medigraphic.com
Instituto Nacional de Salud Pública

2025, Number 1

<< Back Next >>

salud publica mex 2025; 67 (1)

The target trial framework for causal inference with observational studies

Núñez I, Lajous M

Language: Spanish
References: 42
Page: 83-90
PDF size: 272.10 Kb.


ABSTRACT

The use of observational studies for causal inference is a necessity, as randomized trials are not always available or possible to carry out. To reduce sources of bias present in “classical” observational studies, the target trial framework has been proposed. First one defines the following components of the pragmatic clinical trial (the target trial) would answer our research question: eligibility criteria, treatment strategies, assignment, follow-up, outcomes, causal contrast, and statistical analysis plan. Then, these components are modified based on available observational data, and used to emulate the target trial as closely as possible. This leads to observational studies that are generally less biased and with more reliable results. Nonetheless, it is important to consider the limitations of this framework given it is still an observational study and not a randomized experiment.


REFERENCES

  1. Hernán MA. The C-Word: scientific euphemisms do not improve causalinference from observational data. Am J Public Health. 2018;108(5):616-9.https://doi.org/10.2105/AJPH.2018.304337

  2. Hernán MA. A definition of causal effect for epidemiological research. JEpidemiol Community Health. 2004;58(4):265-71. https://doi.org/10.1136/jech.2002.006361

  3. Hernán MA. Methods of public health research – Strengthening causalinference from observational data. N Engl J Med. 2021;385(15):1345-8.https://doi.org/10.1056/NEJMp2113319

  4. Collins R, Bowman L, Landray M, Peto R. The magic of randomizationversus the myth of real-world evidence. N Engl J Med. 2020;382(7):674-8.https://doi.org/10.1056/NEJMsb1901642

  5. Murad MH, Asi N, Alsawas M, Alahdab F. New evidence pyramid. EvidBased Med. 2016;21(4):125-7. https://doi.org/10.1136/ebmed-2016-110401

  6. Hernán MA, Robbins J. Causal inference: what if. Boca Raton: Chapman& Hall/CRC, 2024 [citado mayo, 2024]. Disponible en: https://www.hsph.harvard.edu/miguel-hernan/wp-content/uploads/sites/1268/2024/01/hernanrobins_WhatIf_2jan24.pdf

  7. Hernán MA, Alonso A, Logan R, Grodstein F, Michels K, Willett W,et al. Observational studies analyzed like randomized experiments: anapplication to postmenopausal hormone therapy and coronary heartdisease. Epidemiology. 2008;19(6):766-79. https://doi.org/10.1097/EDE.0b013e3181875e61

  8. Dickerman BA, García-Albéniz X, Logan RW, Denaxas S, Hernán MA.Avoidable flaws in observational analyses: an application to statins andcancer. Nat Med. 2019;25(10):1601-6. https://doi.org/10.1038/s41591-019-0597-x

  9. Hernán MA, Taubman SL. Does obesity shorten life? The importanceof well-defined interventions to answer causal questions. Int J Obes.2008;32(S3):S8-14. https://doi.org/10.1038/ijo.2008.82

  10. Lajous M. Inferencia causal en análisis basados en datos de vigilanciaepidemiológica para Covid-19. Salud Publica Mex. 2021;63(4):459-60.https://doi.org/10.21149/12777

  11. Lodi S, Phillips A, Logan R, Olson A, Costagliola D, Abgrall S, et al.Comparative effectiveness of immediate antiretroviral therapy versusCD4-based initiation in HIV-positive individuals in high-income countries:observational cohort study. Lancet HIV. 2015;2(8):e335-43. https://doi.org/10.1016/S2352-3018(15)00108-3

  12. The HIV-CAUSAL Collaboration. When to initiate combined antiretroviraltherapy to reduce mortality and AIDS-defining illness in HIV-infectedpersons in developed countries: an observational study. Ann Intern Med.2011;154(8):509. https://doi.org/10.7326/0003-4819-154-8-201104190-00001

  13. The INSIGHT START Study Group. Initiation of antiretroviral therapyin early asymptomatic HIV infection. N Engl J Med. 2015;373(9):795-807.https://doi.org/10.1056/NEJMoa1506816

  14. Hernán MA, Sauer BC, Hernández-Díaz S, Platt R, Shrier I. Specifyinga target trial prevents immortal time bias and other self-inflicted injuriesin observational analyses. J Clin Epidemiol. 2016;79:70-5. https://doi.org/10.1016/j.jclinepi.2016.04.014

  15. Matthews AA, Danaei G, Islam N, Kurth T. Target trial emulation:applying principles of randomised trials to observational studies. BMJ.2022;378:e071108. https://doi.org/10.1136/bmj-2022-071108

  16. Hernán MA, Robins JM. Using big data to emulate a target trial when arandomized trial is not available: table 1. Am J Epidemiol. 2016;183(8):758-64. https://doi.org/10.1093/aje/kwv254

  17. Danaei G, Rodríguez LAG, Cantero OF, Logan R, Hernán MA.Observational data for comparative effectiveness research: an emulationof randomised trials of statins and primary prevention of coronaryheart disease. Stat Methods Med Res. 2013;22(1):70-96. https://doi.org/10.1177/0962280211403603

  18. Matthews AA, Young JC, Kurth T. The target trial framework in clinicalepidemiology: principles and applications. J Clin Epidemiol. 2023;164:112-5.https://doi.org/10.1016/j.jclinepi.2023.10.008

  19. Ford I, Norrie J. Pragmatic trials. Drazen JM, Harrington DP, McMurrayJJV, Ware JH, Woodcock J, eds. N Engl J Med. 2016;375(5):454-63. https://doi.org/10.1056/NEJMra1510059

