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.

SourceResearch connectionFrom yearThrough year

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

At least 1,081 records · Page 60Linked to original sources

PubMed2004

Estimating dermal exposure to jet fuel (naphthalene) using adhesive tape strip samples.

A simple, non-invasive dermal sampling technique was developed and tested on 22 human volunteers under laboratory conditions to estimate acute dermal exposure to jet fuel (JP-8). Two sites on the ventral surface of each forearm were exposed to 25 micro l of JP-8 and the non-viable epidermis (stratum corneum) was sequentially tape-stripped using an adhesive tape. Samples were extracted with acetone and analyzed by gas chromatography/mass spectrometry. Analysis of the first tape strips indicated that JP-8 was rapidly removed from the stratum corneum over the 20 min study period. On average, after 5 min of exposure the first two tape strips removed 69.8% of the applied dose. The amount recovered with two tape strips decreased over time to a recovery of 0.9% 20 min after exposure. By fitting a mixed-effects linear regression model to the tape strip data, we were able to estimate accurately the amount of JP-8 initially applied. This study indicates that naphthalene has a short retention time in the human stratum corneum and that the tape stripping method, if used within 20 min of the initial exposure, can be used to measure reliably the amount of naphthalene initially in the stratum corneum due to a single exposure to jet fuel. We are currently investigating the applicability of the developed mixed-effects linear regression model to estimate acute JP-8 exposure levels based upon naphthalene measurements from tape strips collected from occupationally exposed workers.

Adult↗

PubMed2026

Webcam-Based Real-Time Visual Feedback During Baduanjin Practice in Older Adults: 6-Week Pilot Randomized Study.

BACKGROUND: Baduanjin qigong is a traditional mind-body exercise used to support balance and physical health in older adults. Age-related changes in proprioception may make accurate self-directed performance difficult without external guidance. OBJECTIVE: The aim of this study is to explore whether webcam-based real-time visual feedback delivered during supervised laboratory sessions was associated with differences in webcam-derived 2D pose discrepancy and movement consistency during Baduanjin practice in older adults. METHODS: A total of 31 older adults were enrolled, and 28 participants with complete analyzable records were included in this complete-case dataset (feedback group, n=14; nonfeedback group, n=14). All sessions were conducted face-to-face in a supervised motion-analysis laboratory. Weekly 2D pose-discrepancy values were analyzed using a linear mixed-effects model with fixed effects for group, categorical week, and the group-by-week interaction and a participant-specific random intercept. Joint- and movement-specific participant-level 6-week means were analyzed exploratorily using Welch independent-samples t tests. Holm correction was applied across 24 exploratory contrasts (6 week-specific, 8 joint-specific, and 10 movement-specific comparisons), and Hedges g and 95% CIs were reported. Participant-specific weekly slopes and within-participant variability were additionally examined to directly assess longitudinal error drift. RESULTS: The linear mixed-effects model showed no significant group-by-week interaction (Wald χ25=1.09; P=.96) and no significant overall week effect (Wald χ25=6.40; P=.27). Averaged across 6 weeks, the feedback group had an estimated mean 2D pose discrepancy 1.20° lower than the nonfeedback group (95% CI -2.38° to -0.02°; P=.046), although this marginal pilot finding was sensitive to an analytic approach. No week-specific contrast remained significant after Holm adjustment. Nominal right elbow, right shoulder, and right knee differences did not survive global Holm correction. Form 3 showed a lower mean discrepancy in the feedback group (mean difference -3.70°, 95% CI -5.86° to -1.54°; Hedges g=-1.30; unadjusted P=.002; Holm-adjusted P=.04). Direct analyses of participant-specific slopes and within-participant SDs did not support a significant between-group difference in longitudinal error drift. CONCLUSIONS: In this small exploratory pilot study conducted under supervised laboratory conditions, the 6-week trajectories did not differ significantly between groups. A marginally lower average 2D pose discrepancy was observed in the feedback group across the 6 weeks, but no individual week- or joint-specific comparison remained significant after multiplicity adjustment. Form 3 was the only exploratory contrast that remained significant after global Holm correction. Direct longitudinal analyses did not demonstrate prevention of error drift. Larger studies using validated reference measurements, prespecified outcomes, and adequately powered longitudinal designs are required.

