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 397 records · Page 22Linked to original sources
PubMed2026

Integrated Genome-Wide Association Studies and Selection Signature Analysis Reveal the Genetic Architecture of the Wattle Trait in Goats.

Wattles are finger-like appendages on the ventral neck of goats, serving as a distinctive morphological marker for breed identification that serves potential implications for production performance. However, their genetic basis remains incompletely characterized. Here, we integrated a genome-wide association study (GWAS) and selection signature analysis to identify candidate genes and genomic regions associated with the wattle trait in goats. Using a linear mixed model, GWAS on 463 goats (23 wattled and 440 non-wattled) identified 385 quantitative trait loci (QTLs) at a 5% false discovery rate, yielding 346 candidate genes. The most significant association signal was observed on chromosome 10 (72.61-73.48 Mb), where the lead SNP (rs636481767) is located within a region containing GJD2, GREM1, and FMN1, showing strong linkage disequilibrium (r2 > 0.6) with surrounding loci. Subsequent selection signature analysis (23 wattled and 23 non-wattled) identified 83 genomic regions harboring 119 candidate genes. The strongest signals were detected at MFSD14B on chromosome 8 (FST = 0.154, log2π-ratio = 2.611) and PDLIM7 on chromosome 7 (FST = 0.144, log2π-ratio = 0.806). KEGG pathway enrichment analysis revealed that GWAS-associated genes were involved in glycosylation and immune responses, whereas selection-signature genes were enriched in DNA repair and the Hippo, Notch, and Wnt pathways. Furthermore, cross-species PheWAS revealed that human FMN1 is associated with dermatological, skeletal, and metabolic phenotypes, while porcine FMN1 is associated with backfat thickness and loin muscle depth. Overall, this study provides molecular markers of potential value for goat breeding and pinpoints key candidate genes for future functional validation of wattle development.

Animals↗
PubMed2006

Mild-onset presentation of Canavan's disease associated with novel G212A point mutation in aspartoacylase gene.

We describe two sisters with a mild-onset variant of Canavan's disease who presented at age 50 and 19 months with developmental delay but without macrocephaly, hypotonia, spasticity, or seizures. Remarkably, both patients had age-appropriate head control, gross motor development, and muscle tone. There were very mild deficits in fine motor skills, coordination, and gait. Both sisters had a history of strabismus, but otherwise vision was normal. The older child showed evidence of mild cognitive and social impairment, whereas language and behavior were normal for age in the infant. Both patients were found to be compound heterozygotes for C914A (A305E) and G212A (R71H) mutations in ASPA. Like all other known ASPA mutations, this previously unknown G212A mutation appears to have low absolute enzyme activity. Nevertheless, it is associated in these patients with an extremely benign phenotype that is highly atypical of Canavan's disease. Biochemical and clinical data were evaluated using a generalized linear mixed model generated from 25 other subjects with Canavan's disease. There were statistically significant differences in brain chemistry and clinical evaluations, supporting a distinct variant of Canavan's disease. Future studies of ASPA enzyme structure and gene regulation in these subjects could lead to a better understanding of Canavan's pathophysiology and improvements in ASPA gene therapy.

Adult↗
PubMed2005

Is the disease course of rheumatoid arthritis becoming milder? Time trends since 1985 in an inception cohort of early rheumatoid arthritis.

