SEARCH · PubMed Health

Results for “Bayesian analysis”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 793 records · Page 44Linked to original sources

PubMed2004

Bayesian methods for analysis of binary outcome data in cluster randomized trials on the absolute risk scale.

A Bayesian hierarchical modelling approach to the analysis of cluster randomized trials has advantages in terms of allowing for full parameter uncertainty, flexible modelling of covariates and variance structure, and use of prior information. Previously, such modelling of binary outcome data required use of a log-odds ratio scale for the treatment effect estimate and an approximation linking the intracluster correlation (ICC) to the between-cluster variance on a log-odds scale. In this paper we develop this method to allow estimation on the absolute risk scale, which facilitates clinical interpretation of both the treatment effect and the between-cluster variance. We describe a range of models and apply them to data from a trial of different interventions to promote secondary prevention of coronary heart disease in primary care. We demonstrate how these models can be used to incorporate prior data about typical ICCs, to derive a posterior distribution for the number needed to treat, and to consider both cluster and individual level covariates. Using these methods, we can benefit from the advantages of Bayesian modelling of binary outcome data at the same time as providing results on a clinically interpretable scale.

Bayes Theorem↗

PubMed2022

Comparison on Major Gene Mutations Related to Rifampicin and Isoniazid Resistance between Beijing and Non-Beijing Strains of Mycobacterium tuberculosis: A Systematic Review and Bayesian Meta-Analysis.

Objective: The Beijing strain of Mycobacterium tuberculosis (MTB) is controversially presented as the predominant genotype and is more drug resistant to rifampicin and isoniazid compared to the non-Beijing strain. We aimed to compare the major gene mutations related to rifampicin and isoniazid drug resistance between Beijing and non-Beijing genotypes, and to extract the best evidence using the evidence-based methods for improving the service of TB control programs based on genetics of MTB. Method: Literature was searched in Google Scholar, PubMed and CNKI Database. Data analysis was conducted in R software. The conventional and Bayesian random-effects models were employed for meta-analysis, combining the examinations of publication bias and sensitivity. Results: Of the 8785 strains in the pooled studies, 5225 were identified as Beijing strains and 3560 as non-Beijing strains. The maximum and minimum strain sizes were 876 and 55, respectively. The mutations prevalence of rpoB, katG, inhA and oxyR-ahpC in Beijing strains was 52.40% (2738/5225), 57.88% (2781/4805), 12.75% (454/3562) and 6.26% (108/1724), respectively, and that in non-Beijing strains was 26.12% (930/3560), 28.65% (834/2911), 10.67% (157/1472) and 7.21% (33/458), separately. The pooled posterior value of OR for the mutations of rpoB was 2.72 ((95% confidence interval (CI): 1.90, 3.94) times higher in Beijing than in non-Beijing strains. That value for katG was 3.22 (95% CI: 2.12, 4.90) times. The estimate for inhA was 1.41 (95% CI: 0.97, 2.08) times higher in the non-Beijing than in Beijing strains. That for oxyR-ahpC was 1.46 (95% CI: 0.87, 2.48) times. The principal patterns of the variants for the mutations of the four genes were rpoB S531L, katG S315T, inhA-15C > T and oxyR-ahpC intergenic region. Conclusion: The mutations in rpoB and katG genes in Beijing are significantly more common than that in non-Beijing strains of MTB. We do not have sufficient evidence to support that the prevalence of mutations of inhA and oxyR-ahpC is higher in non-Beijing than in Beijing strains, which provides a reference basis for clinical medication selection.

Isoniazid↗

PubMed2000

Bayesian accelerated failure time analysis with application to veterinary epidemiology.

Standard methods for analysing survival data with covariates rely on asymptotic inferences. Bayesian methods can be performed using simple computations and are applicable for any sample size. We propose a practical method for making prior specifications and discuss a complete Bayesian analysis for parametric accelerated failure time regression models. We emphasize inferences for the survival curve rather than regression coefficients. A key feature of the Bayesian framework is that model comparisons for various choices of baseline distribution are easily handled by the calculation of Bayes factors. Such comparisons between non-nested models are difficult in the frequentist setting. We illustrate diagnostic tools and examine the sensitivity of the Bayesian methods.

