SEARCH · PubMed Health

Results for “Models, Statistical”

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 1,459 records · Page 81Linked to original sources

PubMed2003

Using a modified Stroop task to implicitly discern the cognitive organization of alcohol expectancies.

Alcohol expectancies have been statistically modeled as memory networks that influence future consumption. To test the organization of expectancies suggested by these models, a modified Stroop color-naming task incorporated expectancy words associated in past research with heavy and light drinking. Light and heavy drinkers ink-named expectancy targets after being cued with an alcohol beverage word or a nonalcohol beverage word. Consistent with predictions derived from statistical models, heavy drinkers displayed significant interference when arousing expectancy words had been primed by an alcohol beverage word, whereas light drinkers displayed significant interference when sedating expectancy targets had been so primed. These results reinforce the idea that mediation o falcohol use by expectancies may be implicit as well as explicit.

Adolescent↗

PubMed2000

Flavour conditioning and alcohol: a multilevel model of individual differences.

Previous research shows that dependent drinkers respond more strongly to alcohol-related cues and suggests that alcohol cue-reactivity may be relevant to understanding dependence liability. However, a significant weakness in many studies is the fact that cue-reactivity is studied without actually conditioning subjects; responses to alcohol-related cues are simply assumed to be conditioned responses. The current report attempts to overcome this weakness by studying alcohol cue-reactivity following a flavour-conditioning procedure. A statistical model of individual differences in cue-reactivity was constructed using previous alcohol exposure, alcohol tolerance, and personality as predictor variables. Although there was no evidence for overall differences in subjective and psychophysiological responses to alcohol and soft-drink paired flavours, there were marked individual differences in responding to the different flavours. The statistical model showed that reward sensitivity (high extroversion, high neuroticism), heavier levels of drinking, and higher levels of tolerance to the intoxicating effects of alcohol were associated with lower levels of skin conductance in the presence of alcohol paired flavours.

Adult↗

PubMed2001

Multiple imputation for multivariate data with missing and below-threshold measurements: time-series concentrations of pollutants in the Arctic.

Many chemical and environmental data sets are complicated by the existence of fully missing values or censored values known to lie below detection thresholds. For example, week-long samples of airborne particulate matter were obtained at Alert, NWT, Canada, between 1980 and 1991, where some of the concentrations of 24 particulate constituents were coarsened in the sense of being either fully missing or below detection limits. To facilitate scientific analysis, it is appealing to create complete data by filling in missing values so that standard complete-data methods can be applied. We briefly review commonly used strategies for handling missing values and focus on the multiple-imputation approach, which generally leads to valid inferences when faced with missing data. Three statistical models are developed for multiply imputing the missing values of airborne particulate matter. We expect that these models are useful for creating multiple imputations in a variety of incomplete multivariate time series data sets.

Air Pollutants↗

PubMed1989

Clinical experience and predicting survival in coronary disease.

To study the accuracy with which long-term prognosis can be predicted in patients with coronary artery disease, prognostic predictions obtained from a large, diverse sample of practicing cardiologists were compared with predictions from a multivariable statistical model. Test samples of 10 patients each were selected from a large series of medically treated patients with significant coronary disease. Using detailed clinical summaries, 49 cardiologists each predicted the probability of 3-year survival and infarction-free survival for 10 patients. Cox regression models, developed using patients who were not in the test samples, were also used to predict corresponding outcome probabilities for each test patient. Overall, the model estimates of prognosis were significantly better than the doctors' predictions. The rank correlation of model predictions with 3-year survival was 0.60, compared with 0.52 for the physicians. Model predictions added significant prognostic information to the doctors' predictions, whereas the converse was not true. Where predictions were made by multiple doctors, the inter-physician variability was substantial. Neither practice characteristics nor extent of clinical experience significantly affected the physicians' predictive accuracy. In coronary artery disease, statistical models developed from carefully collected data can provide prognostic predictions that are more accurate than predictions of experienced clinicians made from detailed case summaries.

Coronary Disease↗

PubMed1996

An algorithm for the grading of activity in chronic hepatitis C. The METAVIR Cooperative Study Group.