OBJECTIVE: Based on comparisons of short-term cohort studies or cross-sectional samples of patients from different calendar times, it has been suggested that present patients with rheumatoid arthritis (RA) have a milder disease course compared with that of patients in past decades. This study was undertaken to investigate whether the course of disease activity and functional disability in patients with RA has become milder over the past several years. METHODS: We used the Nijmegen inception cohort of early RA, which included all patients with newly diagnosed RA who had attended the department of rheumatology at Radboud University Nijmegen Medical Centre since 1985. Patients were assessed for disease activity by the Disease Activity Score in 28 joints (DAS28) every 3 months and for functional disability by the Health Assessment Questionnaire (HAQ) disability index (DI) every 6 months. Within the total cohort, 4 subcohorts were defined, based on the date of inclusion of the patients (1985-1990, 1990-1995, 1995-2000, 2000-2005). To investigate whether the course of disease activity and functional disability (over time) was different between the subcohorts, longitudinal regression analysis (linear mixed models) was used, with the DAS28 and HAQ DI over time as outcome variables, respectively, and subcohort as the independent variable, correcting for baseline demographic and clinical characteristics. The treatment strategy was compared between the subcohorts. RESULTS: The DAS28 at baseline and over the first 5 years of disease was lower in the more recent subcohorts. The HAQ DI did not show improvement but instead a trend toward worsening functional disability. Using longitudinal regression it was shown that disease activity improved early in the disease course and stabilized thereafter, and that this improvement was greater in patients in the more recent subcohorts and in patients with a higher baseline DAS28. Initially, the HAQ DI also improved but stabilized thereafter, and this initial improvement was less pronounced in patients in the more recent subcohorts and was greater for patients with a higher baseline HAQ DI. The treatment strategy was more aggressive in the more recent subcohorts, as shown by a shorter duration from diagnosis to the start of treatment with prednisone or disease-modifying antirheumatic drugs (DMARDs), and a greater prevalence of DMARD therapy. CONCLUSION: The course of disease activity in RA patients has become milder in more recent years. The reason for this improving trend remains to be elucidated, although the trend coincides with a more aggressive treatment strategy.

Arthritis, Rheumatoid↗
PubMed2005

Behavioral testing of antidepressant compounds: an analysis of crossover design for correlated binary data.

The differential reinforcement of low-rate 72 seconds schedule (DRL-72) is a standard behavioral test procedure for screening potential antidepressant compounds. The protocol for the DRL-72 experiment, proposed by Evenden et al. (1993), consists of using a crossover design for the experiment and one-way ANOVA for the statistical analysis. In this paper we discuss the choice of several crossover designs for the DRL-72 experiment and propose to estimate the treatment effects using either generalized linear mixed models (GLMM) or generalized estimating equation (GEE) models for clustered binary data.

Algorithms↗
PubMed2004

Comparative transcriptional profiling of two human embryonic stem cell lines.

Human embryonic stem cells (ESCs) have generated enormous interest due to their ability to self-renew and produce many different cell types. In conjunction with microarray technology, human ESCs provide a powerful tool for employing a systems-based approach to deciphering the molecular mechanisms that control pluripotency and early development. Recent work has focused on defining "stemness" and pluripotency based on different experimental and analytical approaches in both mouse and human ESCs. Using a mixed linear model statistical approach, we report a stringent direct comparison between data sets obtained from two human ESCs (BG01 and H1) in order to obtain a list of genes that are enriched in ESCs. In addition, we used another pluripotent population derived from BG01 ESCs to obtain a list of genes that we consider important to the maintenance of pluripotency. A total of 133 genes overlapped between the three pluripotent populations. A majority of the 133 genes were classified under the key functional categories of cell-cycle regulation, signaling, and regulation of transcription. Key genes expressed were Oct4, Sox2, LeftyA, and Fgf2. Also found to be enriched in all three populations is FLJ10713, a gene encoding a hypothetical protein of unknown function that has been shown in earlier studies to possess a homolog in mouse ESCs and also to cluster tightly with Oct4 in human ESCs. Although there were many genes unique to each pluripotent population, they shared similarities based on functional ontologies that define pluripotency. The significance of our studies underscores the need for direct comparison of stem cell populations that share biological similarities using uniform stringent analytical approaches, in order to better define pluripotency. Our findings have important implications for the maintenance of pluripotency and in developing directed differentiation strategies for various regenerative applications.

Algorithms↗
PubMed2006

Associations of demographic and lifestyle characteristics with prostate-specific antigen (PSA) concentration and rate of PSA increase.

