Model Formulation n

Objective: To develop a model for Bayesian communication to enable readers to make reported data more relevant by including their prior knowledge and values. Background: To change their practice, clinicians need good evidence, yet they also need to make new technology applicable to their local knowledge and circumstances. Availability of the Web has the potential for greatly affecting the scientific communication process between research and clinician. Going beyond format changes and hyperlinking, Bayesian communication enables readers to make reported data more relevant by including their prior knowledge and values. This paper addresses the needs and implications for Bayesian communication. Formulation: Literature review and development of specifications from readers', authors', publishers', and computers' perspectives consistent with formal requirements for Bayesian reasoning. Results: Seventeen specifications were developed, which included eight for readers (express prior knowledge, view effect size and variability, express threshold, make inferences, view explanation, evaluate study and statistical quality, synthesize multiple studies, and view prior beliefs of the community), three for authors (protect the author's investment, publish enough information, make authoring easy), three for publishers (limit liability, scale up, and establish a business model), and two for computers (incorporate into reading process, use familiar interface metaphors). A sample client-only prototype is available at http://omie.med.jhmi.edu/bayes. Conclusion: Bayesian communication has formal justification consistent with the needs of readers and can best be implemented in an online environment. Much research must be done to establish whether the formalism and the reality of readers' needs can meet. n J Am Med Inform Assoc. 2000;7:254-266. Over the past 30 years, the National Library of Med- icine has promoted the use of the research literature by clinicians. 1 The movement of evidence-based med- icine has gone even further in advocating that rational therapeutics be based on an intelligent reading and use of the literature. 2 Unfortunately, the language for statistical discourse that medicine has used for the past 80 years is derived from other domains—indus- trial statistical quality control and decision making for

[1]  A. Laupacis,et al.  How should the results of clinical trials be presented to clinicians? , 1992, ACP Journal Club.

[2]  Duane Steffey,et al.  Hierarchical bayesian modeling with elicited prior information , 1992 .

[3]  A L Gould,et al.  Sample sizes for event rate equivalence trials using prior information. , 1993, Statistics in medicine.

[4]  D. Spiegelhalter,et al.  A predictive approach to selecting the size of a clinical trial, based on subjective clinical opinion. , 1986, Statistics in medicine.

[5]  P. Armitage,et al.  Design and analysis of randomized clinical trials requiring prolonged observation of each patient. I. Introduction and design. , 1976, British Journal of Cancer.

[6]  Jerome Cornfield,et al.  Bayesian Life Table Analysis , 1977 .

[7]  A L Greer,et al.  The State of the Art Versus the State of the Science: The Diffusion of New Medical Technologies into Practice , 1988, International Journal of Technology Assessment in Health Care.

[8]  D Fitzgerald,et al.  How to keep up with the medical literature: I. Why try to keep up and how to get started. , 1986, Annals of internal medicine.

[9]  R S Wigton,et al.  Controlled trial using computerized feedback to improve physicians' diagnostic judgments , 1992, Academic medicine : journal of the Association of American Medical Colleges.

[10]  B. Lindgren,et al.  Contrasting clinical and statistical significance within the research setting , 1993, Pediatric pulmonology.

[11]  D. Churchill,et al.  Effect of high-flux hemodialysis on quality of life and neuropsychological function in chronic hemodialysis patients. , 1992, American journal of nephrology.

[12]  J B Greenhouse,et al.  On some applications of Bayesian methods in cancer clinical trials. , 1992, Statistics in medicine.

[13]  N. Turkkan,et al.  Using the mean deviation in the elicitation of the prior distribution , 1992 .

[14]  C. Naylor,et al.  Can there be a more patient-centred approach to determining clinically important effect sizes for randomized treatment trials? , 1994, Journal of clinical epidemiology.

[15]  D. Rennie,et al.  The Cochrane Collaboration. Preparing, maintaining, and disseminating systematic reviews of the effects of health care. , 1995, JAMA.

[16]  G. Guyatt,et al.  Assessing the minimal important difference in symptoms: a comparison of two techniques. , 1996, Journal of clinical epidemiology.

[17]  R. Aumann.  Agreeing to disagree. , 1976, Nature cell biology.

[18]  I. R. Dunsmore,et al.  An Introduction to Bayesian Statistical Decision Processes , 1969 .

[19]  S. Goodman,et al.  Toward Evidence-Based Medical Statistics. 2: The Bayes Factor , 1999, Annals of Internal Medicine.

[20]  J. Hampton.  Secondary prevention of acute myocardial infarction with beta-blocking agents and calcium antagonists. , 1990, The American journal of cardiology.

[21]  A. Tversky,et al.  Judgment under Uncertainty: Heuristics and Biases , 1974, Science.

