Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “model selection”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 973 records · Page 54Linked to original sources
PubMed1995

Differential effect of buspirone and diazepam on negative contrast in one-way avoidance learning.

The main aim of the present work was to investigate the effect of buspirone, a 5-HT1A receptor agonist, on successive negative contrast in one-way avoidance learning. Successive negative contrast was induced by shifting rats from a large reward (30 s spent in the safe compartment) to a small reward (1 s). Acute administration of buspirone (0.25, 0.5, 0.75 and 1.0 mg/kg i.p.) did not attenuate the contrast effect, as opposed to that observed for diazepam (1 mg/kg i.p.). The highest dose of buspirone used, however, did interfere with the learning of the avoidance response itself. Chronic buspirone (20 days, 0.5 and 0.75 mg/kg i.p.) did not have any effect on successive negative contrast either. Overall, these results could suggest that the 5-HT1A receptor is not involved in the negative contrast effect studied, quite different to that observed for the gamma-aminobutyric acid (GABA) system. The findings are compared to results obtained with animal models selectively sensitive to some anxiolytic drugs, as are the so-called 'conflict models'.

Animals↗
PubMedDate not supplied

Improved system for object detection and star/galaxy classification via local subspace analysis.

The two traditional tasks of object detection and star/galaxy classification in astronomy can be automated by neural networks because the nature of the problems is that of pattern recognition. A typical existing system can be further improved by using one of the local Principal Component Analysis (PCA) models. Our analysis in the context of object detection and star/galaxy classification reveals that local PCA is not only superior to global PCA in feature extraction, but is also superior to gaussian mixture in clustering analysis. Unlike global PCA which performs PCA for the whole data set, local PCA applies PCA individually to each cluster of data. As a result, local PCA often outperforms global PCA for data of multi-modes. Moreover, since local PCA can effectively avoid the trouble of having to specify a large number of free elements of each covariance matrix of gaussian mixture, it can give a better description of local subspace structures of each cluster when applied on high dimensional data with small sample size. In this paper, the local PCA model proposed by Xu [IEEE Trans. Neural Networks 12 (2001) 822] under the general framework of Bayesian Ying Yang (BYY) normalization learning will be adopted. Endowed with the automatic model selection ability of BYY learning, the BYY normalization learning-based local PCA model can cope with those object detection and star/galaxy classification tasks with unknown model complexity. A detailed algorithm for implementation of the local PCA model will be proposed, and experimental results using both synthetic and real astronomical data will be demonstrated.

Astronomy↗
PubMed1999

1996 Remington lecture: modeling multivariate longitudinal data that are incomplete.

PURPOSE: We describe the impact that missing data may have on model selection for longitudinal multivariate data. METHODS: Maximum likelihood was used to fit several models to ultrasonographic measurements from the Asymptomatic Carotid Artery Progression Study (ACAPS). Graphical techniques were used to examine evidence concerning the underlying missing data mechanisms associated with each model. RESULTS: Using statistical methodology that addressed missing data substantially increased the statistical efficiency of our analysis of ultrasonographic data. Only complex models that included segment-specific parameterizations for longitudinal correlations appeared to allow missing data to be assumed to occur at random. CONCLUSION: Ignoring the nature of missing data in conducting statistical analyses can have serious consequences when missingness is not rare. It may be necessary to fit models of high dimension with maximum likelihood techniques to address missing data appropriately, however these approaches may improve statistical efficiency.

Carotid Stenosis↗
PubMed1994

Synthesis and antibacterial activity of new quinolones containing a 7-[3-(1-amino-1-methylethyl)-1-pyrrolidinyl] moiety. Gram-positive agents with excellent oral activity and low side-effect potential.

