SEARCH · PubMed Health

Results for “Bayesian modelling”

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 451 records · Page 25Linked to original sources

PubMed1993

A graphical user interface to facilitate patient-specific drug dosing.

This paper describes the development of a graphical user-interface (GUI) designed to facilitate the process of generating patient-specific drug doses using bayesian modelling software. The graphical user interface was developed in Visual Basic (Microsoft, Inc.) and runs under the Windows 3.1 (Microsoft, Inc.) operating system. Patient demographic data are stored in a relational database (Access, Microsoft, Inc.). The GUI and the database communicate via dynamic data exchange links. The largely object-oriented nature of the language allowed us to change the entire look and feel of the system with a few simple changes to the underlying code. Use of the relational database to store patient demographic information allows greater flexibility in searching for and displaying patient specific information. The GUI reduces the time required to enter data. The prototype has allowed us to experiment with different presentation methods, greatly improving the clinical acceptance of the dosing programs.

Computer Simulation↗

PubMed2006

Higher incidence of childhood-onset type 1 diabetes mellitus in remote areas: a UK regional small-area analysis.

AIMS/HYPOTHESIS: We investigated the association between the incidence of type 1 diabetes mellitus and remoteness (a proxy measure for exposure to infections) using recently developed techniques for statistical analysis of small-area data. SUBJECTS, MATERIALS AND METHODS: New cases in children aged 0 to 14 years in Northern Ireland were prospectively registered from 1989 to 2003. Ecological analysis was conducted using small geographical units (582 electoral wards) and area characteristics including remoteness, deprivation and child population density. Analysis was conducted using Poisson regression models and Bayesian hierarchical models to allow for spatially correlated risks that were potentially caused by unmeasured explanatory variables. RESULTS: In Northern Ireland between 1989 and 2003, there were 1,433 new cases of type 1 diabetes, giving a directly standardised incidence rate of 24.7 per 100,000 person-years. Areas in the most remote fifth of all areas had a significantly (p=0.0006) higher incidence of type 1 diabetes mellitus (incidence rate ratio=1.27 [95% CI 1.07, 1.50]) than those in the most accessible fifth of all areas. There was also a higher incidence rate in areas that were less deprived (p<0.0001) and less densely populated (p=0.002). After adjustment for deprivation and additional adjustment for child population density the association between diabetes and remoteness remained significant (p=0.01 and p=0.03, respectively). CONCLUSIONS/INTERPRETATION: In Northern Ireland, there is evidence that remote areas experience higher rates of type 1 diabetes mellitus. This could reflect a reduced or delayed exposure to infections, particularly early in life, in these areas.

Adolescent↗

PubMed2006

Variable performance of weaning-predictor tests: role of Bayes' theorem and spectrum and test-referral bias.

OBJECTIVE: We examined whether variation in reported reliability of the frequency-to-tidal volume ratio (f/V(T)) in predicting weaning success is explained by spectrum and test-referral bias, as reflected by variation in pretest probability of success. DESIGN: Two authors extracted data from all studies on reliability of f/V(T) as a weaning predictor. RESULTS: Prevalence of successful weaning in studies of f/V(T) revealed significant heterogeneity; mean success rate was 0.75. The heterogeneity and high success rate reflects occurrence of spectrum bias, suggested by the lower value of f/V(T) in subsequent studies than in the original report (77.4 vs. 89.1) and test-referral bias, suggested by lower specificity of f/V(T) in subsequent studies than in the original report (0.52 vs. 0.64). When data from studies in the ACCP Task Force's meta-analysis of studies on f/V(T) were entered into a Bayesian model with pretest probability (prevalence of success) as the operating point, observed posttest probabilities were closely correlated with values predicted by the original report on f/V(T): positive-predictive value r = 0.86 and negative-predictive value r = 0.82. Average sensitivity, the most precise measure of screening-test reliability, was 0.87 +/- 0.14 and average specificity 0.52 +/- 0.26. CONCLUSIONS: Much of the heterogeneity in performance of f/V(T) can be explained by variation in pretest probability of successful outcome, which may be secondary to spectrum and test-referral bias. The average sensitivity of 0.87 indicates that f/V(T) is a reliable screening test for successful weaning.

Bayes Theorem↗

PubMed2005

Evaluation of flood and landslide risk to the population of Italy.