[22]  K. Dickersin,et al.  Report from the panel on the Case for Registers of Clinical Trials at the Eighth Annual Meeting of the Society for Clinical Trials. , 1988, Controlled clinical trials.

[23]  J Hilden,et al.  Reporting clinical trials from the viewpoint of a patient's choice of treatment. , 1987, Statistics in medicine.

[24]  L. Joseph,et al.  Placing trials in context using Bayesian analysis. GUSTO revisited by Reverend Bayes. , 1995, JAMA.

[25]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[26]  J W Williamson,et al.  Health science information management and continuing education of physicians. A survey of U.S. primary care practitioners and their opinion leaders. , 1989, Annals of internal medicine.

[27]  David M. Eddy,et al.  The Confidence Profile Method: A Bayesian Method for Assessing Health Technologies , 1989, Oper. Res..

[28]  Lisa A. Bero,et al.  The electronic future: What might an online scientific paper look like in five years' time?: Length—and other strengths , 1997 .

[29]  E. Rogers,et al.  Diffusion of Innovations , 1964 .

[30]  D Fitzgerald,et al.  How to keep up with the medical literature: III. Expanding the number of journals you read regularly. , 1986, Annals of internal medicine.

[31]  H. Kraemer.  Reporting the size of effects in research studies to facilitate assessment of practical or clinical significance , 1992, Psychoneuroendocrinology.

[32]  J. Berger,et al.  Testing a Point Null Hypothesis: The Irreconcilability of P Values and Evidence , 1987 .

[33]  J. Cornfield.  A BAYESIAN TEST OF SOME CLASSICAL HYPOTHESES- WITH APPLICATIONS TO SEQUENTIAL CLINICAL TRIALS , 1966 .

[34]  Bruce G. Buchanan,et al.  The MYCIN Experiments of the Stanford Heuristic Programming Project , 1985 .

[35]  Mark A. Musen,et al.  Trial banks : an informatics foundation for evidence-based medicine , 1997 .

[36]  J Cornfield,et al.  The Bayesian outlook and its application. , 1969, Biometrics.

[37]  D G Altman,et al.  Statistics in medical journals. , 1982, Statistics in medicine.

[38]  H P Lehmann,et al.  Implementing the Bayesian paradigm: reporting research results over the World-Wide Web. , 1996, Proceedings : a conference of the American Medical Informatics Association. AMIA Fall Symposium.

[39]  R. Riegelman,et al.  Adjusting the Number Needed to Treat , 1993, Medical decision making : an international journal of the Society for Medical Decision Making.

[40]  Seymour Geisser,et al.  On Prior Distributions for Binary Trials , 1984 .

[41]  D. Lindley.  The 1988 Wald Memorial Lectures: The Present Position in Bayesian Statistics , 1990 .

[42]  S. Shankaran,et al.  Adenosine infusion improves oxygenation in term infants with respiratory failure. , 1996, Pediatrics.

[43]  B. Efron.  Why Isn't Everyone a Bayesian? , 1986 .

[44]  Ross D. Shachter,et al.  A Physician-Based Architecture for the Construction and Use of Statistical Models , 1994, Methods of Information in Medicine.

[45]  D Fitzgerald,et al.  How to keep up with the medical literature: II. Deciding which journals to read regularly. , 1986, Annals of internal medicine.

[46]  G. Keren.  Calibration and probability judgements: Conceptual and methodological issues , 1991 .

[47]  M. Vanamringe,et al.  Awareness, assimilation, and adoption: the challenge of effective dissemination and the first AHCPR-sponsored guidelines. , 1992, QRB. Quality review bulletin.

[48]  J. Cornfield.  Recent methodological contributions to clinical trials. , 1976, American journal of epidemiology.

[49]  E H Shortliffe,et al.  Thomas: building Bayesian statistical expert systems to aid in clinical decision making. , 1990, Computer methods and programs in biomedicine.

[50]  E H Shortliffe,et al.  Update on ONCOCIN: a chemotherapy advisor for clinical oncology. , 1984, Medical informatics = Medecine et informatique.

[51]  H. Raiffa,et al.  Introduction to Statistical Decision Theory , 1996 .

[52]  E. Sonnenblick,et al.  Metoprolol-induced reduction in postinfarction mortality: pooled results from five double-blind randomized trials. , 1992, European heart journal.

[53]  P J Haug,et al.  Interfacing a stand-alone diagnostic expert system with a hospital information system. , 1994, Computers and biomedical research, an international journal.

[54]  Patrice Degoulet,et al.  The number needed to treat: a clinically useful nomogram in its proper context , 1996, BMJ.

[55]  Clifford Hildrethi.  BAYESIAN STATISTICIANS AND REMOTE CLIENTS , 1963 .

[56]  J. Berger.  Statistical Decision Theory and Bayesian Analysis , 1988 .