Abortion, Veterinary↗

PubMed2003

Comparison of the dose-response relationships of 2 lipid-lowering agents: a Bayesian meta-analysis.

BACKGROUND: Comparing the dose-response of a new drug to that of a previously studied drug can aid in understanding their relative potencies. Two dose-finding studies addressed the effect of a new drug, rosuvastatin, on its ability to decrease low-density lipoprotein cholesterol (LDL-C) levels. One of these studies included 2 doses of atorvastatin, and substantial additional information is available in the literature about the effect of atorvastatin on LDL-C level lowering. METHODS: The 2 dose-finding studies of rosuvastatin considered otherwise healthy patients who had hypercholesterolemia. Comparable studies of atorvastatin were identified via a MEDLINE search in December 1999. Multiple reviewer consensus identified 15 of 41 studies on atorvastatin published since 1996 that met these selection criteria: reporting of LDL-C level change from baseline at least 6 weeks after treatment initiation, doses administered, and treatment group sizes. Eligible populations had clinical evidence of hypercholesterolemia. We excluded studies with patients who had severe illness or a previous history of transplantation. Data extraction of the mean, sample sizes, and SDs (or CIs) by dose was carried out independently by multiple reviewers. We combined the results from the various studies with Bayesian hierarchical modeling and analyzed them with Markov chain Monte Carlo techniques. RESULTS: Combining this study and literature results substantially increased the power to compare the dose-response relationships of rosuvastatin and atorvastatin. Rosuvastatin reduced LDL-C level by an estimated 10 to 17 percentage points more than atorvastatin when both were given at the same dose. Approximately one quarter of the dose of rosuvastatin achieved about the same magnitude of LDL-C level reduction as atorvastatin at dosages as high as 80 mg. This finding does not imply a 4-fold difference in efficacy overall and specifically does not describe the results at higher dosage levels. CONCLUSIONS: Bayesian meta-analysis of results from related studies allows the comparison of the dose-response relationships of 2 drugs, better estimates of a particular dose-response relationship within an individual study, and the expression of relative benefits (of dose and drug) in terms of probabilities. Explicitly comparing a study's results with historical data using Bayesian meta-analysis allows clinicians to view the study in the larger context of medical research.

Anticholesteremic Agents↗

PubMed2006

Major gene detection for fusiform rust resistance using Bayesian complex segregation analysis in loblolly pine.

The presence of major genes affecting rust resistance of loblolly pine was investigated in a progeny population that was generated with a half-diallel mating of six parents. A Bayesian complex segregation analysis was used to make inference about a mixed inheritance model (MIM) that included polygenic effects and a single major gene effect. Marginalizations were achieved by using Gibbs sampler. A parent block sampling by which genotypes of a parent and its offspring were sampled jointly was implemented to improve mixing. The MIM was compared with a pure polygenic model (PM) using Bayes factor. Results showed that the MIM was a better model to explain the inheritance of rust resistance than the pure PM in the diallel population. A large major gene variance component estimate (> 50% of total variance), indicated the existence of major genes for rust resistance in the studied loblolly pine population. Based on estimations of parental genotypes, it appears that there may be two or more major genes affecting disease phenotypes in this diallel population.

Basidiomycota↗

PubMed2005

Efficacy of inactivated hepatitis A vaccine in HIV-infected patients: a hierarchical bayesian meta-analysis.

Patients with human immunodeficiency virus-1 (HIV) have elevated risk for hepatitis A virus (HAV) coinfection. Sequelae from coinfection include increased risk of liver-related morbidity and mortality. This study synthesizes the results of trials measuring response to HAV vaccine in HIV-infected patients using Bayesian meta-analysis methodologies. PubMed, OhioLINK/Medline, and other sources were used to search for studies analyzing response to HAV vaccine in HIV-infected patients. Studies were evaluated for quality. A Bayesian hierarchical random-effects model was used to estimate overall response to vaccine. Between-study variance was calculated. Sensitivity analyses were conducted to determine the potential for bias. The literature search yielded eight studies for inclusion in the meta-analysis, with a combined total of 458 patients. Observed proportions of response in individual studies ranged from 50 to 95%. The intention-to-treat meta-analysis estimated a combined proportion of HIV+ patients responding to vaccine of 64% (95% CI 52-75%). Heterogeneity between studies was significant. The overall response rate to HAV vaccine in HIV-infected patients is lower than typically cited. Up to 1/2 of HIV-infected patients may be nonresponders. Future research will be required to better understand the correlates of response.

