On the Heuristic Nature of Medical Decision-Support Systems

C. F. Aliferis; R. A. Miller

doi:10.1055/s-0038-1634584

Methods of Information in Medicine, Table of Contents

Methods Inf Med 1995; 34(01/02): 5-14
DOI: 10.1055/s-0038-1634584

Original article

Schattauer GmbH

On the Heuristic Nature of Medical Decision-Support Systems

C. F. Aliferis

¹Section of Medical Informatics, Department of Medicine, School of Medicine, and Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA, USA

,

R. A. Miller

¹Section of Medical Informatics, Department of Medicine, School of Medicine, and Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA, USA

› Author Affiliations

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.

Keywords:

Heuristics - Medical Artificial Intelligence - Decision Support Systems - Problem Solving - Formal Methods - Ad hoc Methods

Full Text

References

References
1 Rich E, Knight K. Artificial Intelligence. (2nd ed). McGraw-Hill; 1991
2 Sacerdoti ED. Problem solving tactics. AI Magazine Winter 1980; 81 7-15.
3 Winston W. Operations Research. PWS-Kent; 1991. (2nd ed.).
4 Simon H. Search and reasoning in problem solving. Artif Intell 1983; 21: 7-29.
5 Howard RA. The science of decision making. In: Howard RA, Matheson JE. eds. The Principles and Applications of Decision Analysis. Strategic Decisions Group; 1983: 161-76.
6 Cormen TH, Leiserson CE, Rivest RL. Introduction to Algorithms. New York: McGraw-Hill; 1992
7 Sox HC, Blatt MA, Higgins MC, Marton KI. Medical Decision Making. Boston: Butterworth-Heinemann; 1988
8 Levesque HJ, Brachman RJ. A fundamental tradeoff in knowledge representation and reasoning. In: Levesque HJ, Brachman RJ. eds. Readings in Knowledge Representation. Los Altos CA: Morgan Kauffman Publishers; 1985: 42-70.
9 Hertz J, Krogh A, Palmer RG. Introduction to the theory of Neural Computation. Redwood City CA: Addison-Wesley Publ Co; 1991
10 Spirtes P, Glumour C, Sheines R. Causality, Prediction and Search. New York: Springer Verlag; 1992
11 Salmon MH, Earman J, Glymour C. et al. Introduction to the Philosophy of Science. Englewood Cliffs NJ: Prentice-Hall; 1992
12 Miller PL. Evaluation of artificial intelligence systems in medicine. In: Proceedings of the 1985 Symposium of Computer Applications in Medical Care 1985; 281-6.
13 Barr A, Cohen PR, Feigenbaum EA. The Handbook of Artificial Intelligence (vol. I–IV). Reading MA: Addison-Wesley Publ Co; 1982. 1989.
14 Shortliffe EH, Perreault LE. eds. Medical Informatics: Computer applications in Health Care. Reading MA: Addison-Wesley Publ Co; 1990
15 American Heritage Dictionary. Houghton Mifflin Co; 1986. 87. (CD-ROM Version, 1992 Microsoft Bookshelf.)
16 Gove PB. ed. Webster’s Third New International Dictionary. Springfield MA: Merriam-Webster Inc; 1986
17 Stein J, Hauck LC, Su PY. eds. The Random House College Dictionary, Revised Edition. New York: Random House, Inc; 1988
18 Kahneman D, Slovic P, Tversky A. eds. Judgment Under Uncertainty: Heuristics and Biases. Cambridge: Cambridge University Press; 1992
19 Polya G. How to Solve It. (2nd ed.). Princeton NJ: Princeton University Press; 1986
20 Lenat DB. The nature of heuristics. Artif Intell 1982; 19: 189-249.
21 Nilsson NJ. Principles of Artificial Intelligence. Palo Alto CA: Morgan Kaufman, Publishers Inc; 1980
22 Warner HR, Toronto AF, Veasy LG, Stephenson R. A mathematical approach to medical diagnosis: Application to congenital heart diseases. JAMA 1961; 177: 177-83.
23 Miller RA, Pople HE, Myers JD. INTERNIST-I, an experimental computer-based diagnostic consultant for general internal medicine. N Engl J Med 1982; 307: 468-76.
24 Kahn MG. Modelling time in medical decision-support programs. Med Dec Making 1991; 11: 249-64.
25 Frich AM, Gohn AG. Thoughts and afterthoughts on the 1988 Workshop on Principles of Hybrid Reasoning. AI Magazine January 1991; (special issue): 77-85.
26 Chandrasekaran B. Towards a taxonomy of problem solving types. AI Magazine Winter/Spring 1983; 9-17.
27 Minsky M. Logical versus analogical or symbolic versus connectionist or neat versus scruffy. AI magazine Summer 1991; 34-5l.
28 Langlotz CP, Shortliffe EH, Fagan LM. Using decision theory to justify heuristics. In: Proceedings of AAAI. Philadelphia, PA: 1986: 215-9.
