Search PubMed⌕ Search

Biomedical subjects

J Lellouch

Publications and source records attributed to J Lellouch.

At least 19 recordsLinked to original sources

Sample size calculations for risk equivalence testing in pharmacoepidemiology.

Equivalence testing has been widely discussed and is commonly used in pharmacokinetics (bioequivalence) and clinical trials (therapeutic equivalence). It can also be applied to pharmacoepidemiology, where the aim may be to test with a known risk (one-group design) or with another drug (two-group design). Whether the approach is two-sided or one-sided, predefined equivalence limits are required. The definition of the equivalence region can be based on either risk difference or risk ratio. Risk equivalence testing is complicated by the binary nature of the outcome, its low frequency, and by the absence of commonly defined equivalence limits for differences or ratios. In this context, we consider usable formulae for sample sizes. In most cases, at least when the risk studied is large enough (above 1/1,000), it appears that these formulae result in sample sizes that may be acceptable for practical purposes. For example, demonstrating equivalence with a known risk of 0.01, a 20% maximal risk difference, and a one-sided test (alpha = 0.05 and beta = 0.2) requires: under the one-group design (known risk), 15,309 patients; and under the two-group design, 30,617 patients per group. This approach is the appropriate way to conclude equivalence, rather than the commonly used approach of difference testing and concluding equivalence when the null hypothesis of equality is not rejected.

Clinical Trials as Topic↗

Marked 24-h rest/activity rhythms are associated with better quality of life, better response, and longer survival in patients with metastatic colorectal cancer and good performance status.

The rest/activity circadian cycle has been used as a reference for chemotherapy administration at specific times to improve tolerability and efficacy. Because cancer processes may be associated with alterations of circadian rhythms, the rest/activity cycle was monitored noninvasively to assess its relationship with tumor response, survival, and quality of life in 200 patients with metastatic colorectal cancer. Patients wore an actigraph, a wristwatch that records the number of accelerations per minute, for 3 days before receiving chronomodulated chemotherapy. The circadian rhythms in activity were estimated by two robust parameters: the autocorrelation coefficient at 24 h (r24), and the dichotomy index (I<O) for comparing amounts of activity when in bed and out of bed. Accurate data for inclusion, quality of life, response, and survival were available for 192 patients. Survival at 2 years was 5-fold higher (P = 10(-4)) in patients with marked activity rhythm (I<O in upper quartile) than in those with rhythm alteration (I<O in lower quartile). These results were supported by the multivariate Cox analysis. Multivariate regression analysis showed that circadian rhythms in activity (I<O; P = 3 x 10(-4)) and in WBCs (P = 0.03) as well as performance status (P = 0.02) were jointly prognostic of response. Patients with marked rest/activity rhythms also had better quality of life and reported significantly less fatigue. The individual rest/activity cycle provides a novel independent prognostic factor for cancer patients' survival and tumor response as well as a quantitative indicator for quality of life.

Adult↗

Unobserved covariates in the two-sample comparison of survival times: a maximum efficiency robust test.

In analysing a clinical trial with the logrank test, the hazards between the two groups are usually assumed to be proportional. Nevertheless, this hypothesis is no longer valid with unobserved covariates. As a consequence, there is a loss of power of the logrank test for testing the null hypothesis H(0) of no treatment effect. We propose a test suited for taking into account unobserved covariates. The proposed approach is based on a proportional hazard frailty model whereby the omitted covariates are considered as an unobserved frailty variable. The procedure is as follows. In a first step, the weighted logrank test optimal for testing H(0) against a general proportional hazard frailty model is obtained and its specialization for a gamma frailty variable is derived. In a second step, the proposed test is obtained by combining the maximin efficiency robustness principle and the gamma frailty distribution properties. Simulation studies investigate the power properties of the test for different frailty distributions. A breast cancer clinical trial is analysed as an example. The proposed test might be recommended rather than the logrank for practical situations in which one expects heterogeneity related to omitted covariates.

Breast Neoplasms↗

Discussion

Explore the source record for details and available documents.

Journal Article↗

Prevalence of suicide ideation and suicide attempts in nine countries.

BACKGROUND: There are few cross-national comparisons of the rates of suicide ideation and attempts across diverse countries. Nine independently conducted epidemiological surveys using similar diagnostic assessment and criteria provided an opportunity to obtain that data. METHODS: Suicide ideation and attempts were assessed on the Diagnostic Interview Schedule in over 40000 subjects drawn from the United States, Canada, Puerto Rico, France, West Germany, Lebanon, Taiwan, Korea and New Zealand. RESULTS: The lifetime prevalence rates/100 for suicide ideation ranged from 2.09 (Beirut) to 18.51 (Christchurch, New Zealand). Lifetime prevalence rates/100 for suicide attempts ranged from 0.72 (Beirut) to 5.93 (Puerto Rico). Females as compared to males had only marginally higher rates of suicidal ideation in most countries, reaching a two-fold increase in Taiwan. Females as compared to males had more consistently higher rates for suicide attempts, reaching a two- to three-fold increase in most countries. Suicide ideation and attempts in most countries were associated with being currently divorced/separated as compared to currently married. CONCLUSIONS: While the rates of suicide ideation varied widely by country, the rates of suicide attempts were more consistent across most countries. The variations were only partly explained by variation in rates of psychiatric disorders, divorce or separation among countries and are probably due to cultural features that we do not, as yet, understand.

