Flexible modeling of the effects of serum cholesterol on coronary heart disease mortality.

Department of Epidemiology and Biostatistics, McGill University, Montreal, Quebec, Canada.
American Journal of Epidemiology (Impact Factor: 4.98). 04/1997; 145(8):714-29. DOI: 10.1093/aje/145.8.714
Source: PubMed

ABSTRACT Current understanding of the impact of lipids and other risk factors on coronary heart disease is largely based on the results of parametric multiple regression analyses of large prospective studies. To assess the potential impact of the a priori assumption of linearity of continuous risk factors on the results of parametric analyses, the authors completed a secondary analysis of the Lipid Research Clinics Prevalence and Follow-up Studies (1972-1987) data using an assumption-free nonparametric modeling approach. The effects of total serum cholesterol and the ratio of total serum cholesterol to high density lipoprotein cholesterol, adjusted for common risk factors, were estimated using a smoothing spline method available in the generalized additive model extension of the multiple logistic regression. The data set included 2,512 men in the random sample of the Lipid Research Clinics study who did not take lipid-lowering medications. During the median follow-up of 12.6 years, 94 coronary heart disease deaths occurred. The generalized additive model fits the effects of total serum cholesterol (p < 0.01) and the ratio of total serum cholesterol to high density lipoprotein cholesterol (p < 0.02) significantly better than the parametric logistic regression. Validation studies confirmed that, among new observations arising from the same population, generalized additive model estimates predicted outcomes better than the parametric estimates. Nonlinear effects of both lipid measures were robust and may be clinically important. The authors conclude that the linearity assumption inherent in parametric models may result in biased estimates of the effects of total serum cholesterol on coronary heart disease mortality and recommend that their findings be verified in a nonparametric analysis of data from another large prospective study.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Despite the established causal association between cigarette smoking and lung cancer, the relative contributions of age started, duration, years since quitting, and daily amount smoked have not been well characterized. We estimated the contribution of each of these aspects of smoking behavior. A case-control study was conducted in Montreal on the etiology of lung cancer. There were 640 cases and 938 control subjects for whom lifetime smoking histories were collected. We used generalized additive models, incorporating cubic smoothing splines to model nonlinear effects of various smoking variables. We adopted a multistep approach to deal with the multicollinearity among time-related variables. The main findings are that (1) risk increases independently by daily amount and by duration; (2) among current smokers, lung cancer risk doubles for every 10 cigarettes per day up to 30 to 40 cigarettes per day and tails off thereafter; (3) among ex-smokers, the odds ratio decreases with increasing time since quitting, the rate of decrease being sharper among heavy smokers than among light smokers; and (4) absolute risks demonstrate the dramatic public health benefits of long-term smoking cessation. Our results reinforce some previous findings on this issue.
    Journal of Clinical Epidemiology 11/2004; 57(10):1076-85. DOI:10.1016/j.jclinepi.2004.02.014 · 5.48 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Controversy exists concerning the fetal risk associated with exposure to low-dose methylmercury from maternal fish consumption. Previous studies of the effects of acute prenatal mercury exposure identified delays in achieving developmental milestones among exposed children. This led to public health concern that prenatal low-dose exposure from fish consumption could adversely affect the fetus. We evaluated the effects of prenatal methylmercury exposure (through maternal fish consumption) on the age that children walked and first said words in the main study cohort of the Seychelles Child Development Study. We used semiparametric generalized additive models to identify nonlinearities in the relationships between prenatal exposure and developmental outcomes, after adjusting for covariates, and to evaluate their importance. Very slight delays (<1 day) in walking were seen as mercury levels increased from 0 to 7 ppm, but this effect did not persist at the higher exposure levels represented by the cohort, making it difficult to conclude that a cause and effect relationship existed at the exposure levels seen in this cohort. There was no evidence for any association between prenatal exposure and age at talking. Images Figure 1 Figure 2 Figure 3 Figure 4
    Environmental Health Perspectives 09/1998; 106(9):559-64. DOI:10.2307/3434230 · 7.03 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The traditional method of analysing continuous or ordinal risk factors by categorization or linear models may be improved. We propose an approach based on transformation and fractional polynomials which yields simple regression models with interpretable curves. We suggest a way of presenting the results from such models which involves tabulating the risks estimated from the model at convenient values of the risk factor. We discuss how to incorporate several continuous risk and confounding variables within a single model. The approach is exemplified with data from the Whitehall I study of British Civil Servants. We discuss the approach in relation to categorization and non-parametric regression models. We show that non-linear risk models fit the data better than linear models. We discuss the difficulties introduced by categorization and the advantages of the new approach. Our approach based on fractional polynomials should be considered as an important alternative to the traditional approaches for the analysis of continuous variables in epidemiological studies.
    International Journal of Epidemiology 11/1999; 28(5):964-74. DOI:10.1093/ije/28.5.964 · 9.20 Impact Factor


1 Download
Available from