Humans↗

PubMed2026

Polygenic Profiles Are Associated with Multidomain Biochemical Adaptations Across a Competitive Season in Professional Football Players: A Longitudinal Observational Study.

Background/Objectives: The physiological adaptations required to sustain elite football performance are influenced by both genetic background and dynamic biochemical responses, although their interaction across a full competitive season remains insufficiently characterized. This study aimed to examine the association between polygenic profiles and longitudinal biochemical adaptations in professional football players. Methods: Forty male professional football players competing in the Spanish league were monitored across two consecutive seasons. Blood samples were collected at six time points representing different phases of the competitive cycle. Biomarkers related to muscle metabolism, iron status, and hepatic function were analyzed. Polygenic profiles were calculated using Total Genotype Scores (TGS) for muscle performance, hepatic resilience, and metabolic efficiency. Associations were initially explored using Pearson correlations and subsequently evaluated using linear mixed-effects models accounting for repeated measurements within subjects. Results: Exploratory correlation analyses identified several associations between polygenic profiles and biochemical markers. Muscle performance TGS was inversely associated with serum iron (r = -0.36, p = 0.017) and positively associated with CK (r = 0.32, p = 0.041), Hb (r = 0.29, p = 0.046), and Hct (r = 0.33, p = 0.024). Hepatic resilience TGS showed inverse associations with ALT (r = -0.39, p = 0.012), urea (r = -0.51, p = 0.011), and BUN (r = -0.51, p = 0.011). Metabolic efficiency TGS was negatively associated with AST (r = -0.43, p = 0.044), ALT (r = -0.33, p = 0.025), and GGT across multiple time points (p = 0.001-0.013). However, although several nominal associations emerged in linear mixed-effects models accounting for repeated measurements, none remained statistically significant after false discovery rate correction. These findings should therefore be interpreted as exploratory and hypothesis-generating. Conclusions: Polygenic profiles may be associated with inter-individual variability in biochemical adaptations throughout a competitive season. These findings suggest the integration of genomic and biochemical data in precision athlete monitoring, while highlighting causal relationships and predictive applications require further investigation.

Humans↗

PubMed2005

Exposure to oil mist and oil vapour during offshore drilling in norway, 1979-2004.

OBJECTIVES: To describe personal exposure to airborne hydrocarbon contaminants (oil mist and oil vapour) from 1979 to 2004 in the mud-handling areas of offshore drilling facilities operating on the Norwegian continental shelf when drilling with oil-based muds. METHODS: Qualitative and quantitative information was gathered during visits to companies involved in offshore oil and gas production in Norway. Monitoring reports on oil mist and oil vapour exposure covered 37 drilling facilities. Exposure data were analysed using descriptive statistics and by constructing linear mixed-effects models. RESULTS: Samples had been taken during the use of three generations of hydrocarbon base oils, namely diesel oils (1979-1984), low-aromatic mineral oils (1985-1997) and non-aromatic mineral oils (1998-2004). Sampling done before 1984 showed high exposure to diesel vapour (arithmetic mean, AM = 1217 mg m(-3)). When low-aromatic mineral oils were used, the exposure to oil mist and oil vapour was 4.3 and 36 mg m(-3), and the respective AMs for non-aromatic mineral oils were reduced to 0.54 and 16 mg m(-3). Downward time trends were indicated for both oil mist (6% per year) and oil vapour (8% per year) when the year of monitoring was introduced as a fixed effect in a linear mixed-effects model analysis. Rig type, technical control measures and mud temperature significantly determined exposure to oil mist. Rig type, type of base oil, viscosity of the base oil, work area, mud temperature and season significantly determined exposure to oil vapour. Major decreases in variability were found for the between-rig components. CONCLUSIONS: Exposure to oil mist and oil vapour declined over time in the mud-handling areas of offshore drilling facilities. Exposure levels were associated with rig type, mud temperature, technical control measures, base oil, viscosity of the base oil, work area and season.

Aerosols↗

PubMed1993

A modeling approach to hospital location for effective marketing.

