Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Bayesian computational modeling”

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 217 records · Page 12Linked to original sources
PubMed1998

Partial-volume Bayesian classification of material mixtures in MR volume data using voxel histograms.

We present a new algorithm for identifying the distribution of different material types in volumetric datasets such as those produced with magnetic resonance imaging (MRI) or computed tomography (CT). Because we allow for mixtures of materials and treat voxels as regions, our technique reduces errors that other classification techniques can create along boundaries between materials and is particularly useful for creating accurate geometric models and renderings from volume data. It also has the potential to make volume measurements more accurately and classifies noisy, low-resolution data well. There are two unusual aspects to our approach. First, we assume that, due to partial-volume effects, or blurring, voxels can contain more than one material, e.g., both muscle and fat; we compute the relative proportion of each material in the voxels. Second, we incorporate information from neighboring voxels into the classification process by reconstructing a continuous function, rho(x), from the samples and then looking at the distribution of values that rho(x) takes on within the region of a voxel. This distribution of values is represented by a histogram taken over the region of the voxel; the mixture of materials that those values measure is identified within the voxel using a probabilistic Bayesian approach that matches the histogram by finding the mixture of materials within each voxel most likely to have created the histogram. The size of regions that we classify is chosen to match the spacing of the samples because the spacing is intrinsically related to the minimum feature size that the reconstructed continuous function can represent.

Algorithms↗
PubMed2001

Bayesian 2-D deconvolution: a model for diffuse ultrasound scattering.

Observed medical ultrasound images are degraded representations of the true acoustic tissue reflectance. The degradation is due to blur and speckle and significantly reduces the diagnostic value of the images. To remove both blur and speckle, we have developed a new statistical model for diffuse scattering in 2-D ultrasound radio frequency images, incorporating both spatial smoothness constraints and a physical model for diffuse scattering. The modeling approach is Bayesian in nature, and we use Markov chain Monte Carlo methods to obtain the restorations. The results from restorations of some real and simulated radio frequency ultrasound images are presented and compared with results produced by Wiener filtering.

Algorithms↗
PubMed2000

Strategies for estimating the parameters needed for different test-day models.

Currently, most analyses of parameters in test-day models involve two types of models: random regression, where various functions describe variability of (co)variances with regard to days in milk, and multiple traits, where observations in adjacent days in milk are treated as one trait. The methodologies used for estimation of parameters included Bayesian via Gibbs sampling, and REML in the form of derivative-free, expectation-maximization, or average-information algorithms. The first method is simpler and uses less memory but may need many rounds to produce posterior samples. In REML, however, the stopping point is well established. Because of computing limitations, the largest estimations of parameters were on fewer than 20,000 animals. The magnitude and pattern of heritabilities varied widely, which could be caused by simplifications in the model, overparameterization, small sample size, and unrepresentative samples. Patterns of heritability differ among random regression and multiple-trait models. Accurate parameters for large multi-trait random regression models may be difficult to obtain at the present time. Parameters that are sufficiently accurate in practice may be obtained outside the complete prediction model by a constructive approach, where parameters averaged over the lactation would be combined with several typical curves for (co)variances for days in milk. Obtained parameters could be used for any model, and could also aid in comparison of models.

Analysis of Variance↗
PubMed1998

A Bayesian hierarchical survival model for the institutional effects in a multi-centre cancer clinical trial.

In randomized clinical trials comparing treatment effects on diseases such as cancer, a multi-centre trial is usually conducted to accrue the required number of patients in a reasonable period of time. While we interpret the average treatment effect, it is necessary to examine the homogeneity of the observed treatment effects across institutions, that is, treatment-by-institution interaction. If the homogeneity is confirmed, the conclusions concerning treatment effects can be generalized to a broader patient population. In this paper, a Bayesian hierarchical survival model is used to investigate the institutional effects on the efficacy of treatment as well as on the baseline risk. The marginal posterior distributions are estimated by a Markov chain Monte Carlo method, that is, Gibbs sampling, to overcome current computational limitations. The robustness of the inferences to the distributional assumption for the random effects is also examined. We illustrate the methods with analyses of data from a multi-centre cancer clinical trial, which investigated the efficacy of immunochemotherapy as an adjuvant treatment after curative resection of gastric cancer. In this trial there is little difference in the treatment effects across institutions and the treatment is shown to be effective, while there appears to be substantial variation in the baseline risk across institutions. This result indicates that the observed treatment effects might be generalized to a broader patient population.

