Skip to main content
SpringerLink
Log in

Methods for Adjusting for Bias Due to Crossover in Oncology Trials

  • Practical Application
  • Published:
PharmacoEconomics Aims and scope Submit manuscript

Abstract

Trials of new oncology treatments often involve a crossover element in their design that allows patients receiving the control treatment to crossover to receive the experimental treatment at disease progression or when sufficient evidence about the efficacy of the new treatment is achieved. Crossover leads to contamination of the initial randomized groups due to a mixing of the effects of the control and experimental treatments in the reference group. This is further complicated by the fact that crossover is often a very selective process whereby patients who switch treatment have a different prognosis than those who do not. Standard statistical techniques, including those that attempt to account for the treatment switch, cannot fully adjust for the bias introduced by crossover. Specialized methods such as rank-preserving structural failure time (RPSFT) models and inverse probability of censoring weighted (IPCW) analyses are designed to deal with selective treatment switching and have been increasingly applied to adjust for crossover. We provide an overview of the crossover problem and highlight circumstances under which it is likely to cause bias. We then describe the RPSFT and IPCW methods and explain how these methods adjust for the bias, highlighting the assumptions invoked in the process. Our aim is to facilitate understanding of these complex methods using a case study to support explanations. We also discuss the implications of crossover adjustment on cost-effectiveness results.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Notes

  1. In fact, patients who are censored are effectively excluded from future risk sets considered in proportional hazards models for overall survival.

  2. Overall survival follow-up is ongoing and final analyses are expected in 2014.

References

  1. Carroll KJ. Analysis of progression-free survival in oncology trials: some common statistical issues. Pharm Stat. 2007;6(2):99–113.

    Article  PubMed  Google Scholar 

  2. Fleming TR, Rothmann MD, Lu HL. Issues in using progression-free survival when evaluating oncology products. J Clin Oncol. 2009;27(17):2874–80.

    Article  PubMed Central  PubMed  Google Scholar 

  3. Panageas KS, Ben-Porat L, Dickler MN, Chapman PB, Schrag D. When you look matters: the effect of assessment schedule on progression-free survival. J Natl Cancer Inst. 2007;99(6):428–32.

    Article  PubMed  Google Scholar 

  4. Broglio KR, Berry DA. Detecting an overall survival benefit that is derived from progression-free survival. J Natl Cancer Inst. 2009;101(23):1642–9.

    Article  PubMed  Google Scholar 

  5. Chakravarty A, Sridhara R. Use of progression-free survival as a surrogate marker in oncology trials: some regulatory issues. Stat Methods Med Res. 2008;17(5):515–8.

    Article  PubMed  Google Scholar 

  6. Greenland S, Lanes S, Jara M. Estimating effects from randomized trials with discontinuations: the need for intent-to-treat design and G-estimation. Clin Trials. 2008;5(1):5–13.

    Article  PubMed  Google Scholar 

  7. Hernan MA, Cole SR, Margolick J, Cohen M, Robins JM. Structural accelerated failure time models for survival analysis in studies with time-varying treatments. Pharmacoepidemiol Drug Saf. 2005;14(7):477–91.

    Article  PubMed  Google Scholar 

  8. Robins JM, Tsiatis AA. Correcting for non-compliance in randomized trials using rank preserving structural failure time models. Commun Stat Theory Methods. 1991;20(8):2609–31.

    Article  Google Scholar 

  9. Hernan MA, Brumback B, Robins JM. Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men. Epidemiology. 2000;11(5):561–70.

    Article  CAS  PubMed  Google Scholar 

  10. Robins JM, Finkelstein DM. Correcting for noncompliance and dependent censoring in an AIDS Clinical Trial with inverse probability of censoring weighted (IPCW) log-rank tests. Biometrics. 2000;56(3):779–88.

    Article  CAS  PubMed  Google Scholar 

  11. Branson M, Whitehead J. Estimating a treatment effect in survival studies in which patients switch treatment. Stat Med. 2002;21(17):2449–63.

    Article  PubMed  Google Scholar 

  12. Ishak KJ, Caro JJ, Drayson MT, Dimopoulos M, Weber D, Augustson B, et al. Adjusting for patient crossover in clinical trials using external data: a case study of lenalidomide for advanced multiple myeloma. Value Health. 2011;14(5):672–8.

    Article  PubMed  Google Scholar 

  13. Law MG, Kaldor JM. Survival analyses of randomized clinical trials adjusted for patients who switch treatments. Stat Med. 1996;15(19):2069–76.

