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.

SourceResearch connectionFrom yearThrough year

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

At least 217 records · Page 12Linked to original sources

PubMed2026

Impact of smoking on structural failure after arthroscopic rotator cuff repair: a systematic review and meta-analysis.

BACKGROUND: Rotator cuff tears cause significant shoulder pain and functional limitation. Arthroscopic rotator cuff repair improves symptoms, yet structural failure rates remain substantial. Smoking may impair tendon-to-bone healing, but clinical studies report mixed findings due to heterogeneous methodology. Therefore, a systematic synthesis of imaging-confirmed outcomes is needed to clarify the association between smoking and structural failure after arthroscopic rotator cuff repair. METHODS: This review followed PRISMA 2020 and was registered in PROSPERO (CRD420251246197). PubMed, Embase, Scopus, Web of Science, and the Cochrane Library were searched from inception to 12 December 2025. Comparative clinical studies of adults undergoing arthroscopic rotator cuff repair that reported imaging-confirmed structural integrity (magnetic resonance imaging or ultrasonography) at ≥6 months were included. Two reviewers independently screened studies, extracted data, and assessed quality using the Newcastle-Ottawa Scale. The primary outcome (structural failure) was pooled as risk ratios using a random-effects model with the restricted maximum likelihood estimator and Hartung-Knapp adjustment. Secondary continuous outcomes were synthesized using Bayesian random-effects models; subgroup, sensitivity, and meta-regression analyses explored heterogeneity. RESULTS: Ten cohort studies (1,683 shoulders) were included. Smoking was associated with a higher risk of imaging-confirmed structural failure (risk ratio 1.53; 95% confidence interval 1.13-2.08; P = .011) with low heterogeneity (I2 = 24.7%). Subgroup and sensitivity analyses supported robustness, with no evidence of effect modification by region, follow-up duration, tear size, or smoking definition. Meta-regression showed no significant influence of age, smoking prevalence, or diabetes prevalence on the pooled effect. Secondary outcomes (3 studies) suggested slightly lower postoperative American Shoulder and Elbow Surgeons scores among smokers, while visual analog scale pain scores and forward flexion showed no clear between-group differences. No publication-bias signals were detected for the primary outcome. CONCLUSION: Smoking is associated with a higher risk of imaging-confirmed structural failure after arthroscopic rotator cuff repair. Functional outcomes were broadly similar between groups, with only a small, likely clinically negligible reduction in American Shoulder and Elbow Surgeons scores among smokers. These findings support careful smoking history assessment and perioperative risk modification, including smoking cessation strategies.

Humans↗

PubMed1997

Estimates of genetic parameters for a test day model with random regressions for yield traits of first lactation Holsteins.

A model that contains both fixed and random linear regressions is described for analyzing test day records of dairy cows. Estimation of the variances and covariances for this model was achieved by Bayesian methods utilizing the Gibbs sampler to generate samples from the marginal posterior distributions. A single-trait model was applied to yields of milk, fat, and protein of first lactation Holsteins. Heritabilities of 305-d lactation yields were 0.32, 0.28, and 0.28 for milk, fat, and protein, respectively. Heritabilities of daily yields were greater than for 305-d yields and varied from 0.40 to 0.59 for milk yield, 0.34 to 0.68 for fat yield, and 0.33 to 0.69 for protein yield. The highest heritabilities were within the first 10 d of lactation for all traits. Genetic correlations between daily yields were higher as the interval between tests decreased, and correlations of daily yields with 305-d yields were greatest during midlactation.

Algorithms↗

PubMed1993

A Bayesian approach to measurement error problems in epidemiology using conditional independence models.

Risk factors used in epidemiology are often measured with error which can seriously affect the assessment of the relation between risk factors and disease outcome. In this paper, a Bayesian perspective on measurement error problems in epidemiology is taken and it is shown how the information available in this setting can be structured in terms of conditional independence models. The modeling of common designs used in the presence of measurement error (validation group, repeated measures, ancillary data) is described. The authors indicate how Bayesian estimation can be carried out in these settings using Gibbs sampling, a sampling technique which is being increasingly referred to in statistical and biomedical applications. The method is illustrated by analyzing a design with two measuring instruments and no validation group.

Bayes Theorem↗

PubMedDate not supplied

Bayesian analysis of ROC curves using Markov-chain Monte Carlo methods.