Adjuvants, Immunologic↗
PubMed2000

Localization of a quantitative trait locus via a Bayesian approach.

A Bayesian approach to the direct mapping of a quantitative trait locus (QTL), fully utilizing information from multiple linked gene markers, is presented in this paper. The joint posterior distribution (a mixture distribution modeling the linkage between a biallelic QTL and N gene markers) is computationally challenging and invites exploration via Markov chain Monte Carlo methods. The parameter's complete marginal posterior densities are obtained, allowing a diverse range of inferences. Parameters estimated include the QTL genotype probabilities for the sires and the offspring, the allele frequencies for the QTL, and the position and additive and dominance effects of the QTL. The methodology is applied through simulation to a half-sib design to form an outbred pedigree structure where there is an entire class of missing information. The capacity of the technique to accurately estimate parameters is examined for a range of scenarios.

Algorithms↗
PubMed1999

Assessing heterogeneity and correlation of paired failure times with the bivariate frailty model.

We consider bivariate survival times for heterogeneous populations, where heterogeneity induces deviations in an individual's risk of an event as well as associations between survival times. The heterogeneity is characterized by a bivariate frailty model. We measure the heterogeneity effects through deviations associated with hazard functions and an association function defined through the conditional hazard functions: the cross-ratio function proposed by Oakes. We show how the deviation and association measures are determined by the frailty distribution. A Gibbs sampling method is developed for Bayesian inferences on regression coefficients, frailty parameters and the heterogeneity measures. The method is applied to a mental health care data set.

Algorithms↗
PubMed1985

A calculator program for clinical application of the Bayesian method of predicting plasma drug levels.

A pharmacokinetic program that allows individualization of drug dosage regimens through the Bayesian method is described. The program, which is designed for the Hewlett-Packard HP-41 CV calculator, is based upon the one-compartment open model with either instantaneous or zero-order absorption. Individualized estimation of the patient's kinetic parameters (clearance and volume of distribution) is performed by analyzing the plasma levels measured in the patient as well as considering the population data of the drug. After estimating the individual kinetic parameters by the Bayesian method, the program predicts the dosage regimen that will elicit the desired peak and trough plasma levels at steady state. For comparison purposes, the least-squares estimates for clearance and volume of distribution are calculated, and dosage prediction can also be made on the basis of the least-squares estimates. The least-squares estimates can be used to calculate population pharmacokinetic parameters according to the Standard Two-Stage method. Several examples of clinical use of the program are presented. The examples refer to patients with classic hemophilia who were treated with Factor VIII concentrates. In these patients, the Bayesian kinetic parameters of Factor VIII have been estimated through the calculator program. The Bayesian parameter estimates generated by the HP-41 have been compared with those determined by a Bayesian program (ADVISE) designed for microcomputers.

Computers↗
PubMed1999

A hierarchical Bayesian model to predict the duration of immunity to Haemophilus influenzae type b.

A hierarchical Bayesian regression model is fitted to longitudinal data on Haemophilus influenzae type b (Hib) serum antibodies. To estimate the decline rate of the antibody concentration, the model accommodates the possibility of unobserved subclinical infections with Hib bacteria that cause increasing concentrations during the study period. The computations rely on Markov chain Monte Carlo simulation of the joint posterior distribution of the model parameters. The model is used to predict the duration of immunity to subclinical Hib infection and to a serious invasive Hib disease.

Antibodies, Bacterial↗
PubMed1980

Numerical evaluation of cytologic data. V. Bivariate distributions and the Bayesian decision Boundary.

