Statistical Science

Incorporating Bayesian Ideas into Health-Care Evaluation

David J. Spiegelhalter

Full-text: Open access

Abstract

We argue that the Bayesian approach is best seen as providing additional tools for those carrying out health-care evaluations, rather than replacing their traditional methods. A distinction is made between those features that arise from the basic Bayesian philosophy and those that come from the modern ability to make inferences using very complex models. Selected examples of the former include explicit recognition of the wide cast of stakeholders in any evaluation, simple use of Bayes theorem and use of a community of prior distributions. In the context of complex models, we selectively focus on the possible role of simple Monte Carlo methods, alternative structural models for incorporating historical data and making inferences on complex functions of indirectly estimated parameters. These selected issues are illustrated by two worked examples presented in a standardized format. The emphasis throughout is on inference rather than decision-making.

Article information

Source
Statist. Sci. Volume 19, Number 1 (2004), 156-174.

Dates
First available in Project Euclid: 14 July 2004

Permanent link to this document
https://projecteuclid.org/euclid.ss/1089808280

Digital Object Identifier
doi:10.1214/088342304000000080

Mathematical Reviews number (MathSciNet)
MR2086325

Zentralblatt MATH identifier
1057.62105

Keywords
Bayes theorem prior distributions sceptical prior distribution data monitoring committee cost-effectiveness analysis historical data decision theory

Citation

Spiegelhalter, David J. Incorporating Bayesian Ideas into Health-Care Evaluation. Statist. Sci. 19 (2004), no. 1, 156--174. doi:10.1214/088342304000000080. https://projecteuclid.org/euclid.ss/1089808280