A series of the R and S isomers of 7-[3-(1-amino-1-methylethyl)-1-pyrrolidinyl]-1,4-dihydro-4-oxoquinoline- and 1,8-naphthyridine-3-carboxylic acids was prepared to determine the effect on potency of the two methyl groups adjacent to the distal nitrogen in the pyrrolidinyl moiety. The antibacterial efficacy of these dimethylated derivatives was compared to the relevant 7-[3-(aminomethyl)-1-pyrrolidinyl] parent compounds and, to a lesser extent, the 7-[3-(1-aminoethyl)-1-pyrrolidinyl] analogues. The activity of the title and reference compounds was assayed in vitro using an array of Gram-negative and Gram-positive organisms and in vivo using a mouse infection model. Selected derivatives were then screened for potential side effects in a phototoxicity mouse model and an in vitro mammalian cell cytotoxicity protocol. The results showed that the R isomer displayed a 2-20-fold advantage in activity in vitro and a 2-15-fold advantage in vivo over the S isomer. Although equipotent to the 7-[3-(aminomethyl)-1-pyrrolidinyl] parent compounds in vitro, the R isomers of the 7-[3-(1-amino-1-methylethyl)-1-pyrrolidinyl] analogues showed a dramatic increase in in vivo potency, especially via the oral route of administration. These same R isomers also appeared to possess a reduced risk of phototoxicity and cytotoxicity. This combination of superior in vivo performance with a low degree of phototoxicity and mammalian cell cytotoxicity recommends these agents for further study. Of these agents, naphthyridine 16-R represents the optimal blend of potency and safety.

4-Quinolones↗
PubMed2004

Sensitivity analysis for pattern mixture models.

Incomplete series of data is a common feature in quality-of-life studies, in particular in chronic diseases where attrition of patients is high. Two alternative approaches to modeling longitudinal data with incomplete measurements have frequently been proposed in the literature, selection models and pattern-mixture models. In this paper we focus on, by way of sensitivity analysis, extrapolating incomplete patterns using identifying restrictions. Perhaps the best known ones are so-called complete case missing value restrictions (CCMV), where for a given pattern, the conditional distribution of the missing data, given the observed data, is equated to its counterpart in the completers. Available case missing value (ACMV) restrictions equate this conditional density to the one calculated from the subgroup of all patterns for which all required components have been observed. Neighboring case missing value restrictions (NCMV) equate this conditional density to the one calculated from the the pattern with one additional measurement obtained. In this paper, these three identifying restriction strategies are used to multiply impute missing data in a study in metastatic prostate cancer. Multiple imputation is employed to reduce the uncertainty of single imputation. It is shown how hypothesis testing and sensitivity analyses are carried out in this setting.

Humans↗
PubMed2002

Context-tree modeling of observed symbolic dynamics.

Modern techniques invented for data compression provide efficient automated algorithms for the modeling of the observed symbolic dynamics. We demonstrate the relationship between coding and modeling, motivating the well-known minimum description length (MDL) principle, and give concrete demonstrations of the "context-tree weighting" and "context-tree maximizing" algorithms. The predictive modeling technique obviates many of the technical difficulties traditionally associated with the correct MDL analyses. These symbolic models, representing the symbol generating process as a finite-state automaton with probabilistic emission probabilities, provide excellent and reliable entropy estimations. The resimulations of estimated tree models satisfying the MDL model-selection criterion are faithful to the original in a number of measures. The modeling suggests that the automated context-tree model construction could replace fixed-order word lengths in many traditional forms of empirical symbolic analysis of the data. We provide an explicit pseudocode for implementation of the context-tree weighting and maximizing algorithms, as well as for the conversion to an equivalent Markov chain.

Journal Article↗
PubMed2005

A predictive model for exemestane pharmacokinetics/pharmacodynamics incorporating the effect of food and formulation.

