Presentation on theme: "The Case of the Women's Health Initiative Randomized Trial: A Statistician Reads a Paper Dan Freeman, Ph.D. Professor, Preventive Medicine and Community."— Presentation transcript:
The Case of the Women's Health Initiative Randomized Trial: A Statistician Reads a Paper Dan Freeman, Ph.D. Professor, Preventive Medicine and Community Health Director, Office of Biostatistics 2-6355 email@example.com
2/11/20032 The Rationale for the Trial “The preponderance of evidence from the epidemiologic studies strongly supports the view that postmenopausal estrogen therapy can substantially reduce the risk for coronary heart disease....This effect is unlikely to be explained by confounding factors or selection.” (Stampfer Colditz 1991: p 61)
2/11/20033 And, an unexpected ending “Results from the WHI [Women’s Health Initiative] indicate that the combined postmenopausal hormones... should not be initiated or continued for the primary prevention of CHD....” (Writing Group for the Women’s Health Initiative Investigators 2002: p 332)
2/11/20034 July 9, 2002 Study Is Halted Over Rise Seen In Cancer Risk By GINA KOLATA A large federal study of hormone replacement therapy in postmenopausal women was abruptly halted, researchers say, because the drugs caused a slight but significant increase in the risk of invasive breast cancer. JAMA, July 17, 2002 – Vol 288, No. 3
2/11/20035 July 10, 2002 Hormone Replacement Study A Shock to the Medical System By GINA KOLATA with MELODY PETERSEN The announcement yesterday that a hormone replacement regimen taken by six million American women did more harm than good was met with puzzlement and disbelief by women and their doctors across the country. September 3, 2002 Sorting Through the Confusion Over Estrogen By JANE E. BRODY Susan McGee of Bethesda, Md., and Jane Quinn of Brooklyn were not planning to take hormones at menopause. But after many months of sleep disrupted nightly by drenching sweats and changes of bedclothes, they gave in. JAMA, November 6, 2002 – Vol 288, No. 17
2/11/200313 Controlled Trials: Examples Physician’s Health Study –Aspirin and cardiovascular disease Women’s Health Initiative – HRT Virtually, all new drug applications require RCT’s Lind’s study of scurvy
2/11/200315 Comparison of Proportions Science 297, 19 July 2002: 326
2/11/200316 Multiple Hypothesis Tests Something has to be ‘significant’
2/11/200317 Confidence Intervals Uncertainty. The range of likely risk from hormone therapy is wider when the data are adjusted for multiple sampling.
2/11/200318 Conclusions 1.The statistical issues hinge on multiple comparisons 2.The earlier observational studies were correctly executed but have inherent weaknesses. 3.It is possible that the factors that led to the long-term use are also protective against CHD: Exercise – Diet – Not Smoking 4.Further clinical trials are critical
2/11/200319 Further Conclusions Dr. Susan Hendrix, a gynecologist at Wayne State University in Detroit who was an investigator in the federal study. "It's pretty astounding to go from a year ago thinking this is one of the most benign drugs to a 180-degree turn in the opposite direction."
2/11/200320 References 1.Dawson B, Trapp RG. Basic and Clinical Biostatistics 3 rd Ed. New York: Lange Medical Books, 2001 2.Stampfer MJ, Colditz GA. Estrogen replacement therapy and coronary heart disease: A quantitative assessment of the epidemiologic evidence. Prev Med 20, 1991; 47 – 63 3.Waters DD et al. Effects of hormone replacement therapy and antioxidant vitamin supplements on coronary atherolsclerosis in postmenopausal women. JAMA: 288, November 20, 2002; 2432 – 2440 4.Writing Group for the Women’s Health Initiative Investigators. Risks and benefits of estrogen plus progestion in healthy postmenopausal women. JAMA: 288, July 17, 2002; 321 – 333