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 415 records · Page 23Linked to original sources
PubMed1995

Efficient sampling strategies for forecasting pharmacokinetic parameters of irinotecan (CPT-11): implication for area under the concentration-time curve monitoring.

A linear two-compartment Bayesian pharmacokinetic model was developed using a standard two-stage population method for the novel anti-cancer agent CPT-11 from 11 adult patients with refractory cancer. The accuracy and efficiency of this Bayesian model for estimating pharmacokinetic parameters including the area under the concentration-time curve (AUC) was then evaluated using two different sampling strategies in a new study cohort of 13 patients with cancer. Sampling strategies included either one, two, or three nonsteady-state feedback levels determined empirically and from optimal sampling theory (D-optimality). All 24 patients in this study received CPT-11 (60 mg/m2) as a 90-min infusion. Pharmacokinetic parameters derived from the Bayesian model combined with these limited sampling strategies were compared with those parameters obtained from the full sample data sets (n = 10) analyzed by weighted nonlinear least squares regression (reference method). The least-bias and most precise sampling times for estimating AUC were 3.5; 3.5 and 9.5; and 0.5, 3.5, and 9.5 h, respectively. At these times, only marginal improvement in precision of the AUC estimate was observed using two versus three samples. However, the precision of the estimate of clearance was not improved using two versus three samples. The sampling times derived from optimal sampling theory were 0.25, 3.5, 8.5, and 24 h and correlated closely to the actual and best empirical sampling times of 0.5, 3.5, 9.5, and 24 h. These results strongly suggest that Bayesian estimation combined with only two optimally timed samples accurately predicts the AUC of CPT-11 and should be useful for implementing adaptive control dosing for monitoring CPT-11 systemic exposure in patients with cancer.

Adult↗
PubMed1999

Minimal model SG overestimation and SI underestimation: improved accuracy by a Bayesian two-compartment model.

The intravenous glucose tolerance test (IVGTT) single-compartment minimal model (1CMM) method has recently been shown to overestimate glucose effectiveness and underestimate insulin sensitivity. Undermodeling, i.e., use of single- instead of two-compartment description of glucose kinetics, has been advocated to explain these limitations. We describe a new two-compartment minimal model (2CMM) into which we incorporate certain available knowledge on glucose kinetics. 2CMM is numerically identified using a Bayesian approach. Twenty-two standard IVGTT (0.30 g/kg) in normal humans were analyzed. In six subjects, the clamp-based index of insulin sensitivity (ScI) was also measured. 2CMM glucose effectiveness (S2G) and insulin sensitivity (S2I) were, respectively, 60% lower (P < 0.0001) and 35% higher (P < 0.0001) than the corresponding 1CMM S1G and S1I indexes: 2.81 +/- 0.29 (SE) vs. S1G = 4.27 +/- 0.33 ml. min(-1). kg(-1) and S2I = 11.67 +/- 1.71 vs. S1I = 8.68 +/- 1.62 10(2) ml. min(-1). kg(-1) per microU/ml. S2I was not different from ScI = 12.61 +/- 2.13 10(2) ml. min(-1). kg(-1) per microU/ml (nonsignificant), whereas S1I was 60% lower (P < 0.02). In conclusion, a new 2CMM has been presented that improves the accuracy of glucose effectiveness and insulin sensitivity estimates of the classic 1CMM from a standard IVGTT in normal humans.

Adult↗
PubMed2003

MrBayes 3: Bayesian phylogenetic inference under mixed models.

MrBayes 3 performs Bayesian phylogenetic analysis combining information from different data partitions or subsets evolving under different stochastic evolutionary models. This allows the user to analyze heterogeneous data sets consisting of different data types-e.g. morphological, nucleotide, and protein-and to explore a wide variety of structured models mixing partition-unique and shared parameters. The program employs MPI to parallelize Metropolis coupling on Macintosh or UNIX clusters.

Algorithms↗
PubMed2004

Resolution of large and small differences in gene expression using models for the Bayesian analysis of gene expression levels and spotted DNA microarrays.

