Advertisement

Statistics in Biosciences

, Volume 5, Issue 2, pp 344–360 | Cite as

An Analytic Framework for Aligning Observational and Randomized Trial Data: Application to Postmenopausal Hormone Therapy and Coronary Heart Disease

  • Sengwee TohEmail author
  • Joann E. Manson
Article

Abstract

We describe a conceptual analytic framework for aligning observational and randomized controlled trial (RCT) data. The framework allows one to (1) use observational data to estimate treatment effects comparable to their RCT counterparts, (2) properly include early events that occur soon after treatment initiation in the analysis of observational data, (3) estimate various treatment effects that are of clinical and scientific relevance while appropriately adjusting for time-varying confounders in both the RCT and observational analyses, (4) assess the generalizability of RCT findings in the more diverse populations generally found in the observational data, and (5) combine both types of data to study associations that cannot be addressed by one study or a single data set. We describe the theoretical application of this framework to the Women’s Health Initiative data to examine the relation between postmenopausal hormone therapy and coronary heart disease. The analytic framework can be tailored to specific exposure-outcome associations and data sources, and may be refined as more is learned about its strengths and limitations.

Keywords

Postmenopausal hormone therapy Coronary heart disease Marginal structural model Comparative effectiveness research Pharmacoepidemiology Pragmatic trials 

Notes

Acknowledgements

Dr. Toh is partially supported by the Agency for Healthcare and Research Quality (R03HS019024). Dr. Manson is partially supported by the National Heart, Lung, and Blood Institute (R01HL034594, R01HL088521, and N0I-WH32109).

