Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “linear mixed model”

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 757 records · Page 42Linked to original sources
PubMed2005

Borderline personality features in childhood: a short-term longitudinal study.

Borderline personality disorder is a particularly devastating, yet understudied form of psychopathology. One of the most significant gaps in existing knowledge is the lack of systematic, prospective empirical attention to the developmental precursors of borderline personality. The present investigation was an exploratory attempt to address this limitation through (a) development of a psychometrically sound self-report instrument that assesses borderline personality features in childhood, the Borderline Personality Features Scale for Children (BPFS-C); (b) examination of the stability of BPF in childhood; (c) evaluation of gender differences in BPF in childhood; and (d) evaluation of the specificity of the BPFS-C for assessing borderline personality features. These goals were achieved through the prospective study of a normative sample of 400 (54% female) fourth though sixth graders who were assessed during the Fall of Year 1, Spring of Year 1, and Fall of Year 2. The use of linear mixed modeling techniques provided evidence for the construct validity of the BPFS-C. Further, borderline personality features as assessed with the BPFS-C were found to be moderately stable over the course of the study, with girls reporting higher levels of BPF than boys. Results also demonstrated that children's scores on the BPFS-C were uniquely related to indicators of borderline personality pathology above and beyond their scores on the Children's Depression Inventory. The implications of these results for the study of the development and etiology of borderline pathology are discussed.

Aggression↗
PubMed2006

Does music exposure during chemotherapy improve quality of life in early breast cancer patients? A pilot study.

BACKGROUND: Adjuvant chemotherapy is associated with poor quality of life (qol) in breast cancer patients. We tested the effect of listening to music during chemotherapy on quality of life in these patients. MATERIAL/METHODS: We tested in a prospective cohort the changes in qol scores as assessed by European Organization for Research and Treatment of Cancer Quality of Life Questionnaire (EORTC QLQ-C30), and the influence of listening to non-preferred music at the chemotherapy unit on these parameters in a mixed linear model by repeated measures analysis of variance (RMANOVA). RESULTS: For the whole cohort, musical intervention was not associated with a change in any dimension of quality of life. However; the music effect significantly interacted with patient age; patients > 45 years old had improved insomnia and appetite loss scores after musical intervention (F = 6.76, P = 0.019 and F = 11.22, P = 0.004, respectively). CONCLUSIONS: Our results show that brief, non-preferred music exposure at the time of chemotherapy administration does not improve quality of life in patients with early breast cancer. Nonetheless, there is still a possibility that a subgroup will benefit from this approach as suggested by the interaction of the music effect with patient age.

Adult↗
PubMed2006

[Length of postpartum women hospital stay].

OBJECTIVE: Finding maternal factors and hospital characteristics responsible for postpartum length of stay in hospital, as well as assessment of impact of the factors. MATERIALS AND METHODS: 28,469 maternal medical records gathered in 2001-2002 througout nationwide telematic perinatal registry. Linear Mixed Models were used for statistical analysis of two groups: vaginal deliveries and cesarean sections. The outcome variable: postpartum length of stay in hospital. As factors were used: Maternal sociodemographic variables: place of residence, education, marital status, age. Health facts: body mass, if newborn is first baby, length of pregnancy, obstetrical history, diseases before pregnancy. Facts concerning pregnancy, delivery, puerperium: diseases during pregnancy and special events in pregnancy. Hospitals were characterised by reference level. MAIN OBSERVATIONS: Postpartum length of stay depends on mode of delivery, maternal clinical profile (especially length of pregnancy), place of residence, education as well as hospital reference level. RESULTS: Postpartum length of stay for vaginal deliveries is 4,03 days, for CC 6,21 days. Length of stay for urban areas and for the first baby is greater. For delivery < 37 weeks and for complications of puerperium length of stay is greater. For vaginal deliveries under and normal weight shorten it. In CC women with underweight, university education and special events in pregnancy and delivery stay is shorter. Stay in local hospital is longer.