BACKGROUND: The objective of this study was to examine whether demographic and lifestyle characteristics are associated with prostate-specific antigen (PSA) levels and the rate of PSA increase (PSA velocity). METHODS: Data for this study came from 3341 participants in the placebo arm of the Prostate Cancer Prevention Trial who, based on biopsies at the end of the study, were free of prostate carcinoma. Linear regression was used to assess associations of age, race, smoking, body mass index (BMI), physical activity, diet, and supplement use with PSA concentration during the second year of the trial, and linear mixed models were used to assess associations of these factors with PSA velocity (the percentage increase in PSA per year) during 6 years of the trial. RESULTS: Between the group of men ages 50-59 years and the group of men age 70 years and older, mean PSA increased by 0.22 ng/mL, and PSA velocity decreased by 1.2 percentage points (both P < 0.001). The PSA level among men who had a BMI > or = 35 kg/cm(2) was 0.20 ng/mL lower than the PSA level among men who had a BMI < 25 kd/cm(2) (P < 0.001), but BMI was not associated with PSA velocity. PSA velocity was 1.2 percentage points higher in African-American men compared with white men (P = 0.043). Low energy intake and the use of high-dose calcium supplements were associated with significantly lower PSA velocity (both P = 0.05). Weight gain also was associated with lower PSA velocity. CONCLUSIONS: Differences in PSA concentration associated with demographic and lifestyle characteristics were small and were not likely to bias the interpretation of a single PSA test. Age, race, energy intake, calcium supplement use, and weight change were associated with substantial differences in PSA velocity, and the clinical interpretation of PSA velocity may be biased by these factors.

Age Factors↗
PubMed2005

Seasonal mood variation in the elderly: the Leiden 85-plus study.

BACKGROUND: The influence of seasonal changes on mood and behaviour is called seasonality. The prevalence of seasonality in elderly subjects is unknown. AIM: To investigate the seasonality pattern in mood and behaviour at old age. METHODS: All subjects from the Leiden 85-plus Study with an MMSE score of 19 or more were assessed for depressive feelings at age 85 and yearly thereafter. The influence of time of the year, duration of sunlight, daylight, and rain on the prevalence of depressive symptoms was assessed using linear mixed models for repeated measurements. RESULTS: There was no significant seasonal pattern in the data (p=0.44). Within each of the four years of observation (85, 86, 87 and 88 years) and all years combined, there was also no significant association between the one-month cumulation of duration of sunlight, daylight, or rain and the score on the GDS (all p-values >0.05). The results of either the one week or three-month accumulation of sunlight, daylight, or rain were comparable to the one-month results. CONCLUSIONS: Estimates of prevalence of seasonality reported in the literature might be overestimated or a remarkable difference between young and old subjects exists.

Affect↗
PubMed2004

A randomized, placebo-controlled study of the efficacy and safety of sertraline in the treatment of the behavioral manifestations of Alzheimer's disease in outpatients treated with donepezil.

OBJECTIVE: To examine the safety and efficacy of sertraline augmentation therapy in the treatment of behavioral manifestations of Alzheimer's disease (AD) in outpatients treated with donepezil. METHODS AND MATERIALS: Patients with probable or possible AD, and a Neuropsychiatric Inventory (NPI) total score >5 (with a severity score > or =2 in at least one domain), were treated with donepezil (5-10 mg) for 8 weeks, then randomly assigned to 12 weeks of double-blind augmentation therapy with either sertraline (50-200 mg) or placebo. Primary efficacy measures were the 12-item Neuropsychiatric Inventory (NPI) and the Clinical Global Impression Improvement (CGI-I) and Severity (CGI-S) scales. RESULTS: 24 patients were treated with donepezil+sertraline and 120 patients with donepezil+placebo. There were no statistically significant differences at endpoint on any of the three primary efficacy measures. However, a linear mixed model analysis found modest but statistically significantly greater improvements in the CGI-I score on donepezil+sertraline. Moreover, in a sub-group of patients with moderate-to-severe behavioral and psychological symptoms of dementia, 60% of patients on sertraline vs 40% on placebo (p = 0.006) achieved a response (defined as > or = 50% reduction in a four-item NPI-behavioral subscale). One adverse event (diarrhea) was significantly (p < 0.05) more common in the donepezil+sertraline group compared to the donepezil+placebo group. CONCLUSION: Sertraline augmentation was well-tolerated in this sample of AD outpatients. In addition, post hoc analyses demonstrated a modest but statistically significant advantage of sertraline over placebo augmentation in mixed model analyses and a clinically and statistically significant advantage in a subgroup of patients with moderate-to-severe behavioral and psychological symptoms of dementia.