Histological activity reflects the global assessment of basic necroinflammatory lesions and is a criterion of major importance in chronic hepatitis C. The aim of this study was to propose and test the accuracy of a simple algorithm that generates a single activity score based on basic pathological features. A panel of 10 pathologists reviewed 363 chronic hepatitis C liver biopsies and graded the activity of hepatitis according to their own experience (reference activity). Then, a consensual algorithm on the grading of activity was established by the 10 experts in a panel discussion. Finally, stepwise discriminant analysis was performed to define which basic features had been intuitively used in the reference activity (statistical activity). To test the accuracy of the algorithm, concordance between the activity defined by the algorithm and the reference activity was assessed. It was compared with concordance between the activity defined by the statistical model and the reference activity. The algorithm proposed by the panel for the grading of activity included piecemeal necrosis and lobular necrosis. Concordance between reference activity and activity defined by the algorithm was substantial (305 cases, 84%, kappa = .75). Discriminant analysis showed that piecemeal necrosis, lobular necrosis, and portal inflammation were independently used to grade the activity. Concordance between reference activity and activity defined by the statistical model was substantial (300 cases, 83%, kappa = .73), virtually identical to the concordance between reference activity and activity defined by algorithm. This study proposes a simple algorithm for the grading of activity in chronic hepatitis. Its accuracy is as high as that obtained using a statistical approach.

Algorithms↗

PubMed2006

Genotype-by-nutrient interactions assessed in European obese women. A case-only study.

BACKGROUND: The development of obesity is influenced by both genetic and environmental risk factors. Whereas changes in the environment appear to be responsible for the increasing prevalence of obesity, genetic factors interacting with environmental factors would contribute to explain obesity onset and severity. AIM: To explore epidemiologic genotype-by-nutrient interactions in obesity. METHODS: A total of 42 polymorphisms of 26 candidate genes for obesity were genotyped in 549 adult obese women recruited from eight European centres in a case-only study. The nutritional variables assessed in this study were the dietary fibre intake (grams per day), the ratio of dietary polyunsaturated fat to saturated fat (P:S ratio) and the percentage of energy derived from fat in the diet as calculated from a weighed three-day food record (%E). Under the assumption of genotype-nutrient independence in the population, the odds ratio calculated in a sample of obese women would indicate the existence of genotype-by-nutrient interactions, measured as deviations from the multiplicative effects of the genetic and the nutrient factors separately. RESULTS: No new but confirmaty evidences for genotype-by-nutrient interactions in obesity were detected in this case-only study. The test of interaction between fibre intake and the -514 C > T polymorphism of the hepatic lipase gene (LIPC) yielded P-values of 0.01 across different statistical models. Likewise, the -11377G > C polymorphism of the adiponectin gene (ADIPOQ) and the -681 C > G polymorphism of the PPARG3 gene might interact with the percentage of energy derived from fat in the diet for the development of obesity (P-values in the range of 0.01-0.05 across different statistical models). The P-values were not adjusted for multiple testing, so these results should be considered with caution. CONCLUSIONS: Although the use of obese-only samples is theoretically a useful approach to detect interactions, few genotype-by-nutrient interactions have been suggested in obese European women after the analysis of candidate polymorphisms and the selected nutrient variables. The most remarkable multiplicative interaction found in this study refers to the combination of the hepatic lipase gene polymorphism -514 C > T and fibre intake.

Adiponectin↗

PubMed2005

Cost-benefit, cost-effectiveness and cost-utility analyses of periodontitis prevention.

OBJECTIVE: The aim of this paper was to determine whether there is evidence that periodontitis prevention is economically justified. MATERIAL AND METHODS: The characteristics of economic assessments such as cost-benefit, cost-effectiveness and cost-utility analyses were first derived from the literature on health economy. A literature search was conducted using PubMed up to December 2004. Inclusion criteria required that economic analyses be based on scientific principles including a hypothesis, valid comparative groups as well as a cost/benefit, cost/effectiveness and cost/utility assessment. RESULTS: Only 14 papers were located, which included, in the broadest sense, economic parameters. From these papers, three were systematic reviews, three were randomized controlled studies, four were controlled studies, one was a longitudinal cohort study and three papers were based on statistical modelling. Only one paper reported actual costs for periodontal and dental treatment. Extensive programmes aimed at prevention of periodontal disease in a general population group showed no economic benefit. Adjunctive genetic/and or microbiological testing likewise showed no economic benefit. Economic assessments and real costs are not generally available in the literature. Statistical modelling suggested that non-surgical periodontal procedures are more economical compared with surgical interventions. The use of local delivery devices as an adjunct to Sc/RP showed no economic advantage. CONCLUSION: It is suggested that economic parameters as well as patient-centred outcomes be included in clinical trials. These data are essential for the appropriate allocation of resources for preventive measures on an individual patient and population base.

Anti-Infective Agents, Local↗

PubMedDate not supplied

Landscape metrics and estuarine sediment contamination in the mid-Atlantic and southern New England regions.

