SEARCH · PubMed Health

Results for “parameter estimation”

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 793 records · Page 44Linked to original sources

PubMed1995

Population pharmacokinetic modeling: the importance of informative graphics.

PURPOSE: The usefulness of several modelling methods were examined in the development of a population pharmacokinetics model for cefepime. METHODS: The analysis was done in six steps: (1) exploratory data analysis to examine distributions and correlations among covariates, (2) determination of a basic pharmacokinetic model using the NON-MEM program and obtaining Bayesian individual parameter estimates, (3) examination of the distribution of parameter estimates, (4) multiple linear regression (MLR) with case deletion diagnostics, generalized additive modelling (GAM), and tree-based modelling (TBM) for the selection of covariates and revealing structure in the data, (5) final NONMEM modelling to determine the population PK model, and (6) the evaluation of final parameter estimates. RESULTS: An examination of the distribution of individual clearance (CL) estimates suggested bimodality. Thus, the mixture model feature in NONMEM was used for the separation of subpopulations. MLR and GAM selected creatinine clearance (CRCL) and age, while TBM selected both of these covariates and weight as predictors of CL. The final NONMEM model for CL included only a linear relationship with CRCL. However, two subpopulations were identified that differed in slope and intercept. CONCLUSIONS: The findings suggest that using informative graphical and statistical techniques enhance the understanding of the data structure and lead to an efficient analysis of the data.

Adolescent↗

PubMed2003

Numerical non-identifiability regions of the minimal model of glucose kinetics: superiority of Bayesian estimation.

The so-called minimal model (MM) of glucose kinetics is widely employed to estimate insulin sensitivity (S(I)) both in clinical and epidemiological studies. Usually, MM is numerically identified by resorting to Fisherian parameter estimation techniques, such as maximum likelihood (ML). However, unsatisfactory parameter estimates are sometimes obtained, e.g. S(I) estimates virtually zero or unrealistically high and affected by very large uncertainty, making the practical use of MM difficult. The first result of this paper concerns the mathematical demonstration that these estimation difficulties are inherent to MM structure which can expose S(I) estimation to the risk of numerical non-identifiability. The second result is based on simulation studies and shows that Bayesian parameter estimation techniques are less sensitive, in terms of both accuracy and precision, than the Fisherian ones with respect to these difficulties. In conclusion, Bayesian parameter estimation can successfully deal with difficulties of MM identification inherently due to its structure.

Bayes Theorem↗

PubMed2000

To smooth or not to smooth? Bias and efficiency in fMRI time-series analysis.

This paper concerns temporal filtering in fMRI time-series analysis. Whitening serially correlated data is the most efficient approach to parameter estimation. However, if there is a discrepancy between the assumed and the actual correlations, whitening can render the analysis exquisitely sensitive to bias when estimating the standard error of the ensuing parameter estimates. This bias, although not expressed in terms of the estimated responses, has profound effects on any statistic used for inference. The special constraints of fMRI analysis ensure that there will always be a misspecification of the assumed serial correlations. One resolution of this problem is to filter the data to minimize bias, while maintaining a reasonable degree of efficiency. In this paper we present expressions for efficiency (of parameter estimation) and bias (in estimating standard error) in terms of assumed and actual correlation structures in the context of the general linear model. We show that: (i) Whitening strategies can result in profound bias and are therefore probably precluded in parametric fMRI data analyses. (ii) Band-pass filtering, and implicitly smoothing, has an important role in protecting against inferential bias.

Algorithms↗

PubMed2001

Physician and population determinants of rates of middle-ear surgery in Ontario.