This paper develops a mixed integer linear programming model for locating health care facilities. The parameters of the objective function of this model are based on factor rating analysis and grid method. Subjective and objective factors representative of the real life situations are incorporated into the model in a unique way permitting a trade-off analysis of certain factors pertinent to the location of hospitals. This results in a unified approach and a single model whose credibility is further enhanced by inclusion of geographical and demographical factors.

Algorithms↗

PubMed2005

Modeling antitumor activity in xenograft tumor treatment.

To analyze responses of solid tumors to treatment with antitumor therapy, we applied nonparametric mixed-effects models to investigate tumor volumes measured over a fixed. The population and individual response functions were approximated by penalized splines. Linear mixed-effects modeling was applied in the implementation of the estimation. We applied the approach to an analysis of a real xenograft study of a new antitumor agent, temozolomide, combined with irinotecan. The model fitted the data very well. We conducted a sensitivity analysis to determine the effect of informative dropout. We also propose an intuitive approach to a comparison of the antitumor effects of two different treatments. Biological interpretations and clinical implications are discussed.

Animals↗

PubMed2004

A new concept for separability problems in blind source separation.

The goal of blind source separation (BSS) lies in recovering the original independent sources of a mixed random vector without knowing the mixing structure. A key ingredient for performing BSS successfully is to know the indeterminacies of the problem-that is, to know how the separating model relates to the original mixing model (separability). For linear BSS, Comon (1994) showed using the Darmois-Skitovitch theorem that the linear mixing matrix can be found except for permutation and scaling. In this work, a much simpler, direct proof for linear separability is given. The idea is based on the fact that a random vector is independent if and only if the Hessian of its logarithmic density (resp. characteristic function) is diagonal everywhere. This property is then exploited to propose a new algorithm for performing BSS. Furthermore, first ideas of how to generalize separability results based on Hessian diagonalization to more complicated nonlinear models are studied in the setting of postnonlinear BSS.

Algorithms↗

PubMed2004

Estimating the degree of emergency department overcrowding in academic medical centers: results of the National ED Overcrowding Study (NEDOCS).

OBJECTIVES: No single universal definition of emergency department (ED) overcrowding exists. The authors hypothesize that a previously developed site-sampling form for academic ED overcrowding is a valid model to quantify overcrowding in academic institutions and can be used to develop a validated short form that correlates with overcrowding. METHODS: A 23-question site-sampling form was designed based on input from academic physicians at eight medical schools representative of academic EDs nationwide. A total of 336 site-samplings at eight academic medical centers were conducted at 42 computer-generated random times over a three-week period by independent observers at each site. These sampling times ranged from very slow to severely overcrowded. The outcome variable was the degree of overcrowding as assessed by the charge nurse and ED physicians. The full model consisted of objective data that were obtained by counting the number of patients, determining patients' waiting times, and obtaining information from registration, triage, and ancillary services. Specific objective data were indexed to site-specific demographics. The outcome and objective data were compared using a multiple linear regression to determine predictive validity of the full model. A five-question reduced model was calculated using a backward stepdown procedure. Predictive validity and relationships between the outcome and objective data were assessed using a mixed-effects linear regression model, treating center as random effect. RESULTS: Overcrowding occurred 12% to 73% of the time (mean, 35%), with two hospitals being overcrowded more than 50% of the time. Comparison of objective and outcome data resulted in an R(2) of 0.49 (p < 0.001), indicating a good degree of predictive validity. A reduced five-question model predicted the full model with 88% accuracy. CONCLUSIONS: Overcrowding varied widely between academic centers during the study period. Results of a five-question reduced model are valid and accurate in predicting the degree of overcrowding in academic centers.

Academic Medical Centers↗

PubMed2004

Dealing with inter-individual differences in the temporal dynamics of fatigue and performance: importance and techniques.