The authors introduce a Bayesian approach to generalized linear regression models for rating data observed in the evaluation of a diagnostic technology. Such models were previously studied using a non-Bayesian approach. In a Bayesian analysis, the difficulties inherent in an ordinal rating scale are circumvented by using data-augmentation techniques. Posterior distributions for the regression parameters- and thereby for receiver operating characteristic (ROC) curve parameters and values, for the area under a ROC curve, differences between areas, etc.-may then be computed by Markov-chain Monte Carlo methods. Inferences are made in standard Bayesian ways. The methods are exemplified by a study of ultrasonography rating data for the detection of hepatic metastases in patients with colon or breast cancer (previously analyzed) and the results compared.

Bayes Theorem↗

PubMed1993

Generation of pharmacokinetic data during routine therapeutic drug monitoring: Bayesian approach vs. pharmacokinetic studies.

In three groups (each n = 12) of unselected hospitalized patients treated either with digoxin, theophylline, or gentamicin routinely performed TDM measurement of trough steady-state plasma levels (+ peak levels in case of gentamicin) was combined with a pharmacokinetic study at steady state (multiple blood sampling during one dosing interval). Pharmacokinetic parameters (apparent volume of distribution Vd, total plasma clearance CL) needed for individualization of dosage were evaluated by the Bayesian approach and a model-(in)dependent pharmacokinetic program (TOPFIT). Comparison of both methods revealed some small differences in the pharmacokinetic parameters for all three drugs. Mean deviations of the Bayesian estimates from the pharmacokinetic calculations of the three drugs ranged between 20 and 38% for Vd and between 13 and 22% for CL, indicating that the Bayesian approach provided reliable pharmacokinetic estimates for individualizing drug dosage under routine conditions. Therefore, it is suggested that routine TDM combined with Bayesian-based analyses can be regarded as an alternative to pharmacokinetic studies in clinically relevant populations.

Adult↗

PubMed1996

Theophylline population pharmacokinetics from routine monitoring data in very premature infants with apnoea.

1. Theophylline is commonly used in neonatology for the treatment and prophylaxis of apnoea of prematurity, and during ventilator weaning. 2. NONMEM was used to study the population pharmacokinetics of intravenous and oral theophylline from retrospective drug monitoring data in 82 premature neonates, weighing < 1500 g at birth, and < or = 32 weeks gestational age. 3. Clearance (CL), volume of distribution (V), and oral bioavailability (F1) from liquid preparations were modelled alone, and under the influence of demographic and clinical covariates, assuming a 1-compartment model with first-order elimination. 4. The final population models with influential co-variates were as follows: CL (1h-1) = 0.0000123 *body weight (g) + 0.000377 *postnatal age (days); V (1) = 0.000937 *body weight (g); F = 0.918. 5. The CL was lower and V was higher than previously reported for less premature neonates, term babies, and older children. 6. Predictive performance of the population models was evaluated by Bayesian forecasting in a similar, but independent cohort of 30 infants. There was statistically insignificant bias and imprecision between measured and predicted serum theophylline concentrations. 7. Based on the validated population models, recommended maintenance theophylline dosages are provided for infants aged between 2 and 50 days, and weighing 700 to 2000 g.

Apnea↗

PubMed1996

A statistical model of transmission of Hib bacteria in a family.

The simultaneous estimation of family and community transmission rates as well as cure rates from panel data in a recurrent Hib (Haemophilus influenzae type b bacteria) infection is considered. An individual-based stationary Markov process model with constant hazards in two age groups is applied to describe recurrent asymptomatic Hib infection in a family with small children. The problem of estimation is solved in terms of the Bayesian posterior of the model parameters. The model is used to predict prevalence and incidence of Hib carriage in families as a function of the family size and age structure.

Adult↗

PubMed1967

Bayesian analysis of a three-component hierarchical design model.

Explore the source record for details and available documents.

Mathematics↗

PubMed2026

Insights Into the Structural Features, Codon Usage Patterns, and Phylogenetic Analysis in Neoniphon argenteus (Teleostei: Holocentriformes) Based on Complete Mitochondrial Genome.