CONTEXT: Small-area variations in surgical rates raise concerns about access to care, treatment appropriateness, and the quality and cost of care. OBJECTIVE: To measure small-area variations in rates of myringotomy with insertion of tympanostomy tubes (TTs) and to identify determinants of rate variation. DESIGN AND SETTING: Retrospective analyses using hospital discharge data for patients who had undergone a myringotomy with insertion of TT by county in Ontario between April 1, 1996, and March 31, 1999. Information on possible determinants was taken from a survey of otolaryngologists and primary care physicians in 1996 and from the 1996 Canadian census and physician demographic databases for 1996-1999. PARTICIPANTS: A total of 75 358 hospitalizations for TT placement of children and adolescents (aged </=14 years). MAIN OUTCOME MEASURE: Small-area variation in rates of TT. RESULTS: An almost 10-fold difference between the areas with the highest and lowest rates was found (extremal quotient, 9.6; 95% confidence interval [CI], 8.2-11.1; P<.001). Higher rates occurred in counties with higher percentages of high school graduates (parameter estimate, 0.01; 95% CI, 0-0.02; P =.049); and where referring physicians were more likely to be male (parameter estimate, 0.01; 95% CI, 0-0.02; P =.01), North American-trained (parameter estimate, 0.01; 95% CI, 0.01-0.02; P<.001), and have higher propensities to refer for surgery (parameter estimate, 0.40; 95% CI, 0.09-0.72; P =.02). Otolaryngologist opinion was not a significant predictor. CONCLUSION: Substantial area variation in TT rates was observed. The opinion of primary care physicians was the dominant modifiable determinant, suggesting an area of research that may be important in reducing area variation in TT procedures.

Adolescent↗

PubMed1998

Temporal sampling requirements for the tracer kinetics modeling of breast disease.

The physiological parameters measured in the tracer kinetics modeling of data from a dynamic contrast-enhanced magnetic resonance (MR) breast exam (blood flow-extraction fraction product [FE], volume of the extracellular extravascular space [Ve], and blood volume [Vb]) may enable non-invasive diagnosis of breast cancer. One of the factors that compromises the accuracy and precision of the parameter estimates, and therefore their diagnostic potential, is the temporal resolution of the MR scans used to measure contrast agent (gadolinium-diethylenetriamine pentaacetic acid [Gd-DTPA]) concentration in an artery (arterial input function [AIF]) and in the tissue (tissue residue function [TRF]). Using computer simulations, we have examined, for several AIF widths, the errors introduced into estimates of tracer kinetic parameters in breast tissue due to insufficient temporal sampling. Temporal sampling errors can be viewed as uncertainties and biases in the parameter estimates introduced by the uncertainty in the relative alignments of the AIF, TRF, and sampling grid. These effects arise from the model's inherent sensitivity to error in either the AIF or TRF, which is dependent on the values of the tracer kinetic parameters and increases with AIF width. Based on the results of the simulations, to ensure that the error in FE and Ve will be under 10% of their true values, we recommend a rapid bolus injection of contrast agent (approximately 10 s), that the AIF be sampled every second, and that the TRF be sampled every 16 s or less. An accurate measurement of Vb requires that the TRF be sampled at least every 4 s. The results of these investigations can be used to set minimum dynamic imaging rates for tracer kinetics modeling of the breast.

Breast↗

PubMed1989

Allopurinol kinetics in humans as a means to assess liver function: design of a loading test.

A six-compartment model of allopurinol and oxipurinol kinetics, after intravenous allopurinol injection in the human, is studied further to improve the blood and urine specimen collection schedule for clinical use. The effects of various error sources are also investigated by simple techniques like real data set truncation and adding normally distributed random errors to data obtained from simulation of allopurinol and oxipurinol plasma curves with preset parameters. All parameters estimation is performed with the NONLIN parameter estimation program. Main interest was focused on estimation of the fractional rate constant of transport from the central "extracellular" compartment to the metabolically active compartment. This parameter is regarded as a lumped measure of liver perfusion and liver cell membrane transport. The blood sampling schedule can be reduced to six specimens collected over 60 min, without affecting the accuracy and precision of estimated clinical parameters. The maximum allowable coefficient of variation for preanalytical errors and the analytical within-run and between-run errors are around 5, 4, and 5%, respectively. Analytical between-run bias up to 20% does not affect the estimate of the principal parameter, when both allopurinol and oxipurinol are biased in the same direction. Collection and analysis of urine samples was shown to be unnecessary.

Allopurinol↗

PubMed1999

[On the problems of fitting linear regression models for hierarchically structured data in medical research].