BACKGROUND: The detection of small yet statistically significant differences in gene expression in spotted DNA microarray studies is an ongoing challenge. Meeting this challenge requires careful examination of the performance of a range of statistical models, as well as empirical examination of the effect of replication on the power to resolve these differences. RESULTS: New models are derived and software is developed for the analysis of microarray ratio data. These models incorporate multiplicative small error terms, and error standard deviations that are proportional to expression level. The fastest and most powerful method incorporates additive small error terms and error standard deviations proportional to expression level. Data from four studies are profiled for the degree to which they reveal statistically significant differences in gene expression. The gene expression level at which there is an empirical 50% probability of a significant call is presented as a summary statistic for the power to detect small differences in gene expression. CONCLUSIONS: Understanding the resolution of difference in gene expression that is detectable as significant is a vital component of experimental design and evaluation. These small differences in gene expression level are readily detected with a Bayesian analysis of gene expression level that has additive error terms and constrains samples to have a common error coefficient of variation. The power to detect small differences in a study may then be determined by logistic regression.

Algorithms↗
PubMed1997

Bayesian nonparametric population models: formulation and comparison with likelihood approaches.

Population approaches to modeling pharmacokinetic and/or pharmacodynamic data attempt to separate the variability in observed data into within- and between-individual components. This is most naturally achieved via a multistage model. At the first stage of the model the data of a particular individual is modeled with each individual having his own set of parameters. At the second stage these individual parameters are assumed to have arisen from some unknown population distribution which we shall denote F. The importance of the choice of second stage distribution has led to a number of flexible approaches to the modeling of F. A nonparametric maximum likelihood estimate of F was suggested by Mallet whereas Davidian and Gallant proposed a semiparametric maximum likelihood approach where the maximum likelihood estimate is obtained over a smooth class of distributions. Previous Bayesian work has concentrated largely on F being assigned to a parametric family, typically the normal or Student's t. We describe a Bayesian nonparametric approach using the Dirichlet process. We use Markov chain Monte Carlo simulation to implement the procedure. We discuss each procedure and compare our approach with those of Mallet and Davidian and Gallant, using simulated data for a pharmacodynamic dose-response model.

Bayes Theorem↗
PubMed2001

Bayesian approaches to modeling the conditional dependence between multiple diagnostic tests.

Many analyses of results from multiple diagnostic tests assume the tests are statistically independent conditional on the true disease status of the subject. This assumption may be violated in practice, especially in situations where none of the tests is a perfectly accurate gold standard. Classical inference for models accounting for the conditional dependence between tests requires that results from at least four different tests be used in order to obtain an identifiable solution, but it is not always feasible to have results from this many tests. We use a Bayesian approach to draw inferences about the disease prevalence and test properties while adjusting for the possibility of conditional dependence between tests, particularly when we have only two tests. We propose both fixed and random effects models. Since with fewer than four tests the problem is nonidentifiable, the posterior distributions are strongly dependent on the prior information about the test properties and the disease prevalence, even with large sample sizes. If the degree of correlation between the tests is known a priori with high precision, then our methods adjust for the dependence between the tests. Otherwise, our methods provide adjusted inferences that incorporate all of the uncertainty inherent in the problem, typically resulting in wider interval estimates. We illustrate our methods using data from a study on the prevalence of Strongyloides infection among Cambodian refugees to Canada.

Bayes Theorem↗
PubMed2005

Bayesian latent variable models for mixed discrete outcomes.

In studies of complex health conditions, mixtures of discrete outcomes (event time, count, binary, ordered categorical) are commonly collected. For example, studies of skin tumorigenesis record latency time prior to the first tumor, increases in the number of tumors at each week, and the occurrence of internal tumors at the time of death. Motivated by this application, we propose a general underlying Poisson variable framework for mixed discrete outcomes, accommodating dependency through an additive gamma frailty model for the Poisson means. The model has log-linear, complementary log-log, and proportional hazards forms for count, binary and discrete event time outcomes, respectively. Simple closed form expressions can be derived for the marginal expectations, variances, and correlations. Following a Bayesian approach to inference, conditionally-conjugate prior distributions are chosen that facilitate posterior computation via an MCMC algorithm. The methods are illustrated using data from a Tg.AC mouse bioassay study.

