Postmenopausal hormone therapy and mortality before and after the Women's Health Initiative study

Abstract

Weighing risks and benefits of postmenopausal hormone therapy (HT) has proven a balancing act. We aimed to investigate the association between HT and mortality before and after the 2002 publication from the Women's Health Initiative (WHI) study. This publication found that the risk of using HT outweighted the benefits, and thus it caused a marked reduction in systemic HT user prevalence. The 2002 WHI publication may also have caused a change in the subsequent HT user profile, as HT is no longer recommended in the prevention of chronic diseases. This cohort study included two populations followed from 1995: A 5% random sample of female singletons from the Danish general population (n = 52,388) and a sample of Danish female twins (n = 15,261). HT use was evaluated in 1995, 2000, 2005, and 2010. The association between HT, education, and mortality was investigated and controlled for potential unobserved familial confounding in a within-pair analysis. Singletons aged 56-75 using systemic HT in 2000 had a lower mortality compared to non-users (hazard ratio (HR) 0.83, 95% confidence interval (CI) 0.78-0.89). In 2005, the mortality was like that of the background population for this age group (HR 1.02, 95% CI 0.94-1.11). Recently postmenopausal twins showed a similar tendency. Systemic HT users, who had switched to local HT by 2005, had a substantially lower mortality than non-users (HR ranging from 0.42 to 0.67 depending on age group). In conclusion, we found that the prevalence of systemic HT use declined after 2002, and systemic HT users' mortality changed from lower before 2002 to similar to that of the background population after 2002. This indicates that the healthiest users decided to either drop systemic HT or switcted to local HT, as recommendations changed following the WHI publication.

Figure 1

Prevalence of hormone therapy in 1995, 2000, 2005, and 2010 and for separate age groups in both the singleton and twin study population using a logarithmic scale. Note. Due to data being restricted to include those with date of birth before January 1st 1950, prevalence for those aged 51–55 in 2005 and for those aged 51–55 and 56–60 in 2010 is not shown in all four figures.

Figure 2

Forest plot illustrating the association between mortality (shown on a log scale) and hormone therapy (HT), local and systemic HT respectively, in singletons and shown separately for each age group in the years 2000 and 2005. It shows hazard ratio and corresponding 95% confidence interval. For those aged 56–75 the association was adjusted for education but not for those aged 76–90, due to education was missing for 63% in this age group in 2000. Difference in overall association between HT use in 2000 and 2005 is estimated using an interaction p-value.