Inter-individual differences in performance impairment from sleep loss are substantial and consistent, as demonstrated and quantified here by means of the intraclass correlation coefficient (ICC) in two laboratory-based sleep deprivation studies. There is an urgent need, therefore, to consider inter-individual variability in biomathematical models of fatigue and performance, which currently treat individuals as being all the same. Traditional regression techniques do not handle inter-individual variability, but cutting-edge mixed-effects modeling techniques have recently become available to deal with inter-individual differences in the temporal dynamics of fatigue and performance. The standard two stage (STS), restricted maximum likelihood (REML), and non-linear mixed-effects modeling (NMEM) approaches to mixed-effects models are compared here using data from a chronic partial sleep deprivation experiment. Mixed-effects modeling can be incorporated in the two distinct steps (the direct and inverse problems) of biomathematical model development in order to deal with inter-individual differences. This paper demonstrates that inter-individual variability accounts for a large percentage of observed variance in neurobehavioral responses to sleep deprivation, and describes tools that model developers will need to produce a new generation of fatigue and performance models capable of incorporating inter-individual variability and useful for subject-specific prediction.

Fatigue↗

PubMed2003

A longitudinal examination of factors related to changes in serum polychlorinated biphenyl levels.

Consumption of sport-caught fish from the Great Lakes is a recognized source of human exposure to polychlorinated biphenyls (PCBs). Understanding temporal changes in PCB body burden is crucial for evaluating exposure levels and augmenting validity of studies investigating their relationship to adverse health effects. Using data collected from 1980 to 1995, we evaluated longitudinal changes in serum PCB levels among 179 fisheaters and non-fisheaters of the Michigan Fisheater Cohort. Participants identified as fisheaters in 1980 ate 26 lb or more of sport-caught fish per year, whereas non-fisheaters ate less than 6 lb per year. We found a monotonic decline in serum PCB levels among all participants from a mean value of 24 ppb in 1980 to 12 ppb in 1994. This was paralleled by an 83% decrease in mean fish consumption among all participants over the same period. We combined demographic, lifestyle, and fish consumption information with PCB data and evaluated the data using regression models to identify predictors of PCB body burden over a 16-year period. Results of the mixed-effects linear regression model suggest that consumption of Lake Michigan fish before 1980, amount of sport-caught fish eaten in the past year, age, and year of data collection were significant determinants of current PCB body burden over the 16-year study period. PCB levels were particularly elevated for males who were classified as fisheaters in 1980, which may reflect higher levels of sport-caught fish consumption compared with female fisheaters.

Adult↗

PubMed2001

A multiple imputation approach to linear regression with clustered censored data.

We extend Wei and Tanner's (1991) multiple imputation approach in semi-parametric linear regression for univariate censored data to clustered censored data. The main idea is to iterate the following two steps: 1) using the data augmentation to impute for censored failure times; 2) fitting a linear model with imputed complete data, which takes into consideration of clustering among failure times. In particular, we propose using the generalized estimating equations (GEE) or a linear mixed-effects model to implement the second step. Through simulation studies our proposal compares favorably to the independence approach (Lee et al., 1993), which ignores the within-cluster correlation in estimating the regression coefficient. Our proposal is easy to implement by using existing softwares.

Algorithms↗

PubMed2003

Intravenously administered digoxin in patients with acute atrial fibrillation: a population pharmacokinetic/pharmacodynamic analysis based on the Digitalis in Acute Atrial Fibrillation trial.

OBJECTIVE: Atrial fibrillation is commonly treated with intravenously administered digoxin. The main objective of this study was to investigate the relationship between plasma concentration of digoxin and heart rate. SUBJECTS AND METHODS: Plasma concentrations of digoxin were analysed in 105 patients allocated to digoxin therapy in the Digitalis in Acute Atrial Fibrillation (DAAF) trial. A pharmacokinetic/pharmacodynamic (PK/PD) model for the relationship among digoxin dose, plasma concentration and heart rate in patients remaining in atrial fibrillation was constructed using non-linear, mixed-effect modelling. One hundred and twenty-two placebo-treated patients were included as a control group. In 56 patients, one late sample at 16 h after the first dose of digoxin was obtained while in 49 patients an early sample at 0.25-0.5 h and a late sample 16 h after the first dose were obtained. Heart rate was measured at 0, 2, 6, 12 and 16 h after inclusion, with data from 98, 89, 67, 56 and 53 patients available at each time point, respectively. RESULTS: A two-compartment model best described the time course of digoxin concentrations in plasma. Digoxin and creatinine clearance correlated strongly and mean plasma concentration of digoxin at 16 h was within recommended levels (1.6+/-1.0 nM). The decrease in heart rate in placebo-treated patients was, on average, 0.5 beats/min (bpm) per hour. In patients on digoxin, a linear relationship between the estimated digoxin concentration at the effect site and the drop-in heart rate was found. The half-life for the digoxin distribution to the effect compartment was approximately 3.8 h. The degree of reduction was related to the initial heart rate and patients with higher heart rate had a more pronounced decrease. The model predicted that a digoxin concentration of 1 nM at the effect site reduces heart rate by 9.4%. CONCLUSION: A PK/PD model for the relationship between the plasma concentration of digoxin, the estimated concentration at the effect site and the reduction in heart rate during atrial fibrillation could be defined using a population pharmacokinetic approach. Our data indicate that a more aggressive dosing regimen of digoxin may be more effective in terms of heart rate reduction.

