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 1,225 records · Page 68Linked to original sources

PubMed1995

On model selection for standard curve in assay development.

This paper discusses the selection of an appropriate statistical model for representing standard curve in assay development. This is an important issue in assay validation because the accuracy and reliability of the assay result depend on the selected standard curve. In this study, we propose a selection procedure, which is based on the R2 and the mean squared error of the estimation sample, to determine the "best" model. An example concerning an assay validation study is used to illustrate the application of the proposed procedure to discriminate among the five commonly used statistical models.

Calibration↗

PubMed2005

Predicting outcomes after hip fracture repair.

OBJECTIVE: To compare the activities of daily living before and after hip fracture and construct a statistical model for discharge destination and independent walking. The classification accuracy of the model was determined from an independent sample. DESIGN: Prospective study: FIM prefracture, at discharge, and at 6-mo follow-up were obtained from 63 patients who underwent operations for acute hip fractures. A statistical model for discharge destination and independent walking was made and classification accuracy was checked using 78 independent samples. RESULTS: The motor FIM scores at prefracture decreased significantly at discharge (P < 0.0001) and at 6-mo follow-up (P < 0.0001), but at 6-mo follow-up, they had increased significantly compared with those at discharge (P = 0.0103). A mobility subscale was used to predict discharge destination, and mobility and social cognition subscales were related to independent walking. The predictive accuracy was 87%. CONCLUSIONS: Motor FIM scores increase for at least 6 mos after hip fracture, and discharge destination and independent walking were highly predictable from FIM mobility and social cognition subscales.

Activities of Daily Living↗

PubMed2004

A statistical thermodynamic model applied to experimental AFM population and location data is able to quantify DNA-histone binding strength and internucleosomal interaction differences between acetylated and unacetylated nucleosomal arrays.

Imaging of nucleosomal arrays by atomic force microscopy allows a determination of the exact statistical distributions for the numbers of nucleosomes per array and the locations of nucleosomes on the arrays. This precision makes such data an excellent reference for testing models of nucleosome occupation on multisite DNA templates. The approach presented here uses a simple statistical thermodynamic model to calculate theoretical population and positional distributions and compares them to experimental distributions previously determined for 5S rDNA nucleosomal arrays (208-12,172-12). The model considers the possible locations of nucleosomes on the template, and takes as principal parameters an average free energy of interaction between histone octamers and DNA, and an average wrapping length of DNA around the octamers. Analysis of positional statistics shows that it is possible to consider interactions between nucleosomes and positioning effects as perturbations on a random positioning noninteracting model. Analysis of the population statistics is used to determine histone-DNA association constants and to test for differences in the free energies of nucleosome formation with different types of histone octamers, namely acetylated or unacetylated, and different DNA templates, namely 172-12 or 208-12 5S rDNA multisite templates. The results show that the two template DNAs bind histones with similar affinities but histone acetylation weakens the association of histones with both templates. Analysis of locational statistics is used to determine the strength of specific nucleosome positioning tendencies by the DNA templates, and the strength of the interactions between neighboring nucleosomes. The results show only weak positioning tendencies and that unacetylated nucleosomes interact much more strongly with one another than acetylated nucleosomes; in fact acetylation appears to induce a small anticooperative occupation effect between neighboring nucleosomes.

Acetylation↗

PubMed1989

Smoking and lung cancer mortality in Japanese men: estimates for dose and duration of cigarette smoking based on the Japan vital statistics data.