  20. Dahabreh IJ, Bibbins-Domingo K. Causal inference about the effectsof interventions from observational studies in medical journals. JAMA.2024;331(21):1845. https://doi.org/10.1001/jama.2024.7741

  21. Dahabreh IJ, Metthews A, Steingrimsson J, Scharfstein D, Stuart EA.Using trial and observational data to assess effectiveness: trial emulation,transportability, benchmarking, and joint analysis. Epidemiol Rev. 2023;mxac011. https://doi.org/10.1093/epirev/mxac011

  22. Schulz KF, Altman DG, Moher D. CONSORT 2010 Statement: updatedguidelines for reporting parallel group randomized trials. BMC Medicine.2010;152(11):726-32. https://doi.org/10.1186/1741-7015-8-18

  23. Hansford HJ, Cashin AG, Jones MD, Swanson SA, Islam N, Douglas SRG,et al. Reporting of observational studies explicitly aiming to emulate randomizedtrials: a systematic review. JAMA Netw Open. 2023;6(9):e2336023.https://doi.org/10.1001/jamanetworkopen.2023.36023

  24. Núñez I, Soto-Mota A. Uneven resources threaten causal consistencyin randomized trials. Epidemiology. 2023;34(4):531-4. https://doi.org/10.1097/EDE.0000000000001616

  25. Dang LE, Balzer LB. Start with the target trial protocol, then follow theroadmap for causal inference. Epidemiology. 2023;34(5):619-23. https://doi.org/10.1097/EDE.0000000000001637

  26. Núñez I. Canine confounders. Significance. 2022;19(4):24-7. https://doi.org/10.1111/1740-9713.01670

  27. VanderWeele TJ, Shpitser I. A new criterion for confounder selection.Biometrics. 2011;67(4):1406-13. https://doi.org/10.1111/j.1541-0420.2011.01619.x

  28. Núñez I. The importance of using disease causal models in studies ofpreventive interventions: learning from preeclampsia research. Prev Med.2023;177:107790. https://doi.org/10.1016/j.ypmed.2023.107790

  29. Núñez I, Belaunzarán-Zamudio PF. Preventable sources of bias in subgroupanalyses and secondary outcomes of randomized trials. ContempClin Trials. 2024;145:107641. https://doi.org/10.1016/j.cct.2024.107641

  30. Rudolph KE, Keyes KM. Voluntary firearm divestment and suiciderisk: real- world importance in the absence of causal identification.Epidemiology. 2023; 34(1):107-10. https://doi.org/10.1097/EDE.0000000000001548

  31. Suissa S. Immortal time bias in pharmacoepidemiology. Am J Epidemiol.2008;167(4):492-9. https://doi.org/10.1093/aje/kwm324

  32. Núñez I, Caro-Vega Y, MacDonald C, Mosqueda JL, Piñeirúa-Menéndez,Matthews AA. Comparative effectiveness of switching to bictegravir fromdolutegravir, efavirenz, or raltegravir-based antiretroviral therapy amongvirologically suppressed individuals with HIV. Open Forum Infect Dis.2024;11(8):ofae446. https://doi.org/10.1093/ofid/ofae446

  33. Howe CJ, Cole SR, Lau B, Napravnik S, Eron JJ. Selection bias due toloss to follow up in cohort studies. Epidemiology. 2016;27(1):91-7. https://doi.org/10.1097/EDE.0000000000000409

  34. Millard LAC, Fernández-Sanlés A, Carter AR, Hughes RA, Tilling K, MorrisTP, et al. Exploring the impact of selection bias in observational studiesof COVID-19: a simulation study. Int J Epidemiol. 2023;52(1):44-57. https://doi.org/10.1093/ije/dyac221

  35. Haneuse S, Arterburn D, Daniels MJ. Assessing missing data assumptions inEHR-based studies: a complex and underappreciated task. JAMA Netw Open.2021;4(2):e210184. https://doi.org/10.1001/jamanetworkopen.2021.0184

  36. Hughes RA, Heron J, Sterne JAC, Tilling K. Accounting for missing datain statistical analyses: multiple imputation is not always the answer. Int JEpidemiol. 2019;48(4):1294-304. https://doi.org/10.1093/ije/dyz032

  37. Hernán MA, Hernández-Díaz S. Beyond the intention-to-treat incomparative effectiveness research. Clin Trials. 2012;9(1):48-55. https://doi.org/10.1177/1740774511420743

  38. Hernán MA, Robins JM. Per-protocol analyses of pragmatic trials. NEngl J Med. 2017;377(14):1391-8. https://doi.org/10.1056/NEJMsm1605385

  39. Murray EJ, Caniglia EC, Swanson SA, Hernández-Díaz S, Hernán MA.Patients and investigators prefer measures of absolute risk in subgroupsfor pragmatic randomized trials. J Clin Epidemiol. 2018;103:10-21. https://doi.org/10.1016/j.jclinepi.2018.06.009

  40. Hernán MA, Del Amo J. Drug repurposing and observational studies:the case of antivirals for the treatment of COVID-19. Ann Intern Med.2023;176(4):556-60. https://doi.org/10.7326/M22-3582

  41. Swanson SA, Studdert DM, Zhang Y, Prince L, Miller M. Handgundivestment and risk of suicide. Epidemiology. 2023;34(1):99-106. https://doi.org/10.1097/EDE.0000000000001549

  42. Matthews AA, Dahabreh IJ, Fröbert O, Lindahl B, James S, Feychting M,et al. Benchmarking observational analyses before using them to addressquestions trials do not answer: an application to coronary thrombusaspiration. Am J Epidemiol. 2022;191(9):1652-65. https://doi.org/10.1093/aje/kwac098




2020     |     www.medigraphic.com