Neoniphon argenteus, a widely distributed nocturnal coral reef fish in the family Holocentridae, plays an important role in maintaining coral reef ecosystem health, yet its phylogenetic position remains poorly resolved. To bridge this gap, we sequenced and analyzed the complete mitochondrial genome of a specimen from the South China Sea to characterize its structural features, codon usage patterns, and phylogenetic relationships. The 16,569 bp mitogenome (GenBank: PP190474.1) encodes 13 protein-coding genes (PCGs), 22 tRNAs, two rRNAs, and two non-coding regions, exhibiting a distinct A + T bias. All tRNAs fold into typical cloverleaf secondary structures except tRNA-Ser (AGN), which lacks the dihydrouridine (DHU) arm. The control region contains palindromic motifs (TACAT/ATGTA) capable of forming hairpin structures and five conserved sequence blocks, whereas the OL region harbors a conserved 5'-GCCGG-3' motif. RSCU analysis revealed 31 frequently used codons (RSCU > 1) with a pronounced preference for A/C-ending codons. The ΔRSCU method identified 10 candidate optimal codons (GCA, CAA, GAA, GGA, AUU, CUA, CCA, CGA, ACA, and GUC). Selection pressure analysis using EasyCodeML and site-specific models indicated that all PCGs are predominantly under purifying selection, with no significant evidence of pervasive positive selection. ND6 exhibited elevated pairwise Ka/Ks ratios (mean = 1.209 ± 0.047), consistent with reduced selective constraint rather than adaptive evolution. Phylogenetic analysis of 19 Holocentriformes species using maximum likelihood and Bayesian inference with partitioned models based on 13 PCGs and two rRNA genes (12S and 16S) assigned all taxa to two well-supported subfamilies (Holocentrinae and Myripristinae). Within Holocentrinae, Neoniphon species form a monophyletic clade nested within a paraphyletic Sargocentron, suggesting that the genus Sargocentron as currently defined is not monophyletic. This study provides useful baseline molecular data for further exploration of the evolutionary history of N. argenteus and other members of Holocentriformes.

Holocentridae↗

PubMed2026

Efficacy and safety of cannabinoid-based interventions for behavioral and cognitive symptoms in dementia: systematic review and meta-analysis.

BACKGROUND: Behavioral and cognitive symptoms are frequent in Alzheimer's disease and dementia, and available pharmacological options offer limited benefit. Cannabinoid-based therapies have been proposed as alternatives, but evidence remains inconclusive. METHODS: We systematically searched PubMed, Embase, Web of Science, and the Cochrane Library through November 2025 for randomized controlled trials evaluating cannabinoids in Alzheimer's disease or dementia. Primary outcomes were agitation measured by the Cohen-Mansfield Agitation Inventory (CMAI) and neuropsychiatric symptoms assessed by the Neuropsychiatric Inventory-Nursing Home version (NPI-NH). Secondary outcomes included cognition using the Mini-Mental State Examination (MMSE) and adverse events. Standardized Mean Differences (SMDs) and Risk Ratios (RRs) were synthesized using random-effects (REML) and Bayesian random-effects models. Risk of bias was evaluated with RoB 2, and certainty of evidence with GRADE. RESULTS: Nine trials (334 participants) met inclusion criteria. Cannabinoids did not improve CMAI (SMD -0.58, 95% CI -1.71 to 0.55; I2 = 84%), NPI-NH total (SMD -0.02, 95% CI -1.00 to 0.96; I2 = 67%), NPI-NH agitation (SMD -0.44, 95% CI -1.45 to 0.57; I2 = 48%), or MMSE (SMD 0.86, 95% CI -16.33 to 18.06; I2 = 96%). Bayesian posterior estimates were close to zero, supporting the absence of effect. Leave-one-out analyses reduced heterogeneity only after excluding influential trials but did not alter results. Certainty of evidence was moderate for behavioral outcomes and low for cognition. Overall adverse events were similar to placebo, while somnolence was more frequent with cannabinoids (RR 2.03, 95% CI 1.29-3.20). CONCLUSIONS: Cannabinoid-based therapies do not improve agitation, neuropsychiatric symptoms, or cognition in Alzheimer's disease and increase somnolence.

Humans↗

PubMed1997

A Bayesian formulation of the Kalman filter applied to the estimation of individual pharmacokinetic parameters.

