SEARCH · PubMed Health

Results for “Linear Regression”

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 217 records · Page 12Linked to original sources

PubMedDate not supplied

QSAR based on multiple linear regression and PLS methods for the anti-HIV activity of a large group of HEPT derivatives.

Quantitative structure-activity relationships have been developed for a set of 107 inhibitors of the HIV-1 reverse transcriptase, derivatives of a recently reported HIV-1 specific lead: 1-[(2-hydroxyethoxy)methyl]-6-(phenylthio)thymine (HEPT). The activity of these compounds was investigated by means of multiple linear regression (MLR) and PLS regression techniques and topological indexes as well as several tabulated physicochemical substituent constants were used as predictor variables. The results obtained indicate that the anti-HIV activity of the HEPT derivatives is strongly dependent on hydrophobic factors as expressed by the Hansch constant (sigma pi (R1+R2)), and especially dependent on the geometric factors mainly accounted for by the 1 chi N (R2) and 4 chi pN molecular connectivity indexes and also for the molecular volume (Vx), the Taft steric constant (Es(2R1)), and the Verloop parameter for the smallest width value (B1(3R1)). Besides, for this data set, comparison of the quality of MLR and PLS models show that PLS is a better approach to MLR for improving the interpretability of the data and also to exhibit models with a better predictive quality.

Anti-HIV Agents↗

PubMed2000

Development of comprehensive descriptors for multiple linear regression and artificial neural network modeling of retention behaviors of a variety of compounds on different stationary phases.

A new series of six comprehensive descriptors that represent different features of the gas-liquid partition coefficient, K(L), for commonly used stationary phases is developed. These descriptors can be considered as counterparts of the parameters in the Abraham solvatochromic model of solution. A separate multiple linear regression (MLR) model was developed by using the six descriptors for each stationary phase of poly(ethylene glycol adipate) (EGAD), N,N,N',N'-tetrakis(2-hydroxypropyl) ethylenediamine (THPED), poly(ethylene glycol) (Ucon 50 HB 660) (U50HB), di(2-ethylhexyl)phosphoric acid (DEHPA) and tetra-n-butylammonium N,N-(bis-2-hydroxylethyl)-2-aminoethanesulfonate (QBES). The results obtained using these models are in good agreement with the experiment and with the results of the empirical model based on the solvatochromic theory. A 6-6-5 neural network was developed using the descriptors appearing in the MLR models as inputs. Comparison of the mean square errors (MSEs) shows the superiority of the artificial neural network (ANN) over that of the MLR. This indicates that the retention behavior of the molecules on different columns show some nonlinear characteristics. The experimental solvatochromic parameters proposed by Abraham can be replaced by the calculated descriptors in this work.

Linear Models↗

PubMed2006

MLR-tagging: informative SNP selection for unphased genotypes based on multiple linear regression.

UNLABELLED: The search for the association between complex diseases and single nucleotide polymorphisms (SNPs) or haplotypes has recently received great attention. For these studies, it is essential to use a small subset of informative SNPs accurately representing the rest of the SNPs. Informative SNP selection can achieve (1) considerable budget savings by genotyping only a limited number of SNPs and computationally inferring all other SNPs or (2) necessary reduction of the huge SNP sets (obtained, e.g. from Affymetrix) for further fine haplotype analysis. A novel informative SNP selection method for unphased genotype data based on multiple linear regression (MLR) is implemented in the software package MLR-tagging. This software can be used for informative SNP (tag) selection and genotype prediction. The stepwise tag selection algorithm (STSA) selects positions of the given number of informative SNPs based on a genotype sample population. The MLR SNP prediction algorithm predicts a complete genotype based on the values of its informative SNPs, their positions among all SNPs, and a sample of complete genotypes. An extensive experimental study on various datasets including 10 regions from HapMap shows that the MLR prediction combined with stepwise tag selection uses fewer tags than the state-of-the-art method of Halperin et al. (2005). AVAILABILITY: MLR-Tagging software package is publicly available at http://alla.cs.gsu.edu/~software/tagging/tagging.html

Algorithms↗

PubMed1998

The application of multiple linear regression to the measurement of the median particle size of drugs and pharmaceutical excipients by near-infrared spectroscopy.