Acrylates↗
PubMed1999

A Bayesian approach to modelling the natural history of a chronic condition from observations with intervention.

To assess the costs and benefits of screening and treatment strategies, it is important to know what would have happened had there been no intervention. In today's ethical climate, however, it is almost impossible to observe this directly and therefore must be inferred from observations with intervention. In this paper, we illustrate a Bayesian approach to this situation when the observations are at separated and unequally spaced time points and the time of intervention is interval censored. We develop a discrete-time Markov model which combines a non-homogeneous Markov chain, used to model the natural progression, with mechanisms that describe the possibility of both treatment intervention and death. We apply this approach to a subpopulation of the Wisconsin Epidemiologic Study of Diabetic Retinopathy, a population-based cohort study to investigate prevalence, incidence, and progression of diabetic retinopathy. In addition, posterior predictive distributions are discussed as a prognostic tool to assist researchers in evaluating costs and benefits of treatment protocols. While we focus this approach on diabetic retinopathy cohort data, we believe this methodology can have wide application.

Age of Onset↗
PubMed1997

A Bayesian Approach to Model Selection in Hierarchical Mixtures-of-Experts Architectures.

There does not exist a statistical model that shows good performance on all tasks. Consequently, the model selection problem is unavoidable; investigators must decide which model is best at summarizing the data for each task of interest. This article presents an approach to the model selection problem in hierarchical mixtures-of-experts architectures. These architectures combine aspects of generalized linear models with those of finite mixture models in order to perform tasks via a recursive "divide-and-conquer" strategy. Markov chain Monte Carlo methodology is used to estimate the distribution of the architectures' parameters. One part of our approach to model selection attempts to estimate the worth of each component of an architecture so that relatively unused components can be pruned from the architecture's structure. A second part of this approach uses a Bayesian hypothesis testing procedure in order to differentiate inputs that carry useful information from nuisance inputs. Simulation results suggest that the approach presented here adheres to the dictum of Occam's razor; simple architectures that are adequate for summarizing the data are favored over more complex structures. Copyright 1997 Elsevier Science Ltd. All Rights Reserved.

Journal Article↗
PubMed2003

A model-integrated multipoint Bayesian analysis of hypertension in the Framingham Heart Study data finds little evidence of linkage.

This Genetic Analysis Workshop 13 contribution presents a linkage analysis of hypertension in the Framingham data based on the posterior probability of linkage, or PPL. We dichotomized the phenotype, coding individuals who had been treated for hypertension at any time, as well as those with repeated high blood pressure measurements, as affected. Here we use a new variation on the multipoint PPL that incorporates integration over the genetic model. PPLs were computed for chromosomes 1 through 5, 11, 14, and 17 and remained below the 2% assumed prior probability of linkage for 73% of the locations examined. The maximum PPL of 4.5% was obtained on chromosome 1 at 178 cM. Although this is more than twice the assumed prior probability of linkage, it is well below a level at which we would recommend committing substantial additional resources to molecular follow-up. While the PPL analysis of this data remains inconclusive, Bayesian methodology gives us a clear mechanism for using the information gained here in further studies.

Bayes Theorem↗
PubMed1998

Safety and efficacy of a two-compartment Bayesian feedback program for therapeutic tobramycin monitoring in the daily clinical use and comparison with a non-Bayesian one-compartment model.

