Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Bayesian modelling”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,747 records · Page 97Linked to original sources
PubMed2006

Short communication: Optimal random regression models for milk production in dairy cattle.

Legendre polynomials of orders 3 to 8 in random regression models (RRM) for first-lactation milk production in Canadian Holsteins were compared statistically to determine the best model. Twenty-six RRM were compared using LP of order 5 for the phenotypic age-season groupings. Variance components of RRM were estimated using Bayesian estimation via Gibbs sampling. Several statistical criteria for model comparison were used including the total residual variance, the log likelihood function, Akaike's information criterion, the Bayesian information criterion, Bayes factors, an information-theoretic measure of model complexity, and the percentage relative reduction in complexity. The residual variance always picks the model with the most parameters. The log likelihood and information-theoretic measure picked the model with order 5 for additive genetic effects and order 7 for permanent environmental effects. The currently used model in Canada (order 5 for both additive and permanent environmental effects) was not the best for any single criterion, but was optimal when considering all criteria.

Animals↗
PubMed2003

Estimating polygenic effects using markers of the entire genome.

Molecular markers have been used to map quantitative trait loci. However, they are rarely used to evaluate effects of chromosome segments of the entire genome. The original interval-mapping approach and various modified versions of it may have limited use in evaluating the genetic effects of the entire genome because they require evaluation of multiple models and model selection. Here we present a Bayesian regression method to simultaneously estimate genetic effects associated with markers of the entire genome. With the Bayesian method, we were able to handle situations in which the number of effects is even larger than the number of observations. The key to the success is that we allow each marker effect to have its own variance parameter, which in turn has its own prior distribution so that the variance can be estimated from the data. Under this hierarchical model, we were able to handle a large number of markers and most of the markers may have negligible effects. As a result, it is possible to evaluate the distribution of the marker effects. Using data from the North American Barley Genome Mapping Project in double-haploid barley, we found that the distribution of gene effects follows closely an L-shaped Gamma distribution, which is in contrast to the bell-shaped Gamma distribution when the gene effects were estimated from interval mapping. In addition, we show that the Bayesian method serves as an alternative or even better QTL mapping method because it produces clearer signals for QTL. Similar results were found from simulated data sets of F(2) and backcross (BC) families.

Bayes Theorem↗
PubMed1995

Phase I and clinical evaluation of a pharmacologically guided regimen of suramin in patients with hormone-refractory prostate cancer.

PURPOSE: This phase I study was designed with the following objectives: (1) to describe the overall and dose-limiting toxicity (DLT) of suramin administered by intermittent short intravenous infusions until DLT or disease progression; (2) to determine the ability of an adaptive control with feedback (ACF) dosing strategy to maintain suramin plasma concentrations within a preselected range; (3) to develop a population model of suramin pharmacokinetics; and (4) to identify preliminary evidence of antitumor activity. PATIENTS AND METHODS: Seventy-three patients with advanced, incurable, solid tumors (including 69 with hormone-refractory prostate cancer) received an initial 5- to 7-day daily loading treatment followed by intermittent infusions individually determined by ACF using a Bayesian algorithm and relying on population models of suramin pharmacokinetics. Treatment was given to three cohorts of patients based on target plasma suramin concentration ranges (peak, 30 minutes postsuramin, and trough on morning of the treatment day), as follows: cohort 1, 175 to 300 micrograms/mL (27 patients); cohort 2, 150 to 250 micrograms/mL (23 patients); and cohort 3, 100 to 200 micrograms/mL (23 patients). All patients were to receive suramin until DLT or disease progression. RESULTS: The DLT was most commonly seen in cohort 1 and included a syndrome of malaise and fatigue, associated with weight loss, anorexia, and changes in taste. Other reversible toxicities were neurologic, renal, cutaneous, edema, lymphopenia and anemia, ophthalmologic, and alopecia. Forty of 67 assessable patients (60%) had a 50% reduction and 25 of 67 (37%) a 75% reduction in prostate-specific antigen (PSA) levels that lasted more than 4 weeks, seven of 18 (40%) had measurable responses, and 18 of 37 (49%) demonstrated major pain improvement. The overall times to disease progression and survival were 170 and 492 days, respectively. CONCLUSION: We have characterized all toxicities with suramin in a pharmacologically guided phase I study designed to maintain plasma suramin concentrations of 100 to 300 micrograms/mL (cohorts 1 to 3). The incidence of grade 3 to 4 neurologic abnormalities was relatively low, particularly in cohorts 2 and 3 (100 to 250 micrograms/mL). Evidence of significant and durable antitumor activity was seen in all three cohorts.