A number of powdered drugs and pharmaceutical excipients were used to demonstrate the ability of near-infrared spectroscopy to measure median particle size (d50). Sieved fractions and bulk samples of aspirin, anhydrous caffeine, paracetamol, lactose monohydrate and microcrystalline cellulose were particle sized by forward angle laser light scattering (FALLS) and scanned by fibre-optic probe FT-NIR spectroscopy. Two-wavenumber multiple linear regression (MLR) calibrations were produced using: NIR reflectance; absorbance and Kubelka-Munk function data with each of median particle size, reciprocal median particle size and the logarithm of median particle size. Best calibrations were obtained using reflectance data versus the logarithm of median particle size (NIR predicted lnd50 versus ln(FALLS d50) for microcrystalline cellulose and lactose monohydrate sieve fraction calibrations: r = 0.99 in each case). Working calibrations for lactose monohydrate (median particle size range: 19.2-183 microns) and microcrystalline cellulose (median particle size range: 24-406 microns) were set-up using combinations of machine sieve-fractions and bulk samples. This approach was found to produce more robust calibrations than just the use of sieved fractions. The method has been compared with single wavenumber quadratic least squares regression using reflectance and mean-corrected reflectance data with median particle size. Correlation between NIR predicted and FALLS values was significantly better using the MLR method.

Calibration↗

PubMed2002

Optimal method of linear regression in laser remote sensing.

Remote lidar sensing in the photon-counting mode is now the commonly accepted method for studying atmospheric processes in the lower and free atmosphere. However, when processing signals obtained from lidar measurements, investigators necessarily face the problem of achieving accuracy in reconstructing the atmospheric parameters despite the presence of inhomogeneous noise in the measured signals. We propose an optimal method of linear regression (OMLR) of signals. The accuracy of the the method for the reconstructed signal is estimated. An example of application of the OMLR to the reconstruction of the temperature profile from the data obtained with a Raman lidar at the Siberian Lidar Station of the Institute of Atmospheric Optics (Tomsk, Russia) is given. The proposed method is distinguished by simplicity of interpretation of the criteria used, based on careful adherence to statistical principles. This method is shown to be an efficient auxiliary tool for the processing of measured data.

Journal Article↗

PubMed2003

Measurement of quality of life VII. Statistical covariation and global quality of life data: the method of weight-modified linear regression.

Existing standard statistical procedures do not seem to fulfill the needs of the researcher in global quality-of-life (QOL) research, because the most interesting question seems to be the exact size of statistical covariations. A method is necessary if we are to isolate the most important factors connected to quality of life among the thousands of possible factors in life. We have developed a new procedure we call "weight-modified linear regression". Unfortunately as demonstrated in the discussion, the procedure is not totally without problems and weaknesses. In spite of the critique, we believe the procedure to be valid for the purpose of estimating the size of the covariation in population studies including psychometric measures of global quality of life. As we need to be certain that the procedure is valid, we hereby invite the scientific community to give us further critique of the method and suggestions for its improvement.

Humans↗

PubMed2003

Comparative investigation of superoxide trapping by cyclic nitrone spin traps: the use of singular value decomposition and multiple linear regression analysis.

