×

Bayesian statistics and the efficiency and ethics of clinical trials. (English) Zbl 1057.62096

Summary: The Bayesian approach is being used increasingly in medical research. The flexibility of the Bayesian approach allows for building designs of clinical trials that have good properties of any desired sort. Examples include maximizing effective treatment of patients in the trial, maximizing information about the slope of a dose-response curve, minimizing costs, minimizing the number of patients treated, minimizing the length of the trial and combinations of these desiderata. They also include standard frequentist operating characteristics when these are important considerations. Posterior probabilities are updated via Bayes’ theorem on the basis of accumulating data. These are used to effect modifications of the trial’s course, including stopping accrual, extending accrual beyond that originally planned, dropping treatment arms, adding arms, etc.
An important aspect of the approach I advocate is modeling the relationship between a trial’s primary endpoint and early indications of patient performance – auxiliary endpoints. This has several highly desirable consequences. One is that it improves the efficiency of adaptive trials because information is available sooner than otherwise.

MSC:

62P10 Applications of statistics to biology and medical sciences; meta analysis
62C10 Bayesian problems; characterization of Bayes procedures
62F15 Bayesian inference
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Anscombe, F. J. (1963). Sequential medical trials (with discussion). J. Amer. Statist. Assoc. 58 365–387. JSTOR: · doi:10.2307/2283272
[2] Belmont Report (1979). Ethical principles and guidelines for the protection of human subjects of research. The National Commission for the Protection of Human Subjects of Biomedical and Behavioral Research. Available at http://ohrp.osophs. dhhs.gov/humansubjects/guidance/belmont.htm.
[3] Berry, D. A. (1972). A Bernoulli two-armed bandit. Ann. Math. Statist. 43 871–897. · Zbl 0258.62013 · doi:10.1214/aoms/1177692553
[4] Berry, D. A. (1978). Modified two-armed bandit strategies for certain clinical trials. J. Amer. Statist. Assoc. 73 339–345. · Zbl 0399.62107
[5] Berry, D. A. (1993). A case for Bayesianism in clinical trials (with discussion). Statistics in Medicine 12 1377–1404. · Zbl 0972.62107
[6] Berry, D. A. (1995). Decision analysis and Bayesian methods in clinical trials. In Recent Advances in Clinical Trial Design and Analysis (P. Thall, ed.) 125–154. Kluwer, Boston.
[7] Berry, D. A. (1996). Statistics: A Bayesian Perspective . Duxbury, Belmont, CA.
[8] Berry, D. A. and Eick, S. G. (1995). Adaptive assignment versus balanced randomization in clinical trials: A decision analysis. Statistics in Medicine 14 231–246. · Zbl 0972.62107
[9] Berry, D. A. and Fristedt, B. (1985). Bandit Problems: Sequential Allocation of Experiments . Chapman and Hall, London. · Zbl 0659.62086
[10] Berry, D. A., Müller, P., Grieve, A. P., Smith, M., Parke, T., Blazek, R., Mitchard, N. and Krams, M. (2002). Adaptive Bayesian designs for dose-ranging drug trials. In Case Studies in Bayesian Statistics V. Lecture Notes in Statist. 162 99–181. Springer, New York. · Zbl 1022.62109
[11] Berry, D. A. and Stangl, D. K., eds. (1996). Bayesian Biostatistics . Dekker, New York. · Zbl 0851.62082
[12] Cheng, Y., Su, F. and Berry, D. A. (2003). Choosing sample size for a clinical trial using decision analysis. Biometrika 90 923–936. · Zbl 1436.62523 · doi:10.1093/biomet/90.4.923
[13] Clemen, R. T. (1991). Making Hard Decisions . PWS-Kent, Boston.
[14] Colton, T. (1963). A model for selecting one of two medical treatments. J. Amer. Statist. Assoc. 58 388–400. JSTOR: · doi:10.2307/2283274
[15] Ellenberg, S. S., Fleming, T. R. and DeMets, D. L. (2002). Data Monitoring Committees in Clinical Trials: A Practical Perspective . Wiley, New York.
[16] Farr-Jones, S. (2001). Better statistics. BioCentury, The Bernstein Report on BioBusiness 9 (No. 12, March 12.)
[17] Inoue, L. Y. T., Thall, P. F. and Berry, D. A. (2002). Seamlessly expanding a randomized phase II trial to phase III. Biometrics 58 823–831. JSTOR: · Zbl 1210.62168 · doi:10.1111/j.0006-341X.2002.00823.x
[18] Joffe, S. and Weeks, J. C. (2002). Views of American oncologists about the purposes of clinical trials. J. National Cancer Institute 94 1847–1853.
[19] Krams, M., Lees, K. R., Hacke, W., Grieve, A. P., Orgogozo, J.-M. and Ford, G. A. (2003). Acute stroke therapy by inhibition of neutrophils (ASTIN): An adaptive dose–response study of UK-279,276 in acute ischemic stroke. Stroke 34 2543–2548.
[20] Lewis, R. J. and Berry, D. A. (1998). Decision theory. In Encyclopedia of Biostatistics . Wiley, New York.
[21] Lewis, R. J., Berry, D. A., Cryer, H., Fost, N., Krome, R., Washington, G. R., Houghton, J., Blue, J., Bechhofer, R., Cook, T. and Fisher, M. (2001). Monitoring a clinical trial conducted under the new FDA regulations allowing a waiver of prospective informed consent: The DCLHb traumatic hemorrhagic shock efficacy trial. Annals of Emergency Medicine 38 397–404.
[22] Malakoff, D. (1999). Bayes offers a “new” way to make sense of numbers. Science 286 1460–1464.
[23] Sox, H. C., Blatt, M. A., Higgins, M. C. and Marton, K. I. (1988). Medical Decision Making . Butterworth and Heinemann, Boston.
[24] Spiegelhalter, D. J., Freedman, L. S and Parmar, M. K. B. (1994). Bayesian approaches to randomized trials (with discussion). J. Roy. Statist. Soc. Ser. A 157 357–416. JSTOR: · Zbl 1001.62529 · doi:10.2307/2983527
[25] Spiegelhalter, D. J., Myles, J. P., Jones, D. R. and Abrams, K. R. (2000). Bayesian methods in health technology assessment: A review. Health Technology Assessment 4 1–130.
[26] Thompson, W. R. (1933). On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika 25 285–294. · JFM 59.1159.03
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.