There are a large number of the hierarchically structured data in the field of medical sciences, which have been analyzed usually by conventional linear regression models. The objective of this paper is to explore the problems and the relationship of parameter estimates of the three common linear regression models in fitting the hierarchically structured date, and the correction of the precision of parameter estimates. It is shown that the estimate of parameter and it's precision of linear regression models is related to the variation of independent variable between and within level 2 units, and the difference of residual estimates is associated with the difference of parameter estimates. The three common linear regression models are all inappropriate for the hierarchically structured data, but the standard error of the level 1 combined model can be corrected by variance inflation factor in conditions.

Analysis of Variance↗

PubMed1994

Quantification of two-dimensional NOE spectra via a combined linear and nonlinear least-squares fit.

Determining the volumes of peaks in 2D NMR spectra can be prohibitively difficult in cases of overlapping, broad lines. Deconvolution and parameter estimation can be attempted on either the time-domain or the frequency-domain data. We present a method of estimating spectral parameters from frequency-domain data, using a combination of Lorentzian and Gaussian lineshapes for reference lines. This approach combines a previously published method of projecting the data on a linear space spanned by reference lines with a nonlinear least-squares fitting algorithm. Comparison of this method with other published methods of frequency-domain deconvolution shows that it is both more precise and more accurate when estimating 2D volumes.

Algorithms↗

PubMed1995

Bioelectrical impedance analysis as a predictor of survival in patients with human immunodeficiency virus infection.

In patients with AIDS, short-term survival has been related to body weight, body composition, and serum nutritional parameters, but their prognostic impact at earlier stages of the HIV infection is not known. With an individual follow-up period of 1,000 days, we investigated the prognostic relevance of electrical tissue conductivity [resistance R, reactance Xc, phase angle alpha, extracellular mass (ECM), body cell mass (BCM)] measured by bioelectrical impedance analysis, of the CD4+ cell count, and of serum parameters indicating malnutrition in 75 HIV-infected male patients at Walter Reed stages 3-5. After initial recording, 29 patients (38.7%) died from AIDS during this period. Among 12 parameters estimated with a semiparametric Cox regression model adjusted for therapy (pentamidine, azidothymidine), the phase angle alpha (parameter estimate: -1.043, 95% confidence interval of -0.61 to -1.47; p < or = 0.0001), the ECM/BCM ratio, Xc, BCM, serum cholesterol, number of CD4+ cells, and serum albumin had significant prognostic influence on survival, whereas age, body weight, body mass index, resistance, serum protein, and serum triglycerides did not. In a model with four covariates (CD4+ cells, phase angle, pentamidine, azidothymidine), the prognostic impact of the CD4+ cell count (parameter estimate: -0.549) was lower compared with the phase angle alpha (parameter estimate: -0.799; p < or = 0.0001) and did not gain statistical significance (p = 0.0626). The phase angle alpha was the best single predictive factor for survival among all 12 parameters (comparison of the respective Cox models with the likelihood ratio test).(ABSTRACT TRUNCATED AT 250 WORDS)

Adult↗

PubMed2004

On the chi-square approximation to the exact distribution of goodness-of-fit statistics in multinomial models with composite hypotheses.

Multinomial models are increasingly being used in psychology, and this use always requires estimating model parameters and testing goodness of fit with a composite null hypothesis. Goodness of fit is customarily tested with recourse to the asymptotic approximation to the distribution of the statistics. An assessment of the quality of this approximation requires a comparison with the exact distribution, but how to compute this exact distribution when parameters are estimated from the data appears never to have been defined precisely. The main goal of this paper is to compare two different approaches to defining this exact distribution. One of the approaches uses the marginal distribution and is, therefore, independent of the data; the other approach uses the conditional distribution of the statistics given the estimated parameters and, therefore, is data-dependent. We carried out a thorough study involving various parameter estimation methods and goodness-of-fit statistics, all of them members of the general class of power-divergence measures. Included in the study were multinomial models with three to five cells and up to three parameters. Our results indicate that the asymptotic distribution is rarely a good approximation to the exact marginal distribution of the statistics, whereas it is a good approximation to the exact conditional distribution only when the vector of expected frequencies is interior to the sample space of the multinomial distribution.

Binomial Distribution↗

PubMed1985

Estimating the parameters in the two-component model for cell survival from experimental quantal response data.