For the purpose of understanding human carcinogenesis and making a quantitative prediction of lung cancer mortality in a general population of Japanese males, we evaluated a statistical model which assumes lung cancer mortality to be proportional to the 4.5th power of the effective duration of cigarette smoking among smokers and to the 4th power of age among nonsmokers, using Japan Vital Statistics data. For the male birth cohorts aged 30-69 in 1965 in the age range of 40-79, studied by quinquennial calendar time intervals from 1955 to 1985, it was found that, (i) for nonsmokers, the estimated lung cancer mortality rate was comparable to the rates reported in the US or Britain, assigning 20 to 25% proportions of nonsmokers, (ii) for smokers, the estimated duration of smoking was shorter than would be expected from the age when smoking was started according to various epidemiological surveys, and (iii) the estimated average numbers of cigarettes smoked per day by smokers were similar to those obtained by epidemiological studies, when these were estimated by incorporating a part of Doll and Peto's dose-response relationship. Also discussed is the possibility of assessing lung cancer mortality risk for Japanese male smokers by means of the statistical model, alpha x (cigarettes smoked per day + beta) x (age - (age started smoking) - gamma)4.5.

Adult↗

PubMed2004

Statistical parametric mapping for event-related potentials: I. Generic considerations.

In this paper, we frame the strategy and motivations behind developments in statistical parametric mapping (SPM) for the analysis of electroencephalogram (EEG) data. This work deals specifically with SPM procedures for the analysis of event-related potentials (ERP). We place these developments in the larger context of integrating electrophysiological and hemodynamic measurements of evoked brain responses through the fusion of EEG and fMRI data. In this paper, we consider some fundamental issues when selecting an appropriate statistical model that enables diverse questions to be asked of the data and at the same time retains maximum sensitivity. The three key issues addressed in this paper are as follows: (i) should multivariate or mass univariate analyses be adopted, (ii) should time be treated as an experimental factor or as a dimension of the measured response variable, and (iii) how to form appropriate explanatory variables in a hierarchical observation model. We review the relative merits of the different options and explain the rationale for our choices. In brief, we motivate a mass univariate approach in terms of sensitivity to region-specific responses. This involves modeling responses at each voxel or space bin separately. In contradistinction, we treat time as an experimental factor to enable inferences about temporally distributed responses that encompass multiple time bins. In a companion paper, we develop statistical models of ERPs in the time domain that follow from the heuristics established here and illustrate the approach using simulated and real data.

Analysis of Variance↗

PubMed1995

Statistical analyses of electromyographic activity in spasmodic dysphonic and normal control subjects.

Heterogeneity in the quality and task sensitivity of vocal symptoms in the spasmodic dysphonia (SD) population contributes to controversy as to whether this is a single disorder or two disorders with different etiologies (neurogenic versus psychogenic). Perceptual and acoustic assessments of vocal symptoms are inadequate to resolve this controversy. However, myoelectric events are intimately proximal to the source of vocal disruption and may be informative. The present report employs statistical modeling of quantitative amplitude measures of electromyographic activity recorded from thyroarytenoid to examine neuromotor bases of vocal symptoms in SD. Consideration of perceptual ratings of the quality and task sensitivity of vocal symptoms in the context of statistical models provides support for the conclusion that the range of vocal symptoms identified as SD represents a single, neurogenic disorder.

Adult↗

PubMed1995

Exposure assessment in industry specific retrospective occupational epidemiology studies.

Quantitative estimation of exposure for occupational epidemiology studies has received increasing attention in recent years and, as a result, a body of methodological literature has begun to take form. This paper reviews the generic issues in the methodology of exposure assessment, particularly methods for quantitative retrospective assessment studies. A simple framework, termed an exposure data matrix (EDM), for defining and analysing exposure data is proposed and discussed in terms of the definition of matrix dimensions and scales. Several methods for estimation, interpolation, and extrapolation, ranging from subjective ratings to quantitative statistical modelling are presented and discussed. The various approaches to exposure assessment based on the EDM concept are illustrated with studies of lung disease among coal miners and other dust and chemically induced chronic occupational diseases. The advantages of validated statistical models are emphasised. The importance of analysis and control of errors in exposure assessments, and integration of the exposure assessment and exposure-response processes, especially for emerging occupational health issues, is emphasised.

Algorithms↗

PubMed2001

ViewFeature: integrated feature analysis and visualization.

