PubMed Health⌕ Search

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 181 records · Page 10Linked to original sources
PubMed1983

A Bayesian analysis of capillary heterogeneity in the intact pig liver.

Published experimental data on the steady elimination of galactose by five isolated perfused pig livers are interpreted in terms of a model of hepatic uptake, in which the functional properties of the individual liver capillaries (hepatic sinusoids) are not identical. Kinetic parameters, including the Michaelis constant for the local enzyme-substrate interaction, are determined for each preparation on the basis of this model and are compared with previously obtained values based on an earlier model in which the sinusoids were assumed to be functionally identical. Posterior distributions of the degree of functional heterogeneity and the value of the Michaelis constant are given for the case where the livers are considered as a statistically homogeneous group. The degree of functional heterogeneity of the capillaries is found to be consistent with previous independent estimates.

Animals↗
PubMedDate not supplied

[Bayesian analysis of myocardial scintigraphy using 99mTc-Sn(II)-methylenediphosphonate and using 99mTc-Sn(II)-pyrophosphate].

Myocardial scintigraphy with 99mTc-Sn (II)-Methylenediphosphonate (MDP) and with 99mTc-Sn (II) pyrophosphate (PPi) was performed in 185 patients with proven acute myocardial infarction (90 with MDP; 95 with PPi), and in 65 subjects with acute chest pain of a different etiology (37 with MDP; 28 with PPi), during the first five days after the onset of illness. Sensitivity, specificity and accuracy of the procedure were higher with PPi (0.895, 0.893, 0.894) than with MDP (0.822, 0.865, 0.835) in the diagnosis of AMI. Based on the usual clinical electrocardiographic and biochemical criteria, the likelihood of AMI on the population studied with MDP was of 70.9% and with PPi of 77.2%. Application of Bayes' theorem showed an increase in the likelihood of AMI, when myocardial scintigraphy was positive, from 70.9% to 93.7% when MDP was used, and from 77.2% to 96.6 when PPi was the tracer, with incremental ruling in gaings of 22.8% and 19.4%) respectively. A normal scintigraphy, on the other hand, reduced the likelihood of AMI from 70.9% to 33.4% when MDP was used, and from 77.2% to 29.2% when PPi was the tracer, with respective incremental ruling-out gains of 37.5% and 48.0%. Although homogeinity between the populations studied with each tracer was not proven, existing practical, clinical and biochemical evidence allows the conclusion that PPi is a better agent than MDP in the study of patients with acute chest pain.

Adolescent↗
PubMed1997

Antimicrobial prophylaxis prior to shock wave lithotripsy in patients with sterile urine before treatment: a meta-analysis and cost-effectiveness analysis.

OBJECTIVES: To determine the efficacy and cost-effectiveness of routine antimicrobial prophylaxis prior to shock wave lithotripsy (SWL) in patients with a sterile pretreatment urine culture. METHODS: A structured MedLine search revealed eight prospective, randomized, controlled trials (RCTs) of active treatment versus placebo or no treatment (n = 885) and six clinical series (non-RCTs; n = 597) addressing the use of antimicrobial prophylaxis for SWL. A meta-analysis was performed on the eight RCTs, with the primary outcome being the diagnosis of a urinary tract infection (UTI) post-SWL. A cost analysis was performed comparing a prophylactic strategy (prophylaxis for every patient and treatment for post-SWL UTIs) with a treatment-only strategy for post-SWL UTIs using various antimicrobial combinations and the median probability of post-SWL UTIs determined by meta-analysis. RESULTS: The incidence of post-SWL UTIs ranged from 0% to 28% in the control group and from 0% to 7.7% in the patients who underwent prophylaxis. Combining the placebo/no-drug treatment arms in the six RCTs by meta-analysis (Bayesian analysis) resulted in a median probability of a post-SWL UTI of 5.7% (95% confidence interval [CI] 3.8% to 8.4%). For the drug treatment arms, the median probability of a UTI was 2.1% (95% CI 0.9% to 3.6%). Relative risk (RR) analysis resulted in an overall RR of post-SWL UTIs with prophylaxis versus without prophylaxis of 0.45 (95% CI 0.22 to 0.93) (P = 0.0005). Depending on the antimicrobial regimen used for prophylaxis and treatment, a prophylactic strategy added minimally to the overall treatment cost of SWL, and proved cost beneficial when taking into consideration serious UTIs requiring inpatient treatment. CONCLUSIONS: A policy of antibiotic prophylaxis prior to SWL in patients with sterile pretreatment urine cultures is efficacious in reducing the rate of post-SWL UTIs. Discounting inpatient episodes for sepsis and acute pyelonephritis, however, the strategy is not cost-effective. In contrast, using literature-derived incidence estimates for post-SWL urosepsis or pyelonephritis necessitating inpatient treatment, prophylaxis becomes both efficacious and cost-effective, and thus constitutes a dominant strategy.

Antibiotic Prophylaxis↗
PubMed1993

Predicting the probability of helper T cell immunodominant sites through discriminant analysis.

Bayesian discriminant analysis is used to predict whether or not a given protein segment will activate helper T cells. The predictor variables are drawn from the products of frequencies of amino acid residues. The model's predictive validity compares favourably with that of alternative modelling strategies, suggesting that this approach merits further investigation.