Export citation

References

  • Ades, A. E. and Cliffe, S. (2002). Markov chain Monte Carlo estimation of a multiparameter decision model: Consistency of evidence and the accurate assessment of uncertainty. Medical Decision Making 22 359--371.
  • Bather, J. A. (1985). On the allocation of treatments in sequential medical trials (with discussion). Internat. Statist. Rev. 53 1--13, 25--36.
  • Benjamini, Y. and Hochberg, Y. (1995). Controlling the false discovery rate: A practical and powerful approach to multiple testing. J. Roy. Statist. Soc. Ser. B 57 289--300.
  • Benson, K. and Hartz, A. (2000). A comparison of observational studies and randomized controlled trials. New England J. Medicine 342 1878--1886.
  • Berger, J. O. and Berry, D. A. (1988). Statistical analysis and the illusion of objectivity. American Scientist 76 159--165.
  • Berry, D. A. (1994). Discussion of ``Bayesian approaches to randomized trials,'' by D. J. Spiegelhalter, L. S. Freedman and M. K. B. Parmar. J. Roy. Statist. Soc. Ser. A 157 399.
  • Berry, D. A. (2002). Adaptive clinical trials and Bayesian statistics (with discussion). In Pharmaceutical Report---American Statistical Association 9 1--11. Amer. Statist. Assoc., Alexandria, VA.
  • Berry, D. A. (2004). Bayesian statistics and the efficiency and ethics of clinical trials. Statist. Sci. 19 175--187.
  • Berry, D. A., Müller, P., Grieve, A., 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. Lecture Notes in Statist. 162 99--181. Springer, New York.
  • Berry, D. A. and Stangl, D. K. (1996a). Bayesian methods in health-related research. In Bayesian Biostatistics (D. A. Berry and D. K. Stangl, eds.) 3--66. Dekker, New York.
  • Berry, D. A. and Stangl, D. K., eds. (1996b). Bayesian Biostatistics. Dekker, New York.
  • Briggs, A. (2000). Handling uncertainty in cost-effectiveness models. Pharmacoeconomics 17 479--500.
  • Britton, A., McKee, M., Black, N., McPherson, K., Sanderson, C. and Bain, C. (1998). Choosing between randomised and non-randomised studies: A systematic review. Health Technology Assessment 2 1--124.
  • Brooks, S. P. (1998). Markov chain Monte Carlo method and its application. The Statistician 47 69--100.
  • Brophy, J. and Joseph, L. (2000). A Bayesian analysis of random mega-trials for the choice of thrombyotic agents in acute myocardial infarction. In Meta-Analysis in Medicine and Health Policy (D. K. Stangl and D. A. Berry, eds.) 83--104. Dekker, New York.
  • Burton, P. R. (1994). Helping doctors to draw appropriate inferences from the analysis of medical studies. Statistics in Medicine 13 1699--1713.
  • Campbell, G. (1999). A regulatory perspective for Bayesian clinical trials. Food and Drug Administration, Washington.
  • Casella, G. and George, E. (1992). Explaining the Gibbs sampler. Amer. Statist. 46 167--174.
  • Chaloner, K. (1996). Elicitation of prior distributions. In Bayesian Biostatistics (D. A. Berry and D. K. Stangl, eds.) 141--156. Dekker, New York.
  • Chaloner, K. and Rhame, F. (2001). Quantifying and documenting prior beliefs in clinical trials. Statistics in Medicine 20 581--600.
  • Chessa, A. G., Dekker, R., van Vliet, B., Steyerberg, E. W. and Habbema, J. D. F. (1999). Correlations in uncertainty analysis for medical decision making: An application to heart-valve replacement. Medical Decision Making 19 276--286.
  • Christiansen, C. L. and Morris, C. N. (1997a). Improving the statistical approach to health care provider profiling. Annals of Internal Medicine 127 764--768.
  • Christiansen, C. L. and Morris, C. N. (1997b). Hierarchical Poisson regression modeling. J. Amer. Statist. Assoc. 92 618--632.
  • Claxton, K., Lacey, L. F. and Walker, S. G. (2000). Selecting treatments: A decision theoretic approach. J. Roy. Statist. Soc. Ser. A 163 211--225.
  • Claxton, K. and Posnett, J. (1996). An economic approach to clinical trial design and research priority-setting. Health Economics 5 513--524.
  • Cornfield, J. (1966). A Bayesian test of some classical hypotheses---with applications to sequential clinical trials. J. Amer. Statist. Assoc. 61 577--594.