Adult↗
PubMed2006

High prevalence of masked hypertension in treated hypertensive patients with type 2 diabetes mellitus.

This study was undertaken to determine whether self-measured home blood pressure (BP) readings were comparable to clinic visit BP readings in hypertensive type II diabetic patients. We measured the BP of 27 hypertensive patients at home and during the clinic visits over a three week period. The BP readings were analyzed using a mixed linear model with mean daytime ambulatory measure as a covariate. We found that, although there was no significant difference in the mean systolic BP between home and clinic readings (0.6 mm Hg), the mean home BP readings were significantly higher (difference = 6.8 mm p < 0.0006). The proportion of masked hypertension, defined as elevated home systolic or diastolic BP (or both) values despite normal clinic visit BP values, was 40.7%. Three diastolic and one systolic BP measurement at home achieved a reliability coefficient of 0.8. Self-measurement of BP gave highly reliable readings when they were compared with blind readings taken by a trained professional using a mercury sphygmomanometer. We conclude that self-measured BP at home identifies a high prevalence of masked hypertension in treated hypertensive type 2 diabetic patients and that it represents a valuable management adjunct to ensure maximum benefit from antihypertensive drug therapy.

Aged↗
PubMed2006

Normal-appearing white matter changes vary with distance to lesions in multiple sclerosis.

BACKGROUND AND PURPOSE: Multiple sclerosis (MS) disease processes in normal-appearing white matter (NAWM) may be different close to MR-visible lesions than farther from these lesions. We aimed to investigate the relationship of NAWM changes to the distance to the lesions. METHODS: We measured B(1)-corrected T1 and magnetization transfer ratio (MTR) maps in 63 patients with MS (11 primary progressive, 34 relapsing-remitting, 18 secondary progressive). We used histogram analyses to assess the global properties of lesions, of 4 consecutive 1-mm pixel layers of NAWM around the lesions, and of distant NAWM located at least 4-mm from lesions in all directions. In 22 healthy controls, we measured white matter MTR and T1 histograms. Histogram parameters were statistically analyzed by using a linear mixed model. RESULTS: The first and second NAWM pixel layers around the lesions had a significantly lower MTR histogram peak position than distant NAWM, whereas T1 histogram peak position was similar between all types of NAWM. Furthermore, MTR histograms of distant NAWM were statistically indistinguishable from those of control white matter, whereas T1 histograms of distant NAWM had significantly decreased peak height for relapsing-remitting MS and secondary progressive MS and significantly increased peak position for secondary progressive MS. CONCLUSION: Our results may suggest that axonal damage and demyelination in NAWM mainly arise as a secondary result of visible lesions, with the largest effect close to these lesions. NAWM disease farther from the lesions may be mainly characterized by subtle blood-brain barrier damage, with leakage of fibrinogen into the parenchyma and microplaque formation, processes that are detected with T1 but not with MTR.

Adult↗
PubMed2006

In vitro heterogeneity of osteogenic cell populations at various equine skeletal sites.

Bone cell cultures were evaluated to determine if osteogenic cell populations at different skeletal sites in the horse are heterogeneous. Osteogenic cells were isolated from cortical and cancellous bone in vitro by an explant culture method. Subcultured cells were induced to differentiate into bone-forming osteoblasts. The osteoblast phenotype was confirmed by immunohistochemical testing for osteocalcin and substantiated by positive staining of cells for alkaline phosphatase and the matrix materials collagen and glycosaminoglycans. Bone nodules were stained by the von Kossa method and counted. The numbers of nodules produced from osteogenic cells harvested from different skeletal sites were compared with the use of a mixed linear model. On average, cortical bone sites yielded significantly greater numbers of nodules than did cancellous bone sites. Between cortical bone sites, there was no significant difference in nodule numbers. Among cancellous sites, the radial cancellous bone yielded significantly more nodules than did the tibial cancellous bone. Among appendicular skeletal sites, tibial metaphyseal bone yielded significantly fewer nodules than did all other long bone sites. This study detected evidence of heterogeneity of equine osteogenic cell populations at various skeletal sites. Further characterization of the dissimilarities is warranted to determine the potential role heterogeneity plays in differential rates of fracture healing between skeletal sites.