    Article  CAS  PubMed  Google Scholar 

  14. Loeys T, Goetghebeur E. A causal proportional hazards estimator for the effect of treatment actually received in a randomized trial with all-or-nothing compliance. Biometrics. 2003;59(1):100–5.

    Article  CAS  PubMed  Google Scholar 

  15. Walker AS, White IR, Babiker AG. Parametric randomization-based methods for correcting for treatment changes in the assessment of the causal effect of treatment. Stat Med. 2004;23(4):571–90.

    Article  PubMed  Google Scholar 

  16. Colleoni M, Giobbie-Hurder A, Regan MM, Thurlimann B, Mouridsen H, Mauriac L, et al. Analyses adjusting for selective crossover show improved overall survival with adjuvant letrozole compared with tamoxifen in the BIG 1-98 study. J Clin Oncol. 2011;29(9):1117–24.

    Article  CAS  PubMed Central  PubMed  Google Scholar 

  17. Motzer RJ, Escudier B, Oudard S, Hutson TE, Porta C, Bracarda S, et al. Phase 3 trial of everolimus for metastatic renal cell carcinoma: final results and analysis of prognostic factors. Cancer. 2010;116(18):4256–65.

    Article  CAS  PubMed  Google Scholar 

  18. Sternberg CN, Hawkins RE, Wagstaff J, Salman P, Mardiak J, Barrios CH, et al. A randomised, double-blind phase III study of pazopanib in patients with advanced and/or metastatic renal cell carcinoma: final overall survival results and safety update. Eur J Cancer. 2013;49(6):1287–96.

    Article  CAS  PubMed  Google Scholar 

  19. Dental and pharmaceutical benefits agency (TLV). Reimbursement decision for Afinitor; 2012.

  20. NICE. Sunitinib for the treatment of gastrointestinal stromal tumours. Final appraisal determination; 2009. http://www.nice.org.uk/guidance/index.jsp?action=download&o=45125. Accessed Sep 2010.

  21. NICE. Everolimus for the second-line treatment of advanced renal cell carcinoma. Final appraisal determination; 2010. http://www.nice.org.uk/nicemedia/live/12044/49566/49566.pdf. Accessed Sep 2010.

  22. NICE. Pazopanib for the first-line treatment of advanced renal cell carcinoma. Final appraisal determination; 2010. http://www.nice.org.uk/nicemedia/live/12032/52263/52263.pdf.

  23. Demetri GD, Huang X, Garrett CR, et al. Novel statistical analysis of long-term survival to account for crossover in a phase III trial of sunitinib (SU) vs. placebo (PL) in advanced GIST after imatinib (IM) failure. J Clin Oncol. 2008;26(May 20 Suppl):Abstract 10524.

    Google Scholar 

  24. Morden JP, Lambert PC, Latimer N, Abrams KR, Wailoo AJ. Assessing methods for dealing with treatment switching in randomised controlled trials: a simulation study. BMC Med Res Methodol. 2011;11:4.

    Article  PubMed Central  PubMed  Google Scholar 

  25. Delea TE, Duh MS, Wei L-J, Robins JM. Methods to adjust for selective crossover in survival analysis in assessments of cost-effectiveness of cancer therapies. ISPOR workshop presented 23 May 2011 at ISPOR 16th Annual International Meeting, Baltimore. http://www.analysisgroup.com/uploadedFiles/News_and_Events/News/ISPOR2011_Selected_Crossover_Cost-Effectiveness_Cancer_Therapies.pdf. Accessed Feb 2012.

  26. Raymond E, Dahan L, Raoul JL, Bang YJ, Borbath I, Lombard-Bohas C, et al. Sunitinib malate for the treatment of pancreatic neuroendocrine tumors. N Engl J Med. 2011;364(6):501–13.

    Article  CAS  PubMed  Google Scholar 

  27. Cox DR. Regression models and life-tables. J R Stat Soc Ser B (Methodol). 1972;34(2):187–220 (http://www.ida.liu.se/~kawah/Cox2.pdf).

  28. SMC. Advice for treatment of unresectable or metastatic, well-differentiated pancreatic neuroendocrine tumours with disease rogression in adults. SMC No. (698/11); 2011. https://www.scottishmedicines.org.uk/files/advice/sunitinib_Sutent_FINAL_APRIL_2011_for_website.pdf.