  • Cornfield, J. (1969). The Bayesian outlook and its application. Biometrics 25 617--657.
  • Cornfield, J. (1976). Recent methodological contributions to clinical trials. American J. Epidemiology 104 408--421.
  • Cox, D. R. (1999). Discussion of ``Some statistical heresies,'' by J. K. Lindsey. The Statistician 48 30.
  • Cronin, K. A., Freedman, L. S., Lieberman, R., Weiss, H. L., Beenken, S. W. and Kelloff, G. J. (1999). Bayesian monitoring of phase II trials in cancer chemoprevention. J. Clinical Epidemiology 52 705--711.
  • Daniels, M. J. (1999). A prior for the variance components in hierarchical models. Canad. J. Statist. 27 567--578.
  • Decisioneering (2000). Crystal ball. Technical report. Available at http://www.decisioneering.com/crystal_ball.
  • DerSimonian, R. (1996). Meta-analysis in the design and monitoring of clinical trials. Statistics in Medicine 15 1237--1248.
  • Dignam, J. J., Bryant, J., Wieand, H. S., Fisher, B. and Wolmark, N. (1998). Early stopping of a clinical trial when there is evidence of no treatment benefit: Protocol B-14 of the National Surgical Adjuvant Breast and Bowel Project. Controlled Clinical Trials 19 575--588.
  • Dixon, D. O. and Simon, R. (1991). Bayesian subset analysis. Biometrics 47 871--881.
  • Dominici, F., Parmigiani, G., Wolpert, R. and Hasselblad, V. (1999). Meta-analysis of migraine headache treatments: Combining information from heterogeneous designs. J. Amer. Statist. Assoc. 94 16--28.
  • DuMouchel, W. and Normand, S. (2000). Computer-modeling and graphical strategies for meta-analysis. In Meta-Analysis in Medicine and Health Policy (D. K. Stangl and D. A. Berry, eds.) 127--178. Dekker, New York.
  • Eddy, D. M., Hasselblad, V. and Shachter, R. (1992). Meta-Analysis by the Confidence Profile Method: The Statistical Synthesis of Evidence. Academic Press, San Diego.
  • Etzioni, R. D. and Kadane, J. B. (1995). Bayesian statistical methods in public health and medicine. Annual Review of Public Health 16 23--41.
  • Fayers, P. M., Ashby, D. and Parmar, M. K. B. (1997). Tutorial in biostatistics: Bayesian data monitoring in clinical trials. Statistics in Medicine 16 1413--1430.
  • Fayers, P. M., Cuschieri, A., Fielding, J., Craven, J., Uscinska, B. and Freedman, L. S. (2000). Sample size calculation for clinical trials: The impact of clinician beliefs. British J. Cancer 82 213--219.
  • Fletcher, A., Spiegelhalter, D., Staessen, J., Thijs, L. and Bulpitt, C. (1993). Implications for trials in progress of publication of positive results. The Lancet 342 653--657.
  • Fryback, D. G., Stout, N. K. and Rosenberg, M. A. (2001). An elementary introduction to Bayesian computing using WINBUGS. International J. Technology Assessment in Health Care 17 98--113.
  • Gilbert, J. P., McPeek, B. and Mosteller, F. (1977). Statistics and ethics in surgery and anesthesia. Science 198 684--689.
  • Gilks, W. R., Richardson, S. and Spiegelhalter, D. J., eds. (1996). Markov Chain Monte Carlo in Practice. Chapman and Hall, New York.
  • Goldstein, H. and Spiegelhalter, D. J. (1996). League tables and their limitations: Statistical issues in comparisons of institutional performance (with discussion). J. Roy. Statist. Soc. Ser. A 159 385--443.
  • Gould, A. L. (1991). Using prior findings to augment active-controlled trials and trials with small placebo groups. Drug Information J. 25 369--380.
  • Gray, R. J. (1994). A Bayesian analysis of institutional effects in a multicenter cancer clinical trial. Biometrics 50 244--253.
  • Greenhouse, J. B. and Wasserman, L. (1995). Robust Bayesian methods for monitoring clinical trials. Statistics in Medicine 14 1379--1391.
  • Grieve, A. P. (1994). Discussion of ``Bayesian approaches to randomized trials,'' by D. J. Spiegelhalter, L. S. Freedman and M. K. B. Parmar. J. Roy. Statist. Soc. Ser. A 157 387--388.
  • Hanson, T., Bedrick, E., Johnson, W. and Thurmond, M. (2003). A mixture model for bovine abortion and foetal survival. Statistics in Medicine 22 1725--1739.
