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 1,441 records · Page 80Linked to original sources

PubMed2003

Algorithms for large-scale genotyping microarrays.

MOTIVATION: Analysis of many thousands of single nucleotide polymorphisms (SNPs) across whole genome is crucial to efficiently map disease genes and understanding susceptibility to diseases, drug efficacy and side effects for different populations and individuals. High density oligonucleotide microarrays provide the possibility for such analysis with reasonable cost. Such analysis requires accurate, reliable methods for feature extraction, classification, statistical modeling and filtering. RESULTS: We propose the modified partitioning around medoids as a classification method for relative allele signals. We use the average silhouette width, separation and other quantities as quality measures for genotyping classification. We form robust statistical models based on the classification results and use these models to make genotype calls and calculate quality measures of calls. We apply our algorithms to several different genotyping microarrays. We use reference types, informative Mendelian relationship in families, and leave-one-out cross validation to verify our results. The concordance rates with the single base extension reference types are 99.36% for the SNPs on autosomes and 99.64% for the SNPs on sex chromosomes. The concordance of the leave-one-out test is over 99.5% and is 99.9% higher for AA, AB and BB cells. We also provide a method to determine the gender of a sample based on the heterozygous call rate of SNPs on the X chromosome. See http://www.affymetrix.com for further information. The microarray data will also be available from the Affymetrix web site. AVAILABILITY: The algorithms will be available commercially in the Affymetrix software package.

Algorithms↗

PubMed2006

The impact of alcohol taxation on liver cirrhosis mortality.

OBJECTIVE: The objective of this study is to investigate the impact of distilled spirits, wine, and beer taxes on cirrhosis mortality using a large-panel data set and statistical models that control for various other factors that may affect that mortality. METHOD: The analyses were performed on a panel of 30 U.S. license states during the period 1971-1998 (N = 840 state-by-year observations). Exogenous measures included current and lagged versions of beverage taxes and income, as well as controls for states' age distribution, religion, race, health care availability, urbanity, tourism, and local bans on alcohol sales. Regression analyses were performed using random-effects models with corrections for serial autocorrelation and heteroscedasticity among states. RESULTS: Cirrhosis rates were found to be significantly related to taxes on distilled spirits but not to taxation of wine and beer. Consistent results were found using different statistical models and model specifications. CONCLUSIONS: Consistent with prior research, cirrhosis mortality in the United States appears more closely linked to consumption of distilled spirits than to that of other alcoholic beverages.

Alcoholic Beverages↗

PubMed1993

Statistical tests of models of DNA substitution.

Penny et al. have written that "The most fundamental criterion for a scientific method is that the data must, in principle, be able to reject the model. Hardly any [phylogenetic] tree-reconstruction methods meet this simple requirement." The ability to reject models is of such great importance because the results of all phylogenetic analyses depend on their underlying models--to have confidence in the inferences, it is necessary to have confidence in the models. In this paper, a test statistic suggested by Cox is employed to test the adequacy of some statistical models of DNA sequence evolution used in the phylogenetic inference method introduced by Felsenstein. Monte Carlo simulations are used to assess significance levels. The resulting statistical tests provide an objective and very general assessment of all the components of a DNA substitution model; more specific versions of the test are devised to test individual components of a model. In all cases, the new analyses have the additional advantage that values of phylogenetic parameters do not have to be assumed in order to perform the tests.

Animals↗

PubMed2006

Identification of newborns with Fetal Growth Restriction (FGR) in weight and/or length based on constitutional growth potential.