References

  1. 1.
    Allison MA, Manson JE (2006) Observational studies and clinical trials of menopausal hormone therapy: can they both be right? Menopause 13(1):1–3 CrossRefGoogle Scholar
  2. 2.
    Arbogast PG, Ray WA (2009) Use of disease risk scores in pharmacoepidemiologic studies. Stat Methods Med Res 18(1):67–80 MathSciNetCrossRefGoogle Scholar
  3. 3.
    Barrett-Connor E (2007) Hormones and heart disease in women: the timing hypothesis. Am J Epidemiol 166(5):506–510 CrossRefGoogle Scholar
  4. 4.
    Barrett-Connor E, Grady D (1998) Hormone replacement therapy, heart disease, and other considerations. Annu Rev Public Health 19:55–72 CrossRefGoogle Scholar
  5. 5.
    Benson K, Hartz AJ (2000) A comparison of observational studies and randomized, controlled trials. N Engl J Med 342(25):1878–1886 CrossRefGoogle Scholar
  6. 6.
    Cain LE, Robins JM, Lanoy E, Logan R, Costagliola D, Hernán MA (2010) When to start treatment? A systematic approach to the comparison of dynamic regimes using observational data. Int J Biostat 6(2):18 MathSciNetGoogle Scholar
  7. 7.
    Col NF, Pauker SG (2003) The discrepancy between observational studies and randomized trials of menopausal hormone therapy: did expectations shape experience? Ann Intern Med 139(11):923–929 CrossRefGoogle Scholar
  8. 8.
    Cole SR, Stuart EA (2010) Generalizing evidence from randomized clinical trials to target populations: the ACTG 320 trial. Am J Epidemiol 172(1):107–115 CrossRefGoogle Scholar
  9. 9.
    Concato J, Shah N, Horwitz RI (2000) Randomized, controlled trials, observational studies, and the hierarchy of research designs. N Engl J Med 342(25):1887–1892 CrossRefGoogle Scholar
  10. 10.
    Cotter D, Zhang Y, Thamer M, Kaufman J, Hernán MA (2008) The effect of epoetin dose on hematocrit. Kidney Int 73(3):347–353 CrossRefGoogle Scholar
  11. 11.
    Creasman WT, Hoel D, Disaia PJ (2003) WHI: Now that the dust has settled: a commentary. Am J Obstet Gynecol 189(3):621–626 CrossRefGoogle Scholar
  12. 12.
    Danaei G, Garcia Rodriguez LA, Cantero OF, Logan R, Hernan MA (2011) Observational data for comparative effectiveness research: an emulation of randomised trials of statins and primary prevention of coronary heart disease. Stat Methods Med Res. doi: 10.1177/0962280211403603 Google Scholar
  13. 13.
    Diehr P, Yanez D, Ash A, Hornbrook M, Lin DY (1999) Methods for analyzing health care utilization and costs. Annu Rev Public Health 20:125–144 CrossRefGoogle Scholar
  14. 14.
    Eichler HG, Abadie E, Breckenridge A, Flamion B, Gustafsson LL, Leufkens H, Rowland M, Schneider CK, Bloechl-Daum B (2011) Bridging the efficacy-effectiveness gap: a regulator’s perspective on addressing variability of drug response. Nat Rev Drug Discov 10(7):495–506 CrossRefGoogle Scholar
  15. 15.
    Federal Coordinating Council for Comparative Effectiveness Research (2009) Report to the President and Congress on comparative effectiveness research. Department of Health and Human Services Google Scholar
  16. 16.
    Garbe E, Suissa S (2004) Hormone replacement therapy and acute coronary outcomes: methodological issues between randomized and observational studies. Hum Reprod 19(1):8–13 CrossRefGoogle Scholar
  17. 17.
    Golder S, Loke YK, Bland M (2011) Meta-analyses of adverse effects data derived from randomised controlled trials as compared to observational studies: methodological overview. PLoS Med 8(5):e1001026 CrossRefGoogle Scholar
  18. 18.
    Grady D, Rubin SM, Petitti DB, Fox CS, Black D, Ettinger B, Ernster VL, Cummings SR (1992) Hormone therapy to prevent disease and prolong life in postmenopausal women. Ann Intern Med 117(12):1016–1037 CrossRefGoogle Scholar
  19. 19.
    Grimes DA, Lobo RA (2002) Perspectives on the Women’s Health Initiative trial of hormone replacement therapy. Obstet Gynecol 100(6):1344–1353 CrossRefGoogle Scholar
  20. 20.
    Grodstein F, Clarkson TB, Manson JE (2003) Understanding the divergent data on postmenopausal hormone therapy. N Engl J Med 348(7):645–650 CrossRefGoogle Scholar
  21. 21.
    Hernán MA, Alonso A, Logan R, Grodstein F, Michels KB, Willett WC, Manson JE, Robins JM (2008) Observational studies analyzed like randomized experiments: an application to postmenopausal hormone therapy and coronary heart disease. Epidemiology 19(6):766–779 CrossRefGoogle Scholar
  22. 22.
    Hernán MA, Brumback B, Robins JM (2000) Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men. Epidemiology 11(5):561–570 CrossRefGoogle Scholar
  23. 23.
