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 1,477 records · Page 82Linked to original sources
PubMed1999

Motion transparency: making models of motion perception transparent.

In daily life our visual system is bombarded with motion information. We see cars driving by, flocks of birds flying in the sky, clouds passing behind trees that are dancing in the wind. Vision science has a good understanding of the first stage of visual motion processing, that is, the mechanism underlying the detection of local motions. Currently, research is focused on the processes that occur beyond the first stage. At this level, local motions have to be integrated to form objects, define the boundaries between them, construct surfaces and so on. An interesting, if complicated case is known as motion transparency: the situation in which two overlapping surfaces move transparently over each other. In that case two motions have to be assigned to the same retinal location. Several researchers have tried to solve this problem from a computational point of view, using physiological and psychophysical results as a guideline. We will discuss two models: one uses the traditional idea known as 'filter selection' and the other a relatively new approach based on Bayesian inference. Predictions from these models are compared with our own visual behaviour and that of the neural substrates that are presumed to underlie these perceptions.

Journal Article↗
PubMed2000

Achieving target goals most precisely using nonparametric compartmental models and "multiple model" design of dosage regimens.

Multiple model (MM) design and stochastic control of dosage regimens permit essentially full use of all the information contained in either a Bayesian prior nonparametric EM (NPEM) population pharmacokinetic model or in an MM Bayesian posterior updated parameter set, to achieve and maintain selected therapeutic goals with optimal precision (least predicted weighted squared error). The regimens are visibly more precise in the achievement of desired target goals than are current methods using mean or median population parameter values. Bayesian feedback has now also been incorporated into the MM software. An evaluation of MM dosage design using an NPEM population model versus dosage design based on conventional mean population parameter values is presented, using a population model of vancomycin. Further feedback control was also evaluated, incorporating realistic simulated uncertainties in the clinical environment such as those in the preparation and administration of doses.

Anti-Bacterial Agents↗
PubMedDate not supplied

Identifiability and convergence issues for Markov chain Monte Carlo fitting of spatial models.

The marked increase in popularity of Bayesian methods in statistical practice over the last decade owes much to the simultaneous development of Markov chain Monte Carlo (MCMC) methods for the evaluation of requisite posterior distributions. However, along with this increase in computing power has come the temptation to fit models larger than the data can readily support, meaning that often the propriety of the posterior distributions for certain parameters depends on the propriety of the associated prior distributions. An important example arises in spatial modelling, wherein separate random effects for capturing unstructured heterogeneity and spatial clustering are of substantive interest, even though only their sum is well identified by the data. Increasing the informative content of the associated prior distributions offers an obvious remedy, but one that hampers parameter interpretability and may also significantly slow the convergence of the MCMC algorithm. In this paper we investigate the relationship among identifiability, Bayesian learning and MCMC convergence rates for a common class of spatial models, in order to provide guidance for prior selection and algorithm tuning. We are able to elucidate the key issues with relatively simple examples, and also illustrate the varying impacts of covariates, outliers and algorithm starting values on the resulting algorithms and posterior distributions.

Algorithms↗
PubMed1999

Using probabilistic and decision-theoretic methods in treatment and prognosis modeling.

Causal probabilistic networks, also called Bayesian networks, allow both qualitative knowledge about the structure of a problem and quantitative knowledge, derived from case databases, expert opinion and literature to be exploited in the construction of decision support systems for diagnosis, treatment and prognosis. This mixing of qualitative and quantitative knowledge will be illustrated, using the selection of antibiotics for a subset of patients with severe infections. The subset consists of patients where bacteria or fungi have been found in the blood. A simple pathophysiological model of infection is used to calculate a prognosis, dependent on the choice of antibiotics. A decision-theoretic approach is used to balance the therapeutic benefit of antibiotic treatment against the cost of antibiotics in the form of direct monetary cost, side effects and ecological cost. A retrospective trial on patients with bacteria or fungi in the blood stemming from the urinary tract indicates that with this approach, it may be possible to suggest balanced choices of antibiotics that not only achieve greater therapeutic benefit, but also reduce the cost of therapy.

Anti-Bacterial Agents↗
PubMed1997

Disease mapping with errors in covariates.

We describe Bayesian hierarchical-spatial models for disease mapping with imprecisely observed ecological covariates. We posit smoothing priors for both the disease submodel and the covariate submodel. We apply the models to an analysis of insulin Dependent Diabetes Mellitus incidence in Sardinia, with malaria prevalence as a covariate.