This study was carried out to build statistical models for defining FGR (Fetal Growth Restriction) in weight and/or length after taking growth potential of an infant into account. From a cohort of pregnant women having given birth to 47,733 infants in 141 French maternity units, two statistical models gave individualized limits of birth weight and birth length (based on the 5th centile) below which, after adjustment for its individual growth potential, a newborn must be considered as FGR in weight and/or in length. A sample of 906 infants had measures taken of cord blood growth factors (IGF1, IGFBP3). The FGR(W) definition (weight<5th centile for growth potential) permitted the identification of infants who presented rates of maternal hypertension (13.6%) and of Apgar score at 5 min<6 (2.9%) higher than in the classical group SGA(W) (weight<5th centile for sex and gestational age) (9.6% and 2.2% respectively). By combining FGR(W) and SGA(W), a subgroup of infants, not currently recognized as SGA, presented very high rates of maternal hypertension (19.9%) and of low Apgar score (3.9%). Conversely a subgroup of infants, currently recognized as SGA(W), had rates as low as in the normal infants group, and had to be considered as "constitutionally small" (that is to say 24% of the SGA(W)). Combining FGR(W) and FGR(L) (length<5th centile of growth potential), 7.6% of infants appeared growth-restricted, and 1.8% appeared constitutionally small in weight and/or in length. The FGR(W)-FGR(L) infants showed the lowest mean values of IGF1 (126.2+/-3.2) and IGFBP3 (0.86+/-0.03). These new definitions of FGR(W) and FGR(L) could help to better identify infants at birth requiring neonatal care, and monitoring of growth catch-up and neurodevelopmental outcome.

Adult↗

PubMed1992

Is the 'simple carry-over' model useful?

It is argued that the models usually employed for carry-over effects in cross-over trials are not reasonable. The example of a non-linear dose response for a dose-finding trial arranged in a Williams square is developed to show that if carry-over is present to any appreciable degree the usual statistical models provide no guaranteed protection against its effects. It is concluded that the most reasonably defended assumption about carry-over effects is that no important carry-over has taken place and that, where this assumption cannot be defended, statistical models provide no satisfactory substitute for it.

Bias↗

PubMed2004

Effects of temperature and pH on the helicity of a peptide adsorbed to colloidal silica.

The conformation of a cationic alpha-helical peptide (DDDDAAAARRRRR) adsorbed to anionic colloidal silica has been investigated by circular dichroism (CD) spectroscopy as a function of temperature and pH in order to examine how the structure of an adsorbed molecule responds to two simultaneous perturbations. Increased temperature destabilizes the helicity of the peptide in solution, while pH changes alter the substrate surface charge and the corresponding strength of the interaction with the peptide. Near neutral pH, the helicity of the adsorbed peptide, which is determined from the intensity of the CD signal at 222 nm, decreases with increasing temperature, similarly to the temperature-dependent behavior observed for the peptide in aqueous solution. By contrast, at basic pH and a strongly negative surface charge, the helicity of the adsorbed peptide increases with temperature. In order to elucidate the origin of the reversal of the temperature dependence of helicity, a statistical model for the conformation of the adsorbed peptide has been formulated based on the Lifson-Roig model for the helix-coil transition of the peptide in solution. The model provides insight into the trends in fractional helicity and reveals that the temperature dependence of the helicity of the adsorbed peptide results from a competition between the intramolecular interactions that promote helicity and the intermolecular interactions with the surface. The statistical model also enables estimation of the free energy contributions from specific aspects of the adsorption process. Through identification of a connection between the conformation of adsorbed peptide and the interactions of the peptide with the surface, this work suggests a route for the control of adsorbate conformation through peptide and surface engineering.

Adsorption↗

PubMed1998

Pathologic parameters in the diagnosis and prognosis of primary cutaneous melanoma.

Significant progress has been made in the last 10 years on the identification of histologic parameters that are independent predictors of melanoma prognosis, immunohistochemical markers of cells of melanocytic origin and changes in adhesion molecules, cytoskeletal proteins, growth factor receptors, cell signaling, and nuclear proliferation proteins associated with tumor progression. Histologic criteria may never be completely sufficient to predict behavior accurately, because the fundamental change that renders a cell aggressive may not be morphologically reflected and may require immunohistochemical or other molecular markers to establish behavior. To date, it is humbling that no immunohistochemical or molecular marker provides a greater predictable value for aggressive behavior than does the simple calibrated ocular micrometer to measure tumor thickness. Nevertheless, development of multiple histologic parameters with the concept of nontumorigenic RGP and tumorigenic VGP provides a reliable statistical model to predict metastases. Fortunately, nontumorigenic RGP melanomas with greater than 75% regression are rare. Thus, individual patients with melanoma without regression and without the tumorigenic VGP can be given reasonable assurance of 100% survival. Nevertheless, this assurance is based on a statistical model with a finite population studied. Additional studies are needed to confirm this model, as well as more definitive markers to precisely predict outcome for those individuals with tumorigenic VGP melanoma.