    Hernán MA, Lanoy E, Costagliola D, Robins JM (2006) Comparison of dynamic treatment regimes via inverse probability weighting. Basic Clin Pharmacol Toxicol 98(3):237–242 CrossRefGoogle Scholar
  24. 24.
    Hernán MA, Robins JM, García Rodríguez LA (2005) Discussion of Statistical issues arising in the Women’s Health Initiative by Prentice RL, Pettinger M, Andreson GL. Biometrics 61(4):922–930 MathSciNetCrossRefGoogle Scholar
  25. 25.
    Hsia J, Langer RD, Manson JE, Kuller L, Johnson KC, Hendrix SL, Pettinger M, Heckbert SR, Greep N, Crawford S, Eaton CB, Kostis JB, Caralis P, Prentice R (2006) Conjugated equine estrogens and coronary heart disease: the Women’s Health Initiative. Arch Intern Med 166(3):357–365 CrossRefGoogle Scholar
  26. 26.
    Humphrey LL, Chan BK, Sox HC (2002) Postmenopausal hormone replacement therapy and the primary prevention of cardiovascular disease. Ann Intern Med 137(4):273–284 CrossRefGoogle Scholar
  27. 27.
    Institute of Medicine (2009) Initial national priorities for comparative effectiveness research. The National Academies Press, Washington Google Scholar
  28. 28.
    Kurth T, Walker AM, Glynn RJ, Chan KA, Gaziano JM, Berger K, Robins JM (2006) Results of multivariable logistic regression, propensity matching, propensity adjustment, and propensity-based weighting under conditions of nonuniform effect. Am J Epidemiol 163(3):262–270 CrossRefGoogle Scholar
  29. 29.
    Kuss O, Legler T, Borgermann J (2011) Treatments effects from randomized trials and propensity score analyses were similar in similar populations in an example from cardiac surgery. J Clin Epidemiol 64(10):1076–1084 CrossRefGoogle Scholar
  30. 30.
    Liang KY, Zeger SL (1986) Longitudinal data analysis using generalized linear models. Biometrika 73(1):13–22 MathSciNetCrossRefzbMATHGoogle Scholar
  31. 31.
    Machens K, Schmidt-Gollwitzer K (2003) Issues to debate on the Women’s Health Initiative (WHI) study. Hormone replacement therapy: an epidemiological dilemma? Hum Reprod 18(10):1992–1999 CrossRefGoogle Scholar
  32. 32.
    Manson JE, Allison MA, Rossouw JE, Carr JJ, Langer RD, Hsia J, Kuller LH, Cochrane BB, Hunt JR, Ludlam SE, Pettinger MB, Gass M, Margolis KL, Nathan L, Ockene JK, Prentice RL, Robbins J, Stefanick ML (2007) Estrogen therapy and coronary-artery calcification. N Engl J Med 356(25):2591–2602 CrossRefGoogle Scholar
  33. 33.
    Manson JE, Bassuk SS (2007) Invited commentary: hormone therapy and risk of coronary heart disease why renew the focus on the early years of menopause? Am J Epidemiol 166(5):511–517 CrossRefGoogle Scholar
  34. 34.
    Manson JE, Hsia J, Johnson KC, Rossouw JE, Assaf AR, Lasser NL, Trevisan M, Black HR, Heckbert SR, Detrano R, Strickland OL, Wong ND, Crouse JR, Stein E, Cushman M (2003) Estrogen plus progestin and the risk of coronary heart disease. N Engl J Med 349(6):523–534 CrossRefGoogle Scholar
  35. 35.
    McDonough PG (2002) The randomized world is not without its imperfections: reflections on the Women’s Health Initiative Study. Fertil Steril 78(5):951–956 CrossRefGoogle Scholar
  36. 36.
    Mendelsohn ME, Karas RH (2007) HRT and the young at heart. N Engl J Med 356(25):2639–2641 CrossRefGoogle Scholar
  37. 37.
    Michels KB, Manson JE (2003) Postmenopausal hormone therapy: a reversal of fortune. Circulation 107(14):1830–1833 CrossRefGoogle Scholar
  38. 38.
    Mikkola TS, Clarkson TB (2002) Estrogen replacement therapy, atherosclerosis, and vascular function. Cardiovasc Res 53(3):605–619 CrossRefGoogle Scholar
  39. 39.
    Murphy SA (2003) Optimal dynamic treatment regimes. J R Stat Soc B 65(2):331–355 CrossRefzbMATHGoogle Scholar
  40. 40.
    Naftolin F, Taylor HS, Karas R, Brinton E, Newman I, Clarkson TB, Mendelsohn M, Lobo RA, Judelson DR, Nachtigall LE, Heward CB, Hecht H, Jaff MR, Harman SM (2004) The Women’s Health Initiative could not have detected cardioprotective effects of starting hormone therapy during the menopausal transition. Fertil Steril 81(6):1498–1501 CrossRefGoogle Scholar
  41. 41.
    Nallamothu BK, Hayward RA, Bates ER (2008) Beyond the randomized clinical trial: the role of effectiveness studies in evaluating cardiovascular therapies. Circulation 118(12):1294–1303 CrossRefGoogle Scholar
  42. 42.
    North American Menopause Society (2012) The 2012 hormone therapy position statement of the North American Menopause Society. Menopause 19(3):257–271 Google Scholar
  43. 43.
    Phillips LS, Langer RD (2005) Postmenopausal hormone therapy: critical reappraisal and a unified hypothesis. Fertil Steril 83(3):558–566 CrossRefGoogle Scholar