In a previously published study, quantitative relationships were developed between landscape metrics and sediment contamination for 25 small estuarine systems within Chesapeake Bay. These analyses have been extended to include 75 small estuarine systems across the mid-Atlantic and southern New England regions of the USA. Because of the different characteristics and dynamics of the estuaries across these regions, adjustment for differing hydrology, sediment characteristics, and sediment origins were included in the analysis. Multiple linear regression with stepwise selection was used to develop statistical models for sediment metals, organics, and total polycyclic aromatic hydrocarbons (PAHs). The landscape metrics important for explaining the variation in sediment metals levels (R2 = 0.72) were the percent area of nonforested wetlands (negative contribution), percent area of urban land, and point source effluent volume and metals input (positive contributions). The metrics important for sediment organics levels (R2 = 0.5) and total PAHs (R2 = 0.46) were percent area of urban land (positive contribution) and percent area of nonforested wetlands (negative contribution). These models included silt-clay content (metals) or total organic C (organics, total PAHs) of sediments and grouping by estuarine hydrology, suggesting the importance of sediment characteristics and hydrology in mitigating the influence of the landscape metrics on sediment contamination levels. The overall results from this study are indicative of how statistical models can be developed relating landscape metrics to estuarine sediment contamination for distributions of land cover and point source discharges.

Fresh Water↗

PubMed2005

Modelling approach in cell/material interactions studies.

Based on our experiments, we propose a statistical modeling approach of the in vitro interactions between biological objects and materials. The objective of this paper is to provide basic principles for developing more ambitious experiments comparing the simultaneous influence of more than one or two parameters on various observations, taking advantage of convenient statistical and mathematical techniques for the treatment of measured data. Analyzing some examples of our own experiments, the essential features needed for modeling cell/material interaction studies are presented. Firstly, we describe the initial process of designing appropriate experiments that allow for comprehensive modeling. In the second part, we illustrate the different applications of a specific statistical modeling technique, the bootstrap protocol, on either the amplification of data, the elimination of correlation existing between measured parameters or, out of a set of parameters, identification of the most relevant parameter for further statistical analysis. Finally, based on recent statistical analysis tools such as the bootstrap, we illustrate the relative influence of biological and physical parameters in phenomenological studies of cell/material interactions.

Biocompatible Materials↗

PubMed2000

Limits of time-reversal focusing through multiple scattering: long-range correlation

Experimental results of time-reversal focusing in a high-order multiple scattering medium are presented and compared to theoretical predictions based on a statistical model. The medium consists of a random collection of parallel steel rods. An ultrasonic source (3.2 MHz) transmits a pulse that undergoes multiple scattering and is recorded on an array. The time-reversed waves are sent by the array back to the source through the scattering medium. The quality of temporal focusing is very well predicted by a simple statistical model. However, for thicker samples, persistent temporal side-lobes appear. We interpret these side-lobes as a consequence of the growing number of crossing paths in the sample due to high-order multiple scattering. As to spatial focusing, the resolution is practically independent from the array's aperture. With a 16-element array, the resolution was found to be 30 times finer than in a homogeneous medium. Resolutions of the order of the wavelength (0.5 mm) were attained. These results are discussed in relation with the statistical properties of time-reversal mirrors in a random medium.

Journal Article↗

PubMed2005

In vitro quantification of changes in human dentine tubule parameters using SEM and digital analysis.

Dentine hypersensitivity is recognized as a pain arising from fluid movement within dentine tubules that are open to the oral environment. Blocking the tubules is considered to be the principal aim of treatment, and the accurate assessment of tubule occlusion is the primary goal of many in vitro studies. This assessment usually comprises either measuring tubule permeability or scanning electron microscope examination of the dentine surface. Several scanning microscopy studies have claimed to quantify tubule occlusion, but are descriptive, qualitative or semi-quantitative evaluations. The present study was undertaken to assess the use of digital image analysis in quantifying the effectiveness of a selected desensitizing agent from micrographs of control and treated dentine surfaces. Using a dentine disc model, an accurate methodology was sought to investigate the occluding potential of Butler Protect (J.O. Butler, Chicago, IL, USA). Subjective examination of the images indicated there was little difference after a single application, but considerable effect after 20 applications. Quantitative digital analysis of a test image, demonstrated reproducibility between two examiners when used in fully- and semi-automated mode. After a single application of Butler Protect, multilevel statistical modelling demonstrated decreases in tubule area and maximum, minimum and mean diameter measurements (P < 0.001), whereas single level analysis showed increases in area and maximum and mean diameters. Multiple application of Butler Protect demonstrated even greater decreases in all parameters (P < 0.001). This quantitative methodology was reproducible between examiners and, when combined with good controls and multilevel statistical modelling, was able to discriminate a single application of desensitizing agent.

