Pablo Martínez-Camblor

The natural history of chronic airflow obstruction revisited: an analysis of the Framingham offspring cohort

RATIONALEnUnderstanding normal lung development and aging in health and disease, both in men and in women, is essential to interpreting any therapeutic intervention.nnnOBJECTIVESnWe aimed to describe lung function changes in healthy never-smoking males and females, from adolescence to old age, and to determine the effects of smoking and those derived from quitting.nnnMETHODSnProspective cohort study within all participants of the Framingham Offspring cohort who had two or more valid spirometry measurements during follow-up (n = 4,391; age range at baseline 13 to 71 yr), with a median follow-up time of 23 years.nnnMEASUREMENTS AND MAIN RESULTSnTo best fit the curves describing FEV(1) changes with age to raw data, we used a generalized additive model with smooth terms and incorporating the subject-specific (longitudinal) random effects. We found that: (1) healthy never-smoker females achieve full lung growth earlier than males, and their rate of decline with age was slightly, but not significantly, lower; (2) smoking increases the rate of lung function decline, both in males and in females; (3) there is a range of susceptibility to the effects of smoking. The presence of respiratory symptoms at baseline and/or a respiratory diagnosis during follow-up appears to identify a group of susceptible smokers; and (4) quitting smoking has a beneficial effect at any age, but it is more pronounced in earlier quitters.nnnCONCLUSIONSnLung function changes from adolescence to old age differ in males and females, smoking has similar deleterious effects in both sexes, and quitting earlier is better.

Prediction of risk of COPD exacerbations by the BODE index.

OBJECTIVESnThis study assesses the power of the BODE index, a multidimensional grading system that predicts mortality, to predict subsequent exacerbations in patients with COPD.nnnDESIGNnProspective cohort study.nnnPATIENTS AND INTERVENTIONSnA total of 275 COPD patients were followed every 6 months up to 8 years (median of 5.1 years). Baseline clinical variables were recorded and the BODE index was calculated. We investigated the prognostic value of BODE quartiles (scores 0-2, 3-4, 5-6 and 7-10) for both the number and severity of exacerbations requiring ambulatory treatment, emergency room visit, or hospitalization.nnnRESULTSnThe annual rate of COPD exacerbations was 1.95 (95% CI, 0.90-2.1). The mean time to a first exacerbation was inversely proportional to the worsening of the BODE quartiles (7.9 yrs, 5.7 yrs, 3.4 yrs and 1.3 yrs for BODE scores of 0-2, 3-4, 5-6 and 7-10, respectively). Similarly, the mean time to a first COPD emergency room visit was 6.7 yrs, 3.6 yrs, 2.0 yrs and 0.8 yrs for BODE quartiles (all p<0.05). Using ROC curves, the BODE index was a better predictor of exacerbation than the FEV(1) alone (p<0.01).nnnCONCLUSIONSnThe BODE index is a better predictor of the number and severity of exacerbations in COPD than FEV(1) alone.

Non-parametric k-sample tests: Density functions vs distribution functions

Tests for the comparison of k samples based on kernel density estimators (KDE) are introduced. The Double Minimum method as a new and useful procedure for the crucial problem of bandwidth selection is developed. The statistical power of the proposed tests, as well as the impact of the smoothing degree and the performance of the Double Minimum algorithm, are studied via Monte Carlo simulations. Finally, the results of the tests based on the KDE are compared to those of the traditional k-sample tests based on empirical distribution functions (EDF), and to other tests based on the likelihood ratio introduced in the recent literature. Two main conclusions are obtained. First, the proposed bandwidth selection method attains quasi-optimal results. Second, the simulations suggest that KDE-based tests are the most powerful when the underlying populations are different in shape, and that the L1 distance among densities leads to optimal results in the considered situations.

Nonparametric k-sample test based on kernel density estimator for paired design

Comparing whether the marginal distribution functions of a k-dimensional random variable are equal or not is a classical problem in statistical inference. Usually, the parametric ANOVA repeat measures analysis or the nonparametric Friedman test are used. Both procedures allow us to detect differences among the location parameters but not among shapes or spreads of the involved distributions. The AC statistic which is based on the measure of the common area under the respective kernel density estimators is used in order to compare the equality among the marginal densities of a k-dimensional random variable. The BM algorithm is employed to select, automatically, the final bandwidth parameter. Its statistical power is studied from Monte Carlo simulations and a real data analysis is also considered.