Bayes Theorem↗

PubMed2003

Hemodynamic segmentation of MR brain perfusion images using independent component analysis, thresholding, and Bayesian estimation.

Dynamic-susceptibility-contrast MR perfusion imaging is a widely used imaging tool for in vivo study of cerebral blood perfusion. However, visualization of different hemodynamic compartments is less investigated. In this work, independent component analysis, thresholding, and Bayesian estimation were used to concurrently segment different tissues, i.e., artery, gray matter, white matter, vein and sinus, choroid plexus, and cerebral spinal fluid, with corresponding signal-time curves on perfusion images of five normal volunteers. Based on the spatiotemporal hemodynamics, sequential passages and microcirculation of contrast-agent particles in these tissues were decomposed and analyzed. Late and multiphasic perfusion, indicating the presence of contrast agents, was observed in the choroid plexus and the cerebral spinal fluid. An arterial input function was modeled using the concentration-time curve of the arterial area on the same slice, rather than remote slices, for the deconvolution calculation of relative cerebral blood flow.

Adolescent↗

PubMed2004

A Bayesian meta-analysis of the effects of administering an intra-vaginal (CIDR) device in combination with other hormones on the reproductive performance of cycling, anoestrous and inseminated cows.

AIMS: To evaluate the effectiveness of treatment programmes that included controlled internal drug-releasing (CIDR) devices containing progesterone (P4) in improving synchrony of oestrus, and conception and pregnancy rates in cycling, anoestrous and inseminated dairy cows, using meta-analysis. To describe the difference in response between cycling and anoestrous cows to CIDR-based synchrony programmes. METHODS: Scientific papers written in the English language between 1989 and 2002 that investigated the effects of treatment programmes including CIDR devices on reproductive performance in dairy heifers or lactating dairy cows were identified using a computerised literature search. The criteria for inclusion incorporated evidence that treatment allocation was completely randomised; the population studied was lactating dairy cows; and that data were available on submission, conception and pregnancy rates and their associated measures of variability. Reproductive outcomes from 25 synchrony trials (total n=11,058 cows) were analysed. Summary measures of the effect of treatment on reproductive outcome were assessed using fixed- and random-effects Bayesian meta-analysis models. RESULTS: Treatment programmes including a CIDR device increased the risk of submission in cycling cows (predicted Bayesian RR=2.86, 95% credible interval=1.46-5.67). Compared with controls, synchrony programmes including CIDR devices in cycling dairy cows had no effect on the risk of conception to first service post-treatment (predicted Bayesian RR=1.00, 95% credible interval=0.80-1.24). Compared with controls, synchrony programmes including CIDR devices had no effect on the risk of pregnancy throughout the mating period (predicted Bayesian RR=1.02, 95% credible interval=0.89-1.17). In anoestrous cows, CIDR treatment had no effect on the risk of conception to first service post-treatment and no effect on the risk of pregnancy throughout the mating period, compared with anoestrous, untreated controls (predicted Bayesian RR=0.91 and 0.97, respectively; 95% credible interval=0.68-1.26 and 0.59-1.60, respectively). CONCLUSION: The results of this meta-analysis showed that synchrony programmes using CIDR devices combined with other hormones reliably enhanced submission rates in lactating dairy cows. The relatively small number of trials with data suitable for analysis and the heterogeneity of results at the individual trial level limited our ability to confirm either a beneficial or deleterious effect of treatment on conception or pregnancy rates. Further randomised, controlled trials to evaluate the effectiveness of this form of reproductive therapy in commercial dairy farms are needed.

Journal Article↗

PubMedDate not supplied

The impact of prophylactic axillary node dissection on breast cancer survival--a Bayesian meta-analysis.