Acute Disease↗

PubMed2026

The effect of metformin on the pharmacokinetics of rifampicin, isoniazid, and pyrazinamide in adults with tuberculosis.

Metformin is under investigation as adjunctive host-directed therapy for tuberculosis (TB), which might interact with first-line TB treatment. We used population pharmacokinetic modeling to assess whether metformin alters first-line TB-drug pharmacokinetics in HIV/TB-coinfected adults without diabetes. Rifampicin, isoniazid, and pyrazinamide pharmacokinetics were investigated in participants from a randomized clinical trial of adjunctive metformin (500 mg twice daily to week 12) in adults starting HIV-associated TB treatment. Antiretroviral therapy (ART)-naïve participants initiated dolutegravir-based ART within 8 weeks. Intensive and semi-intensive sampling was conducted at week 5; concentration-time data were analyzed using non-linear mixed-effects modeling. Data from 78 individuals (43 receiving metformin, median weight 60.8 kg, 62.8% male, 79.5% on ART) were analyzed. Rifampicin and pyrazinamide were described by one-compartment models with linear elimination; typical clearances were 15.8 L/h (95% CI: 13.5-18.7) and 3.88 L/h (95% CI: 3.54-4.08), respectively. Isoniazid followed a two-compartment model with a mixture model for acetylator status; clearance was 10.5 L/h (95% CI: 9.44-11.9) in slow acetylators and 28.8 L/h (95% CI: 25.6-31.0) in fast/intermediate acetylators. Metformin reduced isoniazid bioavailability by 15.6% (95% CI: 4.45-26.4%, P < 0.009) and rifampicin bioavailability by 24.0% (95% CI: 7.83-36.3%, P < 0.007), decreasing the area under the curve from 0 to 24 h from 18.2 to 15.6 mg·h/L and from 35.9 to 27.1 mg·h/L, respectively. No significant effect on pyrazinamide was detected. We found that non-diabetic patients on metformin had lower isoniazid and rifampicin bioavailability. Lowered rifampicin exposure might be clinically relevant; simulations suggest that this could be offset by a single 150 mg rifampicin dose.CLINICAL TRIALSThis study is registered with ClinicalTrials.gov as NCT04930744.

Humans↗

PubMed2005

Multiple imputation under Bayesianly smoothed pattern-mixture models for non-ignorable drop-out.

Conventional pattern-mixture models can be highly sensitive to model misspecification. In many longitudinal studies, where the nature of the drop-out and the form of the population model are unknown, interval estimates from any single pattern-mixture model may suffer from undercoverage, because uncertainty about model misspecification is not taken into account. In this article, a new class of Bayesian random coefficient pattern-mixture models is developed to address potentially non-ignorable drop-out. Instead of imposing hard equality constraints to overcome inherent inestimability problems in pattern-mixture models, we propose to smooth the polynomial coefficient estimates across patterns using a hierarchical Bayesian model that allows random variation across groups. Using real and simulated data, we show that multiple imputation under a three-level linear mixed-effects model which accommodates a random level due to drop-out groups can be an effective method to deal with non-ignorable drop-out by allowing model uncertainty to be incorporated into the imputation process.