Alkaline Phosphatase↗
PubMed2006

Cognitive decline in older Mexican Americans with diabetes.

OBJECTIVE: To examine social, demographic and health factors associated with cognitive decline over a seven-year period among older Mexican Americans with diabetes. METHODS: A population-based sample of 808 noninstitutionalized Mexican Americans aged >65 years with diabetes who had a Mini-Mental State Examination (MMSE) >17 at baseline from the Hispanic Established Population for the Epidemiological Study of the Elderly (H-EPESE). Measurements included sociodemographics, diabetic treatment received (oral hypoglycemic or insulin), self-reported medical conditions, self-reported diabetes-related complications, high depressive symptoms and ADL limitations. RESULTS: The mean MMSE score at baseline was 25.3 + (SD=3.7). The rate of decline in cognitive function (MMSE) during the follow-up period was 0.37 point per year. Using general linear mixed models, we found that being male, and having high depressive symptoms and diabetic complications (kidney impairment, circulation problems or limb amputation) were factors significantly associated with greater declines in MMSE score over time. CONCLUSION: Circulation problems, kidney impairment and depression are the major factors associated with cognitive decline in older Mexican Americans with diabetes.

Aged↗
PubMed1987

Estimation of additive genetic, non-additive genetic, and permanent environmental sources of variation in preweaning traits in swine using the expectation-maximization algorithm for restricted maximum likelihood.

10188 growth records (performance up to weaning) of 283 Largewhite pigs were used to estimate various components of variance using a mixed linear model for the birth weight, litter size at birth, weaning weight, and litter size at weaning. Restricted maximum likelihood procedures were used. Object of the investigation were the respective additive genetic, non-additive genetic, and permanent environmental variation traits within the overall variation as well as the respective residual components. The results were tabulated and expressed specifically by way of the heritability and repeatability coefficients.

Animals↗
PubMed1995

Intra-articular pressure, elastance, and range of motion in flexion of the equine metacarpophalangeal joint.

A study was done to determine whether intra-articular pressure is increased in equine metacarpophalangeal joints with increasing degrees of synovial distention, and to correlate elastance of the soft tissue forming the dorsal pouch of the metacarpophalangeal joint to maximal range of motion in flexion. Sixty seven metacarpophalangeal joints in 36 horses were categorized by palpation and visual inspection of the palmar pouch into 1 of 4 increasing grades of distention. Intra-articular pressures were then measured, using 2 pressure transducers attached to 22 gauge needles, from the dorsal and palmar pouches simultaneously while horses stood squarely under mild sedation. Intra-articular pressure ranged from -13 to +78 mm of Hg. Mean (+/- SEM) palmar pouch pressure was subatmospheric (-2.53 +/- 2.78 mm of Hg) in joints in which the palmar pouch was not discernible (grade 0), and was markedly increased (+37.13 +/- 2.775 mm of Hg) in joints in which the palmar pouch was distended laterally beyond the lateral branch of the suspensory ligament (grade 3). Grade of distention was positively correlated with intra articular pressure (r = 0.758; P < 0.001). Significant compartmentation (P < 0.002) was observed between the dorsal and palmar pouches in all horses. In 25 of the aforementioned horses, (42 joints), which were active or retired Thoroughbred racehorses with variable degree of metacarpophalangeal joint injury/disease, a third needle was inserted into the dorsal pouch, and 0.5-ml increments of saline solution were added every 10 seconds to perform a pressure/volume (elastance) study of the dorsal pouch. The elastance study for each joint ended when leakage into the palmar pouch was detected by the pressure transducer placed in that region. A flexed lateral radio graphic view was taken of each metacarpophalangeal joint in maximal flexion. The maximal angle of flexion was measured from the radiograph, and this angle was subtracted from 180 degrees to acquire the range of motion in flexion. Range of motion in flexion has strong negative correlation (r= -0.68; P < 0.0001) with elastance (stiffness) of the dorsal pouch, and moderate pouches (r= -0.48; P < 0.0001). To adjust for the possible correlations resulting from repeated measures on limbs within horses, a normal linear mixed model was used to assess the effect of limb (right vs left), range of motion in flexion, and volume of saline solution added on the dependent variable (delta mm of Hg) in the elastance study. There was no significant limb effect, but a highly significant effect regarding volume of saline solution added (P < 0.00001) and range of motion in flexion (P < 0.00001). Loss of range of motion in flexion of this joint is associated with shortening or loss of the initial low elastance (flat) phase of the elastance profile. Measuring the elastance of the dorsal pouch or measuring maximal range of motion in flexion provides an objective measure of the degree of metacarpophalangeal joint stiffness secondary to joint disease.