Biomarkers, Tumor↗

PubMed2005

Detailed diagnostics for a hot bromine plasma by the open M-shell opacity.

The experimental transmission spectrum of a hot bromine plasma [J. E. Bailey, J. Quant. Spectrosc. Radiat. Transf. 81, 31 (2003)] has been simulated by using a detailed level accounting model (DLA). With assumption of the local thermodynamic equilibrium, the major absorption lines of the experimental spectrum are well reproduced by the present DLA calculation, and the details of the absorption line shapes are used to determine the temperature of the plasma. In contrast to the results of two former statistical models, where the temperature was determined via a global fitting to the experimental data, the present DLA diagnoses the plasma temperature by the line ratios of different charge states in the 2p-->3d transition groups resulting in a temperature of 37 eV . It is shown that a change of 1 eV in temperature could cause perceptible changes in the simulated spectrum. It is also shown that the 2 p1/2 -->3 d3/2 absorptions have been overestimated by the statistical models.

Journal Article↗

PubMed2006

Singularities affect dynamics of learning in neuromanifolds.

The parameter spaces of hierarchical systems such as multilayer perceptrons include singularities due to the symmetry and degeneration of hidden units. A parameter space forms a geometrical manifold, called the neuromanifold in the case of neural networks. Such a model is identified with a statistical model, and a Riemannian metric is given by the Fisher information matrix. However, the matrix degenerates at singularities. Such a singular structure is ubiquitous not only in multilayer perceptrons but also in the gaussian mixture probability densities, ARMA time-series model, and many other cases. The standard statistical paradigm of the Cramér-Rao theorem does not hold, and the singularity gives rise to strange behaviors in parameter estimation, hypothesis testing, Bayesian inference, model selection, and in particular, the dynamics of learning from examples. Prevailing theories so far have not paid much attention to the problem caused by singularity, relying only on ordinary statistical theories developed for regular (nonsingular) models. Only recently have researchers remarked on the effects of singularity, and theories are now being developed. This article gives an overview of the phenomena caused by the singularities of statistical manifolds related to multilayer perceptrons and gaussian mixtures. We demonstrate our recent results on these problems. Simple toy models are also used to show explicit solutions. We explain that the maximum likelihood estimator is no longer subject to the gaussian distribution even asymptotically, because the Fisher information matrix degenerates, that the model selection criteria such as AIC, BIC, and MDL fail to hold in these models, that a smooth Bayesian prior becomes singular in such models, and that the trajectories of dynamics of learning are strongly affected by the singularity, causing plateaus or slow manifolds in the parameter space. The natural gradient method is shown to perform well because it takes the singular geometrical structure into account. The generalization error and the training error are studied in some examples.

Journal Article↗

PubMed2005

Fetal lung-to-liver signal intensity ratio at MR imaging: development of a normal scale and possible role in predicting pulmonary hypoplasia in utero.