Aged↗
PubMed2004

Chronic hepatitis C virus infection: does it really impact health-related quality of life? A study in rural Egypt.

Previous Western studies showed a consistent and marked reduction in health-related quality of life (HRQOL) in patients chronically infected with hepatitis C virus (HCV). However, these studies were conducted on patients whose knowledge of their serological status may have affected their HRQOL. This HRQOL survey conducted in the Egyptian rural population provides a unique opportunity to clarify this issue among a population whose serological status is unknown. HRQOL was assessed by an Arabic translation of the Short-Form 12, and a visual analog scale of the relative severity of one's health status. HCV chronic infection was defined by positive tests for anti-HCV antibody and HCV-RNA. HRQOL was compared according to HCV chronic infection status in linear mixed models adjusted for potential confounding factors, such as age, sex, education, and health care-related risk factors, and adjusted for interviewer as a random effect. One hundred forty-six Egyptians chronically infected with HCV had similar Short-Form 12 and visual analog scale scores, compared with 1,140 uninfected controls from the same rural community. In individuals chronically infected with HCV, serum aminotransferase levels did not correlate with HRQOL. In conclusion, this study did not find a significant reduction of HRQOL in patients chronically infected with HCV compared with uninfected, contemporaneous controls. This may be explained in part by a lower morbidity amongst patients chronically infected with HCV in rural Egypt and a higher morbidity amongst uninfected controls as compared with those of Western studies, as well as a lack of awareness of hepatitis C serological status.

Adult↗
PubMed2026

The spatial and temporal distribution of Staphylococcus aureus along a tropical Hawaiian watershed.

Staphylococcus aureus is a leading cause of community-acquired skin and soft-tissue infections worldwide. One major route of exposure is recreating in marine waters, but knowledge is limited regarding the drivers of S. aureus in surface waters that discharge into marine environments. This study explores spatial and temporal distributions of S. aureus, including antimicrobial-resistant and virulence genes, using both culture-dependent and molecular techniques across a tropical Hawaiian watershed with a gradient of human influence. Negative binomial generalized linear mixed models revealed that the interaction between spatial and temporal factors was the strongest predictor of S. aureus and associated genes. Cultured S. aureus was highest at mid-watershed sites in summer, which included a popular swimming hole, suggesting human shedding as a significant source. Molecular detection of S. aureus (femA gene) yielded concentrations two orders of magnitude higher than cultured concentrations and peaked at estuarine sites with the greatest nutrients and water residence times. In the winter at upstream sites with no public access, staphylococci antibiotic-resistant (mecA) and S. aureus virulence gene (etb) were elevated, indicating highly pathogenic S. aureus strains in surface waters may originate from zoonotic sources. Our findings indicate that human and zoonotic sources contribute antibiotic-resistant and virulent S. aureus to watersheds, with streams facilitating environmental transmission to marine waters. This watershed-scale assessment enables the prediction of spatial and temporal conditions associated with elevated S. aureus concentrations, thereby reducing exposure and infections.

Staphylococcus aureus↗
PubMed2002

Long-term immunogenicity of an inactivated virosome hepatitis A vaccine.

