glmtoolbox (version 0.1.12)

uti: Urinary Tract Infections in HIV-infected Men

Description

These data arose from a study conducted in the Department of Internal Medicine at Utrecht University Hospital, in the Netherlands. In this study, 98 HIV-infected men were followed for up to two years. Urinary cultures were obtained during the first visit and every six months thereafter. Also, cultures were obtained between regular scheduled visits when signs and symptoms of urinary tract infections (UTI) occurred, or when patients had a fever of unknown origin. CD4+ cell counts were also measured. A CD4+ count is a blood test to determine how well the immune system works in people diagnosed with HIV. In general, a decreasing CD4+ count indicates HIV progression.

Usage

data(uti)

Format

A data frame with 98 rows and 3 variables:

episodes

a numeric vector indicating the number of episodes, that is, the number of times each patient had urinary tract infections (UTI).

time

a numeric vector indicating the time to follow up, in months.

cd4

a numeric vector indicating the immune status of the patient as measured by the CD4+ cell counts.

References

Hoepelman A.I.M., Van Buren M., Van den Broek J., Borleffs J.C.C. (1992) Bacteriuria in men infected with HIV-1 is related to their immune status (CD4+ cell count). AIDS 6:179-184.

Morel J.G., Nagaraj N.K. (2012) Overdispersion Models in SAS. SAS Institute Inc., Cary, North Carolina, USA.

van den Broek J. (1995) A Score Test for Zero Inflation in a Poisson Distribution. Biometrics 51:738–743.

Examples

data(uti)
dev.new()
uti2 <- within(uti,cd4C <- cut(log(cd4),4,labels=c("low","mid-low","mid-high","high")))
out <- aggregate(cbind(episodes,time) ~ cd4C, sum, data=uti2)
barplot(12*episodes/time ~ cd4C, beside=TRUE, data=out, col="red",
        xlab="CD4+ cell count", ylab="Number of UTIs per year")