Adolescent↗

[Use of GEE for modeling censored correlated data: application to the study of risk factors for withdrawal of totally implantable vascular access devices in cystic fibrosis].

BACKGROUND: The proportional hazards model proposed by Cox for modeling censored data is not suited for correlated delays, for instance when several events can be observed on each subject. METHODS: To analyze correlated delays, we propose to use a log-linear marginal model equivalent to Cox model. Correlations are taken into account through the use of Liang and Zeger's Generalized Estimating Equations (GEE) and of their robust variance estimator. An advantage of this method is that it can be implemented through the SAS GENMOD procedure. When ties are observed, we propose to use multiple imputations, creating M data sets without ties from the original one. RESULTS: This method is applied to a retrospective survey on the risk of withdrawing totally implantable vascular access devices (TIVAD) because of complication in cystic fibrosis patients: 265 TIVAD implanted in 200 patients were observed. Risk factors were characteristics of the device or of the patient. Results obtained with the robust variance estimator and ten imputations show that the use of the device for taking blood (vs exclusive perfusion of antibiotics), polyurethane catheter (vs. silicon), use of counterpressure for upkeeping and pulmonary colonization by Pseudomonas Aeruginosa are significantly associated to withdrawal. Under the Cox model which does not account for the correlations, some conclusions differ because the robust variance of the estimators is smaller than the variance obtained under the working assumption of independent delays. CONCLUSION: This approach allows the modeling of correlated survival data with SAS software. Our results illustrate the necessity of accounting for existing correlations.

Catheters, Indwelling↗

Estimating means and percentages in a complex sampling survey: application to a French national survey on sexual behaviour (ACSF). Analyse des Comportements Sexuels en France.

Two-phase stratification sampling with unequal selection probabilities is a relatively cost-efficient strategy to address problems on a nationwide basis and to perform comparative analyses of specific subgroups. This was the case with the ACSF survey. Specific procedures to estimate the variances of unbiased estimators in complex sampling designs are not included in standard statistical packages and no specialized software is available for two-phase sampling. A detailed synthesis of general basic rules for inference about a target population from a probability sample is first presented. We follow with a standard procedure to estimate means and percentages with their confidence intervals according to the design. Finally, numerical results are discussed.

Acquired Immunodeficiency Syndrome↗

The cross-national epidemiology of panic disorder.

BACKGROUND: Epidemiological data on panic disorder from community studies from 10 countries around the world are presented to determine the consistency of findings across diverse cultures. METHOD: Data from independently conducted community surveys from 10 countries (the United States, Canada, Puerto Rico, France, West Germany, Italy, Lebanon, Taiwan, Korea, and New Zealand), using the Diagnostic Interview Schedule and DSM-III criteria and including over 40,000 subjects, were analyzed with appropriate standardization for age and sex differences among subjects from different countries. RESULTS: The lifetime prevalence rates for panic disorder ranged from 1.4 per 100 in Edmonton, Alberta, to 2.9 per 100 in Florence, Italy, with the exception of that in Taiwan, 0.4 per 100, where rates for most psychiatric disorders are low. Mean age at first onset was usually in early to middle adulthood. The rates were higher in female than male subjects in all countries. Panic disorder was associated with an increased risk of agoraphobia and major depression in all countries. CONCLUSIONS: Panic disorder is relatively consistent, with a few exceptions, in rates and patterns across different countries. It is unclear why the rates of panic and other psychiatric disorders are lower in Taiwan.

Adolescent↗

[Estimation methods in a sampling survey].

The objective of this paper is to present a guide for statistical analysis of a sampling survey. Advantages and disadvantages of classical sampling designs are first discussed. A sampling survey was designed to give more precise estimates of parameters which characterize a targeted well-defined population. Simple sampling design often is impossible in large population and rarely is the optimal solution. According to practical and economic constraints, and to available sampling frames, other strategies (stratification, unequal probabilities, several selection steps) may be necessary or more efficient. Fundamental tools to compute estimators and their confidence intervals are presented. The choice of the sampling method determine for each population unit the probability to include it in the final sample. These inclusion probabilities must be known to formulate estimators, ideally unbiased and with low variance. Difficulties arise from calculating the variance, especially for estimators which are not linear functions of the characteristics of interest. In that case, estimation procedures include Taylor linearization. It is always possible to find at least one linear estimator for a total. The total is the key-parameter in sampling theory, most parameters (such as ratios, means, percentages...), being function of unknown totals. Numerical examples are given.

Confidence Intervals↗

Case counting in epidemiology: limitations of methods based on multiple data sources.