The aim of this study was to predict the long-term protection induced after immunisation with inactivated, aluminium-free virosome hepatitis A vaccine. The study population consisted of adult volunteers enrolled in four different clinical trials. Lower 95% confidence interval limits and seroconversion rate were calculated by using a linear mixed model to estimate the persistence of serum antibodies over time. To assess the robustness of the mathematical model, several sensitivity analyses were performed with more conservative protective threshold (20 mIU/ml vs. 10 mIU/ml), higher yearly decline rate, and exclusion of volunteers who had increasing titres over time. Based on 190 volunteers with at least two valid assessments of titres from year 3 onward, the median duration of protection was 55.5 years, with a lower limit of the 95% CI of 48.7 years. Duration below 25.3 years was predicted for only 5% of the subjects. Women tended to have higher titres to start with, but their rate of decline was higher, resulting in similar duration of protection overall. The use of a more conservative threshold, higher yearly decline rate, and exclusion of volunteers with increasing titres over time did not affect these results. According to this model, 95% of the volunteers should have anti-HAV titres above the minimum protective threshold for 20 years or more following immunisation with two doses of this aluminium-free vaccine.

Female↗
PubMed2004

Use of resampling to select among alternative error structure specifications for GLMM analyses of repeated measurements.

Autocorrelated error and missing data due to dropouts have fostered interest in the flexible general linear mixed model (GLMM) procedures for analysis of data from controlled clinical trials. The user of these adaptable statistical tools must, however, choose among alternative structural models to represent the correlated repeated measurements. The fit of the error structure model specification is important for validity of tests for differences in patterns of treatment effects across time, particularly when maximum likelihood procedures are relied upon. Results can be affected significantly by the error specification that is selected, so a principled basis for selecting the specification is important. As no theoretical grounds are usually available to guide this decision, empirical criteria have been developed that focus on mode fit. The current report proposes alternative empirical criteria that focus on bootstrap estimates of actual type I error an power of tests for treatment effects. Results for model selection before and after the blind is broken are compared. Goodness-of-fit statistics also compare favourably for models fitted to the blinded or unblinded data, although the correspondence to actual type I error and power depends on the particular fit statistic that is considered.

Antidepressive Agents↗
PubMed2002

Does post-voiding residual volume get less as mobility improves in a rehabilitation ward for older adults?

Impaired bladder emptying is common in frail older adults. This study tests the hypothesis that more complete bladder emptying is associated with better mobility in a rehabilitation ward for older adults. Consecutive admissions to a rehabilitation ward for older adults were considered for inclusion in the study in the week after admission to the ward. Exclusion criteria were cognitive impairment such that consent could not be obtained, non-English speaking, or presence of an indwelling urinary catheter. A post-voiding residual (PVR) bladder volume and Rivermead Mobility Index (RMI) were completed for subjects who gave consent, on a weekly basis until discharge. The BladderScan BVI 3000, Diagnostic Ultrasound, instrument was used. Statistical analysis was by a general linear mixed model. In the study period, 114 people were admitted and 57 approached for consent. Twenty-four people gave consent. Fifty percent of participants had at least one PVR greater than 100 mL. One person was found to be in urinary retention, with a PVR of greater than 700 mL, and was excluded from further analysis. The PVR increased by 1.2 mL (95% CI-4.6 to 7) for each unit improvement in the RMI. This study suggests that PVR does not decline with improvement in mobility in older adults receiving inpatient rehabilitation.

Aged↗
PubMed2005

A randomized psychosocial intervention study on the effect of home visits on the well-being of Danish colorectal cancer patients--the INCA Project.

Home visits by health care professionals may constitute a formalized social relationship in which cancer patients can be given emotional and informational support. We aimed at studying the effect of home visits on the well-being of colorectal cancer patients. A total of 249 Danish colorectal cancer patients undergoing abdominal surgery were randomly assigned to a control group or to an intervention group. The intervention group received 10 home visits carried out by a project nurse or a medical doctor during the first 2 years after discharge. Participants were interviewed 3, 6, 12, and 24 months after discharge in order to assess well-being. Using a linear mixed model, we found no overall effect of the intervention on well-being. We recommend that future psychosocial intervention studies include baseline screening for distress and recommend testing the effect of shorter but intensive interventions carried out by trained therapists.

Aged↗
PubMed2002

Advanced methods in meta-analysis: multivariate approach and meta-regression.