A statistical technique is given which can be used to estimate the parameters of the two-component model for cell survival from quantal response multifraction data. The method is a nonlinear logistic regression and relies on a mild assumption relating the probability of death to cell survival level. The method is demonstrated on mouse colon data, where more efficient estimates of the parameters are known, and the agreement is good. Also for some mouse lung LD50 data we obtain estimates of the parameters, and the fit to the data is shown to be better than that of linear-quadratic model.

Animals↗

PubMedDate not supplied

Inverse analyses of transport of chlorinated hydrocarbons subject to sequential transformation reactions.

Chemical and biological transformations can significantly affect contaminant transport in the subsurface. To better understand such transformation reactions, an equilibrium-nonequilibrium sorption transport model, HYDRUS-1D, was modified by including inverse solutions for multiple breakthrough curves resulting from the transport of solutes undergoing sequential transformations. The inverse solutions were applied to miscible-displacement experiments involving dissolved concentrations of trichloroethylene (TCE) undergoing reduction and/or transformations in the presence of zero-valent metal porous media (i.e., iron or copper-coated iron filings) to produce ethylene. The inverse model solutions provided a reasonable description of the transport and transformation processes. Simultaneous fitting of multiple breakthrough curves of TCE and ethylene placed additional constraints on the inverse solution and improved the reliability of parameter estimates. Confidence intervals of optimized parameters were reduced significantly in comparison with those obtained by fitting TCE breakthrough curves independently. Further evidence for accurate parameter estimates was given when the parameter values agreed with previously reported values from independent batch and degradation experiments. Optimized values of the normalized degradation rates for the equilibrium (1.4 x 10(-4) to 7.2 x 10(-5) L h(-1)m(-2)) and nonequilibrium (1.2 x 10(-4) to 5.5 x 10(-5)L h(-1)m(-2)) models compared well with values (0.03 to 6.5 x 10(-5) L h(-1) m(-2)) obtained from previous studies. The estimated TCE-iron sorption coefficients (0.52 to 2.85 L kg(-1)) were also consistent with a previously reported value (1.47 L kg(-1)).

Biotransformation↗

PubMed2005

Evaluating the impact of the HIV pandemic on measles control and elimination.

OBJECTIVE: To estimate the impact of the HIV pandemic on vaccine-acquired population immunity to measles virus because high levels of population immunity are required to eliminate transmission of measles virus in large geographical areas, and HIV infection can reduce the efficacy of measles vaccination. METHODS: A literature review was conducted to estimate key parameters relating to the potential impact of HIV infection on the epidemiology of measles in sub-Saharan Africa; parameters included the prevalence of HIV, child mortality, perinatal HIV transmission rates and protective immune responses to measles vaccination. These parameter estimates were incorporated into a simple model, applicable to regions that have a high prevalence of HIV, to estimate the potential impact of HIV infection on population immunity against measles. FINDINGS: The model suggests that the HIV pandemic should not introduce an insurmountable barrier to measles control and elimination, in part because higher rates of primary and secondary vaccine failure among HIV-infected children are counteracted by their high mortality rate. The HIV pandemic could result in a 2-3% increase in the proportion of the birth cohort susceptible to measles, and more frequent supplemental immunization activities (SIAs) may be necessary to control or eliminate measles. In the model the optimal interval between SIAs was most influenced by the coverage rate for routine measles vaccination. The absence of a second opportunity for vaccination resulted in the greatest increase in the number of susceptible children. CONCLUSION: These results help explain the initial success of measles elimination efforts in southern Africa, where measles control has been achieved in a setting of high HIV prevalence.

Adolescent↗

PubMed1997

Comparison of population pharmacokinetic modeling methods using simulated data: results from the Population Modeling Workgroup.

Statistical modeling methods have had increasing use in drug disposition studies, both to estimate pharmacokinetic parameters and to develop regression models that relate these parameter estimates to patient characteristics. These methods are particularly flexible as they allow non-linearity and sparse within-patient information. In the past few years, multiple analysis methods have become available, but there is a lack of systematic comparisons of their estimates on the same data sets. Two simulated data sets were therefore developed by the Population Modeling Workgroup of the Biopharmaceutical Section of the American Statistical Association. We analysed these data sets using seven population modeling programs, some of which contain multiple analysis methods. Although each data set represents a single replicate from a given model and data collection design, the results suggest that the behaviour of some methods differs from that of the others.