The kinetics of the reaction between superoxide and the spin trapping agents 5,5-dimethyl-1-pyrroline N-oxide (DMPO), 5-(diethoxyphosphoryl)-5-methyl-1-pyrroline N-oxide (DEPMPO), and 5-tert-butoxycarbonyl-5-methyl-1-pyrroline N-oxide (BMPO) were re-examined in the superoxide-generating xanthine/xanthine oxidase system, by competition with spontaneous dismutation. The approach used singular value decomposition (SVD), multiple linear regression, and spectral simulation. The experiments were carried out using a two-syringe mixing arrangement with fast scan acquisition of 100 consecutive EPR spectra. Using SVD analysis, the extraction of both temporal and spectral information could be obtained from in a single run. The superoxide spin adduct was the exclusive EPR active species in the case of DEPMPO and BMPO, and the major component when DMPO was used. In the latter case a very low concentration of hydroxyl adduct was also observed, which did not change during the decay of the DMPO-superoxide adduct. This indicates that the hydroxyl radical adduct is not formed from the spontaneous decay of the superoxide radical adduct, as has been previously suggested [correction]. It was established that in short-term studies (up to 100 s) DMPO was the superior spin trapping agent, but for reaction times longer than 100 s the other two spin traps were more advantageous. The second order rate constants for the spin trapping reaction were found to be DMPO (2.4 M(-1)s(-1)), DEPMPO (0.53 M(-1)s(-1)), and BMPO (0.24 M(-1)s(-1)) determined through competition with spontaneous dismutation of superoxide, at pH 7.4 and 20 degrees C.

Cyclic N-Oxides↗

PubMed2025

A robust transfer learning approach for high-dimensional linear regression to support integration of multi-source gene expression data.

Transfer learning aims to integrate useful information from multi-source datasets to improve the learning performance of target data. This can be effectively applied in genomics when we learn the gene associations in a target tissue, and data from other tissues can be integrated. However, heavy-tail distribution and outliers are common in genomics data, which poses challenges to the effectiveness of current transfer learning approaches. In this paper, we study the transfer learning problem under high-dimensional linear models with t-distributed error (Trans-PtLR), which aims to improve the estimation and prediction of target data by borrowing information from useful source data and offering robustness to accommodate complex data with heavy tails and outliers. In the oracle case with known transferable source datasets, a transfer learning algorithm based on penalized maximum likelihood and expectation-maximization algorithm is established. To avoid including non-informative sources, we propose to select the transferable sources based on cross-validation. Extensive simulation experiments as well as an application demonstrate that Trans-PtLR demonstrates robustness and better performance of estimation and prediction when heavy-tail and outliers exist compared to transfer learning for linear regression model with normal error distribution. Data integration, Variable selection, T distribution, Expectation maximization algorithm, Genotype-Tissue Expression, Cross validation.

Linear Models↗

PubMedDate not supplied

Singapore: hospital capacity prediction by fuzzy linear regression.

Strategic planning for hospital inpatient capacity is important in providing quality healthcare service at a reasonable cost. This study estimates annual average hospital length of stay (LOS) as an aggregate quantity for all private and public hospitals in Singapore. Because LOS depends on a patient's medical history as well as on the severity and type of illness, it is a random variable that involves a wide spread. Hence, providing an accurate estimate for LOS poses a challenge but is very valuable. In this article, a multivariate fuzzy linear regression (FLR) model is developed for predicting aggregate annual LOS. The results show that FLR can provide accurate point and interval forecasts, although the amount of training data is small and the spread is wide.

Hospital Bed Capacity↗

PubMed1990

A two-phase linear regression model for biologic half-life data.

In estimating the biologic half-life of an infused drug or biologic agent, one very frequently used model is the biexponential, which reflects a two-compartment physiologic model. The difficulty in using this model is that it is nonlinear in the parameters and requires relatively sophisticated analysis. Furthermore, an interval estimate is not usually reported. We propose the use of a two-phase linear regression approach, which is tantamount to breaking down the model into two straight lines based on the selection of the logarithm of concentration as the ordinate and time as the abscissa. We show how to determine the joint or changeover point for the two lines using a simple iterative procedure, how to select between a one-phase and a two-phase model, and how to provide a simple confidence interval estimate for half-life when it exists. An example using data from a study of Factor VIII pharmacokinetics is given.

Factor VIII↗

PubMed2000

Statistical testing of drug accumulation in skin tissues by linear regression versus contents of stratum corneum lipids.