Animals↗
PubMed1998

HIV-1 viral load and CD4 cell count in untreated children with vertically acquired asymptomatic or mild disease. Paediatric European Network for Treatment of AIDS (PENTA).

BACKGROUND: Plasma HIV-1 RNA levels are high in vertically infected infants. Information in older children is limited, particularly in those who have not received antiretroviral therapy. OBJECTIVES: To describe the relationships between HIV-1 RNA, age and CD4 cell count in untreated vertically infected children. DESIGN: HIV-1 RNA was measured in 70 children [median age, 3.5 years (range, 0.4-11.9 years); median CD4 cell count, 881 x 10(6)/l (interquartile range, 576-1347 x 10(6) cells/l)] enrolled in a randomized placebo-controlled trial comparing immediate with deferred zidovudine in asymptomatic or mildly symptomatic vertically infected children (PENTA-1 trial). Short-term variability was assessed by comparing HIV-1 RNA at -2 and 0 weeks (prior to randomization). The relationship between age and HIV-1 RNA, and CD4 cell count was analysed using data from all children prior to randomization and sequential samples from 35 remaining on placebo for up to 105 weeks, by fitting mixed linear models. RESULTS: The within-individual SD in viral load was 0.26 log10 copies/ml. The median plasma HIV-1 RNA at enrollment was 4.61 log10 (range, 2.3-6.56 log10 copies/ml), significantly higher in children aged < or = 2 years (median, 5.23 log10 copies/ml) than in those aged > 2 years (4.51 log10 copies/ml; P < 0.0001). Mean HIV-1 RNA fell by 0.38 log10 copies/ml per year up to 2 years of age, by 0.21 log10 copies/ml per year from 2 to 4 years of age, and by 0.03 log10 copies/ml per year from 4 to 6 years of age reaching a nadir of 4.25 log10 copies/ml at 6 years. Mean log10 CD4 cell count declined steadily with age and was not significantly correlated with HIV-1 RNA, although there was some evidence that the rate of log10 CD4 cell decline was negatively correlated with the initial rate of HIV-1 RNA decline. No mutations associated with resistance to zidovudine were observed. CONCLUSIONS: Age is a key factor in the interpretation of both viral load and CD4 cell count in vertically infected children.

Aging↗
PubMed1998

Economic outcomes of antipsychotic agents in a Medicaid population: traditional agents vs. risperidone.