Humans↗

PubMed1993

The etiology of breast cancer. Characteristic alteration in hydroxyl radical-induced DNA base lesions during oncogenesis with potential for evaluating incidence risk.

BACKGROUND: Substantial hydroxyl radical (.OH)-induced base lesions, recently found in the DNA of invasive ductal carcinoma of the female breast, are likely to be intimately related to oncogenesis. However, virtually no information was available regarding relationships between the different base lesions in the normal and cancerous breast. Such information is essential in understanding initial stages in the development of breast cancer and the potential of the base lesions as early predictors of cancer risk. METHODS: The .OH-induced DNA base lesions in normal reduction mammoplasty tissue (RMT) were compared with those from invasive ductal carcinoma (IDC) and nearby microscopically normal tissue (MNT). Comparisons were then undertaken on relationships between the base lesion profiles in the normal and cancerous breast using 22 statistical models. RESULTS: DNA from the RMT was characterized by a high ratio of ring-opening products (e.g., 4,6-diamino-5-formamidopyrimidine) to hydroxy-adducts of adenine and guanine. A dramatic shift in this relationship in favor of carcinogenic hydroxy-adducts (e.g., 8-hydroxyguanine) was found in the cancerous breast. Statistical models with a high sensitivity (91%) and specificity (97%) provided a consistent means of classifying tissues (e.g., 96% correct). CONCLUSIONS: The dramatic shift in the DNA base lesion relationships in oncogenesis is attributed to alterations in the redox potential of the breast favoring oxidative conditions and cancer formation. These findings suggest that base lesion profiles are potential sentinels for cancer risk assessment. Further, intervention in controlling the tissue redox potential may provide benefit in delaying or preventing early oncogenic changes and the ultimate manifestation of cancer.

Breast↗

PubMed1979

[Study on the frequency distribution of the metacercarial density of Clonorchis sinensis in fish host, Pseudorasbora parva]

Since the pattern of the frequency distribution of a parasite within a host showed an overdispersed pattern, various statistical models such as Poisson, negative binomial and lognormal distributions have been applied on the population dynamics in host-parasite relations. The observed data on the number of metacercariae of Clonorchis sinensis in a suitable intermediate host, Pseudorasbora parva which were collected from an endemic area, Juk-Rim River, Kim-Hae Goon, South Kyong-Sang Do were applied on the statistical models. The results obtained are as follows. 1. By the calculation of the raw data, 258(94.9%) out of 272 fish showed positive to the metacercarial infection of C. sinensis. The mean number of metacercaria in a fish was 335.1. The standard deviation was 250.6 and the mode was observed between 250 and 299. 2. The frequency distribution pattern of metacercariae of C. sinensis within the fish host in surveyed area was fitted to the lognormal distribution (0.05<p<0.10) rather than to the negative binomial (p<0.005) distribution. From the above statistical analyses, it was concluded that the lognormal distribution was selected as a distribution pattern of metacercariae of C. sinensis in their suitable fish host.

Journal Article↗

PubMed2005

Role of inflammation in gastrointestinal tract in aetiology and pathogenesis of idiopathic parkinsonism.

Idiopathic parkinsonism (IP) is a common disorder, conventionally regarded as neurodegenerative. Its cardinal features, poverty and slowness of movement, muscle rigidity, postural abnormality and a characteristic tremor, are associated with loss of dopaminergic neurones in the substantia nigra of the brain. Genetic factors explain only a minority of cases, and a common toxic environmental insult remains elusive. We propose that IP is a systemic disorder resulting from a ubiquitous peripheral infection, and that only the tip of the iceberg comes to diagnosis. There is evidence for inflammatory/immune activation peripherally and in the brain. We have used statistical modelling to explore links with non-specific and specific systemic markers of inflammation/infection in IP probands, and explore whether their partners and siblings have a frank or pre-presentation parkinsonian state. Critical to this approach is continuous objective measures of the facets of IP. Hypotheses on causality and mechanism are based on the statistical models. There is pathological and clinical evidence for direct involvement of the gastrointestinal tract in IP. The candidacy of Helicobacter pylori infection as a trigger event or driving infection is relatively high. We have found that eliminating infection in late parkinsonism with cachexia, a stage usually considered intractable, can result in a U-turn. However, eradication therapy may not provide a complete solution. Persistence of antibody against cytotoxin-associated antigen (CagA), increases the predicted probability of being labelled as having parkinsonism. Evidence for autoimmunity and immunocompromise is used to build schemes for the natural history. We conclude that current classifications of neuropsychiatric disease may not prove the best with respect to defining sub-clinical disease, prophylaxis or halting progression.

