A general methodology for designing and developing Intelligent Database Decision Aids, with application to medicine
After more than twenty years of development effort in expert and knowledge-based applications, there are indications of a growing uncertainty in the practical potential of such systems, especially within medical domains. Many difficulties have arisen from attempting to model human experts. These are particularly evident when considering unformalised or nonstandardised domains which are common characteristics of many specialist medical fields. Moreover, little attention has been paid to the prospective users of these systems, the tasks which are routinely undertaken or the environment in which the users must operate. These factors have all contributed to the continued lack of success of such systems. This research reviews the difficulties encountered during the development of know ledgebased systems and conventional systems. From these studies, the importance of fully considering end-users and their needs became evident. It also became apparent that currently, there is a lack of techniques available to medical investigators which would allow them to quickly, easily and thoroughly analyse the information they collect during their research studies. However, the ability to undertake such reviews is crucial if consultants are not only to extend their knowledge of their domain through exploration but if they are also to evolve agreed operational practices. This standardisation of approach would lead to a rationalisation of the tests and procedures routinely undertaken, which in turn would result in the saving of time, money and patient discomfort. Consequently, this research also examines the intended user group, the typical procedures followed and the common tasks undertaken during clinical trials, as well as the environment in which the user group operates. These studies uncovered the typical facilities and assistance required by such investigators. From this information, a general methodology, characterising the processes involved in the construction of a generic Intelligent Database Decision Aid (IDDA), was developed. A suite of computer-based tools then evolved to facilitate the tailoring of such a system by a domain expert, who may be a naive computer user, for a specific investigation. These tools would thus give total control of a study to the domain expert and permit an IDDA system to be quickly and easily constructed for each new investigation. The approach was evaluated by utilising test cases drawn primarily from the medical domain. However, as the methodology was based upon commonly accepted investigative procedures, it was also reviewed in other domains to test its wider applicability. All of the IDDA systems were successfully constructed and the feedback obtained from the trials was very positive, both for the approach adopted and the various IDDA end-systems produced. Therefore, the general methodology proposed by this research has been shown to be effective and its benefits can now begin to be realized.