Bayes Theorem↗
PubMed2007

Phylogenetic relationships among the Lorisoidea as indicated by craniodental morphology and mitochondrial sequence data.

The phylogeny of the Afro-Asian Lorisoidea is controversial. While postcranial data attest strongly to the monophyly of the Lorisidae, most molecular analyses portray them as paraphyletic and group the Galagidae alternately with the Asian or African lorisids. One of the problems that has bedevilled phylogenetic analysis of the group in the past is the limited number of taxa sampled for both ingroup families. We present the results of a series of phylogenetic analyses based on 635 base pairs (bp) from two mitochondrial genes (12S and 16S rRNA) with and without 36 craniodental characters, for 11 galagid and five lorisid taxa. The outgroup was the gray mouse lemur (Microcebus murinus). Analyses of the molecular data included maximum parsimony (MP), neighbor joining (NJ), maximum likelihood (ML), and Bayesian methods. The model-based analyses and the combined "molecules+morphology" analyses supported monophyly of the Lorisidae and Galagidae. The lorisids form two geographically defined clades. We find no support for the taxonomy of Galagidae as proposed recently by Groves [Primate Taxonomy, Washington, DC: Smithsonian Institution Press. 350 p, 2001]. The taxonomy of Nash et al. [International Journal of Primatology 10:57-80, 1989] is supported by the combined "molecules+morphology" analysis; however, the model-based analyses suggest that Galagoides may be an assemblage of species united by plesiomorphic craniodental characters.

Animals↗
PubMed1997

Stability and performance of a population pharmacokinetic model.

This study aimed to determine the stability (in terms of covariate selection) of a population pharmacokinetic model and evaluate its performance in the absence of a test data set. Data from 88 full-term infants, 11 of whom were human immunodeficiency virus (HIV)-seropositive, taking an antiinfective agent were analyzed using exploratory data analysis methods and the nonlinear mixed-effects modeling (NONMEM) program to obtain the final population pharmacokinetic model. The stability of the population pharmacokinetic model was tested using the nonparametric bootstrap approach in four steps: 1) with the base pharmacokinetic model, 100 bootstrap replicates of the original data were generated by sampling with replacement; 2) ascertainment that each bootstrap data replicate was described by the basic structural model using the NONMEM objective function; 3) generalized additive modeling (GAM) applied to empiric Bayesian estimates for covariate selection at alpha = 0.05 and a frequency (f) cutoff value of 0.50; and 4) NONMEM population model building using covariates selected in the third step with alpha = 0.005. Performance of the population pharmacokinetic model was evaluated using 200 additional bootstrap replicates of the data by fitting the model obtained in step 4 to them. Parameters obtained were compared with those obtained in the model stability step, and improved prediction error, a measure of predictive accuracy as an index of internal validation, was computed. The reciprocal of serum creatinine (RSC; f = 0.73) and HIV (f = 0.70) were selected by GAM as predictors of clearance (Cl). The population pharmacokinetic model obtained without the determination of model stability included RSC as a predictor of Cl, but the final model from the model stability step included both HIV and RSC as predictors of Cl. Final population pharmacokinetic parameters were obtained with this model fitted to the original data; however, the 95% confidence interval on the HIV status regression coefficient included zero, indicating no significance. The mean parameter estimates obtained with the additional 200 bootstrap replicates of data were within 15% of those obtained with the final model at the regression stability step. Bootstrap resampling procedure is useful for evaluating the stability and performance of a population model by repeatedly fitting it to the bootstrap samples when there is no test data set.

Adolescent↗
PubMed2006

Inter-rater reliability of nursing home surveys: a Bayesian latent class approach.

In the U.S., federal and state governments perform routine inspections of nursing homes. Results of the inspections allow government to generate fines for findings of non-compliance as well as allow consumers to rank facilities. The purpose of this study is to investigate the inter-rater reliability of the nursing home survey process. In general, the survey data involves 191 binary deficiency variables interpreted as 'deficient' or 'non-deficient'. To reduce the dimensionality of the problem, our proposed method involves two steps. First, we reduce the deficiency categories to sub-categories using previous nursing home studies. Second, looking at the State of Kansas specifically, we take the deficiency data from 1 year, and use Bayesian latent class analysis (LCA) to collapse the sub-categories to a binary variable. We evaluate inter-rater agreement using deficiency data from two separate survey teams on one facility, a matched-pair design. We evaluate the agreement of the two raters on binary data using the weights from the LCA. This allows a two-by-two contingency analysis using a Bayesian beta-binomial model. We elicit informative prior distributions from the nursing home providers. Together, with the experimental data, this provides a posterior distribution of the kappa agreement of the raters for nursing home deficiency citation data.