Gastroenteritis↗

PubMed1990

Confirmatory factor analytic models of the WAIS-R for neuropsychiatric patients.

Five multifactor models, in both orthogonal and oblique versions, and a single-factor model of the WAIS-R's factor pattern were examined by confirmatory maximum likelihood factor analyses of a data matrix constructed from the results for 90 neuropsychiatric patients. None of the models fits the data matrix in an absolute sense, even though all of the models represented an improvement over a null statistical model. For the multifactor models, the best results were obtained by oblique solutions, in which the degree of correlation between the factors varied from .71 to .93. The single-factor model fit nearly as well as, and in some instances better than, many of the multifactor models. The best-fitting model, viz., a three-factor oblique one, was only marginally better in its fit than two of the three two-factor models or the competing three-factor model.

Adult↗

PubMedDate not supplied

A multiple imputation strategy for incomplete longitudinal data.

Longitudinal studies are commonly used to study processes of change. Because data are collected over time, missing data are pervasive in longitudinal studies, and complete ascertainment of all variables is rare. In this paper a new imputation strategy for completing longitudinal data sets is proposed. The proposed methodology makes use of shrinkage estimators for pooling information across geographic entities, and of model averaging for pooling predictions across different statistical models. Bayes factors are used to compute weights (probabilities) for a set of models considered to be reasonable for at least some of the units for which imputations must be produced, imputations are produced by draws from the predictive distributions of the missing data, and multiple imputations are used to better reflect selected sources of uncertainty in the imputation process. The imputation strategy is developed within the context of an application to completing incomplete longitudinal variables in the so-called Area Resource File. The proposed procedure is compared with several other imputation procedures in terms of inferences derived with the imputations, and the proposed methodology is demonstrated to provide valid estimates of model parameters when the completed data are analysed. Extensions to other missing data problems in longitudinal studies are straightforward so long as the missing data mechanism can be assumed to be ignorable.

Bayes Theorem↗

PubMed2004

COACH: profile-profile alignment of protein families using hidden Markov models.

MOTIVATION: Alignments of two multiple-sequence alignments, or statistical models of such alignments (profiles), have important applications in computational biology. The increased amount of information in a profile versus a single sequence can lead to more accurate alignments and more sensitive homolog detection in database searches. Several profile-profile alignment methods have been proposed and have been shown to improve sensitivity and alignment quality compared with sequence-sequence methods (such as BLAST) and profile-sequence methods (e.g. PSI-BLAST). Here we present a new approach to profile-profile alignment we call Comparison of Alignments by Constructing Hidden Markov Models (HMMs) (COACH). COACH aligns two multiple sequence alignments by constructing a profile HMM from one alignment and aligning the other to that HMM. RESULTS: We compare the alignment accuracy of COACH with two recently published methods: Yona and Levitt's prof_sim and Sadreyev and Grishin's COMPASS. On two sets of reference alignments selected from the FSSP database, we find that COACH is able, on average, to produce alignments giving the best coverage or the fewest errors, depending on the chosen parameter settings. AVAILABILITY: COACH is freely available from www.drive5.com/lobster

Algorithms↗

PubMed2003

A model-based analysis of microarray experimental error and normalisation.

A statistical model is proposed for the analysis of errors in microarray experiments and is employed in the analysis and development of a combined normalisation regime. Through analysis of the model and two-dye microarray data sets, this study found the following. The systematic error introduced by microarray experiments mainly involves spot intensity-dependent, feature-specific and spot position-dependent contributions. It is difficult to remove all these errors effectively without a suitable combined normalisation operation. Adaptive normalisation using a suitable regression technique is more effective in removing spot intensity-related dye bias than self-normalisation, while regional normalisation (block normalisation) is an effective way to correct spot position-dependent errors. However, dye-flip replicates are necessary to remove feature-specific errors, and also allow the analyst to identify the experimentally introduced dye bias contained in non-self-self data sets. In this case, the bias present in the data sets may include both experimentally introduced dye bias and the biological difference between two samples. Self-normalisation is capable of removing dye bias without identifying the nature of that bias. The performance of adaptive normalisation, on the other hand, depends on its ability to correctly identify the dye bias. If adaptive normalisation is combined with an effective dye bias identification method then there is no systematic difference between the outcomes of the two methods.

Algorithms↗