The evaluation of cytologic data often involves the classification of observations into alternative categories (data sets). Plotting the elliptical contours of bivariate distributions provides immediate insight into the structure of data sets and their mutual relations. In this paper, the computation of tolerance ellipses and confidence ellipses for bivariate distribution is demonstrated, and the finding of a Bayesian decision boundary between two bivariate distributions is illustrated.

Bayes Theorem↗
PubMed1997

A population approach to initial dose selection.

Before a drug can be marketed, an initial dose must be established. Sheiner et al. argue that a population approach leads to the most informed and rational decision making. We discuss the choice of an initial dose from both a predictive and estimative viewpoint. Our criteria are based upon evaluating the probabilities that a patient from the specified population obtains a response that is at least of a specified size. We demonstrate the approach using a simulation study and compare estimation of population parameters and initial dose using Bayesian and likelihood-based methods.

Bayes Theorem↗
PubMed1997

Bayesian color constancy.

The problem of color constancy may be solved if we can recover the physical properties of illuminants and surfaces from photosensor responses. We consider this problem within the framework of Bayesian decision theory. First, we model the relation among illuminants, surfaces, and photosensor responses. Second, we construct prior distributions that describe the probability that particular illuminants and surfaces exist in the world. Given a set of photosensor responses, we can then use Bayes's rule to compute the posterior distribution for the illuminants and the surfaces in the scene. There are two widely used methods for obtaining a single best estimate from a posterior distribution. These are maximum a posteriori (MAP) and minimum mean-square-error (MMSE) estimation. We argue that neither is appropriate for perception problems. We describe a new estimator, which we call the maximum local mass (MLM) estimate, that integrates local probability density. The new method uses an optimality criterion that is appropriate for perception tasks: It finds the most probable approximately correct answer. For the case of low observation noise, we provide an efficient approximation. We develop the MLM estimator for the color-constancy problem in which flat matte surfaces are uniformly illuminated. In simulations we show that the MLM method performs better than the MAP estimator and better than a number of standard color-constancy algorithms. We note conditions under which even the optimal estimator produces poor estimates: when the spectral properties of the surfaces in the scene are biased.

Color Perception↗
PubMed1995

Adaptive control of therapeutic drug regimens relations between clinical situations: outcomes and simulations using nonlinear dynamic models.

With Bayesian modeling and adaptive control of drug dosage regimens, serum and peripheral drug concentrations can be predicted in clinical situations using linear pharmacokinetic compartmental models (PK). Recently, several pathophysiologic and pharmacodynamic nonlinear models (PD) have been developed. The present report illustrates both their utility and limits for the computation of effects in clinical situations in the setting of actual routine and acute patient care. Patients who received therapy with aminoglycosides or/and vancomycin were selected. For each patient, after estimation of individual pharmacokinetic parameters, the computed outputs of the linear compartmental pharmacokinetic model were used as inputs for 2 different a priori nonlinear dynamic models: 1) the EFFECT modeling program, using a Hill model, and 2) the BACTCIDE program, which is a combination of a simple growth model for the organism and a Hill effect model considering both the microorganism, the antibiotic, and the patient's minimal inhibitory concentration (MIC). The programs (1) and (2) can use as inputs the computed concentrations from any of three compartments: central, peripheral, or a spherical diffusion compartment to compute drug diffusion into endocardial vegetations or abscesses. The EFFECT program can be used alone for the evaluation of drug effects. The BACTCIDE program illustrates differences in activity between concentration-dependent and time-dependent antibiotics. Such nonlinear programs are very sensitive to the MIC values.

Aged↗
PubMed1992

Predictive performance of Bayesian and nonlinear least-squares regression programs for lidocaine.