Clinical trials reveal that the newer atypical antipsychotic agents are more effective and have fewer side effects than traditional agents. However, these newer agents have a higher acquisition cost than traditional agents. This study assessed the differential impact of risperidone and traditional agents on the total schizophrenia-related cost of care for Medicaid patients suffering from schizophrenia. This was a retrospective longitudinal pretest-posttest analysis of Medicaid claims data covering January 1992 to August 1996. Continuously eligible patients (n = 150) with a documented diagnosis of schizophrenia were evaluated. Medical claims were analyzed for patients treated with traditional antipsychotics for at least 12 months and then switched to risperidone and followed for at least 12 months. Patients who failed on at least one traditional agent and who remained on other traditional agents throughout the study timeframe served as a control group. Monthly costs per patient were estimated using mixed model linear regression with age and gender serving as covariates. The total monthly costs per patient for the risperidone and traditional cohorts were similar ($1,050.52 and $946.24, respectively; p = .5438) during the pretest phase of the study. For patients treated with risperidone, drug costs were $177.35 higher (CL0.95 +/- $7.64; p = .0001) per patient per month in the posttest period compared with the pretest period. However inpatient hospital costs were $312.04 lower (CL0.95 +/- $146.76; p = .001) per patient per month in the posttest period compared with the pretest period. In addition, physician costs were $9.55 lower (CL0.95 +/- $5.31; p = .0004) per patient per month in the posttest period. The difference from the pretest to posttest period for outpatient mental health clinic costs was statistically similar. For those in the risperidone cohort, total estimated costs decreased by $204.87 per patient per month during treatment with risperidone (CL0.95 +/- $161.01; p = .0127). Over the same time-frame, total costs increased $160.68 per patient per month (CL0.95 +/- $196.04; n.s.; p = .1082) in the control cohort. While the mean monthly drug cost was significantly higher during treatment with risperidone, this increase was offset by cost reductions elsewhere in the system.

Adult↗
PubMed2006

A non-linear mixed effect dynamic model incorporating prior exposure and adherence to treatment to describe long-term therapy outcome in HIV-patients.

Long term therapy with antiretroviral agents in HIV-infected patients often result in failure to suppress the virus load. Imperfect adherence to prescribed antiviral drugs is an important factor explaining the resurgence of virus. A better understanding of the factors responsible for the virological failure is important for the development of new treatment strategies. Many complex non-linear models have been developed to describe and simulate the dynamics of HIV-1 virus. Those complicated viral dynamic models have not been used in clinical trials to estimate HIV dynamics parameters, due to their complexity, until the recent development of simplification and approximation techniques. The estimation of the parameters associated with the dynamics from real data has been mostly limited to linearized models that can only explain the decay (suppression) of the virus following antiviral treatment. Moreover, no complete characterization of typical clinical data in terms of inter-subject variability and identification of important covariates effecting HIV-1 dynamics has been attempted. The objective of our paper was to develop a hierarchical non-linear mixed effect model characterizing inter-subject variability in the long-term response to treatment of HIV-1 RNA, and show how the model can be used to quantify the effect of important covariates, such as physiological variables, adherence to treatment or previous exposure to treatment, on the dynamics of HIV-1 RNA. As an example we report the analysis of AIDS clinical trial data from AACTG 398, which shows that patients with previous exposure to treatment show faster death rates for HIV-1, and that higher adherence to treatment is associated with lower reproductive ratio.

Algorithms↗
PubMed1999

SIMEX variance component tests in generalized linear mixed measurement error models.

In the analysis of clustered data with covariates measured with error, a problem of common interest is to test for correlation within clusters and heterogeneity across clusters. We examined this problem in the framework of generalized linear mixed measurement error models. We propose using the simulation extrapolation (SIMEX) method to construct a score test for the null hypothesis that all variance components are zero. A key feature of this SIMEX score test is that no assumptions need to be made regarding the distributions of the random effects and the unobserved covariates. We illustrate this test by analyzing Framingham heart disease data and evaluate its performance by simulation. We also propose individual SIMEX score tests for testing the variance components separately. Both tests can be easily implemented using existing statistical software.

Analysis of Variance↗
PubMed1998

Likelihood ratio testing of variance components in the linear mixed-effects model using restricted maximum likelihood.