Visualization interfaces for high performance computing systems pose special problems due to the complexity and volume of data these systems manipulate. In the post-genomic era, scientists must be able to quickly gain insight into structure-function problems, and require flexible computing environments to quickly create interfaces that link the relevant tools. Feature, a program for analyzing protein sites, takes a set of 3-dimensional structures and creates statistical models of sites of structural or functional significance. Until now, Feature has provided no support for visualization, which can make understanding its results difficult. We have developed an extension to the molecular visualization program Chimera that integrates Feature's statistical models and site predictions with 3-dimensional structures viewed in Chimera. We call this extension ViewFeature, and it is designed to help users understand the structural Features that define a site of interest. We applied ViewFeature in an analysis of the enolase superfamily; a functionally distinct class of proteins that share a common fold, the alpha/beta barrel, in order to gain a more complete understanding of the conserved physical properties of this superfamily. In particular, we wanted to define the structural determinants that distinguish the enolase superfamily active site scaffold from other alpha/beta barrel superfamilies and particularly from other metal-binding alpha/beta barrel proteins. Through the use of ViewFeature, we have found that the C-terminal domain of the enolase superfamily does not differ at the scaffold level from metal-binding alpha/beta barrels. We are, however, able to differentiate between the metal-binding sites of alpha/beta barrels and those of other metal-binding proteins. We describe the overall architectural Features of enolases in a radius of 10 Angstroms around the active site.

Algorithms↗

PubMed2004

Vascular segmentation of phase contrast magnetic resonance angiograms based on statistical mixture modeling and local phase coherence.

In this paper, we present an approach to segmenting the brain vasculature in phase contrast magnetic resonance angiography (PC-MRA). According to our prior work, we can describe the overall probability density function of a PC-MRA speed image as either a Maxwell-uniform (MU) or Maxwell-Gaussian-uniform (MGU) mixture model. An automatic mechanism based on Kullback-Leibler divergence is proposed for selecting between the MGU and MU models given a speed image volume. A coherence measure, namely local phase coherence (LPC), which incorporates information about the spatial relationships between neighboring flow vectors, is defined and shown to be more robust to noise than previously described coherence measures. A statistical measure from the speed images and the LPC measure from the phase images are combined in a probabilistic framework, based on the maximum a posteriori method and Markov random fields, to estimate the posterior probabilities of vessel and background for classification. It is shown that segmentation based on both measures gives a more accurate segmentation than using either speed or flow coherence information alone. The proposed method is tested on synthetic, flow phantom and clinical datasets. The results show that the method can segment normal vessels and vascular regions with relatively low flow rate and low signal-to-noise ratio, e.g., aneurysms and veins.

Algorithms↗

PubMed1994

Mixed-effect models for predicting microbial interactions in the vaginal ecosystem.

Three statistical models that predict microbial interactions within the vaginal environment are presented. A large data set was assembled from in vivo studies describing the healthy vaginal environment, and the data set was analyzed to determine whether statistical models which would accurately predict the interactions of the microflora in this environment could be formulated. During assembly of the data set, two new variables were defined and were added to the data set, that is, cycle (sequence of menstrual cycle) and flow stage (subdivision of cycle determined by day of menstrual cycle). Concentrations of total aerobic (includes facultative) bacteria, total anaerobic bacteria, and a Corynebacterium sp. were identified by correlation analysis as variables with significant predictors. By using a regression method with a backward elimination procedure, significant predictors of these outcome variables were identified as the concentrations of Lactobacillus spp., anaerobic Streptococcus spp., and Staphylococcus spp., respectively. For all three outcome variables, pH and flow stage were also identified as significant independent variables. Because some of the data in the data set are repeated measurements for a subject, a mixed-effect model that accounts for the random effects of repeated-measurement data fit best the data set for predicting interactions between various members of the vaginal microflora. The predictive accuracies of the three models were tested by a comparison of model-predicted outcome-variable values with actual mean in vivo outcome-variable values. From these results, we concluded that it is possible to accurately predict vaginal microflora interactions by using a mixed-effect modeling system. The application of this type of modeling strategy and its future use are discussed.