[57]  J. Carlin.  Meta-analysis for 2 x 2 tables: a Bayesian approach. , 1992, Statistics in medicine.

[58]  T. Lieu,et al.  Would better adherence to guidelines improve childhood immunization rates? , 1996, Pediatrics.

[59]  Thomas A. Louis,et al.  Graphical Elicitation of a Prior Distribution for a Clinical Trial , 1993 .

[60]  R J Cook,et al.  Users' guides to the medical literature. IX. A method for grading health care recommendations. Evidence-Based Medicine Working Group. , 1995, JAMA.

[61]  L. Pettit,et al.  Measuring the effect of observations on Bayes factors , 1990 .

[62]  Harold P. Lehmann,et al.  A Decision-Theoretic Model for Using Scientific Data , 2013, ArXiv.

[63]  S. Goodman.  Toward Evidence-Based Medical Statistics. 1: The P Value Fallacy , 1999, Annals of Internal Medicine.

[64]  M. Selwyn,et al.  On Bayesian methods for bioequivalence. , 1984, Biometrics.

[65]  Peter Urbach,et al.  Scientific Reasoning: The Bayesian Approach , 1989 .

[66]  J. Neumann,et al.  Theory of games and economic behavior , 1945, 100 Years of Math Milestones.

[67]  Tom Lang,et al.  How to Report Statistics in Medicine: Annotated Guidelines for Authors, Editors, and Reviewers , 1997 .

[68]  L. Hedges,et al.  Statistical Methods for Meta-Analysis , 1987 .

[69]  James M. Dickey,et al.  Scientific Reporting and Personal Probabilities: Student's Hypothesis , 1973 .

[70]  J. Burnham.  The evolution of editorial peer review. , 1990, JAMA.

[71]  D. Sackett,et al.  The Ends of Human Life: Medical Ethics in a Liberal Polity , 1992, Annals of Internal Medicine.

[72]  R. L. Winkler.  The Assessment of Prior Distributions in Bayesian Analysis , 1967 .

[73]  A R Willan,et al.  Power function arguments in support of an alternative approach for analyzing management trials. , 1994, Controlled clinical trials.

[74]  M D Hughes,et al.  Reporting Bayesian analyses of clinical trials. , 1993, Statistics in medicine.

[75]  J D Habbema,et al.  The marriage of clinical trials and clinical decision science. , 1990, Statistics in medicine.

[76]  N. Jacobson,et al.  Clinical significance: a statistical approach to defining meaningful change in psychotherapy research. , 1991, Journal of consulting and clinical psychology.

[77]  B. Fischhoff,et al.  Training for calibration. , 1980 .

[78]  Morgan Pp.  Confidence intervals: from statistical significance to clinical significance. , 1989 .

[79]  P. Whittle,et al.  Introduction to Probability and Statistics from a Bayesian Viewpoint, Part 1: Probability , 1969 .

[80]  Geyman Jp.  POEMs as a paradigm shift in teaching, learning, and clinical practice. Patient-Oriented Evidence that Matters. , 1999 .

[81]  Richard Simon,et al.  A Bayesian approach to establishang sample size and monitoring criteria for phase II clinical trials , 1994 .

[82]  D. Rubin.  Bayesianly Justifiable and Relevant Frequency Calculations for the Applied Statistician , 1984 .

[83]  David J. Spiegelhalter,et al.  Bayesian Approaches to Randomized Trials , 1994, Bayesian Biostatistics.

[84]  D A Berry,et al.  A case for Bayesianism in clinical trials. , 1993, Statistics in medicine.

[85]  Leonard E. Brahman.  Confidence Intervals Assess Both Clinical Significance and Statistical Significance , 1991 .

[86]  D. Moher,et al.  Statistical power, sample size, and their reporting in randomized controlled trials. , 1994, JAMA.

[87]  J. Wyatt,et al.  Are clinicians interested in up to date reviews of effective care? , 1993, BMJ.

[88]  R M Centor,et al.  Eualuating Physicians' Probabilistic Judgments , 1988, Medical decision making : an international journal of the Society for Medical Decision Making.

[89]  V. Chinburapa,et al.  The importance of side effects and outcomes in differentiating between prescription drug products , 1992, Journal of clinical pharmacy and therapeutics.

[90]  K J Rothman,et al.  A show of confidence. , 1978, The New England journal of medicine.

[91]  M. Tonelli.  The philosophical limits of evidence‐based medicine , 1998, Academic medicine : journal of the Association of American Medical Colleges.

[92]  R. Royall.  Statistical Evidence: A Likelihood Paradigm , 1997 .

[93]  D L Sackett,et al.  An assessment of clinically useful measures of the consequences of treatment. , 1988, The New England journal of medicine.

[94]  A. Birnbaum.  On the Foundations of Statistical Inference , 1962 .