This paper reports the results of an extensive Monte Carlo study of the distribution of the likelihood ratio test statistic using the value of the restricted likelihood for testing random components in the linear mixed-effects model when the number of fixed components remains constant. The distribution of this test statistic is considered when one additional random component is added. The distribution of the likelihood ratio test statistic computed using restricted maximum likelihood is compared to the likelihood ratio test statistic computed from the usual maximum likelihood. The rejection proportion is computed under the null hypothesis using a mixture of chi-square distributions. The restricted likelihood ratio statistic has a reasonable agreement with the maximum likelihood test statistic. For the parameter combinations considered, the rejection proportions are, in most cases, less than the nominal 5% level for both test statistics, though, on average, the rejection proportions for REML are closer to the nominal level than for ML.

Analysis of Variance↗
PubMed1990

Nonlinear mixed effects models for repeated measures data.

We propose a general, nonlinear mixed effects model for repeated measures data and define estimators for its parameters. The proposed estimators are a natural combination of least squares estimators for nonlinear fixed effects models and maximum likelihood (or restricted maximum likelihood) estimators for linear mixed effects models. We implement Newton-Raphson estimation using previously developed computational methods for nonlinear fixed effects models and for linear mixed effects models. Two examples are presented and the connections between this work and recent work on generalized linear mixed effects models are discussed.

Algorithms↗
PubMed2004

Non-linear mixed-effects pharmacokinetic/pharmacodynamic modelling in NLME using differential equations.

The standard software for non-linear mixed-effect analysis of pharmacokinetic/pharmacodynamic (PK/PD) data is NONMEM while the non-linear mixed-effects package NLME is an alternative as long as the models are fairly simple. We present the nlmeODE package which combines the ordinary differential equation (ODE) solver package odesolve and the non-linear mixed effects package NLME thereby enabling the analysis of complicated systems of ODEs by non-linear mixed-effects modelling. The pharmacokinetics of the anti-asthmatic drug theophylline is used to illustrate the applicability of the nlmeODE package for population PK/PD analysis using the available data analysis tools in R for model inspection and validation. The nlmeODE package is numerically stable and provides accurate parameter estimates which are consistent with NONMEM estimates.

Algorithms↗
PubMed2002

Functional mixed effects models.

In this article, a new class of functional models in which smoothing splines are used to model fixed effects as well as random effects is introduced. The linear mixed effects models are extended to nonparametric mixed effects models by introducing functional random effects, which are modeled as realizations of zero-mean stochastic processes. The fixed functional effects and the random functional effects are modeled in the same functional space, which guarantee the population-average and subject-specific curves have the same smoothness property. These models inherit the flexibility of the linear mixed effects models in handling complex designs and correlation structures, can include continuous covariates as well as dummy factors in both the fixed or random design matrices, and include the nested curves models as special cases. Two estimation procedures are proposed. The first estimation procedure exploits the connection between linear mixed effects models and smoothing splines and can be fitted using existing software. The second procedure is a sequential estimation procedure using Kalman filtering. This algorithm avoids inversion of large dimensional matrices and therefore can be applied to large data sets. A generalized maximum likelihood (GML) ratio test is proposed for inference and model selection. An application to comparison of cortisol profiles is used as an illustration.

Bayes Theorem↗
PubMed2006

Estimation of non-linear growth models by linearization: a simulation study using a Gompertz function.

A method based on Taylor series expansion for estimation of location parameters and variance components of non-linear mixed effects models was considered. An attractive property of the method is the opportunity for an easily implemented algorithm. Estimation of non-linear mixed effects models can be done by common methods for linear mixed effects models, and thus existing programs can be used after small modifications. The applicability of this algorithm in animal breeding was studied with simulation using a Gompertz function growth model in pigs. Two growth data sets were analyzed: a full set containing observations from the entire growing period, and a truncated time trajectory set containing animals slaughtered prematurely, which is common in pig breeding. The results from the 50 simulation replicates with full data set indicate that the linearization approach was capable of estimating the original parameters satisfactorily. However, estimation of the parameters related to adult weight becomes unstable in the case of a truncated data set.

Algorithms↗