The University of Edinburgh -
Division of Informatics
Forrest Hill & 80 South Bridge

MSc Thesis #94141

Title:Neo-Dat an Expert System to Support the Deisgners of Clinical Trials.
Date: 1994
Abstract:Randomised, controlled clinical trials are accepted as the most reliable way of determining the efficacy of therapies. However, designing a trial is a task that demands experience, statistical knowledge and time. As a result, many published clinical trials are poorly designed, suggesting that the protocol was incomplete, disorganised or contained errors. The Neo-DaT system is an expert system which helps inexperienced protocol investigators to design clinical trials. The system prompts the physician with suitable design options, comments on the statistical rigour and feasibility of their proposed design and generates a 6-page draft protocol document. The Neo-Dat expert system is a reconstruction and an extension of the basic Design-a-Trial version 1.1 system, using a declarative programming language (PROLOG). This dissertation outlines the process used to design and development of the Neo-Dat expert System.

[Search These Pages] [DAI Home Page] [Comment]