Adaptation, Physiological↗
PubMed2006

Bayesian variable selection for the analysis of microarray data with censored outcomes.

MOTIVATION: A common task in microarray data analysis consists of identifying genes associated with a phenotype. When the outcomes of interest are censored time-to-event data, standard approaches assess the effect of genes by fitting univariate survival models. In this paper, we propose a Bayesian variable selection approach, which allows the identification of relevant markers by jointly assessing sets of genes. We consider accelerated failure time (AFT) models with log-normal and log-t distributional assumptions. A data augmentation approach is used to impute the failure times of censored observations and mixture priors are used for the regression coefficients to identify promising subsets of variables. The proposed method provides a unified procedure for the selection of relevant genes and the prediction of survivor functions. RESULTS: We demonstrate the performance of the method on simulated examples and on several microarray datasets. For the simulation study, we consider scenarios with large number of noisy variables and different degrees of correlation between the relevant and non-relevant (noisy) variables. We are able to identify the correct covariates and obtain good prediction of the survivor functions. For the microarray applications, some of our selected genes are known to be related to the diseases under study and a few are in agreement with findings from other researchers. AVAILABILITY: The Matlab code for implementing the Bayesian variable selection method may be obtained from the corresponding author. CONTACT: mvannucci@stat.tamu.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Algorithms↗
PubMed2007

Population pharmacokinetic model for gatifloxacin in pediatric patients.

The broad spectrum of antimicrobial activity, oral bioavailability, extensive tissue distribution, and once-daily intravenous or oral dosing of gatifloxacin, an expanded-spectrum 8-methoxy fluoroquinolone, make it a potentially useful agent for the treatment of pediatric infections. A population pharmacokinetic model was developed to describe the pharmacokinetics of gatifloxacin in children. Data for analysis were obtained from a single-dose safety/pharmacokinetic study utilizing intensive blood sampling in patients aged 6 months to 16 years. Each subject received a single oral dose of gatifloxacin as a suspension, at doses of 5, 10, or 15 mg/kg of body weight. A total of 845 samples were obtained from 82 patients. A one-compartment model with first-order absorption and elimination was the most appropriate to describe the gatifloxacin concentrations. Covariate analysis using forward selection and backward elimination found that apparent clearance was related to body surface area, and apparent volume of distribution was related to body weight. No effect of age on drug clearance could be identified once clearance was corrected for body surface area. Based on pharmacokinetic simulations, the 10-mg/kg (maximum, 400 mg) once-daily dose of gatifloxacin is expected to provide drug exposure similar to that in healthy adults. The population pharmacokinetic model described herein will be used for Bayesian analyses of sparse pharmacokinetic sampling in phase II/III clinical trials and for Monte Carlo simulation experiments. The success of this strategy provides a model for future pediatric drug development programs.

Administration, Oral↗
PubMed2005

Pharmacokinetic study of tacrolimus in cystic fibrosis and non-cystic fibrosis lung transplant patients and design of Bayesian estimators using limited sampling strategies.