Anti-Arrhythmia Agents↗

PubMed2000

Framework for online optimization of recombinant protein expression in high-cell-density Escherichia coli cultures using GFP-fusion monitoring.

A framework for the online optimization of protein induction using green fluorescent protein (GFP)-monitoring technology was developed for high-cell-density cultivation of Escherichia coli. A simple and unstructured mathematical model was developed that described well the dynamics of cloned chloramphenicol acetyltransferase (CAT) production in E. coli JM105 was developed. A sequential quadratic programming (SQP) optimization algorithm was used to estimate model parameter values and to solve optimal open-loop control problems for piecewise control of inducer feed rates that maximize productivity. The optimal inducer feeding profile for an arabinose induction system was different from that of an isopropyl-beta-D-thiogalactopyranoside (IPTG) induction system. Also, model-based online parameter estimation and online optimization algorithms were developed to determine optimal inducer feeding rates for eventual use of a feedback signal from a GFP fluorescence probe (direct product monitoring with 95-minute time delay). Because the numerical algorithms required minimal processing time, the potential for product-based and model-based online optimal control methodology can be realized.

Algorithms↗

PubMed2000

Non-linear regression analysis with errors in both variables: estimation of co-operative binding parameters.

Four different parameter estimation criteria, the geometric mean functional relationship (GMFR), the maximum likelihood (ML), the perpendicular least-squares (PLS) and the non-linear weighted least squares (WLS), were used to fit a model to the observed data when both regression variables were subject to error. Performances of these criteria were evaluated by fitting the co-operative drug-protein binding Hill model on simulated data containing errors in both variables. Six types of data were simulated with known variances. Comparison of the criteria was done by evaluating the bias, the relative standard deviation (S.D.) and the root-mean-squared error (RMSE), between estimated and true parameter values. Results show that (1) for data with correlated errors, all criteria perform poorly; in particular, the GMFR and ML criteria. For data with uncorrelated errors, all criteria perform equally well with regard to the RMSE. (2) Use of GMFR and ML lead to lower values for S.D. but higher biases compared with WLS and PLS. (3) WLS performs less well when equal dispersion is applied to the two observed variables.

Binding Sites↗

PubMed1991

Moment method for the estimation of mass transfer coefficients for physiological pharmacokinetic models.

In vitro and in vivo techniques have been utilized to estimate mass transfer coefficients for physiological pharmacokinetic models. No single method has been adopted for estimating this parameter, in part, due to the different model structures with which this parameter may be associated. A specific method has been derived to calculate mass transfer coefficients for non-eliminating membrane-limited tissue compartments. The present method is based on observed concentration-time data, and requires the calculation of the areas under the zero and first moment curves for plasma, and the first moment curve for the tissue. A Monte Carlo simulation technique was used to determine the percentage biases of the method based on a published model for streptozoticin and adriamycin. For the latter model, the method was compared to a non-linear regression parameter estimation technique.

Humans↗

PubMed2004

Sampling correction in linkage analysis.

In a linkage analysis that requires the estimation of parameters other than the recombination fraction, we can construct a pedigree likelihood that leads to consistent parameter estimators if the sampling procedures are known. In particular, it is necessary to identify the subset of pedigree members "relevant to sampling" (RS), where by sampling we mean both pedigree ascertainment through a proband combination and the selective inclusion of the sampled pedigrees in the data that are analyzed. If both these procedures are independent of the marker phenotypes and the model of trait inheritance is known, then no sampling or ascertainment correction is needed to obtain a consistent estimator of the recombination fraction. Otherwise, the correction can be of two types: sampling-model-based, in which the ascertainment and inclusion procedures are modeled and used in the likelihood expression, or sampling-model-free, in which the data RS are "conditioned out" without any modeling of the sampling procedures. In either case, the pedigree proband sampling frame must be identified.

Chromosome Mapping↗