PURPOSE: To define retrospectively a normal range for lung-to-liver signal intensity ratio (LLSIR) in fetuses of 16-40 weeks gestation by using half-Fourier single-shot turbo spin-echo magnetic resonance (MR) imaging. MATERIALS AND METHODS: Approval from the regional ethics review board for retrospective evaluation was obtained, and informed consent was waived. Retrospective analysis and follow-up of 157 pregnant women who underwent MR imaging over the past 4 years were performed. Seventy-four fetuses were subsequently identified as having clinically normal lung function or normal lung morphologic features at autopsy. A total of 141 normal lungs were analyzed, and the LLSIR was calculated from images on an MR workstation. A mixed-effects statistical model was applied, and 95% prediction intervals were calculated. Ten fetuses with hypoplastic lungs at autopsy were also evaluated. RESULTS: Plotting LLSIR against gestational age demonstrated that, according to the fitted mean curve, the signal intensity ratio was higher with more advanced gestational age. Statistical modeling suggests a quadratic relationship between gestational age and LLSIR. For fetuses in the normal population, the LLSIR ranged from 1.52 at 21 weeks gestation to 4.31 at 34 weeks gestation. For all hypoplastic lungs in fetuses at or beyond 25 weeks gestation, the LLSIR was outside the lower bound of the 95% prediction interval for the normal population. The distinction between hypoplastic lungs and normal lungs at less than 25 weeks gestation is less definitive. CONCLUSION: This study provides a normal scale with a 95% prediction interval for LLSIR.

Female↗

PubMedDate not supplied

Maximizing patient outcomes of antiinfective therapy.

Drug treatment of infectious disease requires consideration of both short- and long-term therapy. Although in most settings patients receive antimicrobials for acute events, long-term management of certain infections with drugs that delay progression of the disease adds a new facet to pharmacotherapy. In the past, broad questions regarding efficacy were posed: a drug was evaluated as either effective or not effective for a particular disorder. The actual question is, in whom is a given drug at a given dosage effective? Antibiotic control, restriction, and pharmacokinetic dosing programs have been useful, but they are reactive as opposed to proactive. The expensive products of biotechnology and the availability of oral drugs with activity exceeding that of parenteral antimicrobials require a more expanded scope of clinical pharmacy practice where patients are identified for these therapies prospectively using statistical models based on disease and other readily identified factors. Predictor variables for patient outcomes such as retreatment with other antibiotics, rehospitalization, toxicity, and mortality following the use of new drugs should be identified. Maximizing these outcome measurements will involve strategies that integrate epidemiology and statistical modeling techniques with principles of pharmaceutical care.

Anti-Infective Agents↗

PubMed1996

Analysis of meiotic segregation, using single-sperm typing: meiotic drive at the myotonic dystrophy locus.

Meiotic drive at the myotonic dystrophy (DM) locus has recently been suggested as being responsible for maintaining the frequency, in the human population, of DM chromosomes capable of expansion to the disease state. In order to test this hypothesis, we have studied samples of single sperm from three individuals heterozygous at the DM locus, each with one allele larger and one allele smaller than 19 CTG repeats. To guard against the possible problem of differential PCR amplification rates based on the lengths of the alleles, the sperm were also typed at another closely linked marker whose allele size was unrelated to the allele size at the DM locus. Using statistical models specifically designed to study single-sperm segregation data, we find no evidence of meiotic segregation distortion. The upper limit of the two-sided 95% confidence interval for the estimate of the common segregation probability for the three donors is at or below .515 for all models considered, and no statistically significant difference from .5 is detected in any of the models. This suggests that any greater amount of segregation distortion at the myotonic dystrophy locus must result from events following sperm ejaculation. The mathematical models developed make it possible to study segregation distortion with high resolution by using sperm-typing data from any locus.

Adult↗

PubMed2026

The Mediating Role of Immune Cells in the Genetically Predicted Relationship between Gut Microbiota and Puerperal Sepsis: A Mendelian Randomization Study.

