Biomedical subjects

Philippe Lambert

Publications and source records attributed to Philippe Lambert.

6 recordsLinked to original sources

PubMed2006

Functional ANOVA with random functional effects: an application to event-related potentials modelling for electroencephalograms analysis.

The differential effects of basic visual or auditory stimuli on electroencephalograms (EEG), named event related potentials (ERPs), are often used to evaluate the impact of treatments on brain performances. In the present paper, we propose a P-splines based model that can be used to evaluate treatment effect on the timing and the amplitude of some peaks of the ERPs curves. Functional ANOVA is an adaptation of linear model or analysis of variance to analyse functional observations. The changes in the functional of interest effects are generally described using smoothing splines. Eilers and Marx proposed to work with P-splines, a combination of B-splines and difference penalties on coefficients. We define a P-splines model for ERPs curves combined with random effects. In particular, we show that it is a useful alternative to classical strategies requiring the visual and usually imprecise localization of specific ERP peaks from curves with a low signal-to-noise ratio.

Analysis of Variance↗

PubMed2006

Discrimination of shifts in a soil microbial community associated with TNT-contamination using a functional ANOVA of 16S rRNA hybridized to oligonucleotide microarrays.

A functional ANOVA analysis of the thermal dissociation of RNA hybridized to DNA microarrays was used to improve discrimination between two soil microbial communities. Following hybridization of in vitro transcribed 16S rRNA derived from uncontaminated and 2,4,6-trinitrotoluene contaminated soils to an oligonucleotide microarray containing group- and species-specific perfect match (PM) probes and mismatch (MM) variants, thermal dissociation was used to analyze the nucleic acid bound to each PM-MM probe set. Functional ANOVA of the dissociation curves generally discriminated PM-MM probe sets when Td values (temperature at 50% probe-target dissociation) could not. Maximum discrimination for many PM and MM probes often occurred at temperatures greaterthan the Td. Comparison of signal intensities measured prior to dissociation analysis from hybridizations of the two soil samples revealed significant differences in domain-, group-, and species-specific probes. Functional ANOVA showed significantly different dissociation curves for 11 PM probes when hybridizations from the two soil samples were compared, even though initial signal intensities for 3 of the 11 did not vary.

Analysis of Variance↗

PubMed2005

Bayesian proportional hazards model with time-varying regression coefficients: a penalized Poisson regression approach.

One can fruitfully approach survival problems without covariates in an actuarial way. In narrow time bins, the number of people at risk is counted together with the number of events. The relationship between time and probability of an event can then be estimated with a parametric or semi-parametric model. The number of events observed in each bin is described using a Poisson distribution with the log mean specified using a flexible penalized B-splines model with a large number of equidistant knots. Regression on pertinent covariates can easily be performed using the same log-linear model, leading to the classical proportional hazard model. We propose to extend that model by allowing the regression coefficients to vary in a smooth way with time. Penalized B-splines models will be proposed for each of these coefficients. We show how the regression parameters and the penalty weights can be estimated efficiently using Bayesian inference tools based on the Metropolis-adjusted Langevin algorithm.

Bayes Theorem↗

PubMed2004

Parametric accelerated failure time models with random effects and an application to kidney transplant survival.

Accelerated failure time models with a shared random component are described, and are used to evaluate the effect of explanatory factors and different transplant centres on survival times following kidney transplantation. Different combinations of the distribution of the random effects and baseline hazard function are considered and the fit of such models to the transplant data is critically assessed. A mixture model that combines short- and long-term components of a hazard function is then developed, which provides a more flexible model for the hazard function. The model can incorporate different explanatory variables and random effects in each component. The model is straightforward to fit using standard statistical software, and is shown to be a good fit to the transplant data.

Adult↗

PubMed2002

A copula-based model for multivariate non-normal longitudinal data: analysis of a dose titration safety study on a new antidepressant.

A new model for multivariate non-normal longitudinal data is proposed. In a first step, each longitudinal series of data corresponding to a given response is modelled separately using a copula to relate the marginal distributions of the response at each time of observation. In a second step, at each observation time, the conditional (on the past) distributions of each response are related using another copula describing the relationship between the corresponding variables. Note that there is no need to consider the same family of distributions for these response variables. The technique is illustrated in a dose titration safety study on a new antidepressant. The haemodynamic effect on diastolic blood pressure, systolic blood pressure and heart rate is studied. These three responses are measured repeatedly over time on ten healthy volunteers during the dose escalation. The available covariates are sex and the concentration of drug in the plasma at time of measurement.

Antidepressive Agents↗

PubMed2002

On the joint analysis of longitudinal responses and early discontinuation in randomized trials.

Our focus is on the joint analysis of longitudinal nonnormal responses and early discontinuation in (pre)-clinical trials. Separate models are fitted to the two series (response and discontinuation) to account for covariate and time effects. The serial dependence and the dependence between response and drop-out are also modeled. This is done using particular dependence functions, called copulas. Copulas are used to create a joint distribution with given marginal distributions. Applications are given for the analysis of heart rate/morbidity in toxicology and pain severity/intake of rescue medications in a trial on migraine. Using copulas, the level of dependence between two variables remains invariant to changes in the marginal distribution of either variable. This proves interesting in modeling the association in a longitudinal setting when responses change over time.

Algorithms↗