Zengri Wang | PubMed Health

PubMed2004

Marginalized binary mixed-effects models with covariate-dependent random effects and likelihood inference.

Marginal models and conditional mixed-effects models are commonly used for clustered binary data. However, regression parameters and predictions in nonlinear mixed-effects models usually do not have a direct marginal interpretation, because the conditional functional form does not carry over to the margin. Because both marginal and conditional inferences are of interest, a unified approach is attractive. To this end, we investigate a parameterization of generalized linear mixed models with a structured random-intercept distribution that matches the conditional and marginal shapes. We model the marginal mean of response distribution and select the distribution of the random intercept to produce the match and also to model covariate-dependent random effects. We discuss the relation between this approach and some existing models and compare the approaches on two datasets.

Air Pollution↗

PubMed2002

Imiquimod 5-percent cream does not alter the natural history of recurrent herpes genitalis: a phase II, randomized, double-blind, placebo-controlled study.

Present strategies for control of herpes genitalis recurrences require multiple daily doses of antiviral medication. Imiquimod, an immune response modifier, induces alpha interferon and interleukin-12; application in the presence of local herpes antigens during a recurrence may augment herpes simplex virus (HSV)-specific cell-mediated immunity. To test this theory, we performed a randomized, double-blind, placebo-controlled study of imiquimod 5% cream to assess safety and efficacy for decreasing recurrences. Patients with six or more recurrences of herpes genitalis per year applied study cream (imiquimod or placebo) to lesions one, two, or three times per week for 3 weeks for each recurrence during a 16-week treatment period. This was followed by a 16-week observation period. Of 124 patients randomized to the study, 103 completed the treatment period and 93 completed the observation period. The median times to first genital herpes recurrence were 53 days for those receiving placebo (n = 30) and 54, 60, and 64 days for those receiving imiquimod one time per week (n = 34), two times per week (n = 32), and three times per week (n = 28), respectively. The median annualized recurrence rates during the treatment period were 3.8, 4.9, 3.2, and 3.1, respectively. There were no statistically significant differences in the time to first recurrence or in the annualized recurrence rate between the imiquimod and placebo groups in either the treatment or the observation period. A trend in increased rates of local adverse events at the application site and a delay in lesion healing with more frequent dosing suggested a pharmacologic effect. Although clinical efficacy has been observed for imiquimod in other conditions in which a TH1-type immune response may be beneficial, including other viral infections such as those caused by human papillomavirus, no apparent effect on the short-term natural history of herpes genitalis recurrences was observed.

Adjuvants, Immunologic↗