BACKGROUND: Because of the general acceptance of the NSABP B-04 study, prophylactic axillary node dissection for women with clinically negative axillae is considered diagnostic, but not therapeutic, by many oncologists. Nevertheless, several authors have shown that B-04 did not include enough patients to exclude a small survival advantage. METHODS: A Bayesian meta-analysis of the available literature was performed comparing standard treatment to standard treatment without axillary node dissection. Six randomized controlled trials were identified, consisting of nearly 3000 patients and spanning four decades. RESULTS: All six trials showed that prophylactic axillary node dissection improved survival, ranging from 4% to 16%, corresponding to a risk reduction of 7%-46%. Combining the six trials showed an average survival benefit of 5.4% (95% CI = 2.7-8.0%, probability of survival benefit > 99.5%). Adjusting for biases in the individual studies did not alter the conclusions, nor did subset analysis of Stage I patients. CONCLUSIONS: Axillary node dissection improves survival in women with operable breast cancer. Nevertheless, two important limitations of this analysis are noteworthy. Few of the patients in the six trials had T1a tumors, so extrapolation of these results to this subset (and those with nonpalpable tumors) may be inappropriate. Essentially no patients in the six trials were treated with adjuvant therapy, as contrasted to current clinical practice. It is possible that the risk reduction seen in this meta-analysis may be diminished in patients receiving adjuvant chemotherapy. Despite these limitations, this study suggests that axillary dissection should be performed in most women with palpable tumors for diagnostic, as well as therapeutic, purposes.

Axilla↗

PubMed1984

Medical diagnosis aboard submarines. Use of a computer-based Bayesian method of analysis in an abdominal pain diagnostic program.

The medical issues that arise in the isolated environment of a submarine can occasionally be grave. While crewmembers are carefully screened for health problems, they are still susceptible to serious acute illness. Currently, the submarine medical department representative, the hospital corpsman, utilizes a history and physical examination, clinical acumen, and limited laboratory testing in diagnosis. The application of a Bayesian method of analysis to an abdominal pain diagnostic system utilizing an onboard microcomputer is described herein. Early results from sea trials show an appropriate diagnosis in eight of 10 cases of abdominal pain, but the program should still be viewed as an extended "laboratory test" until proved effective at sea.

Abdomen, Acute↗

PubMed1996

Bayesian meta-analysis, with application to studies of ETS and lung cancer.

Meta-analysis enables researchers to combine the results of several studies to assess the information they provide as a whole. It has been used to give a systematic overview of many areas in which data on a possible association between an exposure and an outcome have been collected in a number of studies but where the overall picture remains obscure, both as to the existence or size of the effect. This paper outlines some innovations in meta-analysis, based on using Markov chain Monte Carlo (MCMC) techniques for implementing Bayesian hierarchical models, and compares these with a more well-known random effects (RE) model. The new techniques allow different aspects of variation to be incorporated into descriptions of the association, and in particular enable researchers to better quantify differences between studies. Both the classical and Bayesian methods are applied, in this paper, to the current collection of studies of the association between incidence of lung cancer in female never-smokers and exposure to environmental tobacco smoke (ETS), both in the home through spousal smoking and in the workplace. In this paper it is demonstrated that compared with the RE model, the Bayesian methods: (a) allow more detailed modeling of study heterogeneity to be incorporated; (b) are relatively robust against a wide choice of specifications of such information on heterogeneity; (c) allow for more detailed and satisfactory statements to be made, not only about the overall risk but about the individual studies, on the basis of the combined information. For the workplace exposure data set, the Bayesian methods give a somewhat lower overall estimate of relative risk of lung cancer associated with ETS, indicating the care that needs to be taken in using point estimates based on any one method of analysis. On the larger spousal data set the methods give similar answers. Some of the other concerns with meta-analysis are also considered. These include: consistency between different geographic areas (Asia and the United States), and our studies show that Bayesian methods permit an account of the overall picture to be taken, thus improving the ability to estimate accurately in the subgroups; and publication bias which, as shown with the spousal exposure data, may lead to an inflated excess risk.

Air Pollution, Indoor↗

PubMed2006

Variations in primary open-angle glaucoma prevalence by age, gender, and race: a Bayesian meta-analysis.

