophotometric data analysis are demonstrated on the protonation constants of the ionizable anticancer drug 7-ethyl-10-hydroxycamptothecine, using data double checked with the SQUAD(84) and SPECFIT/32 regression programs and with factor analysis of the INDICES program. The experimental determination of protonation constants with their computational prediction based on a knowledge of chemical structures of the drug was through the combined MARVIN and PALLAS programs. If the proposed model adequately represents the data, the residuals should form a random pattern with a normal distribution N(0, s2), with the residual mean equal to zero, and the standard deviation of residuals being near to experimental noise. Examination of residual plots may be assisted by a graphical analysis of residuals, and systematic departures from randomness indicate that the model and parameter estimates are not satisfactory.

• Publication type
• Journal Article MeSH