A general method of Bayesian forecasting employing the dynamic linear model has been adapted to the problem of estimating individual pharmacokinetic parameters. The Bayesian forecasting method incorporates an efficient Kalman filter algorithm for updating pharmacokinetic parameter estimates when further observations are made. The Kalman filter is more general and flexible than other Bayesian methods currently used and simulation studies have demonstrated its practicality for three different pharmacokinetic models. The method serves as the basis for a computer program for general clinical use.

Algorithms↗

PubMed1991

Individualising gentamicin dosage regimens. A comparative review of selected models, data fitting methods and monitoring strategies.

The various components required for individualising clinical drug dosage regimens are reviewed, including a study of 3 types of fitting procedures, 2 types of gentamicin pharmacokinetic model and the utility of D-optimal times for obtaining serum gentamicin concentrations. The combination of the current Bayesian fitting procedure, the kslope pharmacokinetic model [in which the elimination rate constant (kel) can change from dose to dose with changing creatinine clearance] and the explicit measurement of the assay error pattern yielded predictions of future serum gentamicin concentrations which were (a) slightly better than those found using weighted nonlinear least squares; (b) somewhat better than those found with Bayesian fitting and a fixed-kel model; (c) better than those found using the traditional linear regression fitting procedure and a fixed kel model. D-Optimally timed pairs of concentrations also predicted future concentrations at least as well, and more cost effectively.

Data Interpretation, Statistical↗

PubMedDate not supplied

Open-loop-feedback control of serum drug concentrations: pharmacokinetic approaches to drug therapy.

Recent developments to optimize open-loop-feedback control of drug dosage regimens, generally applicable to pharmacokinetically oriented therapy with many drugs, involve computation of patient-individualized strategies for obtaining desired serum drug concentrations. Analyses of past therapy are performed by least squares, extended least squares, and maximum a posteriori probability Bayesian methods of fitting pharmacokinetic models to serum level data. Future possibilities for truly optimal open-loop-feedback therapy with full Bayesian methods, and conceivably for optimal closed-loop therapy in such data-poor clinical situations, are also discussed. Implementation of these various therapeutic strategies, using automated, locally controlled infusion devices, has also been achieved in prototype form.

Aged↗

PubMed2026

Exploring hormonal influences on nicotine craving and use across the perinatal period: A prospective longitudinal study.

INTRODUCTION: Perinatal nicotine use is common despite well-documented adverse consequences. We examined associations between reproductive-related hormones with nicotine craving and use during the perinatal period to identify potential novel intervention points. METHODS: All participants reported use of nicotine during the perinatal period. Participants were enrolled at gestational week ≥ 36 and followed to postpartum week 12 via daily surveys (i.e., nicotine craving via 100-point scale, dichotomous use) and weekly hormone measurement in saliva (cortisol, oxytocin) or dried blood spots (progesterone, estradiol, testosterone, dehydroepiandrosterone sulfate). Bayesian mixed-effects models accounted for within-person correlation while estimating hormone effects. RESULTS: Participants (n = 46) were 28.9 ± 4.9 years old. During follow-up, exclusive combustible cigarettes (n = 20), electronic nicotine delivery systems (ENDS; n = 13), or dual (n = 2) use was observed, with variability in use and craving across participants and over time. During pregnancy, higher oxytocin was linked to greater craving (β=16.31, 95% CI: 3.71, 28.83). Greater peripartum declines in oxytocin were associated with more craving (β=8.71, 95% CI: 0.75, 16.93) and use (β=1.13, 95% CI: 0.05, 2.43). During postpartum, lower estradiol was linked to more craving (β=-1.17, 95% CI: -2.15, -0.18) and use (β=-0.40, 95% CI: -0.76, -0.03). In models simultaneously evaluating all postpartum hormones, the lone meaningful association was between estradiol and craving (β=-1.66, 95% CI: -2.84, -0.48). CONCLUSIONS: The results of this study suggest that oxytocin and estradiol may contribute to the risk of perinatal nicotine use. Additional research is needed to replicate our observations in more diverse study samples and explore implications for clinical intervention.

Bayesian↗

PubMed1993

Evaluating the quality of a probabilistic diagnostic system using different inferencing strategies.

In this paper we describe the evaluation of a probabilistic diagnostic system for patients with renal mass. Three inference models: Multi-membership Bayesian (MB), Minimal Diagnosis (MD) and Bayesian Network (BN), and 72 patients are used to illustrate three interrelated measures of system performance: accuracy, reliability and discriminating power. The inferencing strategies we tested demonstrated the kind of trade-offs in the performance measures that can be expected from imperfect systems. Ultimately, the purpose and expected use of a system should dictate the relative importance ascribed to different aspects of system performance.

