Tacrine treatment and nursing home placement: Application of the Cox proportional hazards model with time-dependent covariates

Cox proportional hazards regressions with time-dependent covariates were used to determine the effect of continuous, long-term, open-label tacrine hydrochloride (Cognex®) treatment on nursing home placement in patients with Alzheimer's disease (AD). The results were compared with those obtained using logistic regression analyses, life table survival plots, and Kaplan-Meier estimates. Patients with probable AD (NINCDS criteria) initially randomized in a 30-week double-blind, placebo-controlled, parallel-group, high-dose study of tactrine could continue on long-term, open-label treatment at doses up to 160 mg/day. The population of interest consisted of patients who remained on tacrine or were off tacrine for only a short period of time (1- 60 days) prior to an event. Using last tacrine dose, the Cox proportional hazards regression approach with time-dependent covariates demonstrated there was a dose-response trend favoring higher doses (risk ratio = 1.7, p = 0.056) and a statistically significant difference favoring medium and higher doses combined (risk ratio = 1.8, p = 0.014).