摘要：Objectives. We examined the cessation of hormone replacement therapy (HRT) among British women, by educational level, social class, and cardiovascular risk factors, at the time of publicity about 2 clinical trials of HRT that were halted after adverse findings. Methods. A total of 1387 women aged 57 years reported their monthly HRT use between January 2002 and February 2003. A succession of regression-based time-series models were fitted to detect changes in the proportion of HRT users stratified by education level, social class, hypertension, and obesity. Results. The overall percentage of HRT users declined from 31% in January 2002 to less than 26% by February 2003. Changes in trends of HRT use were first detected in June 2002 (for women with advanced secondary educational qualification or higher) and in July 2002 (for all other groups). The rate of decline was greatest for women with no formal educational qualifications, from the manual social class, or who were hypertensive or obese. Conclusions. These decreases coincided with the announced cessation of a large US clinical trial of HRT. This publicity may have had a differential influence on the immediate decline in HRT use by various groups of British women. Previous articles have examined the problematic issue of reporting results from medical research in ways that do not provoke detrimental public health outcomes. 1 – 3 For instance, controversy and confusion arose among the UK public after reports of a link between autism/bowel syndrome and the triple measles, mumps, and rubella vaccine. 1 , 2 It led to a marked drop in vaccination rates among children and a consequent increased risk of these diseases. 1 In July 2002, another debate, this one surrounding HRT for menopausal women, occurred. The National Institutes of Health issued a press release announcing that after 5.6 years they had prematurely stopped the American Women’s Health Initiative (WHI), a major clinical trial examining the risks and benefits of combined estrogen and progestin treatment. The press release reported the relative change in risk for a range of health outcomes among women on HRT compared with those of the placebo group, including a “41% increase in the risk of strokes,” “a doubling of the rates of venous thromboembolism,” and “a 26% increase in the rates of breast cancer.” 3 Although they also reported the absolute change, for instance that among 10 000 postmenopausal women on the type of HRT studied, 8 more would have breast cancer, it was the relative percentage change that made the headlines. 4 The press release omitted confidence intervals for the results, although these were reported in the supporting peer-reviewed paper a week later. 5 At least 1 media commentator suggested that the percentage change in risk could easily be misinterpreted in absolute terms, so that women on HRT might conclude that they had a 24%, or nearly 1 in 4 chance of developing breast cancer. 4 Unsurprisingly the reports not only caused alarm among women but also may have influenced the decision of those on HRT to discontinue treatment. For example, in Australia the sales of most commonly prescribed HRT preparations declined by 30% within 5 weeks of the initial press release. 4 As a consequence of the results from the WHI study, in October 2002 the UK Medical Research Council (MRC) decided to stop the Women’s International Study of Long Duration Estrogen After Menopause (WISDOM) trial, for which recruitment had started in 1999. 6 We examine the timing and magnitude of cessation trends for HRT use by social class and educational level among British women between January 1999 and February 2003 and estimate the immediate effect of publicity surrounding the early termination of these trials. Because reports of the WHI trial may have indicated an increased risk of cardiovascular disease (CVD) that was contrary to expectations, 7 trends in HRT use were also investigated by level of CVD risk as characterized by blood pressure and body mass index.