  • Harrell, F. E. and Shih, Y. C. T. (2001). Using full probability models to compute probabilities of actual interest to decision makers. International J. Technology Assessment in Health Care 17 17--26.
  • Hasselblad, V. (1998). Meta-analysis of multi-treatment studies. Medical Decision Making 18 37--43.
  • Healy, M. J. R. and Simon, R. (1978). New methodology in clinical trials. Biometrics 34 709--712.
  • Heitjan, D. F. (1997). Bayesian interim analysis of phase II cancer clinical trials. Statistics in Medicine 16 1791--1802.
  • Higgins, J. P. and Whitehead, A. (1996). Borrowing strength from external trials in a meta-analysis. Statistics in Medicine 15 2733--2749.
  • Ibrahim, J. G. and Chen, M.-H. (2000). Power prior distributions for regression models. Statist. Sci. 15 46--60.
  • International Conference on Harmonisation E9 Expert Working Group (1999). Statistical principles for clinical trials: ICH harmonised tripartite guideline. Statistics in Medicine 18 1905--1942. Available at http://www.ich.org.
  • Ioannidis, J. P. A., Haidich, A. B., Pappa, M., Pantazis, N., Kokori, S. I., Tektonidou, M. G., Contopoulos-Ioannidis, D. G. and Lau, J. (2001). Comparison of evidence of treatment effects in randomized and nonrandomized studies. J. American Medical Association 286 821--830.
  • Kadane, J. B. (1995). Prime time for Bayes. Controlled Clinical Trials 16 313--318.
  • Kass, R. E. and Greenhouse, J. B. (1989). A Bayesian perspective. Comment on ``Investigating therapies of potentially great benefit: ECMO,'' by J. H. Ware. Statist. Sci. 4 310--317.
  • Krams, M., Lees, K., Hacke, W., Grieve, A., Orgogozo, J. and Ford, G. (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.
  • Kunz, R. and Oxman, A. D. (1998). The unpredictability paradox: Review of empirical comparisons of randomised and non-randomised clinical trials. British Medical J. 317 1185--1190.
  • Larose, D. T. and Dey, D. K. (1997). Grouped random effects models for Bayesian meta-analysis. Statistics in Medicine 16 1817--1829.
  • Lau, J., Schmid, C. H. and Chalmers, T. C. (1995). Cumulative meta-analysis of clinical trials builds evidence for exemplary medical care. J. Clinical Epidemiology 48 45--57.
  • Lindley, D. V. (1994). Discussion of ``Bayesian approaches to randomized trials,'' by D. J. Spiegelhalter, L. S. Freedman and M. K. B. Parmar. J. Roy. Statist. Soc. Ser. A 157 393.
  • Lindley, D. V. (2000). The philosophy of statistics (with discussion). The Statistician 49 293--337.
  • Matthews, R. A. J. (2001). Methods for assessing the credibility of clinical trial outcomes. Drug Information J. 35 1469--1478.
  • Natarajan, R. and Kass, R. E. (2000). Reference Bayesian methods for generalized linear mixed models. J. Amer. Statist. Assoc. 95 227--237.
  • Normand, S.-L., Glickman, M. E. and Gatsonis, C. A. (1997). Statistical methods for profiling providers of medical care: Issues and applications. J. Amer. Statist. Assoc. 92 803--814.
  • O'Hagan, A. and Luce, B. (2003). A Primer on Bayesian Statistics in Health Economics and Outcomes Research. Centre for Bayesian Statistics in Health Economics, Sheffield, UK.
  • O'Hagan, A., Stevens, J. W. and Montmartin, J. (2000). Inference for the cost-effectiveness acceptability curve and cost-effectiveness ratio. Pharmacoeconomics 17 339--349.
  • O'Hagan, A., Stevens, J. W. and Montmartin, J. (2001). Bayesian cost-effectiveness analysis from clinical trial data. Statistics in Medicine 20 733--753.
  • O'Neill, R. T. (1994). Conclusions. 2. Statistics in Medicine 13 1493--1499.
  • Palisade Europe (2001). @RISK 4.0. Technical report. Available at http://www.palisade-europe.com.
  • Parmar, M. K. B., Griffiths, G. O., Spiegelhalter, D. J., Souhami, R. L., Altman, D. G. and van der Scheuren, E. (2001). Monitoring of large randomised clinical trials---a new approach with Bayesian methods. The Lancet 358 375--381.
  • Parmar, M. K. B., Spiegelhalter, D. J. and Freedman, L. S. (1994). The CHART trials: Bayesian design and monitoring in practice. Statistics in Medicine 13 1297--1312.
  • Parmar, M. K. B., Ungerleider, R. S. and Simon, R. (1996). Assessing whether to perform a confirmatory randomized clinical trial. J. National Cancer Institute 88 1645--1651.