We have compiled a database of floods and landslides that occurred in Italy between AD 1279 and 2002 and caused deaths, missing persons, injuries, and homelessness. Analysis of the database indicates that more than 50,593 people died, went missing, or were injured in 2580 flood and landslide events. Harmful events were inventoried in 26.3% of the 8103 Italian municipalities. Fatal events were most frequent in the Alpine regions of northern Italy and were caused by both floods and landslides. In southern Italy, landslides were the principal agents of fatalities and were most numerous in the Campania region. Casualties were most frequent in the autumn. Fast-moving landslides, including rock falls, rockslides, rock avalanches, and debris flows, caused the largest number of deaths. In order to assess the overall risk posed by these processes, we merged the historical catalogs and identified 2682 "hydrogeomorphological" events that triggered single or multiple landslides and floods. We estimated individual risk through the calculation of mortality rates for both floods and landslides and compared these rates to the death rates for other natural, medical, and human-induced hazards in Italy. We used the frequency distribution of events with fatalities to ascertain the magnitude and frequency of the societal risks posed by floods and landslides. We quantified these risks in a Bayesian model that describes the probabilities of fatal flood and landslide events in Italy.

Bayes Theorem↗

PubMed2006

Estimating the number of coding mutations in genotypic- and phenotypic-driven N-ethyl-N-nitrosourea (ENU) screens.

N-ethyl-N-nitrosourea (ENU) is a widely used mutagen in genotypic and phenotypic screens aimed at elucidating gene function. The high rate at which ENU induces point mutations raises the possibility that an observed phenotype may be to the result of another unidentified linked mutation. This article presents methods for estimating the probability of additional linked coding mutations (1) in a given region of DNA using both Poisson and Bayesian models and in (2) an F(1) animal exposed to ENU that has undergone b number of backcrosses. Applying these methods to the mouse data set of Quwailid et al., we estimate that the probability that a confounding mutation is linked to a cloned mutation when the candidate region is 5 Mb is very slim (p < 0.002). Where mutants are identified by genotypic methods, we show that backcrossing in the absence of marker-assisted selection is an inefficient means of eliminating linked confounding mutations.

Animals↗

PubMed2003

Relation of risk of systemic lupus erythematosus to west African admixture in a Caribbean population.

Risk of systemic lupus erythematosus (SLE) is higher in people of west African descent than in Europeans. The objective of this study was to distinguish between genetic and environmental explanations for this ethnic difference by examining the relationship of disease risk to individual admixture (defined as the proportion of the genome that is of west African ancestry); 124 cases of SLE and 219 matched controls resident in Trinidad were studied. Analysis of admixture was restricted to 52 cases and 107 controls who reported no Indian or Chinese ancestry. These individuals were typed with a panel of 26 single-nucleotide polymorphisms and five insertion/deletion polymorphisms chosen to have large allele frequency differentials between west African, European and Native American populations. A Bayesian model for population admixture, individual admixture and locus ancestry was fitted by Markov chain simulation. Mean west African admixture (M) was 0.81 in cases and 0.74 in controls (P=0.01). The risk ratio for SLE associated with unit change in M was estimated as 32.5 with a 95% confidence interval (CI) of 2.0-518. Adjustment for measures of socioeconomic status (household amenities in childhood and years of education) altered this risk ratio only slightly (adjusted risk ratio: 28.4, 95% CI 1.7-485). These results support an additive genetic model for the ethnic difference in risk of SLE between west Africans and Europeans, rather than an environmental explanation or an "overdominant" model in which risk is higher in heterozygous than in homozygous individuals. This conclusion lays a basis for localizing the genes underlying this ethnic difference in risk of SLE by admixture mapping.

Adult↗

PubMed2006

Bridge-it: a system for predicting implementation fidelity for school-based tobacco prevention programs.