AIMS: Exemestane (Aromasin) is an irreversible aromatase inactivator used for the treatment of postmenopausal women with advanced breast cancer. The objective of this study was to evaluate the effect of formulation comparing a sugar-coated tablet (SCT) with a suspension and food on the pharmacokinetics (PK) and pharmacodynamics (PD) with respect to plasma estrone sulphate (E1S) concentrations of exemestane, using a PK/PD approach. METHODS: This was an open, three-period, randomized, crossover study. Twelve healthy postmenopausal women received single oral doses of 25 mg exemestane as a SCT after fasting or food and as a suspension after fasting. Exemestane and E1S concentrations were determined before and up to 14 days after drug administration. Population analysis was performed in two steps: (i) a compartmental PK model was selected incorporating the effect of food and formulation; (ii) conditional on the PK model, a PD model was developed employing indirect response models. Model selection was performed using standard statistical tests. Validation and assessment of the predictive capability of the selected model was performed using real test data sets obtained from the literature. RESULTS: A three-compartment model with first-order elimination rate best described exemestane disposition (k12 0.454, k21 0.158, k13 0.174, k31 0.016 and k 0.738 h(-1)). Absorption was described by a mono-exponential function [ka 2.3 (SCT after fasting), 1.1 (SCT after food) and 7.6 h(-1) (suspension); lag time 0.2 h]. The PD model assumed that E1S plasma concentrations are determined by a zero-order synthesis rate (6.5 pg ml(-1) h(-1)) and a first-order elimination constant (0.032 h(-1)). Exemestane inhibited E1S synthesis with a C50 value of 22.1 pg ml(-1). The mean population estimates were used to simulate the administration of different doses of the drug (0.5, 1, 2.5, 5 and 25 mg day(-1)). The model predictions were in agreement with historical data. CONCLUSIONS: Exemestane absorption is influenced by the formulation of the drug and by food, but its disposition is independent of both. PK differences do no translate into clinically important differences in the PD. The PK/PD model developed was able to predict successfully the response to different doses and administration schedules with respect to oestrogen suppression.

Administration, Oral↗
PubMed2006

Detecting pulsatile hormone secretions using nonlinear mixed effects partial spline models.

Neuroendocrine ensembles communicate with their remote and proximal target cells via an intermittent pattern of chemical signaling. The identification of episodic releases of hormonal pulse signals constitutes a major emphasis of endocrine investigation. Estimating the number, temporal locations, secretion rate, and elimination rate from hormone concentration measurements is of critical importance in endocrinology. In this article, we propose a new flexible statistical method for pulse detection based on nonlinear mixed effects partial spline models. We model pulsatile secretions using biophysical models and investigate biological variation between pulses using random effects. Pooling information from different pulses provides more efficient and stable estimation for parameters of interest. We combine all nuisance parameters including a nonconstant basal secretion rate and biological variations into a baseline function that is modeled nonparametrically using smoothing splines. We develop model selection and parameter estimation methods for the general nonlinear mixed effects partial spline models and an R package for pulse detection and estimation. We evaluate performance and the benefit of shrinkage by simulations and apply our methods to data from a medical experiment.

Animals↗
PubMed2001

Product liability forecasting for asbestos-related personal injury claims: a multidisciplinary approach.

This paper focuses on three aspects of forecasting models for asbestos-related disease/injuries relating to the Manville asbestos case: (1) The structure of forecasting models for asbestos-related personal injuries. (2) The epidemiologic evidence supporting the selected model structure and the constraints on the modeling assumptions imposed by that evidence. (3) The range of uncertainty associated with projections based on these forecasting models and issues relating to decision making under uncertainty.

Asbestos↗
PubMedDate not supplied

[Development of a mathematical model for simulation of artificial ventilation].

This article describes a mathematical model for the simulation of artificial ventilation employing only the figures for air pressure and air flow between respirator and lungs. A discussion of methodological aspects of the problem shows that the model of the respiratory system can be reduced to an equivalent circuit diagram comprising only resistances and capacitances. The structure of the mathematical model is oriented to the elements of the real respiratory system, and its modularity permits ready adaptation to a variety of real-life situations. Particular emphasis was placed on the correct parametrization of the model with the aid of data originally collected from physical experiments. Finally, some selected model runs that demonstrate the range of validity and the accuracy of the model are presented.

Airway Resistance↗
PubMed2005

Complex mixture toxicity for single and multiple species: proposed methodologies.