OBJECTIVES: To: (i) test different pharmacokinetic models to fit full tacrolimus concentration-time profiles; (ii) estimate the tacrolimus pharmacokinetic characteristics in stable lung transplant patients with or without cystic fibrosis (CF); (iii) compare the pharmacokinetic parameters between these two patient groups; and (iv) design maximum a posteriori Bayesian estimators (MAP-BE) for pharmacokinetic forecasting in these patients using a limited sampling strategy. METHODS: Tacrolimus blood concentration-time profiles obtained on three occasions within a 5-day period in 22 adult lung transplant recipients (11 with CF and 11 without CF) were retrospectively studied. Three different one-compartment models with first-order elimination were tested to fit the data: one with first-order absorption, one convoluted with a gamma distribution to describe the absorption phase, and one convoluted with a double gamma distribution able to describe secondary concentration peaks. Finally, Bayesian estimation using the best model and a limited sampling strategy was tested in the two groups of patients for its ability to provide accurate estimates of the main tacrolimus pharmacokinetic parameters and exposure indices. RESULTS: The one-compartment model with first-order elimination convoluted with a double gamma distribution gave the best results in both CF and non-CF lung transplant recipients. The patients with CF required higher doses of tacrolimus than those without CF to achieve similar drug exposure, and population modelling had to be performed in CF and non-CF patients separately. Accurate Bayesian estimates of area under the blood concentration-time curve from 0 to 12 hours (AUC12), AUC from 0 to 4 hours, peak blood concentration (Cmax) and time to reach Cmax were obtained using three blood samples collected at 0, 1 and 3 hours in non-CF patients (correlation coefficient between observed and estimated AUC12, R2 = 0.96), and at 0, 1.5 and 4 hours in CF patients (R2 = 0.91). CONCLUSION: A particular pharmacokinetic model was designed to fit the complex and highly variable tacrolimus blood concentration-time profiles. Moreover, MAP-BE allowing tacrolimus therapeutic drug monitoring based on AUC12 were developed.

Adult↗
PubMed2005

Efficient kernel density estimation of shape and intensity priors for level set segmentation.

We propose a nonlinear statistical shape model for level set segmentation which can be efficiently implemented. Given a set of training shapes, we perform a kernel density estimation in the low dimensional subspace spanned by the training shapes. In this way, we are able to combine an accurate model of the statistical shape distribution with efficient optimization in a finite-dimensional subspace. In a Bayesian inference framework, we integrate the nonlinear shape model with a nonparametric intensity model and a set of pose parameters which are estimated in a more direct data-driven manner than in previously proposed level set methods. Quantitative results show superior performance (regarding runtime and segmentation accuracy) of the proposed nonparametric shape prior over existing approaches.

Algorithms↗
PubMed2003

Population pharmacokinetic analysis of nonlinear behavior of piperacillin during intermittent or continuous infusion in patients with cystic fibrosis.

The purpose of this study was to describe the nonlinear pharmacokinetics of piperacillin observed during intermittent infusion and continuous infusion by using a nonparametric population modeling approach. Data were 120 serum piperacillin concentration measurements from eight adult cystic fibrosis (CF) patients. Individual pharmacokinetic parameter estimates during intermittent infusion or continuous infusion were calculated by noncompartmental analysis and with a maximum iterative two-stage Bayesian estimator. To simultaneously describe concentration-time data during intermittent infusion and continuous infusion, nonlinear models were parameterized as two-compartment Michaelis-Menten models. Models were fit to the data with the nonparametric expectation maximization algorithm. The calculations were executed on a remote supercomputer. Nonlinear models were evaluated by log-likelihood estimates, residual plots, and R(2) values, and predictive performance was based on bias (mean weighted error [MWE]) and precision (mean weighted square error [MWSE]). A linear pharmacokinetic model could not describe combined intermittent infusion and continuous infusion data well. A good population model fit to the intermittent infusion and continuous infusion data was obtained with the constructed nonlinear models. Maximum a posteriori probability (MAP) Bayesian R(2) values for the nonlinear models were 0.96 to 0.97. Median parameter estimates for the best nonlinear model were as follows: K(m), 58 +/- 75 mg/liter (mean and standard deviation); V(max), 1,904 +/- 1,009 mg/h; volume of distribution of the central compartment, 14.1 +/- 3.0 liters; k(12), 0.63 +/- 0.41 h(-1); and k(21), 0.37 +/- 0.19 h(-1). The median bias (MWE) and precision (MWSE) values for MAP Bayesian estimation with the Michaelis-Menten model were 0.05 and 4.6 mg/liters, respectively. The developed nonlinear pharmacokinetic models can be used to optimize piperacillin therapy administered via continuous infusion in patients with CF and have distinct advantages over conventional linear models.