Properly implemented school programs to prevent tobacco use and addiction can lower smoking prevalence up to 60%. However, numerous programs are not successful due to poor implementation. A system for estimating likelihood of future implementation fidelity of school-based prevention programs was tested using data collected at baseline and two year follow-up in 47 middle schools and high schools participating in the Texas Tobacco Prevention Initiative. The Bridge-It system includes an eight-factor, 36-item survey to analyze capacity for program implementation and a companion Bayesian model which provides estimations of likelihood of implementation fidelity several years after program initiation. The survey also asks about amount of implementing activity for each of the multiple components recommended in federal guidelines for school programs to prevent tobacco use. Criterion referenced cross-tabulations showed the system's forecast of implementation fidelity was correct in 74% of cases (p < .01). Model reliability was confirmed in regression analyses. Implementation fidelity at follow-up was predicted by the combination of the model's eight capacity factors at baseline. It includes program, implementation support, and non-program factors. Integration of the Bridge-It system, or comparable tools, into the dissemination and evaluation of school-based prevention programs can help to increase understanding of factors that influence implementation and provide guidance for capacity building. If administrators can identify at baseline schools likely to fall short of implementation goals, plans for resource allocation and provision of guidance, training, and technical assistance can be specifically tailored to identified needs.

Humans↗

PubMed2006

Humans ignore motion and stereo cues in favor of a fictional stable world.

As we move through the world, our eyes acquire a sequence of images. The information from this sequence is sufficient to determine the structure of a three-dimensional scene, up to a scale factor determined by the distance that the eyes have moved. Previous evidence shows that the human visual system accounts for the distance the observer has walked and the separation of the eyes when judging the scale, shape, and distance of objects. However, in an immersive virtual-reality environment, observers failed to notice when a scene expanded or contracted, despite having consistent information about scale from both distance walked and binocular vision. This failure led to large errors in judging the size of objects. The pattern of errors cannot be explained by assuming a visual reconstruction of the scene with an incorrect estimate of interocular separation or distance walked. Instead, it is consistent with a Bayesian model of cue integration in which the efficacy of motion and disparity cues is greater at near viewing distances. Our results imply that observers are more willing to adjust their estimate of interocular separation or distance walked than to accept that the scene has changed in size.

Computer Simulation↗

PubMed2005

Implementation of automated signal generation in pharmacovigilance using a knowledge-based approach.

Automated signal generation is a growing field in pharmacovigilance that relies on data mining of huge spontaneous reporting systems for detecting unknown adverse drug reactions (ADR). Previous implementations of quantitative techniques did not take into account issues related to the medical dictionary for regulatory activities (MedDRA) terminology used for coding ADRs. MedDRA is a first generation terminology lacking formal definitions; grouping of similar medical conditions is not accurate due to taxonomic limitations. Our objective was to build a data-mining tool that improves signal detection algorithms by performing terminological reasoning on MedDRA codes described with the DAML+OIL description logic. We propose the PharmaMiner tool that implements quantitative techniques based on underlying statistical and bayesian models. It is a JAVA application displaying results in tabular format and performing terminological reasoning with the Racer inference engine. The mean frequency of drug-adverse effect associations in the French database was 2.66. Subsumption reasoning based on MedDRA taxonomical hierarchy produced a mean number of occurrence of 2.92 versus 3.63 (p < 0.001) obtained with a combined technique using subsumption and approximate matching reasoning based on the ontological structure. Semantic integration of terminological systems with data mining methods is a promising technique for improving machine learning in medical databases.

Adverse Drug Reaction Reporting Systems↗

PubMed2005

Lung cancer in an urban area in Northern Italy near a coke oven plant.

Coke ovens are well-known sources of potentially carcinogenic air pollutants, but studies on resident populations are still poor. This study investigates the incidence of lung cancer near a coke oven in Cornigliano, a district of the Genoa municipality in Northern Italy. Genoa proper and one district similar to Cornigliano as regards socio-economic deprivation were selected as referents. Incidence data were drawn from the Ligurian Cancer Registry for 1986-1997 calendar period. Concentrations of pollutants related to the industrial activity (namely benzene, benzo[a]pyrene, PM(10), CO, NO(2) and SO(2)) were collected in selected locations before and after the coke oven closing. Spatial trend around the plant was assessed by Stone's test, while the pattern of risk across Cornigliano was evaluated via disease mapping in a Bayesian model. A gradient of air pollutants was observed around the coke oven, which disappeared after its closing. In Cornigliano, 158 lung cancer cases were observed in males and 28 in females. Only a marginal excess risk was observed versus the two selected referents, while a gradient in the areas close to the plant emerged among females. Disease mapping revealed another cluster of risk for both sexes in the Eastern part of the district, where a foundry was operative until the early 1980s. The excess risk for females is consistent with pollution measurements and with other epidemiological evidence. The geographic pattern of incidence suggests a role of industrial air pollution as a risk factor for lung cancer.