Methods for the assessment of ecological risks associated with exposure to defined mixtures of toxicants are reviewed and formalized for single-species toxicity. Depending on the modes of action of toxicants in a mixture, these methods apply either the model for concentration additivity (CA) or the model for response additivity (RA). For complex mixtures, the present paper advocates the use of a new, two-step, mixed-model approach as a logical extension of model selection: Mixture toxicity for individual modes of action is evaluated with the CA model, and the toxicities of different modes of action are combined using the RA model. Using comparable mixture toxicity strategies in combination with the concept of species-sensitivity distributions, we develop a method to address and predict the risk for direct effects on the composition of species assemblages and biodiversity. The data needed for modeling can be obtained from existing databases, and lack of data can, in part, be addressed by the use of toxicity patterns in those databases. Both single- and multiple-species methods of mixture risk prediction are useful for risk management, because they allow ranking of polluted sites and affected species as well as identification of the most hazardous contaminants, at least in a comparative way. Validation of the proposed methods is feasible but currently limited because of a lack of appropriate data.

Animals↗
PubMed1976

Control of immune responses by cyclic AMP and lymphocytes that adhere to histamine columns.

Mixed lymphocytes from human peripheral blood, murine spleens, lymph nodes or thymus glands have pharmacologically specific receptors for histamine, beta mimetic catecholamines and prostaglandins. When these cells are exposed to the panoply of drugs mentioned above, their intracellular cyclic AMP concentrations increase. The biologic consequences of such an increase were at first elusive. Now we know that the immune potential of some murine spleen cells may be modulated and the release of lysosomal enzymes and histamine from human leukocytes may be inhibited. This paper concentrates on the effects that manipulation of cells with amine receptors has on their immune function. Recent studies have revealed that a subpopulation of splenic suppressor T cells responds to increases in its cyclic AMP content by reversing its suppressive effects on the humoral antibody response. When these T cells are removed from the murine cell population by their differential adherence to insolubilized conjugates of histamine with albumin, the remainder of the cells are more responsive to sheep cell antigen, as tested by transferring the spleen cells together with the antigen into lethally irradiated recipient animals. The suppressor T cells that adhere to the insolubilized conjugates of histamine-albumin (called histamine-rabbit serum albumin-Sepharose, or HRS) are Ia positive, they appear to have receptors for histamine, beta adrenergic amines and prostaglandins of the E series, and when stimulated by these agents their in vivo and in vitro suppressor actions are reversed. The reversal seems quantitatively dependent on cyclic AMP accumulation. Receptors for the amines and prostaglandins are found on the T cell precursors of cell mediated immunity. They develop on some T effector cells in selected models of allogeneic target cell lysis. The receptors also appear to develop on selected B cells once these cells become committed to antibody production. The distribution of receptors on all leukocytes has not been adequately studied nor has their full potential in the immune response been studied in detail.

Animals↗
PubMed2005

Prediction of kinetics of doxorubicin release from sulfopropyl dextran ion-exchange microspheres using artificial neural networks.

The purpose of this work was to develop artificial neural networks (ANN) models to predict in vitro release kinetics of doxorubicin (Dox) delivered by sulfopropyl dextran ion-exchange microspheres. Four ANN models for responses at different time points were developed to describe the release profiles of Dox. Model selection was performed using the Akaike information criterion (AIC). Sixteen data sets were used to train the ANN models and two data sets for the validation. Good correlations were obtained between the observed and predicted release profiles for the two randomly selected validation data sets. The difference factor (f1) and similarity factor (f2) between the ANN predicted and the observed release profiles indicated good performance of the ANN models. The established models were then applied to predict release kinetics of Dox from the microspheres of various initial loadings in media of different ionic strengths and NaCl/CaCl2 ratios. The results suggested that ANN offered a flexible and effective approach to predicting the kinetics of Dox release from the ion-exchange microspheres.