Adult↗
PubMed2003

Pharmacokinetics and pharmacodynamics of mesna-mediated plasma cysteine depletion.

Cellular glutathione (GSH) levels are related to the resistance of tumor cells to platinum and alkylating agents, and depletion of GSH may enhance the activity of these drugs. The pharmacodynamic effects of mesna on depleting plasma cysteine, a GSH precursor, were evaluated in 22 patients as part of a Phase I study. Escalating doses of ifosfamide and mesna were administered; carboplatin was administered to achieve an AUC of 4 mg x min/mL. Plasma samples were collected and assayed by reverse-phase high-performance liquid chromatography (HPLC) for total mesna and total cysteine concentrations at 0, 1, 3, 6, 24, 25, 28, and 48 hours. A one-compartment pharmacokinetic model was fit to the mesna plasma concentrations, using M.A.P. Bayesian estimation (ADAPT II). Pharmacodynamics were evaluated by fitting an inhibitory Emax model to the cysteine concentration data. Both the pharmacokinetic (median R2 = 0.95; range = 0.85-0.98) and pharmacodynamic (median R2 = 0.96; range = 0.74-1.0) models fit the data well. Mean (coefficient of variation [CV%]) mesna pharmacokinetic parameter estimates were as follows: Vss of 15.3 (29) L/m2, CL of 4.6 (29) L/h/m2, and half-life of 2.2 (37) hours. Mean (CV%) pharmacodynamic parameter estimates were as follows: Emax of 31.7 (19) microg/mL and EC50 of 10.3 (52) microg/mL. Mesna produced a rapid, concentration-dependent reduction in plasma cysteine concentrations that could be adequately characterized by an inhibitory Emax pharmacodynamic model. The depletion of plasma cysteine was facilitated by ifosfamide, suggesting a pharmacodynamic interaction between these two agents. Further increases in mesna doses beyond those administered in this study would be unlikely to provide additional benefit.

Antineoplastic Agents, Alkylating↗
PubMedDate not supplied

The representation of uncertainty in medical expert systems.

The development of the rule-based expert system has provided important new techniques for the representation of knowledge. However, continued use of this representational scheme has highlighted some of its deficiencies. In particular, many within scientific and non-scientific fields attempting to use the rule-base design to describe natural phenomena often find it difficult to represent the complexities of the world as 'absolute' rules. For this reason, many investigators acknowledge the need to add an uncertainty mechanism to the rule-base construct. Such a facility would allow the quantification of accuracy or strength of association within individual rules Although agreement exists on the need for an uncertainty representation facility, the debate concerning the most appropriate methodology is far from resolved. The purpose of this paper is to provide a review and commentary on the current state of debate over the five most popular candidate uncertainty models: symbolic representation, MYCIN certainty factors, Bayesian, Dempster-Shafer and fuzzy set logic. The advantages and disadvantages of each uncertainty calculi will be presented and assessed with respect to their applicability to the medical expert systems domain.

Bayes Theorem↗
PubMed1998

Population pharmacokinetics of gentamicin in horses.