This investigation is a contribution to standardization in in vitro drug penetration measurements using excised human skin and to statistical treatment of the observations. The wide variations observed in measurements of drug accumulation in and drug permeation through the stratum corneum are caused not only by analytical errors but also by the variability of the horny layer lipid composition. The last-mentioned systematic influence can be compensated for by stepwise (multiple) linear regression using the contents of the main lipid classes as independent variables. In consequence, the S.E. of estimate given by the regression calculation is lower than the S.E. of the means of the observations. Significant differences in drug quantities accumulated in skin tissues (stratum corneum and dermis) are sensitively detected by Chow's F-test of structural change. Accumulation data of flufenamic acid and hydrocortisone penetrated from different bases are given as examples. The calculation mode is exemplarily explained and discussed. The results of the test for structural change, two-independent-groups t-test and paired-samples t-test are compared. The F-test of structural change proves to be a helpful statistical method suitable to the assessment of biopharmaceutical quality parameters and to measurements using biological materials.

Administration, Topical↗

PubMed1999

Determination of drug-plasma protein binding using human serum albumin chromatographic column and multiple linear regression model.

Reversible attachment to serum proteins plays a significant role in pharmacokinetics and pharmacodynamics, and a clear understanding of this process is fundamental in the development of the rational use of many therapeutics agents. Over the last few years, it has been demonstrated that immobilized human serum albumin (HSA) could be used to estimate plasma protein binding. A series of 40 structurally unrelated pharmaceutical compounds were chromatographed on an immobilized HSA column in order to construct a protein binding 'calibration curve' and multiple linear regression system. When studying the relationship between the chromatographic retention and the percentage of binding determined in vitro, a good correlation can be observed (r(2) = 0.799) using a wide variety of compounds with different binding affinities (from 0 to 99% binding). Using a quantitative structure-retention relationships (QSRR) approach to analysing chromatographic data, the correlation was improved compared to the traditional approach (r(2) = 0.824).

Chromatography, Liquid↗

PubMed1997

Relationship between human genotype and phenotype of N-acetyltransferase (NAT2) as estimated by discriminant analysis and multiple linear regression: 1. Genotype and N-acetylation in vivo.

Twenty-six healthy Caucasian subjects were evaluated for polymorphic N-acetyltransferase (NAT2) metabolic activity in vivo by sulfamethazine phenotyping and for their respective NAT2 genotype. Application of discriminant analysis allowed the separation of the rapid and slow acetylators solely on the base of their respective mutation pattern with identical results as achieved by the classical method of discrimination according to the phenotyping results. Multiple linear regression analysis was used to obtain a quantitative relationship between allelic pattern and the phenotypic outcome. It is shown that the computation methods produce relationships enabling the influence of particular mutations and/or allelic configurations on the metabolic activity in vivo to be estimated. This may be important in cases of discordant or overlapping phenotype and genotype results as well as in investigating the NAT2 polymorphism as a risk factor for cancer and other disease in epidemiological studies.

Acetylation↗

PubMed2003

Linear regression analysis and its application to the multivariate spectral calibrations for the multiresolution of a ternary mixture of caffeine, paracetamol and metamizol in tablets.

The multivariate spectral calibration methods, tri-linear regression-calibration (TLRC) and multi-linear regression-calibration (MLRC) were developed for the multiresolution of a ternary mixture of caffeine (CAF), paracetamol (APAP), metamizol (MET), which have closely overlapped in the spectra. The calibration algorithms were briefly described for the three-component system, CAF-APAP-MET. By using the various synthetic mixtures of three compounds, the validity of the TLRC and MLRC methods was confirmed and applied to the real samples containing the above-mentioned compounds in two different commercial tablet formulations. The TLCR and MLRC methods which are very rapid, easy to apply, yet not expensive, are powerful tools with very simple mathematical contents for multiresolution of the three- or multi-component mixture systems. The data treatments were carried out by the MAPLE V, EXCEL and SPSS 10.0 Softwares. The obtained results were successfully compared with each other as well as with those obtained by other literature methods.

Acetaminophen↗

PubMed1995

Separation of fetal and maternal ECG complexes from a mixed signal using an algorithm based on linear regression.