The predictive value of a two-compartment Bayesian feedback program for tobramycin dose optimization was retrospectively evaluated in 199 hospitalized patients and compared with that of a simple non-Bayesian one-compartment model. Before dose adjustment, 64% of the patients were underdosed indicating that tobramycin monitoring is still necessary to avoid ineffective antibiotic therapy. When physicians adhered to the dose instructions calculated with the Bayesian method, 90% of the patients had optimal concentration-time profiles as opposed to only 53% of the 43 patients in whom dose recommendations were not followed. In young patients with normal renal function, precision and accuracy of the Bayesian feedback and the one-compartment method were well correlated, whereas in elderly patients (> 60 years) and patients with impaired renal function (estimated creatinine clearance < 60 ml/minute), the Bayesian method was significantly more precise. Multiple regression analysis revealed that renal function was the only independent variable predicting the performance of the Bayesian program. The results of this study indicate that the Bayesian feedback method is a reliable method for the therapeutic tobramycin monitoring under clinical conditions and in particular, elderly patients in whom renal impairment is frequent.

Absorption↗
PubMed2004

Cerebral modeling and dynamic Bayesian networks.

The understanding and the prediction of the clinical outcomes of focal or degenerative cerebral lesions, as well as the assessment of rehabilitation procedures, necessitate knowing the cerebral substratum of cognitive or sensorimotor functions. This is achieved by activation studies, where subjects are asked to perform a specific task while data of their brain functioning are obtained through functional neuroimaging techniques. Such studies, as well as animal experiments, have shown that sensorimotor or cognitive functions are the offspring of the activity of large-scale networks of anatomically connected cerebral regions. However, no one-to-one correspondence between activated networks adn functions can be found. Our research aims at understanding how the activation of large-scale networks derives from cerebral information processing mechanisms, which can only explain apparently conflicting activation data. Our work falls at the crossroads of neuroimaging interpretation techniques and computational neuroscience. Since knowledge in cognitive neuroscience is permanently evolving, our research aims more precisely at defining a new modeling formalism and at building a flexible simulator, allowing a quick implementation of the models, for a better interpretation of cerebral functional images. It also aims at providing plausible models, at eht level of large-scale networks, of cerebral information processing mechanisms in humans. In this paper, we propose a formalism, based on dynamic Bayesian networks (DBNs), that respects the following constraints: an oriented, networks architecture, whose nodes (the cerebral structures) can all be different, the implementation of causality--the activation of the structure is caused by upstream nodes' activation--the explicit representation of different time scales (from 1 ms for the cerebral activity to many seconds for a PET scan image acquisition), the representation of cerebral information at the integrated level of neuronal populations, the imprecision of functional neuroimaging data, the nonlinearity and the uncertainty in cerebral mechanisms, and brain's plasticity (learning, reorganization, modulation). One of the main problems, nonlinearity, has been tackled thanks to new extensions of the Kalman filter. The capabilities of the formalism's current version are illustrated by the modeling of a phoneme categorization process, explaining the different cerebral activations in normal and dyslexic subjects.

Bayes Theorem↗
PubMedDate not supplied

Meta-analysis and the synthesis of evidence.

Use of meta-analytical (quantitative overview) techniques is now commonplace in a large range of medical-research contexts, with a rapid rise in its frequency of use being particularly apparent in the last decade. Many methods of meta-analysis have been proposed and used, from crude 'vote-counting' of studies showing significant or nonsignificant results, through methods for combination of effect-size estimates based on fixed- or random-effects models, to general, linear, mixed models and Bayesian methods. The history of meta-analysis and the advantages and disadvantages of various approaches to it are briefly reviewed in this paper, with reference to its application in health-services research and related fields. Broader approaches to the synthesis of evidence in these contexts using conventional multilevel modelling and hierarchical Bayesian models to address the combination of evidence from disparate types of study are then outlined.

Bayes Theorem↗
PubMed1997

Bayesian registration of models using finite element eigenmodes.

This paper is concerned with registering three-dimensional wire-frame organ models. This involves finding correspondences between points on the models of two different examples of the same organ. Such registration is widely used in the processing of medical data; for example in segmentation, or to superimpose functional information on a more detailed structural map. The algorithm described in this paper is based on matching the modes of deformation of organ shapes. Modes with lower spatial frequency characterise large scale organ features whereas small scale variations determine the high frequency modes. First, the organ sizes are normalised using a generalised version of the centroid size metric. The axes of the fundamental frequency modes are then aligned to provide initial rigid-body registration. The registration is refined by matching increasingly high frequency modes using the 'Highest confidence first' algorithm. The matches are evaluated using a Bayesian combination of local prior and likelihood functions. The prior is derived from the Gompertz metric of biological growth and ensures that physically impossible matches are not accepted. The likelihood function is a measure of the similarity between local modal deformation components. The registration algorithm has been applied by the authors in the analysis of three dimensional ultrasound data. Results are presented showing the registration of two liver models derived from 3D ultrasound.