29 Buchanan BG, Shortliffe EH. Rule-based Expert Systems: the Mycin Experiments of the Stanford Heuristic Programming Project. Reading, Mass: Addison Wesley; 1984
30 Thomason RH. Symbolic Logic: An Introduction. London: Collier-Macmillan; 1970
31 Tabachnick BG, Fidell LS. Using Multivariate Statistics. New York NY: Harper Collins Publ; 1989
32 Heckerman DE. Probabilistic interpretations for mycin’s certainty factors. In: Kanal LN, Lemmer JF. eds. Uncertainty in Artificial Intelligence. Amsterdam: North-Holland Publ Comp; 1986: 167-96.
33 Pozen MW, D’Agostino RB, Selker HP. et al. A predictive instrument to improve coronary-care-unit admission practices in acute ischemic heart disease: a prospective multicenter clinical trial. N Engl J Med 1984; 310: 1273-8.
34 Agresti A. Categorical Data Analysis. New York NY: John Wiley & Sons; 1990
35 Miller RA, Masarie Jr FE. The demise of the “Greek Oracle” model for medical diagnostic systems. Meth Inform Med 1990; 29: 1-2.
36 De Dombal FT, Leaper DJ, Staniland JR. et al. Computer-aided diagnosis of acute abdominal pain. BMJ 1972; 2: 9-13.
37 Woods W A. What’s in a link: foundations for semantic networks. In: Bobrow DG, Collins AM. eds. Representation and Understanding: Studies in Cognitive Science. New York: Academic Press; 1975: 35-82.
38 Cheesman P. An inquiry into computer understanding (with commentaries). Comput Intell 1988; 4: 58-142.
39 Heckerman DE, Shortliffe EH. From certainty factors to belief networks. Report KSL-91-56, September 1991
40 Heckerman D, Nathwani BN. An evaluation of the diagnostic accuracy of Pathfinder. Comp Biomed Res 1992; 25: 56-74.
41 Yu VL, Fagan LM, Wraith SM. et al. Antimicrobial selection by a microcomputer. JAMA 1979; 242: 1279-82.
42 Eddy DM. Probabilistic reasoning in clinical medicine: Problems and opportunities. In: Kahneman D, Siovic P, Tversky A. eds. Judgment Under Uncertainty: Heuristics and Biases. Cambridge: Cambridge University Press; 1992: 249.
43 Giuse NB, Giuse DA, Miller RA. et al. Evaluating consensus among physicians in medical knowledge base construction. Meth Inform Med 1993; 32: 137-45.
44 Shwe M, Cooper GF. An empirical analysis of likelihood-weighting simulation on a large multiply connected medical belief network. Comp Biomed Res 1991; 24: 453-75.
45 Masarie FE, Miller RA, Myers JD. INTERNIST-I Properties: representing common sense and good medical practice in a computerized medical knowledge base. Comp Biomed Res 1985; 18: 458-79.
46 Goldman L, Cook EF, Brand DA. et al. A computer protocol to predict myocardial infarction in emergency department patients with chest pain. N Engl J Med 1988; 318: 797-803.
47 Baxt WG. Use of an artificial neural network for the diagnosis of myocardial infarction. Ann Intern Med 1991; 115: 834-8.
48 Campbell DT. Experimental and Quasi-Experimental Design for Research. Chicago IL: Rand McNally; 1971
49 Bankowitz RA, McNeil MA, Challinor SM. et al. Effect of a computer-assisted general medicine diagnostic consultation service on housestaff diagnostic strategy. Meth Inform Med 1989; 28: 352-6.
50 Cooper GF. et al. A Bayesian method for the induction of probabilistic networks from data. Machine learning 1992; 9: 309-47.
51 Aliferis C, Chao C, Cooper G. Data Explorer: A Prototype Expert System for Statistical Analysis. Poceedings of the 17th annual SCAMC 1993; 389-93.
52 Pearl J. On the discovery and generation of certain heuristics. AI Magazine Winter/Spring 1983; 23-33.
53 Lenat DB. The ubiquity of discovery. Artif Intell 1978; 9: 257-85.
54 Cohen PR. A survey of the eighth national conference on artificial intelligence: pulling together or pulling apart?. AI Magazine Spring 1991; 16-41.
55 Schank RC. Where’s the A. I.?. AI Magazine Winter 1991; 38-49.
56 Nilsson NJ. Artificial intelligence: engineering, science, or slogan?. AI Magazine Winter 1981; 82: 2-9.
57 Pentland AP, Fischler MA. A more rational view of logic or, Up against the wall, logic imperialists!. AI Magazine Winter 1983; 15-8.
58 Shortliffe EH. The adolescence of AI in medicine: Will the field come of age in the ’90s?. Artif Intell Med 1993; 5: 93-106.
59 Ginsberg ML. Readings in Nonmonotonic Reasoning. Los Altos CA: Morgan Kaufmann Publ Inc; 1987