Bayesian Computer-Based Approach to the Physician's Use of the Clinical ResearchLiterature

摘要

In this dissertation, the author considers the thesis that Bayesian decisiontheory can provide the foundation for a computer-based environment that helps physicians to use the research literature. As a basis for evaluating approaches to solving the literature problem, the author argues for the use of Bayesian statistics over classical statistics. The shift to Bayesian statistics requires a change in the paradigm within which research data are evaluated. To show that the new paradigm can be implemented in a functioning computer system, the author has developed a prototype system, called THOMAS, that gives the physician reader a number of capabilities.