Bayes Theorem↗
PubMed2007

Survival curve estimation for informatively coarsened discrete event-time data.

Interval-censored, or more generally, coarsened event-time data arise when study participants are observed at irregular time periods and experience the event of interest in between study observations. Such data are often analysed assuming non-informative censoring, which can produce biased results if the assumption is wrong. This paper extends the standard approach for estimating survivor functions to allow informatively interval-censored data by incorporating various assumptions about the censoring mechanism into the model. We include a Bayesian extension in which final estimates are produced by mixing over a distribution of assumed censoring mechanisms. We illustrate these methods with a natural history study of HIV-infected individuals using assumptions elicited from an AIDS expert.

Bayes Theorem↗
PubMed1991

Identifying the fertile phase of the human menstrual cycle.

The identification of the human fertile phase as the time during which a woman or a couple may conceive is elusive. The fertile time depends on many factors in each individual menstrual cycle and may be said to be more of a statistical than a physiological entity. This paper reviews the application of statistical methods to three areas related to conception and the fertile phase. The first is the prediction and detection of ovulation from serial measurements, such as hormones, basal body temperature and cervical mucus, throughout the menstrual cycle. Typically, such variables increase from some baseline level to a peak around ovulation (the most fertile time), then subside to low levels in the postovulatory phase. The statistical challenge is to detect the rise (signalling the onset of potential fertility) and subsequent fall. Analytic methods considered include thresholds, Bayesian change-point models and particularly the cumulative sum (cusum) technique which is both simple to apply and understand, and effective. The second area comprises appropriate methods of analysing and interpreting data from clinical studies of the fertile phase, especially in so-called natural family planning (NFP) where it is usual for women to observe several indices of potential fertility. Such studies usually try to establish the temporal relationships between markers of the fertile phase and examine the success of different combinations of markers in delineating the fertile time in comparison with a standard 'defined' phase, for example, the interval from three days before to two days after the peak of luteinizing hormone. The third area is the assessment of the probability of conception on certain days of the cycle, which is vital to the understanding of the fertile phase and its application to NFP. Direct estimation of such probabilities is impractical; instead, resort must be made to estimation by maximum likelihood of the parameters of specially constructed models. Suitable models are described. Finally, the need for a new prospective study of the probability of conception in relation to the markers of the fertile phase used in the symptothermal method of NFP is discussed.

Female↗
PubMed2002

Bayesian estimation of dynamical systems: an application to fMRI.

This paper presents a method for estimating the conditional or posterior distribution of the parameters of deterministic dynamical systems. The procedure conforms to an EM implementation of a Gauss-Newton search for the maximum of the conditional or posterior density. The inclusion of priors in the estimation procedure ensures robust and rapid convergence and the resulting conditional densities enable Bayesian inference about the model parameters. The method is demonstrated using an input-state-output model of the hemodynamic coupling between experimentally designed causes or factors in fMRI studies and the ensuing BOLD response. This example represents a generalization of current fMRI analysis models that accommodates nonlinearities and in which the parameters have an explicit physical interpretation. Second, the approach extends classical inference, based on the likelihood of the data given a null hypothesis about the parameters, to more plausible inferences about the parameters of the model given the data. This inference provides for confidence intervals based on the conditional density.

Bayes Theorem↗
PubMed2005

Hospital rates of maternal and neonatal infection in a low-risk population.

BACKGROUND: In 2003, the Agency for Healthcare Quality and Research (AHRQ) published its Quality Indicators for healthcare, and set out methodological criteria for the evaluation of potential candidates. OBJECTIVES: Because perinatal infections may result from poor obstetrical practices, we intended to describe the variability of maternal and congenital neonatal infections across different types of hospital ownership (e.g., not for profit, government), and to assess whether rates of these infections meet criteria as quality indicators. RESEARCH DESIGN: Population-based cohort study. SUBJECTS: All laboring women without maternal, fetal, or placental complications who delivered in California in 1997, and their neonates, as reported through hospital discharge data. MEASURES: A Bayesian hierarchical logistic regression model was used to quantify the effects of both "patient-level" risk factors such as parity and prior cesarean history, and "hospital-level" risk factors such as ownership and teaching status. RESULTS: The 308,841 mother-newborn pairs in this low-risk study population delivered at 281 hospitals; 0.39% had uterine infections and 1.3% had neonatal infections. Hospital ownership and teaching status were strongly associated with perinatal infection. Secondly, methods used to estimate and analyze hospital-specific infection rates identified hospitals with exceptionally high rates. Twenty-eight hospitals had neonatal infection rates that ranged from 3% to 28%. CONCLUSIONS: The methods presented here were consistent with AHRQ methods and criteria for potential Quality Indicators. They also identified hospitals with exceptionally high rates of infectious morbidity. The relationship between hospital ownership and obstetrical practice patterns, and the feasibility of practice improvement, remain to be studied.