BACKGROUND: The application of capture-recapture methods in epidemiology has been proposed as an alternative to field surveys. This methodology is important for the future of epidemiology and deserves a critical analysis. METHODS: This paper reviews conditions for applying the capture-recapture models to epidemiological data, taking into account practical considerations, in particular the problem of case definition. RESULTS: The underlying assumptions are particularly restrictive resulting in a theoretical limitation of their applicability. In spite of the statistical developments designed to overcome these difficulties, the practical conditions for using the existing lists are often not fulfilled (availability, confidentiality). The major restriction is on the quality of the data which are often far below the standards required in specific prevalence surveys and which may differ between lists. This may result in a dramatic lack of specificity. The definition of the virtual subgroup of patients missing in all lists as generated by the statistical procedure, is questionable particularly when counting living patients. Field studies would be necessary for validation. CONCLUSIONS: In some particular situations (e.g. deceased patients, rare diseases), this methodology may provide a useful approximation to the number of ill subjects events, but users should be aware of their poor specificity. It can also be useful to complement data from surveillance systems by careful cross-checking with independent sources of information. Currently, this method cannot, in any way, replace direct population prevalence or incidence surveys.

Epidemiologic Methods↗

A regression survival model for testing the proportional hazards hypothesis.

A semi-parametric generalization of the proportional hazards regression model is defined, whereby the hazard functions can cross for different values of the covariates. In the two-sample comparison, it includes in particular the case of two Weibull distributions differing in scale and shape parameters. A global test of the proportional hazards assumption is proposed against such defined alternatives. Its power in the two-sample case is compared to that of previously described tests by using simulation experiments. Survival data of patients with breast carcinoma, including several prognostic factors, are presented as an illustration.

Antineoplastic Agents↗

Classification and epidemiology of social phobia.

The individualization of social phobia among other phobic disorders is very recent, although previous clinical descriptions can be found in the literature. The new classifications (DSM-III, DSM-IV and ICD-10) have provided operationalized criteria for this disorder, which have allowed researchers to conduct epidemiological studies. However, some diagnostic issues are not completely solved, namely, those with other boundary disorders. Cross-cultural prevalence and risk factors of social phobia are reviewed. Results of a French community study have found a lifetime prevalence rate of 2.1% in males and 5.4% in females. Comorbidity of social phobia with other anxiety disorders and major depression was high. Suicidal tendencies, family history and health services utilization were analyzed according to the lifetime comorbidity pattern of social phobia and depression.

Adolescent↗

Environmental exposure to cadmium and human birthweight.

Fetal toxicity of cadmium (Cd) is well documented in rodents. However, little information is available regarding the human fetus. To investigate the effect of low levels of Cd on the human placenta and the consequences on birthweight, we conducted a study of 102 mothers and their newborns in an obstetrical care unit. Placental and hair samples were collected at delivery to determine Cd concentrations. The main finding of this study was the relationship between a decrease in birthweight and an increase of newborn hair Cd which varied in the presence of placental calcification. In cases of parenchymal calcifications, placental Cd levels were higher (Wilcoxon test, P < 0.05) and newborn hair Cd levels were lower (Wilcoxon test, P < 0.01) than in the absence of calcification. These relationships remained significant even after taking into account smoking habits and gestational age. In the presence of calcification, an increase in the level of Cd in newborn hair was related to a decrease in birthweight which was independent of placental Cd concentration (rpartial = -0.49, P < 0.01). In the absence of calcification, a decrease in birthweight was observed for the upper values of newborn hair Cd (r = -0.44, P < 0.05 when Cd > or = 0.3 ppm). The difference in birthweight between infants in the first and last quartiles of newborn hair Cd was 472 g in cases of calcifications and 122 g in the absence of calcification. Other placental parameters were not significantly related to placental Cd concentration.

Birth Weight↗

The succession procedure for interim analysis: extensions for early acceptance of Ho and for flexible times of analysis.

The succession procedure is a new method for group sequential analysis based on a succession of significant tests. In this paper, the procedure is extended by the addition of a lower boundary, which allows the early acceptance of the null hypothesis Ho according to the stochastic curtailing approach. The succession procedure is also adapted to the type I error spending rate function alpha *(t), leading to the method of semisequential analysis for which the times of analysis need not be specified in advance.

Algorithms↗

Upper limb injuries and handedness plasticity.

In a questionnaire survey of 9591 men between 17 and 27 years of age, there was an association between present handedness score and report of an earlier injury causing a temporary shift of hand use. The proportion of weak right-handers was higher among those who reported injuries. Overall, there was no association between left-handedness and injuries. Nevertheless, injuries occurring before the school attendance age, which concerned only a very small fraction of the respondents, were associated with an increased frequency of left-handedness. The data emphasize the plasticity of human handedness, and do not suggest that innate left- or non-right-handedness is a risk factor for accident occurrence.

Adolescent↗

[Internal validation of a measurement scale: relation between principal component analysis, Cronbach's alpha coefficient and intra-class correlation coefficient].

The objective is to establish a simple relationship between two frequently used validation techniques which have been developed in the literature along the same lines: Principal Component Analysis and Cronbach's alpha. We have shown that under certain conditions, it is possible to estimate the reliability by using the results of a Principal Component Analysis only. Moreover, we report the relation between Cronbach's alpha and intraclass correlation coefficient, which are both used to estimate the reliability of continuous measures.

Data Interpretation, Statistical↗