Colony Count, Microbial↗

PubMed2001

Comorbidity-based payment methodology for Medicaid enrollees with HIV/AIDS.

Managed care organizations (MCOs) may be incurring financial losses from persons with human immunodeficiency virus (HIV) or acquired immunodeficiency syndrome (AIDS) (PWHA). This study developed a statistical model to examine which specific comorbidities are important contributors to the variations in health care costs of PWHA. Individuals were classified into cost groups to simulate biased selection in MCOs. Capitation payments for various cost groups under different methodologies were compared. The statistical model closely matched payments with the actual costs of care. Capitation payments for HIV/AIDS enrollees based on this model will better protect MCOs than the traditional risk-adjustment methods.

Capitation Fee↗

PubMed2004

A simple model to predict the sensitivity to change of visual acuity measurements.

BACKGROUND: Estimates of test-retest variability (TRV) in the form of a 95% range have been suggested as providing a cutoff value (or "change-criterion") against which measured acuity changes can be judged to decide whether they are indicative of a clinically important change. This approach is based on ensuring that the specificity of the procedure is 95% in individuals with no real change. In an earlier article we investigated empirically the ability of the procedure to detect varying degrees of change (its sensitivity). In this article, we develop a simple statistical model to examine further the sensitivity of the approach. METHODS: A statistical model was developed, and predictions from the model were compared with empirical visual acuity data. RESULTS: The model predicts that for changes equal in size to the magnitude of the change-criterion, sensitivity will be 50%. For changes 1.65 times the change-criterion, sensitivity is 90% and increasing to 95% for changes 1.84 times the size of the change-criterion. Predicted sensitivities agreed well with those measured empirically. CONCLUSIONS: The 95% range for TRV is often used to decide whether measured changes are indicative of clinically important changes. Evaluating the performance of visual acuity charts using a method analogous to that of estimating the sensitivity and specificity of a screening test highlights some limitations of this method. Use of the 95% range as a change-criterion ensures a high specificity, but a simple statistical model indicates that changes must approach twice the size of the change-criterion before they will be detected with sensitivity in excess of 95%. This has implications for the clinician attempting to assess the reliability of visual acuity charts, and in other similar tests, to detect change.

Humans↗

PubMed2003

Statistical-physical model for foliage clutter in ultra-wideband synthetic aperture radar images.

Analyzing foliage-penetrating (FOPEN) ultra-wideband synthetic aperture radar (SAR) images is a challenging problem owing to the noisy and impulsive nature of foliage clutter. Indeed, many target-detection algorithms for FOPEN SAR data are characterized by high false-alarm rates. In this work, a statistical-physical model for foliage clutter is proposed that explains the presence of outliers in the data and suggests the use of symmetric alpha-stable (SalphaS) distributions for accurate clutter modeling. Furthermore, with the use of general assumptions of the noise sources and propagation conditions, the proposed model relates the parameters of the SalphaS model to physical parameters such as the attenuation coefficient and foliage density.

Journal Article↗

PubMed1990

A note on the statistical properties of animal locations.

A statistical model of the successive locations of an animal in the plane induces a statistical model of the relative positions of successive locations. A common locational model is that the Cartesian coordinates of successive locations in the plane are independent bivariate normal random variables. This note gives the statistical properties of the direction and length of the vector joining successive locations.

Animals↗

PubMed1999

Predictors of mortality in adult patients with blunt injuries in New York State: a comparison of the Trauma and Injury Severity Score (TRISS) and the International Classification of Disease, Ninth Revision-based Injury Severity Score (ICISS).