OBJECTIVE: To develop and validate a population pharmacokinetic model for gentamicin in horses, using retrospective clinical data. ANIMALS: 62 horses that had been treated IV with multiple doses of gentamicin at our veterinary teaching hospital between 1987 and 1996. Procedure-46 horses were assigned to the study group, and 16 to the validation group. Detailed history of dosage, sample collection times, and selected pathophysiologic variables were recorded for each patient. Samples were analyzed by use of a fluorescence polarization immunoassay method. Pharmacostatistical analysis was conducted, using computer software. The predictive model correlates pharmacokinetic parameters to concomitant pathophysiologic variables and estimates the inter- and intraindividual variability in disposition. RESULTS: A two-compartment model best described the data. Clearance (CI) was linearly correlated to body weight and serum creatinine concentration. Volume of the central compartment (Vd(c)) was linearly related to body weight. Interindividual coefficients of variability for CI and Vd(c) were 24 and 16%, respectively. The residual variability (intraindividual) was 13%; mean prediction error percent (bias) was 2%; and mean absolute prediction error percent (precision) was 29%. CONCLUSIONS: Population pharmacokinetic analysis allows study of the basic features of gentamicin disposition in horses with sparse data per individual. A considerable proportion of the pharmacokinetic variability of gentamicin in our study population was explained by differences in body weight and serum creatinine concentration. CLINICAL RELEVANCE: Population pharmacokinetics can be used to design first-dosage regimens according to the clinical characteristics of individual animals. Population pharmacokinetic models could also be included in Bayesian forecasting strategies to improve plasma concentration predictions in individual patients.

Age Factors↗
PubMed2003

The minimal model: an evolving methodology.

After more than 20 years, minimal model analysis of intravenous glucose tolerance test glucose and insulin concentrations continues to be widely employed in studies of insulin sensitivity and insulin resistance. Moreover, problems encountered in solving the minimal model equations continue to find new solutions. Bayesian techniques enable prior knowledge to be incorporated into parameter estimation routines. They offer particular advantages in the measurement of insulin sensitivity with the minimal model, and provide an elegant means of improving model identification success rates and parameter precision. This comment describes the study by Agbaje and colleagues in this issue of Clinical Science that exemplifies a new phase in the evolution of minimal model practice.

Bayes Theorem↗
PubMed2006

Application of the secondary structure model of rRNA for phylogeny: D2-D3 expansion segments of the LSU gene of plant-parasitic nematodes from the family Hoplolaimidae Filipjev, 1934.

Knowledge of rRNA structure is increasingly important to assist phylogenetic analysis through reconstructing optimal alignment, utilizing molecule features as an additional source of data and refining appropriate models of evolution of the molecule. We describe a procedure of optimization for alignment and a new coding method for nucleotide sequence data using secondary structure models of the D2 and D3 expansion fragments of the LSU-rRNA gene reconstructed for fifteen nematode species of the agriculturally important and diverse family Hoplolaimidae, order Tylenchida. Using secondary structure information we converted the original sequence data into twenty-eight symbol codes and submitted the transformed data to maximum parsimony analysis. We also applied the original sequence data set for Bayesian inference. This used the doublet model with sixteen states of nucleotide doublets for the stem region and the standard model of DNA substitution with four nucleotide states for loops and bulges. By this approach, we demonstrate that using structural information for phylogenetic analyses led to trees with lower resolved relationships between clades and likely eliminated some artefactual support for misinterpreted relationships, such as paraphyly of Helicotylenchus or Rotylenchus. This study as well as future phylogenetic analyses is herein supported by the development of an on-line database, NEMrRNA, for rRNA molecules in a structural format for nematodes. We also have developed a new computer program, RNAstat, for calculation of nucleotide statistics designed and proposed for phylogenetic studies.

Animals↗
PubMed2005

A multi-group model of Schistosoma japonicum transmission dynamics and control: model calibration and control prediction.

Previously we formulated a quantitative model to characterize site-specific schistosomiasis transmission. In this paper, we present a procedure to calibrate the model to data collected in endemic villages of south-western Sichuan, China, with the objective of reducing parametric uncertainty to allow the model to describe local transmission with relative confidence. A Bayesian approach using local epidemiological data and expert opinion is employed to calibrate the model. Results indicate that, after calibration, the output uncertainty is reduced substantially. The calibrated model is then used for prediction of the effects of different intervention options. Simulations reflect a bimodal transmission in both human (early summer and early fall) and snail (late summer and late fall) infections in this area, for which there is some field evidence. Also shown in the simulations are relatively high reinfection rates following chemotherapy in these endemic villages. These results suggest that a sustainable control strategy is essential in reducing transmission, and that transmission can be reduced by chemotherapy, focal snail (e.g. snail clusters) control, and egg control. Our work demonstrates the feasibility of characterizing site-specific schistosomiasis transmission using a mathematical model and a calibration approach that integrates diverse field data, and the use of the calibrated model to design control strategies.