California↗
PubMed2005

Variations in the incidence of postpartum hemorrhage across hospitals in California.

OBJECTIVE: Because postpartum hemorrhage may result from factors related to obstetrical practice patterns, we examined the variability of postpartum hemorrhage and related risk factors (obstetrical trauma, chorioamnionitis, and protracted labor) across hospital types and hospitals in California. METHODS: Linked birth certificate and hospital discharge data from 507,410 births in California in 1997 were analyzed. Cases were identified using International Classification of Diseases, Ninth Edition, Clinical Modification (ICD-9-CM) codes. Comparisons were made across hospital types and individual hospitals. Risk adjustments were made using 1) sample restriction to a subset of 324,671 low-risk women, and 2) Bayesian hierarchical logistic regression model to simultaneously quantify the effects of patient-level and hospital-level risk factors. RESULTS: Postpartum hemorrhage complicated 2.4% of live births. The incidence ranged from 1.6% for corporate hospitals to 4.9% for university hospitals in the full sample, and from 1.4% for corporate hospitals to 3.9% for university hospitals in the low-risk sample. Low-risk women who delivered at government, HMO and university hospitals had two- to threefold increased odds (odds ratios 1.98 to 2.71; 95% confidence sets ranged from 1.52 to 4.62) of having postpartum hemorrhage compared to women who delivered at corporate hospitals, irrespective of patient-level characteristics. They also had significantly higher rates of obstetrical trauma and chorioamnionitis. Greater variations were observed across individual hospitals. CONCLUSION: The incidence of postpartum hemorrhage and related risk factors varied substantially across hospital types and hospitals in California. Further studies using primary data sources are needed to determine whether these variations are related to the processes of care.

Bayes Theorem↗
PubMed1995

Pharmacokinetics and pharmacodynamics of 21-day continuous oral etoposide in pediatric patients with solid tumors.

PURPOSE: The objectives of this study were to determine etoposide pharmacokinetics during continuous low-dose oral administration to children with solid tumors and to evaluate the relationships between parameters of etoposide systemic exposure and toxicity. PATIENTS AND METHODS: In this phase I study, children were administered oral etoposide (25 to 75 mg/m2/day) for 21 days as a diluted solution of the intravenous preparation, divided into three equal daily doses. Plasma pharmacokinetics were studied on day 1 of therapy in 18 children and again on day 21 in 14 of these children. Etoposide plasma concentration-time data were fitted to a first-order absorption, two-compartment model with use of bayesian estimation. Pharmacokinetic parameter estimates from day 1 were used to estimate steady-state etoposide systemic exposure in all children. Stepwise multivariate regression was used in an exploratory manner to determine patient, laboratory, or pharmacokinetic predictors of toxicity. RESULTS: Although there was substantial intrapatient variability, there was no difference in the area under the concentration-time curve [AUC(0-8hr)] measured at day 21 compared with the steady-state AUC(0-8hr) estimated from day 1 pharmacokinetic parameters (p = 0.64). Degree of neutropenia was best predicted by the estimated duration that steady-state plasma etoposide concentrations were maintained above 1 microgram/ml (t > 1 microgram/ml) rather than peak plasma concentrations, AUC(0-8hr), dosage, or other patient characteristics. Assuming a bioavailability of the oral solution of approximately 50%, the median etoposide systemic clearance was 21.4 ml/min/m2, a value similar to clearance estimates after intravenous etoposide in pediatric populations. CONCLUSION: We conclude that a parameter reflective of etoposide systemic exposure (t > 1 microgram/ml) correlates more strongly with neutropenia than does dosage or other patient characteristics.

Administration, Oral↗
PubMed1990

Modelling human tibia structural vibrations.