PURPOSE: To quantify the variation in primary open-angle glaucoma (OAG) prevalence with age, gender, race, year of publication, and survey methodology. METHODS: Medline, EMBASE, and PubMed were searched for studies of OAG prevalence. Studies with defined population samplings were sought. Forty-six published observational studies of OAG prevalence (103,567 participants with 2509 cases of OAG) were identified for inclusion in the systematic review and meta-analysis. Data on the number of people and the number of cases of OAG by age, race, and gender were sought for each study. Additional information was obtained regarding whether the definition of glaucoma relied on raised intraocular pressure (IOP) and whether visual field examination was performed routinely on all individuals. Bayesian meta-analysis was used to model the associations between the log odds of OAG and age, race, gender, year of publication, method of visual field testing, and effect of reliance on IOP in the definition of OAG. RESULTS: Black populations had the highest OAG prevalence at all ages, but the proportional increase in prevalence of OAG with age was highest in white populations. The odds ratio per decade increase in age was 2.05 in white populations (95% credible interval, 1.91 to 2.18), 1.61 (95% credible interval, 1.53 to 1.70) in black populations, and 1.57 (95% credible interval, 1.46 to 1.68) in Asian populations. The average estimated prevalence in those older than 70 years of age was 6% in white populations, 16% in black populations, and 3% in Asian populations. After adjusting for age, race, year of publication, and survey methods, men were 1.37 (95% credible interval, 1.22 to 1.53) times more likely than women to have OAG. The prevalence of OAG was one third lower in studies in which routine visual fields were not assessed and that used an IOP criterion in the definition of glaucoma; this effect was reduced to the null after adjustment for age, racial group, and year of publication. CONCLUSIONS: Although black populations had the highest prevalence of OAG at all ages, white populations showed the steepest increase in OAG prevalence with age. Men were more likely than women to have OAG.

Adult↗

PubMed2001

Bayesian cost-effectiveness analysis. An example using the GUSTO trial.

A desirable element of cost-effectiveness analysis (CEA) modeling is a systematic way to relate uncertainty about input parameters to uncertainty in the computational results of the CEA model. Use of Bayesian statistical estimation and Monte Carlo simulation provides a natural way to compute a posterior probability distribution for each CEA result. We demonstrate this approach by reanalyzing a previously published CEA evaluating the incremental cost-effectiveness of tissue plasminogen activator compared to streptokinase for thrombolysis in acute myocardial infarction patients using data from the GUSTO trial and other auxiliary data sources. We illustrate Bayesian estimation for proportions, mean costs, and mean quality-of-life weights. The computations are performed using the Bayesian analysis software WinBUGS, distributed by the MRC Biostatistics Unit, Cambridge, England.

Bayes Theorem↗

PubMed2004

Clonazepam and lorazepam in acute mania: a Bayesian meta-analysis.

BACKGROUND: Clonazepam and lorazepam are used in the treatment of acute mania but trial results are conflicting. METHODS: Studies were identified by searching MEDLINE and EMBASE for lorazepam or clonazepam in acute mania between 1966 and 2000. Seven randomized controlled trials were found comparing clonazepam or lorazepam to placebo, haloperidol or lithium in acute mania. Data on 206 patients were analyzed. RESULTS: The heterogeneity of trial designs and the use of different comparators necessitated a Bayesian hierarchical meta-analysis with three models: (a) random trial effect and fixed treatment effects, (b) random trial and treatment effects, (c) random trial and treatment effects with trial variance unknown. With all models, clonazepam decreased psychopathology scores statistically significantly with the following standardized responses: model (a): 1.26 (95% predictive interval (PI) 0.33 to 2.28), model (b): 1.21 (95% PI 0.08 to 2.53), model (c): 1.41 (95% PI 0.12 to 2.67). Lorazepam did not yield statistically significant standardized responses for any of the three models: model (a): 0.79 (95% PI -0.29 to 1.89), model (b): 0.77 (95% PI -0.57 to 2.24) and model (c): 0.74 (-0.82 to 2.20). Haloperidol yielded statistically significant standardized responses in the three models but lithium effect was statistically significant only in model (a). Safety data were in line with the usual safety profile of benzodiazepines. LIMITATIONS: Trial designs were heterogenous and patient number was limited. CONCLUSIONS: This meta-analysis suggests that clonazepam is efficient and safe in the treatment of acute mania, but the results remain inconclusive for lorazepam.

Bayes Theorem↗

PubMed2001

Bayesian model selection: analysis of a survival model with a surviving fraction.