  44. 44.
    Platt R, Carnahan RM, Brown JS, Chrischilles E, Curtis LH, Hennessy S, Nelson JC, Racoosin JA, Robb M, Schneeweiss S, Toh S, Weiner MG (2012) The U.S. food and drug administration’s mini-sentinel program: status and direction. Pharmacoepidemiol Drug Saf 21(Suppl 1):1–8 Google Scholar
  45. 45.
    Prentice RL, Langer R, Stefanick ML, Howard BV, Pettinger M, Anderson G, Barad D, Curb JD, Kotchen J, Kuller L, Limacher M, Wactawski-Wende J (2005) Combined postmenopausal hormone therapy and cardiovascular disease: toward resolving the discrepancy between observational studies and the Women’s Health Initiative clinical trial. Am J Epidemiol 162(5):404–414 CrossRefGoogle Scholar
  46. 46.
    Prentice RL, Langer RD, Stefanick ML, Howard BV, Pettinger M, Anderson GL, Barad D, Curb JD, Kotchen J, Kuller L, Limacher M, Wactawski-Wende J (2006) Combined analysis of Women’s Health Initiative observational and clinical trial data on postmenopausal hormone treatment and cardiovascular disease. Am J Epidemiol 163(7):589–599 CrossRefGoogle Scholar
  47. 47.
    Prentice RL, Manson JE, Langer RD, Anderson GL, Pettinger M, Jackson RD, Johnson KC, Kuller LH, Lane DS, Wactawski-Wende J, Brzyski R, Allison M, Ockene J, Sarto G, Rossouw JE (2009) Benefits and risks of postmenopausal hormone therapy when it is initiated soon after menopause. Am J Epidemiol 170(1):12–23 CrossRefGoogle Scholar
  48. 48.
    Psaty BM, Siscovick DS (2010) Minimizing bias due to confounding by indication in comparative effectiveness research: the importance of restriction. JAMA 304(8):897–898 CrossRefGoogle Scholar
  49. 49.
    Ray WA (2003) Evaluating medication effects outside of clinical trials: new-user designs. Am J Epidemiol 158(9):915–920 CrossRefGoogle Scholar
  50. 50.
    Robins JM (1986) A new approach to causal inference in mortality studies with sustained exposure periods—application to control of the health worker survivor effect. Math Model 7:1393–1512 MathSciNetCrossRefzbMATHGoogle Scholar
  51. 51.
    Robins JM (1989) The analysis of randomized and non-randomized AIDS treatment trials using a new approach to causal inference in longitudinal studies. In: Sechrest L, Freeman H, Mulley A (eds) Health service research methodology: a focus on AIDS. NCHSR, US Public Health Service, Washington, pp 113–159 Google Scholar
  52. 52.
    Robins JM (1993) Analytic methods for estimating HIV treatment and cofactor effects. In: Ostrow DG, Kessler R (eds) Methodological issues of AIDS mental health research. Plenum, New York, pp 213–290 Google Scholar
  53. 53.
    Robins JM, Hernán MA (2008) Estimation of the causal effects of time-varying exposures. In: Fitzmaurice G, Davidian M, Verbeke G, Molenberghs G (eds) Longitudinal data analysis. Chapman and Hall/CRC Press, New York, pp 553–599 CrossRefGoogle Scholar
  54. 54.
    Robins JM, Hernán MA, Brumback B (2000) Marginal structural models and causal inference in epidemiology. Epidemiology 11(5):550–560 CrossRefGoogle Scholar
  55. 55.
    Robins JM, Hernán MA, Siebert U (2004) Effects of multiple interventions. In: Ezzati M, Lopez AD, Murray CJL (eds) Comparative quatification of health risks: global and regional burden of disease attributable to selected major risk factors. World Health Organization, Geneva Google Scholar
  56. 56.
    Rosenbaum PR, Rubin DB (1983) The central role of the propensity score in observational studies for causal effects. Biometrika 70:41–55 MathSciNetCrossRefzbMATHGoogle Scholar
  57. 57.
    Rossouw JE (2005) Coronary heart disease in menopausal women: implications of primary and secondary prevention trials of hormones. Maturitas 51(1):51–63 CrossRefGoogle Scholar
  58. 58.
    Rossouw JE, Prentice RL, Manson JE, Wu L, Barad D, Barnabei VM, Ko M, LaCroix AZ, Margolis KL, Stefanick ML (2007) Postmenopausal hormone therapy and risk of cardiovascular disease by age and years since menopause. JAMA 297(13):1465–1477 CrossRefGoogle Scholar
  59. 59.
    Rothman KJ, Greenland S, Lash TL (eds) (2008) Modern epidemiology, 3rd edn. Lippincott Williams & Wilkins, Philadelphia Google Scholar
  60. 60.
    Santen RJ, Allred DC, Ardoin SP, Archer DF, Boyd N, Braunstein GD, Burger HG, Colditz GA, Davis SR, Gambacciani M, Gower BA, Henderson VW, Jarjour WN, Karas RH, Kleerekoper M, Lobo RA, Manson JE, Marsden J, Martin KA, Martin L, Pinkerton JV, Rubinow DR, Teede H, Thiboutot DM, Utian WH (2010) Postmenopausal hormone therapy: an endocrine society scientific statement. J Clin Endocrinol Metab 95:s1–s66 CrossRefGoogle Scholar