Algorithms↗
PubMedDate not supplied

Generalization of map estimation in SAAM II: validation against ADAPT II in a glucose model case study.

Bayesian approaches to model identification [e.g., maximum a posteriori (MAP) estimation] are receiving increasing attention in metabolism since important quantitative knowledge has become available in the last decades, e.g., from tracer experiments. By suitably exploiting this knowledge, more complex physiological models than those solely based on experimental data (Fisherian approach) become resolvable. While ADAPT II is the reference software for MAP estimation in pharmacokinetic/pharmacodynamic/metabolic system analysis, another popular, user-friendly and state-of-the-art software is SAAM II. However, SAAM II does not handle a priori information on correlation among parameters, thus allowing a limited version of MAP estimation to be performed. The aim here is twofold. First, we show that this limitation of SAAM II can be easily overcome by resorting to a probability theory result. Second, we test SAAM II vs ADAPT II implementation of MAP estimation in a real case study: the Bayesian identification of a recently proposed two-compartment minimal model of glucose kinetics during an intravenous glucose tolerance test. SAAM II MAP estimates of glucose effectiveness (SG) and insulin sensitivity (S(I)) obtained in a group of 22 healthy humans are in excellent agreement with those of ADAPT II: S(G) = 2.84 +/- 0.27 vs. 2.84 +/- 0.27 (mlmin(-1) kg(-1), mean +/- SD) and S(I) = 11.46 +/- 1.69 vs. 11.47 +/- 1.69 [10(-2) ml kg(-1) min(-1)/ (microU ml(-1))]. The SAAM II vs. ADAPT II estimates are virtually identical (P > 0.44 and 0.68 for S(G) and S(I), respectively) and also closely correlated (p = 0.9998 and 0.9999).

Algorithms↗
PubMed2001

Projecting cancer incidence and mortality using Bayesian age-period-cohort models.

BACKGROUND: We present a practical application of an age-period-cohort model in a Bayesian frame-work for making cancer-burden projections. METHODS: Second degree autoregressive smoothing was used on the age, period and cohort effects for estimating future incidence and mortality. RESULTS: We are able to demonstrate the feasibility, flexibility and strengths of this approach. Compared with previously used methods, it performed better for providing point estimates when past trends continued into the future. However, the extremely wide credible intervals need careful interpretation. DISCUSSION: Part of the uncertainty is attributable to the possible inadequacy of the model and not necessarily relevant in the prediction of what would happen if the present trends continue into the future.

Age Factors↗
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↗
PubMed1993

Exploring the relationship between rationality and bounded rationality in medical knowledge-based systems.

If our goal in Artificial Intelligence in Medicine (AIM) is to engineer systems health-care providers will both use and, in the process, improve their performance, we must concentrate on the development of causal theories of knowledge and problem solving. One broad direction in pursuing this goal is understanding the relationships between existing models of rationality and bounded rationality for similar tasks. Models of rationality refer to those approaches in which the optimal properties of the models are deductively provable, i.e. in which the processing is rational. Representative models of rationality used in AIM are deductive logical models, statistical models such as Bayesian inference models, and decision-analytic models. Models of bounded rationality are those which do not guarantee such optimal properties nor yield to deductive correctness proofs. These models have their roots in cognitive psychology. In this article we show how explicating the relationship between models of rationality and bounded rationality might be done in the case of abductive tasks in medicine. This is done by positioning these modeling approaches within the same framework (an abstract computational model) and interpreting in this context both computational complexity results concerning the nature of the task and empirical results studies of human problem-solving behavior.

Artificial Intelligence↗