Mode shapes and natural frequencies of human long bones play an important role in the interpretation, prediction and control of their dynamic response to external mechanical loads. This paper describes an experimental and theoretical study of free vibrations in an excised human tibia. Experimentally, seven tibial natural frequencies in the range 0-3 kHz were identified through measured structural transfer functions. Theoretically, a beam type Finite Element model of a human tibia is suggested. Unknown parameters in this model are determined by a Bayesian parameter estimation approach, by which very fine model/observation-accordance was achieved with realistic parameter estimates. A sensitivity analysis of the model confirms that the human tibia in a vibrational sense is more uniform than its complicated geometry would immediately suggest. Accordingly, two simple tibia models are identified, based on uniform beam theory with inclusion of shear deformations.

Biomechanical Phenomena↗
PubMed1996

On the interpretation of certainty factors in expert systems.

Despite the strong theoretical foundation the Bayesian probabilistic approach to model uncertainty in medicine meets many difficulties at the implementation step. One of these difficulties is related to a large amount of conditional probabilities to be assessed and in many cases this task was recognised to be practically insoluble. The MYCIN certainty factors model is a widely distributed pragmatical approach for modeling reasoning under uncertainty that substantially simplifies the problem, at the sacrifice of theoretical soundness. One can determine certainty factors as a function of prior and posterior probability. However, this approach is only consistent with the modularity axiom for certainty factors for tree-structure inference networks, which is rarely true for practical applications. In this paper we abandon the requirement of a direct probabilistic interpretation of certainty factors and build a model of propagation of uncertainty in terms of absolute belief and belief updates. We describe our model for propagating uncertainty in terms of matrix multiplication with specifically defined addition and multiplication which correspond to parallel and sequential combinations of certainty factors. It is possible to define these operations in such a manner that they form a field, and therefore to obtain some useful properties. Finally we present a method of determining certainty factors from statistical data using nonlinear regression and illustrate it with a leukemia diagnostics problem.

Artificial Intelligence↗
PubMed2006

Geographic variability in alcohol-related crashes in response to legalized Sunday packaged alcohol sales in New Mexico.

On July 1, 1995 the state of New Mexico lifted its ban on Sunday packaged alcohol sales. Legislation lifting the ban included a local option allowing individual communities within the state to hold an election to reinstitute the ban on Sunday packaged alcohol sales. Previous research has shown a clear statewide increase in alcohol-related crash and crash fatality rates after the ban was lifted. The goal of this study is to measure county-level variability in changes in alcohol-related crash rates while adjusting for county socio-demographic characteristics, spatial patterns in crash rates and temporal trends in alcohol-related crash rates. Bayesian hierarchical binomial regression models were fit to the observed quarterly crash counts for all counties between July 1, 1990 and June 30, 2000. Results show marked variability in the impact of legalized Sunday packaged alcohol sales on alcohol-related crash rates. Relative risks of an alcohol-related crash for the post-repeal versus pre-repeal period vary across counties from 1.04 to 1.90. Counties with older population suffered a greater negative impact of legalized Sunday packaged alcohol sales. Counties with communities that quickly passed the local option to re-ban packaged sales on Sundays were able to mitigate most of the deleterious impact of increased alcohol availability that was observed across the state.

Accidents, Traffic↗
PubMed2025

Leveraging functional annotations to map rare variants associated with Alzheimer disease with gruyere.

Increased availability of whole-genome sequencing (WGS) has facilitated the study of rare variants (RVs) in complex diseases. Multiple RV association tests are available to study the relationship between genotype and phenotype, but most do not fully leverage the availability of variant-level functional annotations. We propose genome-wide rare variant enrichment evaluation (gruyere), an empirical Bayesian framework that complements existing methods by learning global, trait-specific weights for functional annotations to improve variant prioritization. We apply gruyere to WGS data from the Alzheimer's Disease Sequencing Project to identify Alzheimer disease (AD)-associated genes and annotations. Growing evidence suggests that the disruption of microglial regulation is a key contributor to AD risk, yet existing methods have not examined rare non-coding effects that incorporate such cell-type-specific information. To address this gap, we (1) define per-gene non-coding RV test sets using predicted enhancer and promoter regions in microglia and other brain cell types (oligodendrocytes, astrocytes, and neurons) and (2) include cell-type-specific variant effect predictions (VEPs) as functional annotations. gruyere identifies 13 significant genetic associations not detected by other RV methods, four of which remain significant in omnibus tests. We find that deep-learning-based VEPs for splicing, transcription factor binding, and chromatin state are highly predictive of functional non-coding RVs. Our study establishes a robust framework incorporating functional annotations, coding RVs, and cell-type-associated non-coding RVs to perform genome-wide association tests, uncovering AD-relevant genes and annotations.

Alzheimer Disease↗