This tutorial on advanced statistical methods for meta-analysis can be seen as a sequel to the recent Tutorial in Biostatistics on meta-analysis by Normand, which focused on elementary methods. Within the framework of the general linear mixed model using approximate likelihood, we discuss methods to analyse univariate as well as bivariate treatment effects in meta-analyses as well as meta-regression methods. Several extensions of the models are discussed, like exact likelihood, non-normal mixtures and multiple endpoints. We end with a discussion about the use of Bayesian methods in meta-analysis. All methods are illustrated by a meta-analysis concerning the efficacy of BCG vaccine against tuberculosis. All analyses that use approximate likelihood can be carried out by standard software. We demonstrate how the models can be fitted using SAS Proc Mixed.

BCG Vaccine↗
PubMed2002

Network meta-analysis for indirect treatment comparisons.

I present methods for assessing the relative effectiveness of two treatments when they have not been compared directly in a randomized trial but have each been compared to other treatments. These network meta-analysis techniques allow estimation of both heterogeneity in the effect of any given treatment and inconsistency ('incoherence') in the evidence from different pairs of treatments. A simple estimation procedure using linear mixed models is given and used in a meta-analysis of treatments for acute myocardial infarction.

Angioplasty↗
PubMed2003

An evaluation of methods for the stratified analysis of clustered binary data in community intervention trials.

A simulation study is conducted in a community intervention setting. Several methods of stratified analysis of clustered binary data are compared in terms of empirical significance and empirical power levels. They are the Mantel-Haenszel test statistic (chi(2) (MH)), the adjusted Mantel-Haenszel test statistic of Donald-Donner (chi(2) (DD)), Rao-Scott (chi(2) (RSN) and chi(2) (RSP)), and Zhang-Boos (chi(2) (ZBN) and chi(2) (ZBP)), Wald (chi(2) (W)), robust Wald (chi(2) (RW)), score (chi(2) (S)), robust score (chi(2) (RS)), and the test statistic based on generalized linear mixed model (GLMM) (chi(2) (GLMM)). When rho not equal 0, chi(2) (MH) has inflated type I error, and it should not be used when observations are correlated. The results also warn of the use of chi(2) (RSN) and chi(2) (RW) due to their poor performance in terms of empirical significance level. chi(2) (ZBP) and chi(2) (GLMM) have better empirical significance levels as compared to other statistics; however, chi(2) (ZBP) tends to have lower empirical powers than other statistics when the number of clusters (N) is less than 24. chi(2) (RSP) provides the highest empirical powers when rho > or = 0.1 and N < or = 12. When rho < or = 0.01, we recommend the use of chi(2) (RS) and chi(2) (GLMM) since they have better overall performance in terms of empirical significance levels and empirical power levels.

Adolescent↗
PubMed2005

Sample size calculations for a split-cluster, beta-binomial design in the assessment of toxicity.

Mouse embryo assays are recommended to test materials used for in vitro fertilization for toxicity. In such assays, a number of embryos is divided in a control group, which is exposed to a neutral medium, and a test group, which is exposed to a potentially toxic medium. Inferences on toxicity are based on observed differences in successful embryo development between the two groups. However, mouse embryo assays tend to lack power due to small group sizes. This paper focuses on the sample size calculations for one such assay, the Nijmegen mouse embryo assay (NMEA), in order to obtain an efficient and statistically validated design. The NMEA follows a stratified (mouse), randomized (embryo), balanced design (also known as a split-cluster design). We adopted a beta-binomial approach and obtained a closed sample size formula based on an estimator for the within-cluster variance. Our approach assumes that the average success rate of the mice and the variance thereof, which are breed characteristics that can be easily estimated from historical data, are known. To evaluate the performance of the sample size formula, a simulation study was undertaken which suggested that the predicted sample size was quite accurate. We confirmed that incorporating the a priori knowledge and exploiting the intra-cluster correlations enable a smaller sample size. Also, we explored some departures from the beta-binomial assumption. First, departures from the compound beta-binomial distribution to an arbitrary compound binomial distribution lead to the same formulas, as long as some general assumptions hold. Second, our sample size formula compares to the one derived from a linear mixed model for continuous outcomes in case the compound (beta-)binomial estimator is used for the within-cluster variance.

Animals↗