BACKGROUND: The purpose of this study was to determine the statistical model that best predicted mortality from blunt trauma using a contemporary population-based database. METHODS: 1994-1995 New York State Trauma Registry data for patients with blunt injuries were used to predict mortality using three statistical models: (1) the original Trauma and Injury Severity Score (TRISS) model based on Major Trauma Outcome Study data, (2) a new TRISS model whose coefficients were derived using New York data, and (3) the International Classification of Disease, Ninth Revision-based Injury Severity Score (ICISS) with predicted survival values obtained from the Agency for Health Care Policy and Research's Health Care Utilization Project. The models were compared with respect to discrimination (using the C statistic) and calibration (using the Hosmer-Lemeshow [H-L] statistic). In addition, the models were tested to see how well they predicted outcomes for each of the three mechanisms of blunt injury. RESULTS: The ICISS model had a significantly higher C statistic (0.878) and a better H-L statistic (29.38) for predicting mortality for all adult patients with blunt injuries. The original TRISS model had very poor calibration (H-L = 687.38). None of the three models predicted mortality accurately for victims of motor vehicle crashes or victims of low falls. When separate models were developed for all motor vehicle crashes, low falls, and other blunt injuries, the ICISS and New York TRISS models both fit well, although the calibration was marginal in most cases. The ICISS model had a statistically significantly higher C statistic for other blunt injuries and for motor vehicle crashes. The New York TRISS model had better calibration for low falls. CONCLUSIONS: The ICISS has promise as an alternative to TRISS, but many more comparative studies need to be undertaken using updated TRISS coefficients. Models should also be developed for mechanisms of injury, not just for blunt and penetrating injuries.

Accidental Falls↗

PubMed2003

Depicting a protein's two faces: GPCR classification by phylogenetic tree-based HMMs.

Related proteins with similar biological functions generally share common features, allowing us to extract the common sequence features. These common features enable us to build statistical models that can be used to classify proteins, to predict new members, and to study the sequence-function relationship of this protein function group. Although evolution underlies the basis of multiple sequence analysis methods, most methods ignore phylogenetic relationships and the evolutionary process in building these statistical models. Previously we have shown that a phylogenetic tree-based profile hidden Markov model (T-HMM) is superior in generating a profile for a group of similar proteins. In this study we used the method to generate common features of G protein-coupled receptors (GPCRs). The profile generated by T-HMM gives high accuracy in GPCR function classification, both by ligand and by coupled G protein.

Animals↗

PubMed1987

ISMOD: an all-subsets regression program for generalized linear models. I. Statistical and computational background.

This paper describes a system written to carry out regression analyses under certain generalized linear models that are widely used in biomedical research. These include continuous response models such as the Weibull, log-logistic, log-normal and Cox proportional hazards models used in survival analysis, and also discrete Poisson, binomial and multinomial response regression models. The system fits models, generates residuals and other diagnostic output, and has an all-subsets regression feature. This paper describes the models implemented and gives statistical background; Part II describes the ISMOD system and presents examples of its application.

Biometry↗

PubMed1994

A screening algorithm to identify clinically significant changes in neuropsychological functions in the Diabetes Control and Complications Trial. DCCT Research Group.

Neuropsychological (NP) evaluations provide an accepted means of monitoring safety in multi-center long-term medical trials. However, using neuropsychologists to review test protocols and rate level of clinical impairment can be a costly and logistically complex undertaking. To facilitate that process, the DCCT Research Group developed a computerized screening strategy that utilized statistical models to identify individuals with possible cognitive deterioration. Two hundred and eight subjects with insulin-dependent diabetes mellitus were assessed twice, 2 years apart, with an extensive battery of NP tests, and the results were rated by expert clinicians. Multiple logistic regression was used to develop a statistical model to predict clinically significant NP worsening (as determined by clinical raters) on the basis of changes in scores (year 2--baseline) derived from the actual tests. A subsequent performance evaluation with an additional 1087 subjects demonstrated that the computerized algorithm was highly successful in identifying individuals with significantly worsened NP performance. Despite a high false positive rate, the algorithm can achieve an 80-90% reduction in the number of cases requiring evaluation by expert neuropsychologists.

Adolescent↗