INTRODUCTION: The causal relationship between gut microbiota and puerperal sepsis (PS) remains unclear, and there is a lack of in-depth research regarding the potential mediating role of immune cells in this context. OBJECTIVE: This study aims to investigate the causal relationship between gut microbiota and PS using Mendelian randomization (MR) analysis and to assess the mediating effects of immune cells on the risk of PS onset through mediation analysis. MATERIALS AND METHODS: We selected data from large-scale genome-wide association studies (GWAS) involving 473 gut microbiota species, 731 immune cell phenotypes, and PS datasets. Univariate MR (UVMR) analysis was employed to explore the causal relationship between gut microbiota and PS, with the primary statistical method being inverse variance weighting (IVW). Multiple statistical models were applied for sensitivity analysis to minimize the confounding effects of horizontal pleiotropy and heterogeneity. Subsequently, a two-step mediation MR analysis was conducted to evaluate whether immune cells mediate the relationship between gut microbiota and PS. RESULTS AND DISCUSSION: Analysis using various statistical models indicated that 11 gut microbiota species (e.g., Azorhizobium, Bacillus velezensis, CAG-245 sp000435175, Lentimicrobiaceae, and Providencia) exhibited a causal relationship with PS. Further reverse causal analysis between PS and gut microbiota ruled out the possibility of reverse causality. The two-step mediation MR analysis demonstrated that the percentage of IgD-CD27- B cells (10.26%) and CD62L- monocytes (17.29%) partially mediated the effect of CAG-245 sp000435175 on PS risk. CONCLUSION: This study provides evidence of a causal relationship between the abundance of certain gut microbiota species and PS, while also revealing a potential mediating role of immune cells. These findings offer valuable theoretical insights into personalized treatment strategies and the development of novel diagnostic biomarkers for PS.

Humans↗

PubMed2004

Standard mixtures for proteome studies.

Mixtures of moderate complexity were formed from 23 peptides and 12 proteins digested with trypsin, all individually characterized. These mixtures were analyzed with replicates in full and windowed m/z ranges using online high-performance reverse phase liquid chromatography coupled via electrospray ionization to an ion trap mass spectrometer. The resulting spectra were searched using SEQUEST against databases of different sizes and contents and confidences of the observed identifications were evaluated by our earlier statistical model. These data were then combined with biologically derived spectral data, searched, and further evaluated. All peptides but one and all proteins were identified with high confidence. Additionally, the presence and behavior of quadruply charged peptides was analyzed. The properties of the proposed peptide and protein mixtures as well as the performance of the statistical model were carefully investigated. These mixtures mimic the complexity seen in large-scale proteomics experiments, and are proposed to serve as quality assessment standards for future proteome studies.

Animals↗

PubMedDate not supplied

Issues for covariance analysis of dichotomous and ordered categorical data from randomized clinical trials and non-parametric strategies for addressing them.

Analysis of covariance is an effective method for addressing two considerations for randomized clinical trials. One is reduction of variance for estimates of treatment effects and thereby the production of narrower confidence intervals and more powerful statistical tests. The other is the clarification of the magnitude of treatment effects through adjustment of corresponding estimates for any random imbalances between the treatment groups with respect to the covariables. The statistical basis of covariance analysis can be either non-parametric, with reliance only on the randomization in the study design, or parametric through a statistical model for a postulated sampling process. For non-parametric methods, there are no formal assumptions for how a response variable is related to the covariables, but strong correlation between response and covariables is necessary for variance reduction. Computations for these methods are straightforward through the application of weighted least squares to fit linear models to the differences between treatment groups for the means of the response variable and the covariables jointly with a specification that has null values for the differences that correspond to the covariables. Moreover, such analysis is similarly applicable to dichotomous indicators, ranks or integers for ordered categories, and continuous measurements. Since non-parametric covariance analysis can have many forms, the ones which are planned for a clinical trial need careful specification in its protocol. A limitation of non-parametric analysis is that it does not directly address the magnitude of treatment effects within subgroups based on the covariables or the homogeneity of such effects. For this purpose, a statistical model is needed. When the response criterion is dichotomous or has ordered categories, such a model may have a non-linear nature which determines how covariance adjustment modifies results for treatment effects. Insight concerning such modifications can be gained through their evaluation relative to non-parametric counterparts. Such evaluation usually indicates that alternative ways to compare treatments for a response criterion with adjustment for a set of covariables mutually support the same conclusion about the strength of treatment effects. This robustness is noteworthy since the alternative methods for covariance analysis have substantially different rationales and assumptions. Since findings can differ in important ways across alternative choices for covariables (as opposed to methods for covariance adjustment), the critical consideration for studies with covariance analyses planned as the primary method for comparing treatments is the specification of the covariables in the protocol (or in an amendment or formal plan prior to any unmasking of the study.