Adolescent↗

PubMed2006

A motion-dependent distortion of retinotopy in area V4.

When one element in an apparent motion sequence differs in color from the others, it is perceived as shifted along the motion trajectory. We examined whether V4 neurons encode the physical or perceived location of this "flashed" element by recording neuronal responses while monkeys viewed these stimuli. The retinotopic locus of V4 activity evoked by the flashed element shifted along the motion trajectory. The magnitude of the shift is consistent with the perceptual shift in humans viewing identical stimuli. This retinotopic distortion depended on the presence of a flashed element but was observed for both color-selective and non-color-selective neurons. The distortion was undiminished when the flashed element terminated the sequence, a condition that reduced the perceptual shift in humans. These findings are consistent with a Bayesian model of localization in which perceived location is derived from position signals optimally integrated across visual areas.

Action Potentials↗

PubMed2006

Resolution of uncertainty in prefrontal cortex.

Making optimal decisions in the face of uncertain or incomplete information arises as a common problem in everyday behavior, but the neural processes underlying this ability remain poorly understood. A typical case is navigation, in which a subject has to search for a known goal from an unknown location. Navigating under uncertain conditions requires making decisions on the basis of the current belief about location and updating that belief based on incoming information. Here, we use functional magnetic resonance imaging during a maze navigation task to study neural activity relating to the resolution of uncertainty as subjects make sequential decisions to reach a goal. We show that distinct regions of prefrontal cortex are engaged in specific computational functions that are well described by a Bayesian model of decision making. This permits efficient goal-oriented navigation and provides new insights into decision making by humans.

Adult↗

PubMed2007

Spatial analysis of bovine spongiform encephalopathy in Galicia, Spain (2000-2005).

In Spain, the first bovine spongiform encephalopathy (BSE) case was detected in 2000 in a cow born in the Galicia region (Northwestern Spain). From then and until October 2005, 590 cases were detected, 223 of them in Galicia. In 1994, meat and bone meal (MBM) was banned on ruminant feed and, in 1996, an EU decision mandating an overall change in MBM processing was implemented. This decision was gradually applied in the territory and not enforced before July 1998. The objective of this study was to explore clustering of BSE cases and estimate the standard incidence ratio (SIR) of BSE in Galicia. Our study was based on the BSE cases detected during the surveillance period 2000-2005 in the Galicia region. These cases were divided, based on birth date, into two periods: animals born from 1994 to July 1998, and those born after July 1998. We tested the role of cross-contamination on the geographical SIR distribution for both periods. Hierarchical Bayesian models were used to model the overdispersion and lack of independence of the SIR estimates. The geographical distribution of the standard incidence ratio of BSE between both periods was different. In the second period, the SIR was reduced in some areas. The reduction in these areas could be attributable to the changes in the processing of MBM. We did not find any statistical link between the poultry population and the standard incidence ratio, but pig population had a positive effect.

Animal Feed↗

PubMed2005

Assessing intervention effects in a community-based trial to reduce self-harm: a methodological case study.

This paper considers the assessment of the impact of a community-based randomized controlled trial to reduce repeat deliberate self-harm. It considers the drawbacks in simplistic applications of conventional significance testing procedures, as well as possible failures regarding the statistical assumptions underlying such tests. Instead, the paper considers how relevant prior information might be incorporated within a fully Bayesian-model-based assessment procedure. The model includes a latent trait approach to patient morbidity; controlling for morbidity and other patient characteristics enhances the impact of the intervention (measured by a hazard rate ratio). If allowance is made for external information (e.g. ethical approval of the treatment), the weight of evidence shifts towards a positive intervention effect.

Adolescent↗

PubMed2006

Rural habitat and risk of death in small areas of Southern Spain.

The purpose of this paper is to study the linkage between type of habitat and mortality from all causes in small areas of Southern Spain. An ecological study was conducted on 99,870 people who died between 1985 and 1999. The municipality was taken as the unit of analysis. Data analysis was carried out through hierarchical spatio-temporal bayesian models. Results show a 13.3% reduction in mortality rates among men and 14.1% among women in the most rural areas compared to more urban environments. The study demonstrates the usefulness of socio-demographic indices in small-area geographical analyses.

