Medical Decision Aids Research Articles

Some points on the use of 'independent Bayes' to diagnose acute abdominal pain.

This paper outlines some of the difficulties encountered when using independent Bayes as a statistical decision aid for acute abdominal pain. Methods of reducing the resultant problems are suggested. Restriction of the number of facets in the system reduces violation of the simplifying assumption of symptom independence without adversely affecting efficiency. Introduction of a realistic utility structure is investigated as is the potential transportability of the decision aid. Generalizations of the results are discussed and potential uses of medical decision aids are considered.

Expert systems for medical consultation

After reviewing some of the elements that permit a clearer understanding of what characterizes the “expert systems” approach, representation of medical concepts, symbolic manipulation rather than numeric calculation, causal reasoning, etc., this paper will try to deal with some of the most noteworthy developments in medical decision aid, teaching, research, before discussing some problems raised by the evaluation of expert systems in medicine.

Cost/benefit analysis and capital investment decisions in nuclear cardiology

This paper demonstrates an application of Cost-Benefit Analysis as an aid in capital investment medical decision making. Specifically, a cost-benefit analysis is used to compare three nuclear cardiology instruments (i.e. Nuclear Stethoscope, Mobile Camera/Computer and Fixed Cardiac Computer). The study examined both non-quantitative and quantitative comparative factors. Results of the study show: (1) Conversion of the non-quantitative factors into a numerical system (via medical opinion) greatly delineates the relative merits of each instrument. (2) Simulating the stochastic economic and equipment utilization factors reveals instrument selection to be a function of patient flow and amortization procedures. (3) Adjusting the quantitative assessment of each instrument by the non-quantitative assessment (via the numerical system) aids in the capital investment decision.

Knowledge Representation and Utilisation in a Man-Machine Dialogue with a Medical Decision Aid System

This study presents the man-machine communication procedure, called MEDIUM, with the medical decision aid system SPHINX. The knowledge processed by this procedure is concerned with the entities of the medical discourse, that is the signs, the symptoms and the results of clinical and paraclinical examinations. At first level, the knowledge is constituted by the definitions of the entities and their specific properties. At a second level, the knowledge is constituted by logical formulas which translate the relations that link entities. Part of the coherence of the discourse is judged with regard to the definitions of the entities. The coherence is completely established by evaluating the truth values of the formulas according to the data already stored during the session. Parts of sessions with the procedure MEDIUM are presented and results are discussed.

Computers and clinical decision making: Whether, how, and for whom?

Optimal design and implementation of computer-based medical decision aids must give explicit attention to the nature of the intended audience of such programs. The need for sophisticated capabilities and interfaces argues for the incorporation of artificial intelligence techniques. To guard against the premature clinical use of inadequately tested decision aids and to insure both safety and efficacy, we propose a hierarchical scheme for the evaluation of such programs.