Antipsychotic Agents↗

PubMed2007

A comparison of mixed-effects quantile stratification propensity adjustment strategies for longitudinal treatment effectiveness analyses of continuous outcomes.

The propensity adjustment is used to reduce bias in treatment effectiveness estimates from observational data. We show here that a mixed-effects implementation of the propensity adjustment can reduce bias in longitudinal studies of non-equivalent comparison groups. The strategy examined here involves two stages. Initially, a mixed-effects ordinal logistic regression model of propensity for treatment intensity includes variables that differentiate subjects who receive various doses of time-varying treatments. Second, a mixed-effects linear regression model compares the effectiveness of those ordinal doses on a continuous outcome over time. Here, a simulation study compares bias reduction that is achieved by implementing this propensity adjustment through various forms of stratification. The simulations demonstrate that bias decreased monotonically as the number of quantiles used for stratification increased from two to five. This was particularly pronounced with stronger effects of the confounding variables. The quartile and quintile strategies typically removed in excess of 80-90 per cent of the bias detected in unadjusted models; whereas a median-split approach removed from 20 to 45 per cent of bias. The approach is illustrated in an evaluation of the effectiveness of somatic treatments for major depression in a longitudinal, observational study of affective disorders.

Adult↗

PubMed2026

Obesity Polygenic Risk and Healthy Lifestyle Interactions on Weight Trajectories in Women and Men.

BACKGROUND: Genetics and environmental factors contribute to obesity risk, but the extent to which healthy behaviors can offset genetic susceptibility remains unclear. We examined the interaction between obesity polygenic risk and a composite healthy lifestyle score on body mass index (BMI) trajectories in women and men. METHODS: We analyzed 13 780 women from the Nurses' Health Study and 8242 men from the Health Professionals Follow-Up Study, all of European ancestry and free of major chronic disease at baseline. The lifestyle score comprised American Heart Association Essential 8 components (nonsmoking, physical activity, healthy eating, adequate sleep) plus moderate alcohol intake, modeled as a time-varying variable. A genome-wide polygenic score for BMI was derived from genome-wide association study. Adjusted linear mixed-effects models estimated associations and interactions on biennial BMI measures over up to 26 years. RESULTS: Each SD increase in the polygenic score was associated with 1.80 kg/m2 (95% CI, 1.72-1.87) and 1.12 kg/m2 (95% CI, 1.06-1.19) higher BMI in women and men, respectively. Significant interactions between the polygenic score and healthy lifestyle score (both P<0.05) showed a dose-response attenuation of the genetic effects with healthier lifestyles. Comparing the healthiest with the least healthy lifestyle groups, genetic effects on BMI were 35% lower in women and 28% lower in men. In sensitivity analyses, higher diet quality and physical activity consistently attenuated genetic associations in both cohorts, whereas current smoking showed similar effects in women only. CONCLUSIONS: Adherence to a healthier lifestyle attenuated the association between obesity polygenic risk and BMI in a dose-response manner.

Humans↗

PubMed1992

A longitudinal approach to modeling outcomes in a nursing home study.

Recent developments in longitudinal statistical methodology have improved our ability to model dynamic processes such as adaptation to nursing homes. Longitudinal observations provide information on individual patterns of change and factors affecting them. However, longitudinal analyses are often complicated by unequal periods of observation and individual variability in patterns of change. This paper demonstrates the use of a linear mixed-effects model to study adaptation in a longitudinal nursing home study with different numbers of repeated measurements for each individual because of discharges, transfers, and mortality.

Adaptation, Psychological↗

PubMedDate not supplied

Inferring systemic exposure from a pharmacokinetic screen: model-free and model-based approaches.

To infer patterns of average systemic exposure and to estimate individual exposures in phase III clinical trials of a new anxiolytic, two statistical methodologies were applied and compared: non-linear mixed-effect modelling, and a model-free approach based on quartiles of dose-normalized plasma concentrations of the drug. Although the model-based approach provides more quantitative insight about relationships between average exposure and demographic covariates, the model-free approach provides qualitatively similar results about average clearance and quantitatively similar results about individual exposures, and the model-free approach is easy and inexpensive to implement.

Adult↗