Bayes Theorem↗

PubMed2004

A Bayesian approach to prediction of stallion daily sperm output.

In equine breeding, the number of spermatozoa ejaculated is considered an important factor in fertility. Methods for predicting the number of spermatozoa have been derived from semen collection procedures. A once-daily collection period for 10 days is a standard recommendation to predict long-term daily sperm output (DSO). The first objective of this study was to determine the precision or repeatability of these DSO predictions. Semen was collected and evaluated daily during four periods for 10 days, for 15 different stallions. The analytical methods utilized hierarchal Bayesian modeling as implemented by Gibbs Sampling. The overall population model showed an initial decline in total sperm number of 1.54 billion spermatozoa per day until the observed mean change point of 4.71 days, at which time mean DSO was estimated at 5.28 billion spermatozoa per day. The hierarchal model showed standard deviations in DSO within-stallion of 0.67 billion spermatozoa per day and among-stallion of 1.86 billion spermatozoa per day. The study's second objective was to determine how testicular size affected DSO models. When the model was extended to include testicular size, the optimal prediction of DSO was that DSO = 0.79 + 0.018 x testicular size (in milliliters). Testicular size explained 36.5% of the among-stallion standard deviation in DSO, but was not significantly related to the mean number of collection-days required to reach DSO.

Animals↗

PubMed2004

Effects on orientation perception of manipulating the spatio-temporal prior probability of stimuli.

Spatial and temporal regularities commonly exist in natural visual scenes. The knowledge of the probability structure of these regularities is likely to be informative for an efficient visual system. Here we explored how manipulating the spatio-temporal prior probability of stimuli affects human orientation perception. Stimulus sequences comprised four collinear bars (predictors) which appeared successively towards the foveal region, followed by a target bar with the same or different orientation. Subjects' orientation perception of the foveal target was biased towards the orientation of the predictors when presented in a highly ordered and predictable sequence. The discrimination thresholds were significantly elevated in proportion to increasing prior probabilities of the predictors. Breaking this sequence, by randomising presentation order or presentation duration, decreased the thresholds. These psychophysical observations are consistent with a Bayesian model, suggesting that a predictable spatio-temporal stimulus structure and an increased probability of collinear trials are associated with the increasing prior expectation of collinear events. Our results suggest that statistical spatio-temporal stimulus regularities are effectively integrated by human visual cortex over a range of spatial and temporal positions, thereby systematically affecting perception.

Bayes Theorem↗

PubMed2004

Monophyly and relationships of wrens (Aves: Troglodytidae): a congruence analysis of heterogeneous mitochondrial and nuclear DNA sequence data.

The wrens (Aves: Troglodytidae) are a group of primarily New World insectivorous birds, the monophyly of which has long been recognized, but whose intergeneric relationships are essentially unknown. In order to test the monophyly of the group, and to attempt to resolve relationships among genera within it, sequences from the mitochondrial cytochrome b gene and the fourth intron of the nuclear beta-fibrinogen gene were obtained from nearly all genera of wrens, from their relatives as suggested by traditional taxonomy and DNA-DNA hybridization analyses, and from additional passerines. Maximum likelihood analysis of the two data sets yielded maximal congruence between independently derived estimates of relationship, outperforming a variety of weighted parsimony methods. Hierarchical likelihood ratio tests indicated that the two gene regions differed significantly in every estimated parameter of sequence evolution, and combined analysis of the two data sets was accomplished using a heterogeneous-model Bayesian approach. Independent and simultaneous analyses of both data sets supported monophyly of the wrens (excluding one recently added member, the monotypic genus Donacobius) and a sister-group relationship between wrens and the gnatcatchers (Polioptila). Additionally, strong support was found for paraphyly of the genus Thryothorus, and for a sister-group relationship between the genera Cistothorus and Troglodytes. Analyses of these data failed to resolve basal relationships within wrens, possibly due to ambiguity in rooting with a distant, species-poor outgroup. Analysis of the combined data for wrens alone yielded results which were largely congruent with relationships inferred using the complete data set, with the benefit of stronger support for relationships within the group. However, alternative rootings of this ingroup tree were weakly supported by nucleotide substitution data. Insertion-deletion events suggest that the genus Salpinctes may be sister to all other wrens.

Animals↗