Calcium Chloride↗
PubMed1999

Subtype selective alpha1-adrenoceptor antagonists for the treatment of benign prostatic hyperplasia.

Benign prostatic hyperplasia (BPH) is highly prevalent in the male population beyond the age of 60. Impairment of urinary flow due to prostate enlargement gives rise to symptoms of 'prostatism' that have a detrimental impact on the quality of life. The current trend in the management of symptomatic BPH favours pharmacotherapy as a first line option, while the number of surgical procedures being performed has experienced a steady decline during the last ten years. Among the pharmacological treatments, the use of alpha1-adrenoceptor blockers has demonstrated to be an effective treatment option for BPH. These agents reduce the adrenergic tone to the prostate and increase urinary flow, with a concomitant reduction of lower urinary tract symptoms. The alpha1-blockers currently approved include compounds such as alfuzosin, terazosin and doxazosin, originally developed for the treatment of hypertension, and more recently tamsulosin, an alpha1-subtype selective drug. The blockade of alpha1-adrenoceptors present in vascular smooth muscle is largely responsible for the most prominent side effects of current drugs, which can be severe and require patients dose titration. The limitation imposed by side effects naturally raises the possibility that complete blockade of prostatic alpha1 receptors is not attained at the maximum tolerated dose. The extensive efforts by the pharmaceutical industry towards the development of uroselective alpha1-blockers, is the subject of this review. Advances in the molecular cloning of genes encoding three alpha1-adrenoceptors led to the identification of the alpha1A-subtype as the predominant receptor responsible for the contraction of prostate smooth muscle. In preclinical animal models, selective alpha1A-antagonists have consistently been found to have minimal cardiovascular effects, thus providing a pharmacological rationale for uroselectivity. It has also become apparent, however, that uroselectivity can emerge in a poorly understood manner from the pharmacodynamic properties of compounds without alpha1A-subtype selectivity. Clinical experience with tamsulosin, an alpha1A/alpha1D selective drug, has failed to demonstrate a significant improvement in efficacy beyond that demonstrated for non-subtype selective alpha1-blockers, and gives support to the notion that alpha1A-selective antagonists might achieve greater efficacy for the treatment of BPH. Given the demonstrated uroselectivity of alpha1A-selective antagonists in preclinical models, it is anticipated that third generation alpha1-blockers will exhibit improved urinary flow efficacy and be better tolerated than tamsulosin. The extent to which the improvement in urinary flow will translate to the relief of symptoms of prostatism, however, remains to be demonstrated in randomised placebo-controlled clinical trials of alpha1A-selective antagonists.

Journal Article↗
PubMed1986

The dynamics of interlocus associations in the three locus hitchhiking model. 1. The three-way linkage disequilibrium function.

The dynamical behavior of the three-way linkage disequilibrium function is investigated within deterministic, three locus hitchhiking systems consisting of two neutral loci and one selected locus. The analysis is based on the case in which at least one of the neutral loci is initially in linkage equilibrium with the selected locus. It also applies approximately, whenever the product Dn1SDn2S, is negligible relative to the three-way association, where DniS denotes the pairwise linkage disequilibrium between the selected locus and neutral locus i. A complete qualitative description of the resulting behavior is given for several selection models as a function of the gene frequency at the selected locus, the strength of selection, the degree of recombination among the loci, and the relative position of the selected locus. A major finding is that, although not functionally equivalent, the dynamics are qualitatively like those found previously for the pairwise association between a neutral locus and a linked, selected locus (Asmussen and Clegg 1981). Ultimately, the three-way linkage disequilibrium will decay at a rate faster than expected for three neutral loci. The range of gene frequencies associated with the accelerated decay steadily expands as selection intensifies, and either grows or shrinks with increasing recombination among the loci, depending upon the mode of selection operating. In the early stages of a trajectory, the triple interaction may increase in magnitude only if the selection intensity exceeds the frequency with which a detectable recombination occurs between the middle and end loci, and a favored allele (at the selected locus) is rare. When it exists, the region of increase first enlarges, then shrinks as selection intensifies, and contracts with increasing recombination among the loci. An interesting position effect is that systems in which the selected locus is to one side of the two neutral loci may have a greater three-way interaction, and hence a greater hitchhiking effect, than equivalent systems in which the selected locus is between the neutral loci.