Adolescent↗

PubMed2025

Coupling of spectroscopy and nitrogen-oxygen isotopes unveils the mechanisms of dissolved organic matter and nitrate pollution in lakes within the agro-pastoral transition zone.

Lakes in arid and semi-arid regions are subjected to severe ecological stress, such as organic pollution, eutrophication, and salinization, due to climate change and human activities. This study investigates Chagannur Lake, a typical arid-region lake that is representative and ecologically sensitive in Northern China's agro-pastoral ecotone, to uncover its pollution characteristics and mechanisms. We employed fluorescence spectroscopy and stable isotope analysis to trace dissolved organic matter (DOM) and nitrate sources. The DOM composition was dominated by microbial metabolic byproducts and protein-like substances, suggesting that microbial processes are key to organic matter transformation. Source apportionment revealed that pollutants primarily originated from livestock and poultry manure (37.6 %), agricultural fertilizers (35.6 %), and soil erosion (24.7 %), with agricultural fertilizers contributing most significantly in the Gogstai River (63.3 %). A structural equation model (SEM) coupling spectral and mass spectrometric data revealed that microbial transformation significantly impairs the lake's self-purification capacity, thereby promoting pollutant accumulation (path coefficient = 0.91,*p < 0.05). Moreover, microbial processes link endogenous and exogenous pollution, a mechanism effectively traced by isotopic and fluorescence indices (path coefficient = 0.55, ⁎⁎p < 0.01). These findings enhance the understanding of pollution sources and transformation mechanisms in arid-region lakes and offer foundational theoretical support for policymakers engaged in pollution control strategies.

Lakes↗

PubMed1995

Bayesian forecasting of serum vancomycin concentrations in neonates and infants.

A dynamic pharmacokinetic model for i.v. vancomycin administration was developed and tested in 47 neonates and infants. Twenty-nine patients (Group 1), having two or more concentrations, were used to estimate population parameters by nonlinear least-squares analysis. Multiple stepwise linear regression techniques showed that estimated creatinine clearance, Clcr, and postnatal age were significant demographic factors related to vancomycin clearance (CL). No strong associations were found for the apparent volume of distribution. A one-compartment model was constructed using the associations of CLcr and postnatal age with vancomycin CL. Eighteen patients (Group 2), receiving 35 courses of vancomycin therapy, with both initial and subsequent sets of peak and trough concentrations, were used to test the predictive performance of the model with and without the use of Bayesian forecasting. Using only population-based parameters, the respective mean error (ME) (bias) and mean absolute error (MAE) (precision) for predicting subsequent peak concentrations were -1.20 and 3.89 mg/L and for trough concentrations, 0.83 and 2.23 mg/L, respectively. For the Bayesian method, these values were, respectively, 0.45 and 4.13 mg/L for peak concentrations and 1.55 and 2.40 mg/L for trough concentrations. When predicted concentrations occurred within 30 days of feedback concentrations, the Bayesian method tended to be slightly less biased and more precise than the population-based parameters. The opposite was true > 30 days of the initial set of feedback concentrations. The use of population-specific pharmacokinetic parameters and Bayesian forecasting should allow accurate dosage regimen design as well as minimize the need for monitoring serum vancomycin concentrations in neonates and young infants.

Bayes Theorem↗

PubMed1996

A technique for measuring epidemiologically useful features of birthweight distributions.

Birthweight distributions have been conceptualized as a predominant Gaussian distribution contaminated in the tails by an unspecified 'residual' distribution. Acknowledging this idea, we propose a technique for measuring certain features of birthweight distributions useful to epidemiologists: the mean and variance of the predominant distribution; the proportions of births in the low- and high-birthweight residual distributions, and the boundaries of support for these residual distributions. Our technique, based on an underlying multinomial sampling distribution, involves estimating parameters in a mixture model for the multinomial bin probabilities after having chosen the support of the residual distribution with a model selection criterion. A modest simulation study and experience with a few actual datasets indicate that use of a Bayesian information criterion (BIC) as model selection criterion is superior to use of Akaike's information criterion (AIC) in this application.

Analysis of Variance↗