  • Peto, R. (1985). Discussion of ``On the allocation of treatments in sequential medical trials,'' by J. Bather. Internat. Statist. Rev. 53 31--34.
  • Pocock, S. (1976). The combination of randomized and historical controls in clinical trials. J. Chronic Diseases 29 175--188.
  • Prevost, T. C., Abrams, K. R. and Jones, D. R. (2000). Hierarchical models in generalized synthesis of evidence: An example based on studies of breast cancer screening. Statistics in Medicine 19 3359--3376.
  • Racine, A., Grieve, A. P., Fluhler, H. and Smith, A. F. M. (1986). Bayesian methods in practice---experiences in the pharmaceutical industry (with discussion). Appl. Statist. 35 93--150.
  • Reeves, B., MacLehose, R., Harvey, I., Sheldon, T., Russell, I. and Black, A. (2001). A review of observational, quasi-experimental and randomized study designs for the evaluation of the effectiveness of healthcare interventions. In The Advanced Handbook of Methods in Evidence Based Healthcare (A. Stevens, K. Abrams, J. Brazier, R. Fitzpatrick and R. Lilford, eds.) 116--135. Sage, London.
  • Sanderson, C., McKee, M., Britton, A., Black, N., McPherson, K. and Bain, C. (2001). Randomized and non-randomized studies: Threats to internal and external validity. In The Advanced Handbook of Methods in Evidence Based Healthcare (A. Stevens, K. Abrams, J. Brazier, R. Fitzpatrick and R. Lilford, eds.) 95--115. Sage, London.
  • Shakespeare, T. P., Gebski, V. J., Veness, M. J. and Simes, J. (2001). Improving interpretation of clinical studies by use of confidence levels, clinical significance curves, and risk-benefit contours. The Lancet 357 1349--1353.
  • Simon, R. (1994). Some practical aspects of the interim monitoring of clinical trials. Statistics in Medicine 13 1401--1409.
  • Simon, R., Dixon, D. O. and Friedlin, B. (1996). Bayesian subset analysis of a clinical trial for the treatment of HIV infections. In Bayesian Biostatistics (D. A. Berry and D. K. Stangl, eds.) 555--576. Dekker, New York.
  • Song, F., Altman, D., Glenny, A. and Deeks, J. J. (2003). Validity of indirect comparison for estimating efficacy of competing interventions: Empirical evidence from published meta-analyses. British Medical J. 326 472--476.
  • Spiegelhalter, D. J. (2001). Bayesian methods for cluster randomized trials with continuous responses. Statistics in Medicine 20 435--452.
  • Spiegelhalter, D. J., Abrams, K. R. and Myles, J. P. (2004). Bayesian Approaches to Clinical Trials and Health Care Evaluation. Wiley, New York.
  • Spiegelhalter, D. J. and Best, N. G. (2003). Bayesian approaches to multiple sources of evidence and uncertainty in complex cost-effectiveness modelling. Statistics in Medicine 22 3687--3708.
  • 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.
  • Spiegelhalter, D. J., Myles, J., Jones, D. and Abrams, K. (2000). Bayesian methods in health technology assessment: A review. Health Technology Assessment 4 1--130.
  • Stangl, D. K. and Greenhouse, J. B. (1998). Assessing placebo response using Bayesian hierarchical survival models. Lifetime Data Analysis 4 5--28.
  • Sutton, A. J., Abrams, K. R., Jones, D. R., Sheldon, T. A. and Song, F. (2000). Methods for Meta-Analysis in Medical Research. Wiley, New York.
  • Tsiatis, A. A. (1981). The asymptotic joint distribution of the efficient scores test for the proportional hazards model calculated over time. Biometrika 68 311--315.
  • Turner, R., Omar, R. and Thompson, S. (2001). Bayesian methods of analysis for cluster randomized trials with binary outcome data. Statistics in Medicine 20 453--472.
  • Whitehead, A. (2002). Meta-Analysis of Controlled Clinical Trials. Wiley, New York.
  • Whitehead, J. (1997). The Design and Analysis of Sequential Clinical Trials, 2nd ed. Wiley, New York.
  • Zucker, D. R., Schmid, C. H., McIntosh, M. W., D'Agostino, R. B., Selker, H. P. and Lau, J. (1997). Combining single patient ($N$-of-1) trials to estimate population treatment effects and to evaluate individual patient responses to treatment. J. Clinical Epidemiology 50 401--410.