Amino Acid Sequence↗
PubMed1991

Meta-analysis for combining Bayesian probabilities.

Bayesian analysis is a method by which the reliability of diagnostic tests can be determined. It produces a probability of a patient having the disease given a positive test result (posterior probability). If more than one study of a given test's diagnostic accuracy is done, then how can we determine which of these studies has produced the most reliable posterior probability? Meta-analysis is a method whereby data from different studies can be combined. This paper proposes that meta-analysis more accurately estimates the true Bayesian posterior probability than other methods of data pooling.

Bayes Theorem↗
PubMed2001

Using Bayesian inference to perform meta-analysis.

Bayesian modeling offers an elegant approach to meta-analysis that efficiently incorporates all sources of variability and relevant quantifiable external information. It provides a more informative summary of the likely value of parameters after observing the data than do non-Bayesian approaches. This leads to direct probabilistic inference about model parameters such as the average treatment effect, the between-study variance, and individual study treatment effects. The latter are weighted averages of the common mean and individual study means with weights reflecting the amount of information provided by each study relative to the others. Homogeneity among these posterior study estimates indicates that pooling these studies is appropriate; heterogeneity suggests that some cause of between-study variation should be explored. The author describes the construction of such models and shows how to use them to estimate a common mean and regression slopes. Two examples illustrate the additional inferences available with the Bayesian methodology.

Angiotensin-Converting Enzyme Inhibitors↗
PubMed1990

Analysing clinical decision analyses.

We present a critical review of aspects of clinical decision analysis which uses an application to screening for familial intracranial aneurysms. The analysis is reported together with methods for assessing decision trees. These methods appear to be powerful checks on the usually rather intuitive way in which decision trees are built. The problem of assessing the uncertainty in the results of a decision analysis is discussed in detail. In practice, sensitivity analysis covers nearly every calculation apart from the standard evaluation of the decision tree. Different forms of sensitivity analysis are distinguished and given appropriate names: influence analysis, threshold analysis, full Bayesian analysis, Bayesian influence analysis, attribute analysis, generalization analysis and scenario analysis. The biostatistical community may well contribute to the much needed methodological improvement in decision analysis and its different forms of sensitivity analysis, especially if prepared to look beyond the standard statistical techniques.

Adult↗
PubMed1989

31P NMR Bayesian spectral analysis of rat brain in vivo.

Bayesian spectrum analysis for parameter estimation is a rigorous statistical (non-Fourier-based) method. Herein the Bayesian quadrature NMR model is introduced and applied to analysis of 31P NMR time domain data from in vivo rat brain. Immunity to both the brain spectrum "baseline hump" and the phase twist is demonstrated.

Animals↗
PubMed2001

Sensitivity analysis, Monte Carlo risk analysis, and Bayesian uncertainty assessment.

Standard statistical methods understate the uncertainty one should attach to effect estimates obtained from observational data. Among the methods used to address this problem are sensitivity analysis, Monte Carlo risk analysis (MCRA), and Bayesian uncertainty assessment. Estimates from MCRAs have been presented as if they were valid frequentist or Bayesian results, but examples show that they need not be either in actual applications. It is concluded that both sensitivity analyses and MCRA should begin with the same type of prior specification effort as Bayesian analysis.

Bayes Theorem↗
PubMed1997

Bayesian statistical analysis of protein side-chain rotamer preferences.

We present a Bayesian statistical analysis of the conformations of side chains in proteins from the Protein Data Bank. This is an extension of the backbone-dependent rotamer library, and includes rotamer populations and average chi angles for a full range of phi, psi values. The Bayesian analysis used here provides a rigorous statistical method for taking account of varying amounts of data. Bayesian statistics requires the assumption of a prior distribution for parameters over their range of possible values. This prior distribution can be derived from previous data or from pooling some of the present data. The prior distribution is combined with the data to form the posterior distribution, which is a compromise between the prior distribution and the data. For the chi 2, chi 3, and chi 4 rotamer prior distributions, we assume that the probability of each rotamer type is dependent only on the previous chi rotamer in the chain. For the backbone-dependence of the chi 1 rotamers, we derive prior distributions from the product of the phi-dependent and psi-dependent probabilities. Molecular mechanics calculations with the CHARMM22 potential show a strong similarity with the experimental distributions, indicating that proteins attain their lowest energy rotamers with respect to local backbone-side-chain interactions. The new library is suitable for use in homology modeling, protein folding simulations, and the refinement of X-ray and NMR structures.

Bayes Theorem↗
PubMedDate not supplied

Selected topics in statistical analysis of clinical research.

Statistical analysis usually is employed in the evaluation of clinical research studies. This paper reviews and makes recommendations in three areas frequently overlooked in the conduct of clinical research: power analysis, specification of a priori research hypotheses, and Bayesian analysis. Power analysis determines the number of subjects required to conduct a meaningful study and should be performed during the planning phase. Research and null hypotheses are essential elements of research design and should be specified prior to statistical analysis. Bayesian analysis can be used both to evaluate diagnostic tests and as an alternative to traditional statistical approaches for testing multiple hypotheses. Application of these methods is described and clinical examples are provided. The discussion is nontechnical and is directed toward the clinical researcher.

Aged↗