  29. NICE. Renal cell carcinoma (first line metastatic) - pazopanib: Evidence Review Group report; 2010. http://www.nice.org.uk/guidance/index.jsp?action=download&o=52305. Accessed Feb 2013.

  30. NICE. Pazopanib for the first-line treatment of advanced renal cell carcinoma. NICE technology appraisal guidance 215. Issued: February 2011; last modified: August 2013; 2011. http://www.nice.org.uk/nicemedia/live/13346/53185/53185.pdf.

  31. NICE. Everolimus for the second-line treatment of advanced renal cell carcinoma. NICE technology appraisal guidance 219; 2011. http://www.nice.org.uk/nicemedia/live/13437/54111/54111.pdf.

  32. Foo J, Michor F. Evolution of resistance to targeted anti-cancer therapies during continuous and pulsed administration strategies. PLoS Comput Biol. 2009;5(11):e1000557.

    Article  PubMed Central  PubMed  Google Scholar 

  33. Howe CJ, Cole SR, Chmiel JS, Munoz A. Limitation of inverse probability-of-censoring weights in estimating survival in the presence of strong selection bias. Am J Epidemiol. 2011;173(5):569–77.

    Article  PubMed Central  PubMed  Google Scholar 

  34. Odondi L, McNamee R. Performance of statistical methods for analysing survival data in the presence of non-random compliance. Stat Med. 2010;29(29):2994–3003.

    Article  PubMed  Google Scholar 

  35. NICE. Lenalidomide for the treatment of multiple myeloma in people who have received at least one prior therapy. NICE technology appraisal guidance 171; 2009. http://www.nice.org.uk/nicemedia/pdf/ta171guidance.pdf.

Download references

Acknowledgments

K. Jack Ishak and Irina Proskorovsky are employees of Evidera, which received payment from Pfizer Inc. in the development of this manuscript and analyses being reported. The manuscript was funded jointly by Evidera and Pfizer Inc. This study was sponsored by Pfizer. Rickard Sandin is a full-time employee of Pfizer and holds Pfizer stock. Beata Korytowsky was a full-time employee of Pfizer during the commencement, writing, and completion of this manuscript, and holds Pfizer stock. Juan Valle has received honoraria from Pfizer. Sandrine Faivre has received consulting fees or honoraria as well as payment for lectures, including service on speaking bureaus from Pfizer.

Disclosures

K. Jack Ishak is the overall guarantor of the paper. He led the conceptualization of the paper, description of the methodology, oversaw analyses of the trial data and interpretation of the results, and drafting of the manuscript. Irina Proskorovsky was involved in the conceptualization of the paper, carried out the analyses, interpreted results and reviewed drafts of the paper. Rickard Sandin and Beata Korytowsky were involved in the conceptualization of the paper, review and interpretation of results, and review of drafts of the manuscript. Juan Valle and Sandrine Faivre provided clinical expertise supporting the interpretation of the results from analyses and reviewed drafts of the paper.

Author information

Authors and Affiliations

  1. Evidera, 7575 Trans-Canada Highway, Suite 500, St-Laurent, QC, H4T 1V6, Canada

    K. Jack Ishak & Irina Proskorovsky

  2. Global Health Economics and Outcomes Research, Pfizer Oncology, New York, NY, USA

    Beata Korytowsky

  3. Global Health Economics and Outcomes Research, Pfizer Oncology, Sollentuna, Sweden

    Rickard Sandin

  4. Department of Medical Oncology (INSERM U728–PRES Paris 7 Diderot), Beaujon University Hospital, Assistance Publique, Hôpitaux de Paris, Clichy-La-Garenne, France

    Sandrine Faivre

  5. The Christie Foundation Trust, Wimslow Road, Manchester, UK

    Juan Valle

  6. School of Cancer and Enabling Sciences, University of Manchester, Manchester Cancer Research Centre and Manchester Academic Health Sciences Centre, Manchester, UK

    Juan Valle

Authors
  1. K. Jack Ishak
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Irina Proskorovsky
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Beata Korytowsky
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Rickard Sandin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sandrine Faivre
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Juan Valle
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to K. Jack Ishak.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ishak, K.J., Proskorovsky, I., Korytowsky, B. et al. Methods for Adjusting for Bias Due to Crossover in Oncology Trials. PharmacoEconomics 32, 533–546 (2014). https://doi.org/10.1007/s40273-014-0145-y

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40273-014-0145-y

Keywords

Search

Navigation