Biometry↗
PubMed2006

A game-theoretic model for punctuated equilibrium: species invasion and stasis through coevolution.

A general theory of coevolution is developed that combines the ecological effects of species' densities with the evolutionary effects of changing phenotypes. Our approach also treats the evolutionary changes between coevolving species with discreet traits after the appearance of a new species. We apply this approach to habitat selection models where new species first emerge through competitive selection in an isolated habitat. This successful invasion is quickly followed by evolutionary changes in behavior when this species discovers the other habitat, leading to punctuated equilibrium as the final outcome.

Biological Evolution↗
PubMed2025

AWGE-ESPCA: An edge sparse PCA model based on adaptive noise elimination regularization and weighted gene network for Hermetia illucens genomic data analysis.

Hermetia illucens is an important insect resource. Studies have shown that exploring the effects of Cu2+-stressed on the growth and development of the Hermetia illucens genome holds significant scientific importance. There are three major challenges in the current studies of Hermetia illucens genomic data analysis: firstly, the lack of available genomic data which limits researchers in Hermetia illucens genomic data analysis. Secondly, to the best of our knowledge, there are no Artificial Intelligence (AI) feature selection models designed specifically for Hermetia illucens genome. Unlike human genomic data, noise in Hermetia illucens data is a more serious problem. Third, how to choose those genes located in the pathway enrichment region. Existing models assume that each gene probe has the same priori weight. However, researchers usually pay more attention to gene probes which are in the pathway enrichment region. Based on the above challenges, we initially construct experiments and establish a new Cu2+-stressed Hermetia illucens growth genome dataset. Subsequently, we propose AWGE-ESPCA: an edge Sparse PCA model based on adaptive noise elimination regularization and weighted gene network. The AWGE-ESPCA model innovatively proposes an adaptive noise elimination regularization method, effectively addressing the noise challenge in Hermetia illucens genomic data. We also integrate the known gene-pathway quantitative information into the Sparse PCA(SPCA) framework as a priori knowledge, which allows the model to filter out the gene probes in pathway-rich regions as much as possible. Ultimately, this study conducts five independent experiments and compared four latest Sparse PCA models as well as representative supervised and unsupervised baseline models to validate the model performance. The experimental results demonstrate the superior pathway and gene selection capabilities of the AWGE-ESPCA model. Ablation experiments validate the role of the adaptive regularizer and network weighting module. To summarize, this paper presents an innovative unsupervised model for Hermetia illucens genome analysis, which can effectively help researchers identify potential biomarkers. In addition, we also provide a working AWGE - ESPCA model code in the address: https://github.com/yhyresearcher/AWGE_ESPCA.

Animals↗
PubMed2002

Use of randomization testing to detect multiple epistatic QTLs.

Here, we describe a randomization testing strategy for mapping interacting quantitative trait loci (QTLs). In a forward selection strategy, non-interacting QTLs and simultaneously mapped interacting QTL pairs are added to a total genetic model. Simultaneous mapping of epistatic QTLs increases the power of the mapping strategy by allowing detection of interacting QTL pairs where none of the QTL can be detected by their marginal additive and dominance effects. Randomization testing is used to derive empirical significance thresholds for every model selection step in the procedure. A simulation study was used to evaluate the statistical properties of the proposed randomization tests and for which types of epistasis simultaneous mapping of epistatic QTLs adds power. Least squares regression was used for QTL parameter estimation but any other QTL mapping method can be used. A genetic algorithm was used to search for interacting QTL pairs, which makes the proposed strategy feasible for single processor computers. We believe that this method will facilitate the evaluation of the importance at epistatic interaction among QTLs controlling multifactorial traits and disorders.

Algorithms↗