The predictive performance of two computer programs for lidocaine dosing were evaluated. Two-compartment Bayesian and nonlinear least-squares regression programs were used in two groups of patients (15 acute arrhythmia patients and 14 chronic arrhythmia patients). Lidocaine was given as a 1.5 mg/kg bolus and a 2.8 mg/min infusion for 48 h. A second bolus (0.5 mg/kg) was given 10 min after the first bolus over 2 min. Serum samples of the patients receiving lidocaine were drawn at 2, 15, 30 min and 1, 2, and 4 h and were used in forecasting the serum concentrations at 6, 8, 12, and 48 h. Predictive performance was assessed by mean error and mean-squared error. The results (mean +/- 95% confidence intervals) demonstrated the Bayesian program predicted a significant (p less than 0.05) difference at 12 h between the two arrhythmia groups (acute 0.52 [-0.95; -0.09] and chronic 0.28 [0.12; 0.44]). The results also demonstrated the Bayesian method was significantly more precise compared to the nonlinear least-squares regression program at 8, 12, and 48 h for the acute group. While caution is warranted, this study demonstrated that the predictive performance by a two-compartment Bayesian model is more accurate in predicting future lidocaine serum concentrations than that by nonlinear least-squares regression.

Acute Disease↗
PubMed1994

Pharmacokinetics and dosage regimens of amikacin in intensive care unit patients.

The pharmacokinetics of amikacin have been studied in 40 intensive care unit (ICU) patients using a two-compartment model and the Bayesian estimation method implemented in the USC PC-PACK program of Jelliffe et al. The volume of the central compartment was significantly higher in these patients (0.36 l.kg-1) than in the reference population (0.20 l.kg-1). A method has been designed to compute dosage regimens in order to maintain a constant steady-state average plasma concentration of 8 mg.l-1 for repeated i.v. infusions. The regimen calculated for the 'average' ICU patient varies between 11 mg.kg-1 three times per day for the patient with normal renal function and 6 mg.kg-1 every 2 days for the anuric patient. This regimen is intended to begin amikacin therapy in an ICU patient, while the population pharmacokinetic parameters would allow the individualization of the regimen by means of the Bayesian method.

Amikacin↗
PubMed1994

Application of USC*PACK clinical programs to vancomycin in neutropenic patients.

The pharmacokinetics of vancomycin were studied in 10 neutropenic patients (4 male, 6 female) using the USC*PACK Clinical Programs. The experimental data was determined after the first administration of 1000 mg injected as a 1-h infusion. Eight blood samples were collected between 15 min and 11 h after the end of the infusion. Plasma vancomycin concentrations were measured by immunoassay procedure. Creatinine clearance and urine flow were also measured. Pharmacokinetic parameters were computed using a two-compartment model: Vc = 0.270665 +/- 0.161033 (l.kg-1); Kcp = 0.732927 +/- 0.464449 (h-1); Ks = 0.004952 +/- 0.00272 (min.ml-1.h-1); Kpc = 0.470243 +/- 0.194677 (h-1); Ki = 0.011675 +/- 0.004086 (h-1); Ke = 0.644415 +/- 0.239376 (h-1). When we compared this population to the general population of the program, Ke was increased. Elimination constant Ke was not correlated to either creatinine clearance or urine flow. Evaluation of the predictive performance of the Bayesian PC Program for adaptive control of vancomycin therapy in neutropenic patients is the next step of this study.

Adolescent↗
PubMed2001

Bayesian 2-D deconvolution: effect of using spatially invariant ultrasound point spread functions.

Observed ultrasound images are degraded representations of the-true tissue reflectance. The specular reflections at boundaries between regions of different tissue types are blurred, and the diffuse scattering within homogenous regions causes speckle because of the oscillating nature of the transmitted pulse. To reduce both blur and speckle, we have developed algorithms for the restoration of simulated and real ultrasound images based on Markov random field models and Bayesian statistical methods. The algorithm is summarized here, although a more detailed description can be found in our companion paper [1]. Because the point spread function (psf) is unknown, we investigate the effects of using incorrect frequencies and sizes for the model psf during the restoration process. First, we degrade the images either with a known simulated psf or a measured psf. Then, we use different psf shapes during restoration to study the robustness of the method. We found that small variations in the parameters characterizing the psf, less than +/- 25% change in frequency, width, or length, still yielded satisfactory results. When altering the psf more than this, the restorations were not acceptable. The restorations were particularly sensitive to large increases in the restoring psf frequency. Thus, 2-D Bayesian restoration using a fixed psf may yield acceptable results as long as the true variant psfs have not varied too much during imaging.

Bayes Theorem↗