On the Heuristic Nature of Medical Decision-Support Systems

Abstract

Abstract:In the realm of medical decision-support systems, the term “heuristic systems” is often considered to be synonymous with “medical artificial intelligence systems” or with “systems employing informal model(s) of problem solving”. Such a view may be inaccurate and possibly impede the conceptual development of future systems. This article examines the nature of heuristics and the levels at which heuristic solutions are introduced during system design and implementation. The authors discuss why heuristics are ubiquitous in all medical decision-support systems operating at non-trivial domains, and propose a unifying definition of heuristics that encompasses formal and ad hoc systems. System developers should be aware of the heuristic nature of all problem solving done in complex real world domains, and characterize their own use of heuristics in describing system development and implementation.

Some features of query construction in an expert system according to the peculiarities of knowledge structuring (using the domain of nanotechnology as an example)

“…M. Salem state, expert systems currently "solve part or whole of a significant problem" and "reduce the essential need for human experts" in the domains of "law, engineering, airspace, military, medicine, chem-istry and banking" . It is worth mentioning that one of the leading domains, where the expert systems are useful and helpful, is medicine; that is proven by a great number of papers that discuss their application (e. g.: Singla et al 2014;Zeki et al 2012;Garcia et al 2001;Kumar, Bhimrao 2012;Aliferis, Miller 1995;Arsene et al 2015, Shabut et al 2018). Moreover, even educational sphere and quality of life evaluations can be regulated by expert systems [Lee et al 2018;Herrero-Jiménez 2012;Atanasova, Krupka 2013].…”

“…What is important in this respect is how a user may interact with an expert system and retrieve the necessary data. Query-answer regime is one of the ways to do so [Alonso et al 2012]. However the development of such tool may face a number of problems [Hu, Liu 2006] and new approaches to how this should be done and what principles should be taken into consideration are suggested and discussed [Sena, Furtado 1998].…”

Representing and Processing Medical Knowledge Using Formal Concept Analysis

“…It can be transformed into a context understood by both medical and informatics professionals. Therefore, formal contexts can be a common basis for both in terms of communication and, possibly, overcoming the polarization of the two groups [53]. Following Buchanan and others [54][55][56][57], conceptualization and formalization are phases in the acquisition process.…”

Introduction

“…Problems of subjectivity arise even with the consensus of recognized experts. 76 In general, developers should not serve as experts, 5 although they can help focus a study or interpret the results. In rare circumstances, a developer may in fact be the most appropriate expert, as was the case in one study of the use rather than the performance of a system.…”