Article

Application of statistical decision theory to treatment choices: implications for the design and analysis of clinical trials.

Statistics in Medicine (Impact Factor: 2.04). 09/1986; 5(5):411-20. DOI: 10.1002/sim.4780050505
Source: PubMed

ABSTRACT This paper explores the application of statistical decision theory to treatment choices in cancer which involve difficult value judgements in weighing beneficial and deleterious outcomes of treatment. Strengths and weaknesses of using decision theory are illustrated by considering the problem of selecting chemotherapy in advanced ovarian cancer. The paper includes an assessment of individual preferences in 27 volunteers and a discussion of some problems in utility assessment. An alternative approach, using threshold analysis, is presented in which the results of the decision analysis are expressed as a function of utility parameters. By knowing what sets of utilities favour each treatment, the assessment of patient preferences can then be focused on important differences of treatment options. The implications of these results for the design and analysis of clinical trials are discussed.

0 Bookmarks
 · 
51 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: This review examines the state of Bayesian thinking as Statistics in Medicine was launched in 1982, reflecting particularly on its applicability and uses in medical research. It then looks at each subsequent five-year epoch, with a focus on papers appearing in Statistics in Medicine, putting these in the context of major developments in Bayesian thinking and computation with reference to important books, landmark meetings and seminal papers. It charts the growth of Bayesian statistics as it is applied to medicine and makes predictions for the future. From sparse beginnings, where Bayesian statistics was barely mentioned, Bayesian statistics has now permeated all the major areas of medical statistics, including clinical trials, epidemiology, meta-analyses and evidence synthesis, spatial modelling, longitudinal modelling, survival modelling, molecular genetics and decision-making in respect of new technologies.
    Statistics in Medicine 12/2006; 25(21):3589-631. · 2.04 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: To estimate the effects of key uncertainties on the effectiveness and cost-effectiveness of breast cancer prevention with tamoxifen. The incremental cost-effectiveness ratio of tamoxifen therapy relative to placebo was estimated using decision analysis with Markov modelling of health states, outcomes and costs for a simulated cohort of women at high risk for breast cancer. Relative effects of tamoxifen's benefits and harms were estimated from meta-analyses of randomised controlled trials. Cost estimates were based on Australian treatment patterns and costs. The main outcome measure was cost per quality-adjusted life year (QALY) gained with costs and effects discounted at a 5% annual rate. Tamoxifen therapy over five years reduces the incidence of breast cancer by approximately 1.4%, which is offset by an increase in endometrial cancer of 0.7% and pulmonary embolism of 0.2%. If the reduction is permanent (preventing new breast cancers emerging over five years and no further treatment effect thereafter), the model estimates an increase in life expectancy of 0.057 QALYs and an extra cost of $2,193; or $38,271/QALY gained. A model assuming further treatment effects of tamoxifen preventing new breast cancers emerging for up to 10 years results in an incremental cost of $19,354/QALY. However, if five years of tamoxifen therapy merely delays when these breast cancers appear (such that by 10 years there is no longer a reduced incidence), the incremental cost per QALY saved is estimated to be $199,149. Tamoxifen is potentially cost-effective in preventing breast cancer in women at high risk. However, its cost-effectiveness as a preventive therapy is highly sensitive to whether these cancers are permanently prevented or their clinical presentation is only delayed. Long-term follow-up in randomised controlled trials is therefore crucial in forming health policy.
    Australian and New Zealand Journal of Public Health 02/2003; 27(1):34-40. · 1.64 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The aim of this study was to investigate the influence of implant surface topography and surgical technique on bone response. For the experiment, 48 screw-designed implants were used with two different surface finishes, i.e. machined and 'blasted, etched'. The implants were inserted into the left and right medial femoral condyle of eight goats using three different surgical approaches: press-fit (implant diameter=implant bed diamete(r), undersized (implant bed diameter<implant diameter) and osteotome. Each femoral condyle received three implants. After an implantation period of 12 weeks, the implants were retrieved and prepared for histological and histomorphometrical evaluation (bone contact and bone mass). Light microscopy revealed that in general, the bone response to all implants was very similar. On the other hand, histomorphometry suggested that the bone-to-implant contact for the 'blasted, etched' implants inserted by an undersized technique was higher compared with machined implants and the other surgical approaches, but the observed differences were not significant. Bone mass measurements did not reveal the occurrence of clear differences between groups and surgical approaches. Supported by our findings, we conclude that implants provided with a 'blasted, etched' surface and installed in trabecular bone using an undersized preparation technique appear to support an enhanced bone-implant contact. The use of an osteotome technique did not lead to improved results.
    Clinical Oral Implants Research 09/2007; 18(4):489-95. · 3.43 Impact Factor