Analysis of Variance↗

PubMed2005

Analysis of VH gene sequences using two web-based immunogenetics resources gives different results, but the affinity maturation status of chronic lymphocytic leukaemia clones as assessed from either of the resulting data sets has no prognostic significance.

Some cellular and molecular features of chronic lymphocytic leukaemia (CLL) cells that are associated with prognosis may reflect the context within which their progenitors encountered antigen. It follows that the nature of antigen drive in CLL could influence the clinical course and we were prompted to assess the impact, if any, of affinity maturation (an antigen-driven process) on prognosis. Statistical models for assessing affinity maturation status are typically applied to V(H) gene sequence data analysed using a web-based resource like IMGT or VBASE. Since these resources differ with respect to some key relevant features, we evaluated a cohort of CLL cases by applying statistical models to V(H) data derived from both IMGT and VBASE. Important differences between the resulting data sets became apparent. These resulted from database variance and because IMGT and VBASE define complementarity-determining and framework regions (CDRs, FRs) in different ways. Thus, the numbers of mutations identified and their distribution between CDRs/FRs varied between the data sets for the majority of clones. Consequently, two different but overlapping sets of cases with evidence of affinity maturation were defined. Notwithstanding their differences, no significant associations of affinity maturation status with CD38 expression, p53 functional status or survival were identifiable in either data set.

ADP-ribosyl Cyclase↗

PubMed2006

Profiling providers on use of adjuvant chemotherapy by combining cancer registry and medical record data.

PURPOSE: Treatment information collected by cancer registries can be used to monitor the provision of guideline-recommended chemotherapy to colorectal cancer patients. Incomplete information may bias comparisons of these rates. We developed statistical methods that combine data from a registry and physicians' records to assess hospital quality. DATA: From California Cancer Registry data, we selected all patients (n=12,594) newly diagnosed with stage III colon cancer or stage II or III rectal cancer from 428 hospitals during the years 1994 to 1998. To assess rates and predictors of underreporting of chemotherapy, we surveyed physicians treating 1449 of these patients from 98 hospitals during the years 1996 to 1997. METHODS: Using Bayesian statistical models, we imputed unobserved treatments. We studied the impact of underreporting on provider profiling by comparing rankings, estimates, and credible intervals based only on registry data to those incorporating physician survey data. RESULTS: Analyses that account for incompleteness of reporting yielded wider credible intervals for provider profiles than those that ignored such incompleteness. Among the 109 (25%) hospitals in the highest quartile of chemotherapy rates according to the registry data, 16 were not so classified when incomplete reporting was taken into account. With the more comprehensive model, 12 hospitals could be identified that ranked in the top quartile with probability>0.90. CONCLUSION: Estimates of adjusted hospital chemotherapy rates based solely on cancer registry data overstate the precision of assessments of hospital quality. Using additional information from a physician survey and applying rigorous statistical models, better inferences can be drawn about provider quality.

Adolescent↗

PubMed2004

The influence of temperature and relative humidity on the development of Lepidoglyphus destructor (Acari: Glycyphagidae) and its production of allergens: a laboratory experiment.

Laboratory experiments with Lepidoglyphus destructor on a diet of mainly whole wheat were conducted to study the mite's development and production of a specific allergen, Lep d 2, at four different temperatures (5, 10, 15 and 20 degrees C) and three levels of relative humidity (ca. 70-88%). Statistical models were used to analyse the role played by temperature, relative humidity and time in explaining the observed number of L. destructor and the amount of allergen produced. Moreover, the life stage distributions of the mites were determined and related to the population growth. Based on a statistical model the intrinsic rate of natural increase, rm, was computed for a range of different temperatures and relative humidities. High relative humidity in combination with temperatures at about 25 degrees C will lead to the highest rm (ca. 0.15 day-1). The highest concentration of Lep d 2 was 3 micrograms g-1 grain, found at 20 degrees C and high relative humidity at a mite density of 254 mites g-1 grain. The concentration of allergens in the grain was best explained by a model that incorporated both the current and the cumulative numbers of mites.

Acaridae↗