  61. 61.
    Schneeweiss S, Patrick AR, Sturmer T, Brookhart MA, Avorn J, Maclure M, Rothman KJ, Glynn RJ (2007) Increasing levels of restriction in pharmacoepidemiologic database studies of elderly and comparison with randomized trial results. Med Care 45(10 Supl 2):S131–142 CrossRefGoogle Scholar
  62. 62.
    Solomon DH, Avorn J, Sturmer T, Glynn RJ, Mogun H, Schneeweiss S (2006) Cardiovascular outcomes in new users of coxibs and nonsteroidal antiinflammatory drugs: high-risk subgroups and time course of risk. Arthritis Rheumatol 54(5):1378–1389 CrossRefGoogle Scholar
  63. 63.
    Sorensen HT, Lash TL, Rothman KJ (2006) Beyond randomized controlled trials: a critical comparison of trials with nonrandomized studies. Hepatology 44(5):1075–1082 CrossRefGoogle Scholar
  64. 64.
    Stampfer M (2004) Commentary: Hormones and heart disease: do trials and observational studies address different questions? Int J Epidemiol 33(3):454–455 CrossRefGoogle Scholar
  65. 65.
    Stampfer MJ, Colditz GA (1991) Estrogen replacement therapy and coronary heart disease: a quantitative assessment of the epidemiologic evidence. Prev Med 20(1):47–63 CrossRefGoogle Scholar
  66. 66.
    Sturdee DW, Pines A, Archer DF, Baber RJ, Barlow D, Birkhauser MH, Brincat M, Cardozo L, de Villiers TJ, Gambacciani M, Gompel AA, Henderson VW, Kluft C, Lobo RA, MacLennan AH, Marsden J, Nappi RE, Panay N, Pickar JH, Robinson D, Simon J, Sitruk-Ware RL, Stevenson JC (2011) Updated IMS recommendations on postmenopausal hormone therapy and preventive strategies for midlife health. Climacteric 14(3):302–320 CrossRefGoogle Scholar
  67. 67.
    Tannen RL, Weiner MG, Xie D, Barnhart K (2007) A simulation using data from a primary care practice database closely replicated the women’s health initiative trial. J Clin Epidemiol 60(7):686–695 CrossRefGoogle Scholar
  68. 68.
    Taubman SL, Robins JM, Mittleman MA, Hernan MA (2009) Intervening on risk factors for coronary heart disease: an application of the parametric g-formula. Int J Epidemiol 38(6):1599–1611 CrossRefGoogle Scholar
  69. 69.
    The Women’s Health Initiative Study Group (1998) Design of the Women’s Health Initiative clinical trial and observational study. Control Clin Trials 19(1):61–109 CrossRefGoogle Scholar
  70. 70.
    The Writing Group for the Women’s Health Initiative Investigators (2002) Risks and benefits of estrogen plus progestin in healthy postmenopausal women: principal results from the Women’s Health Initiative randomized controlled trial. JAMA 288(3):321–333 CrossRefGoogle Scholar
  71. 71.
    Thompson WA Jr (1977) On the treatment of grouped observations in life studies. Biometrics 33(3):463–470 MathSciNetCrossRefzbMATHGoogle Scholar
  72. 72.
    Toh S, Hernán MA (2008) Causal inference from longitudinal studies with baseline randomization. Int J Biostat 4(1):22 MathSciNetGoogle Scholar
  73. 73.
    Toh S, Hernández-Díaz S, Logan R, Robins JM, Hernán MA (2010) Estimating absolute risks in the presence of nonadherence: an application to a follow-up study with baseline randomization. Epidemiology 21(4):528–539 CrossRefGoogle Scholar
  74. 74.
    Toh S, Hernández-Díaz S, Logan R, Rossouw JE, Hernán MA (2010) Coronary heart disease in postmenopausal recipients of estrogen plus progestin therapy: does the increased risk ever disappear? A randomized trial. Ann Intern Med 152(4):211–217 CrossRefGoogle Scholar
  75. 75.
    van der Laan M, Petersen ML, Joffe MM (2005) History-adjusted marginal structural models and statically-optimal dynamic treatment regimens. Int J Biostat 1:4 MathSciNetGoogle Scholar
  76. 76.
    Vandenbroucke JP (2004) When are observational studies as credible as randomised trials? Lancet 363(9422):1728–1731 CrossRefGoogle Scholar
  77. 77.
    Wasserman L (2006) All of nonparametric statistics. Springer, New York zbMATHGoogle Scholar
  78. 78.
    Young JG, Cain LE, Robins JM, O’Reilly EJ, Hernán MA (2011) Comparative effectiveness of dynamic treatment regimes: an application of the parametric g-formula. Stat Biosci 2011(3):119–143 CrossRefGoogle Scholar

Copyright information

© International Chinese Statistical Association 2012

Authors and Affiliations

  1. 1.Department of Population MedicineHarvard Medical School and Harvard Pilgrim Health Care InstituteBostonUSA
  2. 2.Division of Preventive Medicine, Brigham and Women’s HospitalHarvard Medical SchoolBostonUSA

Personalised recommendations