Fetal scalp ECG and Doppler ultrasound are the two methods universally used to derive the fetal heart rate (FHR) for cardiotocography. Other fetal signal sources have not been used successfully because of the complexity of the signal and the need for an additional maternal ECG input. In this paper, we present an algorithm for separating the fetal and maternal ECG signals obtained from intrauterine electrodes during labour. The algorithm detects all occurrences of ECG complexes and uses linear regression functions to compare each complex with a set templates. Sets of templates are identified as either maternal or fetal in origin and two signals are output for heart rate measurement. The outputs are also processed to eliminate artefacts that may occur when the maternal and fetal complexes are coincident. The algorithm processes 10 seconds of data at a time (in about 200 ms on a standard PC) while a further 10 s of data is being acquired. It has the advantage that no extra input is required, such as maternal ECG obtained from chest leads, and only assumes that two different populations of complexes of two different shapes are present in the input signal. The algorithm could also be used for the separation of fetal and maternal signals obtained from abdominal electrodes.

Algorithms↗

PubMed1976

An application of non-linear regression analysis to tests of liver function.

Serum samples from 42 cases of acute hepatitis were analysed for up to 10 tests of liver function. The results of these tests were then analysed by standard statistical methods. A curve fitting exercise was performed and regression coefficients and comparative data were calculated for each of six curve types, relating to each pair of liver function tests. The correlation coefficients found were then tested for significance. From the 216 correlation coefficients tested eleven were found to be highly significant (p less than 0.001) and of these, seven were of non-linear regression curves. Examples have been given of the use of regression equations in assessing the relative sensitivities of different tests at levels on the borderline of the normal range.

Acute Disease↗

PubMed2000

Application of Multiple Linear Regression and Extended Principal-Component Analysis to Determination of the Acid Dissociation Constant of 7-Hydroxycoumarin in Water/AOT/Isooctane Reverse Micelles.

The apparent pK(a) of dyes in water-in-oil microemulsions depends on the charge of the acid and base forms of the buffers present in the water pool. Extended principal-component analysis allows the precise determination of the apparent pK(a) and of the spectra of the acid and base forms of the dye. Combination with multiple linear regression increases the precision. The pK(a) of 7-hydroxycoumarin (umbelliferone) was spectrophotometrically measured in a water/AOT/isooctane microemulsion in the presence of a series of buffers carrying different charges at various different water/surfactant ratios. The spectra of the acid and base forms of the dye in the microemulsion are very similar to those in bulk water in the presence of Tris and ammonia. The presence of carbonate changes somewhat the spectrum of the acid form. Results are discussed taking into account the profile of the electrostatic potential drop in the water pool and the possible partition of umbelliferone between the aqueous core and the surfactant. The pK(a) values corrected for these effects are independent of w(0) and are close to the value of the pK(a) in bulk water. Copyright 2000 Academic Press.

Journal Article↗

PubMed1991

Determination of oestrogen receptors: application of the Passing-Bablock linear regression technique for comparison of enzyme immunoassay and radioligand binding assay in 1841 breast cancer tumours.

To test the qualities of two assays in the same laboratory on the same tumours, a single-point dextran-coated charcoal radioligand binding assay (RLA-DCC) and the Abbott enzyme immunoassay (EIA) were used to perform oestrogen receptor determinations on cytosols from 1841 breast cancers over a 2-year period. Statistical analysis of the data was performed by the Passing-Bablock linear regression technique. The final regression curve between EIA (y) and RLA-DCC (x) yielded y = 1.187 x fmol/mg of protein. However, a high variability in this correlation was observed from 1986 to 1988. This variability could be explained by calibration problems in the immunoassay kits and changes in our technical team. The binding assay appears to be more sensitive to the technicians' experience than the immunoassay. Other technical points are discussed, particularly cytosol preparation and KCl presence or absence in the homogenisation buffer. Finally, the Passing-Bablock and the least squares regression procedures are compared. The conditions allowing optimal correlation and routine determination reliability are defined and the correlation variability is discussed.

Breast Neoplasms↗