Article

Illustrating the Impact of a Time-Varying Covariate With an Extended Kaplan-Meier Estimator

The American Statistician (Impact Factor: 0.98). 02/2005; 59(November):301-307. DOI: 10.1198/000313005X70371
Source: RePEc
1 Bookmark
 · 
84 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Elevated resting heart rate is associated with mortality in general populations. Smokers may be at particular risk. The association between resting heart rate (RHR), smoking status and cardiovascular and total mortality was investigated in a general population. Prospective study of 16,516 healthy subjects from the Copenhagen City Heart Study. 8709 deaths, hereof 3821 cardiovascular deaths, occurred during 33 years of follow-up. In multivariate Cox models with time-dependent covariates RHR was significantly associated with both cardiovascular and total mortality. Current and former smokers had, irrespective of tobacco consumption, greater relative risk of elevated RHR compared to never smokers. The relative risk of all-cause mortality per 10 bpm increase in RHR was (95% CI): 1.06 (1.01-1.10) in never smokers, 1.11 (1.07-1.15) in former smokers, 1.13 (1.09-1.16) in moderate smokers, and 1.13 (1.10-1.16) in heavy smokers. There was no gender difference. The risk estimates for cardiovascular and all-cause mortality were essentially similar. In univariate analyses, the difference in survival between a RHR in the highest (> 80 bpm) vs lowest quartile (< 65 bpm) was 4.7 years in men and 3.6 years in women. In multivariate analyses, the difference was about one year in never smokers and about two years in current and former smokers. In a healthy population resting heart rate is associated with total and cardiovascular mortality. Elevated resting heart rate is associated with greater risk in subjects with a history of smoking than in never smokers.
    International journal of cardiology 09/2011; 151(2):148-54. · 6.18 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Background Attention deficit-hyperactivity disorder (ADHD) is a common disorder that has been associated with criminal behavior in some studies. Pharmacologic treatment is available for ADHD and may reduce the risk of criminality. Methods Using Swedish national registers, we gathered information on 25,656 patients with a diagnosis of ADHD, their pharmacologic treatment, and subsequent criminal convictions in Sweden from 2006 through 2009. We used stratified Cox regression analyses to compare the rate of criminality while the patients were receiving ADHD medication, as compared with the rate for the same patients while not receiving medication. Results As compared with nonmedication periods, among patients receiving ADHD medication, there was a significant reduction of 32% in the criminality rate for men (adjusted hazard ratio, 0.68; 95% confidence interval [CI], 0.63 to 0.73) and 41% for women (hazard ratio, 0.59; 95% CI, 0.50 to 0.70). The rate reduction remained between 17% and 46% in sensitivity analyses among men, with factors that included different types of drugs (e.g., stimulant vs. nonstimulant) and outcomes (e.g., type of crime). Conclusions Among patients with ADHD, rates of criminality were lower during periods when they were receiving ADHD medication. These findings raise the possibility that the use of medication reduces the risk of criminality among patients with ADHD. (Funded by the Swedish Research Council and others.).
    New England Journal of Medicine 11/2012; 367(21):2006-14. · 54.42 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: There are very few data from men on the risk of HIV acquisition associated with penile human papillomavirus (HPV) infection and no data on the potential modifying effect of male circumcision. Therefore, this study evaluated whether HPV is independently associated with risk of HIV. A cohort study of HPV natural history nested within a randomized control trial of male circumcision to reduce HIV incidence in Kisumu, Kenya. Prospective data from 2519 men were analyzed using 6-month discrete-time Cox models to determine if HIV acquisition was higher among circumcised or uncircumcised men with HPV compared to HPV-uninfected men. Risk of HIV acquisition was nonsignificantly increased among men with any HPV [adjusted hazard ratio (aHR) 1.72; 95% confidence interval (CI) 0.94-3.15] and high-risk HPV (aHR 1.92; 95% CI 0.96-3.87) compared to HPV-uninfected men, and estimates did not differ by circumcision status. Risk of HIV increased 27% with each additional HPV genotype infection (aHR 1.27; 95% CI 1.09-1.48). Men with persistent (aHR 3.27; 95% CI 1.59-6.72) or recently cleared (aHR 3.05; 95% CI 1.34-6.97) HPV had a higher risk of HIV acquisition than HPV-uninfected men. Consistent with the findings in women, HPV infection, clearance, and persistence were associated with an increased risk of HIV acquisition in men. Given the high prevalence of HPV in populations at risk of HIV, consideration of HPV in future HIV-prevention studies and investigation into mechanisms through which HPV might facilitate HIV acquisition are needed.
    AIDS (London, England) 10/2013; · 4.91 Impact Factor