Diferencias por sexo en la supervivencia relativa y los factores pronósticos de pacientes con un primer infarto agudo de miocardio en Guipúzcoa

Introduccion y objetivos Estimar la supervivencia a los 28 dias y a los 5 anos y los factores pronosticos asociados en personas que han sufrido un primer infarto agudo de miocardio. Metodos Se estudio a 1.677 pacientes con un primer infarto agudo de miocardio que accedieron a un hospital de Guipuzcoa entre 1997 y 2000. Resultados Las mujeres eran unos 10 anos mayores, presentaron mas diabetes mellitus e hipertension y un cuadro clinico mas desfavorable y recibieron menos recursos terapeuticos, aunque eran menos fumadoras que los varones. La supervivencia fue superior entre los varones mayores de 60 anos a los 28 dias y a los 5 anos. En el periodo de 29 dias a 5 anos, los varones de todos los grupos de edad presentaron una supervivencia relativa mas larga. Los factores relacionados con la supervivencia a corto y largo plazo difirieron entre uno y otro sexo. La gravedad de la enfermedad en la fase aguda y la edad en la fase tardia fueron factores relacionados con la supervivencia de varones y mujeres y en el resto de las variables el comportamiento fue distinto entre uno y otro sexo. Conclusiones El infarto es una enfermedad con una elevada mortalidad en la fase aguda. Existe una interaccion entre el sexo y la edad que afecta a la supervivencia tras un infarto agudo de miocardio. Varios factores se asocian a un peor pronostico precoz y tardio en ambos sexos.

Sex Differences in Relative Survival and Prognostic Factors in Patients With a First Acute Myocardial Infarction in Guipuzcoa, Spain

INTRODUCTION AND OBJECTIVESnTo determine 28-day and 5-year survival rates in patients who have experienced a first acute myocardial infarction and to identify prognostic factors for survival.nnnMETHODSnThis study involved 1,677 patients with a first acute myocardial infarction who were treated at a hospital in Guipuzcoa, Spain between 1997 and 2000.nnnRESULTSnWomen were approximately 10 years older than men, presented more often with diabetes and hypertension, were in a less favorable clinical condition, and consumed fewer medical resources, but were less likely to smoke. Survival rates at 28 days and 5 years were higher in men over 60 years of age. In the period from 29 days to 5 years, the relative survival rate was higher in men from all age groups. Factors associated with short- and long-term survival varied between the sexes. Disease severity in the acute phase and, later on, age were associated with survival in both men and women, whereas the effect of other variables differed between the sexes.nnnCONCLUSIONSnMyocardial infarction is a condition associated with high mortality in the acute phase. There is an interaction between sex and age that affects survival after an acute myocardial infarction. A number of factors are associated with poor short- and long-term prognoses in both sexes.

Testing the equality among distribution functions from independent and right censored samples via Cramér--von Mises criterion

The traditional Cramér–von Mises criterion is used in order to develop a test to compare the equality of the underlying lifetime distributions in the presence of independent censoring times. Its asymptotic distribution is proved and a resampling plan, which is valid for unbalanced data situations, is proposed. Its statistical power is studied and compared with commonly used linear rank tests by Monte Carlo simulations and a real data analysis is also considered. It is observed that the new test is clearly more powerful than the traditional ones when there exists no uniform dominance among involved distributions and in the presence of late differences. Its statistical power is also good in the other considered scenarios.

Statistical comparison of the genetic sequence type diversity of invasive Neisseria meningitidis isolates in northern Spain (1997–2008)

Abstract A secondary effect derived from the mass vaccination campaigns against meningococcal disease could be the increase in the genetic sequence type variability of the Neisseria meningitidis. The study and measurement of diversity (or/and richness) is an old problem from Ecology. However, although there exist a huge number of diversity indices, they often do not have satisfactory statistical properties and their use in inference is limited or null. In this paper, the ratio of the number of different observed species (S) to the number of observed individuals (dNxa0=xa0S/N) is analyzed from both non-parametric and parametric approaches. The two methodologies are applied to the problem to know whether the genetic diversity of the invasive Neisseria meningitidis is equal or not along the last twelve years (1997–2008) in a region of northern Spain (Basque Country) where two mass immunization campaigns have been carried out during this period.

Testing the equality of diagnostic effectiveness of one measure with respect to k different features

In several cases the same measurement is used as a marker for two or more population features, and it is useful to test whether this measurement has the same diagnostic effectiveness with respect to different features. In this paper we use the area under receiver operating characteristic curve as index for the discriminatory power among continuous variables and population features (eventuality, two or more diseases), and we propose a test to contrast the equality of the diagnostic effectiveness of this measurement.