New reasoning methods for artificial intelligence in medicine

doi:10.1016/S0020-7373(87)80062-7

International Journal of Man-Machine Studies

Volume 26, Issue 6, June 1987, Pages 707-718

https://doi.org/10.1016/S0020-7373(87)80062-7 Get rights and content

Abstract

The discovery and validation of knowledge representations for new types of reasoning is a vital step in artificial intelligence (AI) research. A clear example of this process arises in our recent study of expert physicians' knowledge of the physiological mechanisms of the body. First, we observed that the reliance on weighted associations between findings and hypotheses in first-generation medical expert systems made it impossible for them to express knowledge of disease mechanisms. Second, to obtain empirical constraints on the nature of this knowledge of mechanism in human experts, we collected and analysed verbatim transcripts of expert physicians solving selected clinical problems. This analysis led us to the key aspects of a qualitative representation for the structure and behavior of mechanisms. The third step required a computational study of the problem of inferring behavior from structure, and resulted in a completely specified and implemented knowledge representation and a qualitative simulation algorithm (QSIM). Within this representation, we built a structural description for the mechanism studied in the transcripts, and the simulation produced the same qualitative prediction made by the physicians. Finally, the system is validated in two ways. A mathematical analysis demonstrates the power and limitations of the representation and algorithm as a qualitative abstraction of differential equations. The medical content of the knowledge base is evaluated and refined using the standard knowledge-engineering methodology. We believe that this combination of cognitive, computational, mathematical, and domain knowledge constraints provides a useful paradigm for the development of new knowledge representations in artificial intelligence.

References (15)

R. Davis
Interactive transfer of expertise: acquisition of new inference rules
Artificial Intelligence
(1979)
J.P. Kassirer et al.
Toward a theory of clinical expertise
The American Journal of Medicine
(1982)
B.J. Kuipers
Qualitative simulation
Artificial Intelligence
(1986)
B.J. Kuipers et al.
Causal reasoning in medicine: analysis of a protocol
Cognitive Science
(1984)
P. Szolovits et al.
Categorical and probabilistic reasoning in medical diagnosis
Artificial Intelligence
(1978)
K.A. Ericsson et al.
Verbal reports as data
Psychological Review
(1980)

There are more references available in the full text version of this article.

Cited by (13)

The qualitative and semiqualitative analysis of environmental problems
1995, Environmental Software
The analysis of many biochemical engineering problems in environmental modelling is based upon the development and solution of sets of differential equations. A complete analytical solution of such a model requires that every numerical constant in this set of equations is precisely known. This paper describes the use of methods from artificial intelligence which permit the solution of such sets of equations when some constant values are unknown. The use of the methods are illustrated with the solution of a set of equations representing one model of an anaerobic fermentor, and a computer program that implements the methods is described.
Cognitive modelling of fighter aircraft process control: a step towards an intelligent on-board assistance system
1992, International Journal of Man-Machine Studies
A baseline description of a cognitive model that has been successfully implemented on high-speed, low-altitude navigation fighter plane missions illustrates designs for an intelligent assistance system for future French combat aircraft. The outcomes are based on several empirical studies. Task complexity (risk, uncertainty, time pressure) is extreme and provides a prototypical example of a rapid process control situation which requires specific assistance problems. The paper is divided into three sections:
- 1.
  1. A general review discusses implications of the specific requirements for coupling an intelligent assistance system to pilots. Special attention is paid to understanding and coherence of the aid, both of which directly influence the nature of the system.
- 2.
  2. An empirical analysis of missions carried out by novice and experienced pilots forms the basis for a cognitive model of in-flight navigation problem solving. Because of time pressure and risk, pilots have as much difficulty applying solutions as diagnosing problems. Pilots tend to develop a sophisticated model of the situation in order to anticipate problems and actively avoid or minimize problem difficulty. In contrast, poor solutions tend to be found for unexpected problems and generally result in renunciation of the mission and/or crash.
- 3.
  3. The cognitive model described above serves as the basis for a computer cognitive model for flying high-speed, low-altitude navigation missions. The model splits functional knowledge into two levels: the local level deals with sub-goals and short-term activities; the global level deals with mission objectives and handles medium- and long-term activities. A resource manager coordinates the two levels. The program uses an Al actor programming style. This computer cognitive model serves to develop an intelligent navigation assistance system which can function as an automaton or as a tactical support system.
A methodology for common-sense model development
1991, Computers in Industry
Common-sense analysis of engineering problems is less than one decade old. In spite of this, common-sense models (naive physics, qualitative model) offer a very flexible formal tool to deal with realistic engineering tasks. An engineering interpretation of the basic concepts (qualitative variable, qualitative model, set of qualitative states, state graph) is given. A methodology for qualitative modeling is studied in connections with deep and shallow knowledge. The expert system Q SENECA for qualitative modeling is described. A qualitative model of undamped and damped oscillations is presented.
Modeling rare interactions in time series data through qualitative change: Application to outcome prediction in intensive care units
2020, Frontiers in Artificial Intelligence and Applications
Modeling rare interactions in time series data through qualitative change: application to outcome prediction in intensive care units
2020, arXiv
Perspectives on cognitive task analysis: Historical origins and modern communities of practice
2012, Perspectives on Cognitive Task Analysis: Historical Origins and Modern Communities of Practice

View all citing articles on Scopus

^†: This is a revised version of an invited presentation to Hippocrate 2001: The 1985 International Medical Systems Congress, Monte Carlo, Monaco, 5 November 1985.

View full text

New reasoning methods for artificial intelligence in medicine†

Abstract

Artificial Intelligence

The American Journal of Medicine

Artificial Intelligence

Cognitive Science

Artificial Intelligence

Verbal reports as data

Psychological Review