Animals↗
PubMed2000

Using Bayesian networks to analyze expression data.

DNA hybridization arrays simultaneously measure the expression level for thousands of genes. These measurements provide a "snapshot" of transcription levels within the cell. A major challenge in computational biology is to uncover, from such measurements, gene/protein interactions and key biological features of cellular systems. In this paper, we propose a new framework for discovering interactions between genes based on multiple expression measurements. This framework builds on the use of Bayesian networks for representing statistical dependencies. A Bayesian network is a graph-based model of joint multivariate probability distributions that captures properties of conditional independence between variables. Such models are attractive for their ability to describe complex stochastic processes and because they provide a clear methodology for learning from (noisy) observations. We start by showing how Bayesian networks can describe interactions between genes. We then describe a method for recovering gene interactions from microarray data using tools for learning Bayesian networks. Finally, we demonstrate this method on the S. cerevisiae cell-cycle measurements of Spellman et al. (1998).

Algorithms↗
PubMed2005

Mixed model estimation methods for the Rasch model.

Mixed models take the dependency between observations based on the same person into account by introducing one or more random effects. After introducing the mixed model framework, it is explained, by taking the Rasch model as a generic example, how item response models can be conceptualized as generalized linear and nonlinear mixed models. Common estimation methods for generalized linear and nonlinear models are discussed. In a simulation study, the performance of four estimation methods is assessed for the Rasch model under different conditions regarding the number of items and persons, and the degree of interindividual differences. The estimation methods included in the study are: an approximation of the integral over the random effect by means of Gaussian quadrature; direct maximization with a sixth-order Laplace approximation to the integrand; a linearized approximation of the nonlinear model employing PQL2; and finally a Bayesian MCMC method. It is concluded that the estimation methods perform almost equally well, except for a slightly worse recovery of the variance parameter for PQL2 and MCMC.

Data Interpretation, Statistical↗
PubMed2002

NasoNet, modeling the spread of nasopharyngeal cancer with networks of probabilistic events in discrete time.

The spread of cancer is a non-deterministic dynamic process. As a consequence, the design of an assistant system for the diagnosis and prognosis of the extent of a cancer should be based on a representation method that deals with both uncertainty and time. The ultimate goal is to know the stage of development of a cancer in a patient before selecting the appropriate treatment. A network of probabilistic events in discrete time (NPEDT) is a type of Bayesian network for temporal reasoning that models the causal mechanisms associated with the time evolution of a process. This paper describes NasoNet, a system that applies NPEDTs to the diagnosis and prognosis of nasopharyngeal cancer. We have made use of temporal noisy gates to model the dynamic causal interactions that take place in the domain. The methodology we describe is general enough to be applied to any other type of cancer.

Artificial Intelligence↗
PubMed2005

Phylogenetic relationships of South American lizards of the genus Stenocercus (Squamata: Iguania): A new approach using a general mixture model for gene sequence data.

The South American iguanian lizard genus Stenocercus includes 54 species occurring mostly in the Andes and adjacent lowland areas from northern Venezuela and Colombia to central Argentina at elevations of 0-4000m. Small taxon or character sampling has characterized all phylogenetic analyses of Stenocercus, which has long been recognized as sister taxon to the Tropidurus Group. In this study, we use mtDNA sequence data to perform phylogenetic analyses that include 32 species of Stenocercus and 12 outgroup taxa. Monophyly of this genus is strongly supported by maximum parsimony and Bayesian analyses. Evolutionary relationships within Stenocercus are further analyzed with a Bayesian implementation of a general mixture model, which accommodates variability in the pattern of evolution across sites. These analyses indicate a basal split of Stenocercus into two clades, one of which receives very strong statistical support. In addition, we test previous hypotheses using non-parametric and parametric statistical methods, and provide a phylogenetic classification for Stenocercus.

Animals↗