We describe a methodology for model comparison in a Bayesian framework as applied to survival with a surviving fraction. This is illustrated using a case study of a randomized and controlled clinical trial investigating time until recurrence of depression. Posterior distributions are simulated using Metropolis-within-Gibbs Markov chain methods. Models reflecting the effects of covariates on the log odds of being in the surviving fraction, the log of the hazard rate, as well as both and neither are compared. Bayes factors for comparing the models are obtained by using the bridge sampling method of calculating normalizing constants.

Algorithms↗

PubMed2007

The application of a Bayesian approach to the analysis of a complex, mechanistically based model.

The Bayesian approach has been suggested as a suitable method in the context of mechanistic pharmacokinetic-pharmacodynamic (PK-PD) modeling, as it allows for efficient use of both data and prior knowledge regarding the drug or disease state. However, to this day, published examples of its application to real PK-PD problems have been scarce. We present an example of a fully Bayesian re-analysis of a previously published mechanistic model describing the time course of circulating neutrophils in stroke patients and healthy individuals. While priors could be established for all population parameters in the model, not all variability terms were known with any degree of precision. A sensitivity analysis around the assigned priors used was performed by testing three different sets of prior values for the population variance terms for which no data were available in the literature: "informative", "semi-informative", and "noninformative", respectively. For all variability terms, inverse gamma distributions were used. It was possible to fit the model to the data using the "informative" priors. However, when the "semi-informative" and "noninformative" priors were used, it was impossible to accomplish convergence due to severe correlations between parameters. In addition, due to the complexity of the model, the process of defining priors and running the Markov chains was very time-consuming. We conclude that the present analysis represents a first example of the fully transparent application of Bayesian methods to a complex, mechanistic PK-PD problem with real data. The approach is time-consuming, but enables us to make use of all available information from data and scientific evidence. Thereby, it shows potential both for detection of data gaps and for more reliable predictions of various outcomes and "what if" scenarios.

Algorithms↗

PubMed1997

Grouped random effects models for Bayesian meta-analysis.

Meta-analysis refers to quantitative methods to combine results from independent studies so as to draw overall conclusions. Frequently, results from dissimilar studies are inappropriately combined, resulting in suspect inferential synthesis. We present a straightforward method to identify and address this problem through the development of grouped random effect models for meta-analysis. We examine 15 comparative studies that investigate the efficacy of a new anti-epileptic drug, progabide. The flexibility of this modelling scheme is exemplified by the result that the open studies support the efficacy of progabide while the closed studies support the reverse hypothesis. Bayesian approaches for meta-analysis are preferable because of the small number of studies prevalent in meta-analysis. We specify diffuse proper prior and hyperprior distributions to assure posterior propriety. We investigate sensitivity of the posterior to choice of prior. We use Gibbs sampling and the Metropolis algorithm to generate samples from the relevant posteriors. We analyse posterior summaries and plots of model parameters to suggest solutions to questions of interest.

Algorithms↗

PubMed1991

Pure absorption-mode spectra from Bayesian maximum entropy analysis of ion cyclotron resonance time-domain signals.

Fourier transform ion cyclotron resonance (FT/ICR) mass spectra are normally reported in the (phase-independent) magnitude-mode format. In principle, the absorption-mode format offers spectral resolution enhanced by a factor ranging from square root of 3 to 2 over the corresponding magnitude-mode spectrum obtained by discrete FT of the same unapodized time-domain data. However, an absorption-mode display is generally unsuitable in practice because of the auxiliary spectral peaks (Gibbs oscillations) resulting from the relatively long time delay between excitation and detection. Although the resulting large phase variation (up to 100 pi rad or more across the Nyquist spectral bandwidth) can be corrected exactly for a continuous time-domain signal, phase correction of a discrete time-domain signal results in Gibbs oscillations even for a perfectly phased absorption-mode spectrum. In this paper, we show that a Bayesian "maximum-entropy" analysis of simulated and experimental ion cyclotron resonance time-domain noisy signals can recover a precisely phased absorption-mode frequency-domain spectrum that is devoid of Gibbs oscillations, is less sensitive to noise, and offers improved mass accuracy over that obtained from a conventional magnitude-mode discrete fast Fourier transform (FFT) spectrum.

Fourier Analysis↗