Download PDF
Methods Inf Med 1988; 27(01): 23-33
DOI: 10.1055/s-0038-1635517
Original Article
Schattauer GmbH

Treatment of Uncertainty in an Oncology Protocol by Probabilistic and Artificial Intelligence Approaches

Bewältigung ungewisser Angaben in einem onkologischen Protokoll durch Ansätze der Probabilistik und der künstlichen Intelligenz
Fiorella de Rosis
1   (From the Institute of Information Science, University of Bari, the Institute of Biomedical Technology, C.N.R., Rome, and the Radiological Institute, University “La Sapienza”, Rome, Italy)
,
G. Steve
1   (From the Institute of Information Science, University of Bari, the Institute of Biomedical Technology, C.N.R., Rome, and the Radiological Institute, University “La Sapienza”, Rome, Italy)
,
C. Biagini
1   (From the Institute of Information Science, University of Bari, the Institute of Biomedical Technology, C.N.R., Rome, and the Radiological Institute, University “La Sapienza”, Rome, Italy)
,
R. Maurizi-Enrici
1   (From the Institute of Information Science, University of Bari, the Institute of Biomedical Technology, C.N.R., Rome, and the Radiological Institute, University “La Sapienza”, Rome, Italy)
› Author Affiliations
Further Information

Publication History

Publication Date:
20 February 2018 (online)

  PDF Download  Permissions and Reprints

Summary

The decision process for diagnosis and treatment of Hodgkin’s disease at the Institute of Radiology of Rome has been modelled integrating the guidelines of a protocol with uncertainty aspects. Two models have been built, using a PROSPECTOR-like Expert System shell for microcomputers: the first of them treats the uncertainty by the inferential engine of the shell, the second is a probabilistic model. The decisions suggested in a group of simulated and real cases by a section of the two models have been compared with an “objective” final diagnosis; this analysis showed that, in some cases, the two models give different suggestions and that “approximations” of the shell’s inferential engine may induce wrong conclusions. A sensitivity analysis of the probabilistic model showed that the outputs are greatly influenced by variations of parameters, whose subjective estimation appears to be especially difficult. This experience gives the opportunity to consider the risks of building clinical decision models based on Expert System shells, if the assumptions and approximations hidden in the shell have not been previously analyzed in a careful and critical way.

Der Entscheidungsprozeß für Diagnose und Behandlung des Morbus Hodgkin am Institut für Radiologie in Rom wurde unter Integration eines Protokolls mit Ungewißheitsaspekten modelliert. Zwei Modelle wurden unter Verwendung einer PROSPEKTOR-ähnlichen Exper-tensystemschale für Mikrocomputer entwickelt: Das erste bewältigt die Ungewißheit durch die Inferenzmaschine der Schale; das zweite ist ein probabilistisches Modell. Die in einer Gruppe simulierter und wirklicher Fälle vorgeschlagenen Entscheidungen wurden mit einer »objektiven« endgültigen Diagnose verglichen; diese Analyse ergab, daß in manchen Fällen die beiden Modelle Verschiedenes vorschlagen und daß »Annäherungen« der Inferenzmaschine der Schale zu falschen Schlußfolgerungen führen können. Eine Sensitivitätsanalyse des probabili-stischen Modells ergab, daß die Ergebnisse durch Variationen der Parameter in hohem Maße beeinflußt werden, deren subjektive Einschätzung weitere Schwierigkeiten mit sich bringt. Diese Erfahrung ermöglicht die Berücksichtigung der Gefahren bei der Entwicklung auf Expertensystemschalen basierender klinischer Entscheidungsmodelle, wenn die in der Schale verborgenen Annahmen und Annäherungen zuvor sorgfältig und kritisch analysiert worden sind.

Key-Words:

Clinical Decision Making - Oncology Protocols - Uncertainty - Statistical Methods - Expert Systems

Schlüssel-Wörter:

Klinische Entscheidungsfindung - onkologische Protokolle - Ungewißheit - statistische Methoden - Expertensysteme
 

  • REFERENCES

  • 1 Baila J. I. Logical thinking and the diagnostic process. Meth. Inform. Med 1980; 19: 88-92.
    PubMedGoogle Scholar
  • 2 Cohen P. R. Heuristic Reasoning about Uncertainty in Artificial Intelligence Approach. Boston: Pitman Adv. Publ. Prog; 1985
    Google Scholar
  • 3 Cox P. R, Broughton R. K. Microexpert Users Manual. Version 3. Redhill: ISIS Systems Ltd; 1984
    Google Scholar
  • 4 De Finetti B. Teoría della Probabilità. Torino: Giulio Einaudi; 1970
    Google Scholar
  • 5 Duda R. O, Hart P. E, Nilsson N. J. Subjective Bayesian methods for rule-based inference systems. Proc. National Computer Conf. 1976: 1075-1081.
    Google Scholar
  • 6 Gashnig J. PROSPECTOR, an expert system for mineral exploration. In Bond A. (Edit.) State of the Art Report on Machine Intelligence. 1981
    Google Scholar
  • 7 Gashnig J, Klahr P, Pople H, Shortliffe E, Terry A. Evaluation of expert systems, issues and case studies. In Hayes-Roth E, Waterman D. A., Lenat D. B.. (Eds) Building Expert Systems. London: Addison-Wesley; 1983
    Google Scholar
  • 8 Glymour C. Independence assumptions and Bayesian updating. Art. Intell 1985; 25: 95-99.
    CrossrefPubMedGoogle Scholar
  • 9 Grosov B. N. Evidential confirmation as transformed probability, on the duality of priors and updates. In Kanal L. N., Lemmer J. F.. (Eds) Uncertainty in Artificial Intelligence. North-Holland: Amsterdam; 1986
    Google Scholar
  • 10 Heckerman D. Probabilistic interpretation for MYCIN’S certainty factors. In Kanal L. N., Lemmer J. F.. (Eds) Uncertainty in Artificial Intelligence. North-Holland: Amsterdam; 1986
    Google Scholar
  • 11 Hickman D. H, Shortliffe E. H, Bishoff M. B, Carlisle Scott A, Jacobs C. D. Evaluation of the ONCOCYN System. Heuristic Programming Project. Memo HPP-84-9. 1984
    Google Scholar
  • 12 Johnson R. W. Independence and Bayesian updating methods. Proc. Uncertainty and Probability in AI. UCLA ‘85
    PubMed
  • 13 Kaplan H. S. Hodgkin’s Disease. Cambridge, Mass: Harvard Univ. Press; 1972
    Google Scholar
  • 14 Langlotz C. P, Fagan L. M, Tu S. W, Sikic B. I, Shortliffe E. H. A therapy planning architecture that combines decision theory and artificial intelligence techniques. Comput. Biomed. Res 1987; 20: 279-303.
    CrossrefPubMedGoogle Scholar
  • 15 Maurizi-Enrici R, Capotondi C, Biagini C, de Rosis E. A computerized hospital register for Hodgkin’s disease. Proc. VII Internat. Congr. Medical Informatics in Europe. Rome: 1987
    Google Scholar
  • 16 Pednault E. P. D, Zucker S. W, Muresan L. V. On the independence assumptions underlying Bayesian updating. Art. Intell. J 1981; 16: 213-222.
    PubMedGoogle Scholar
  • 17 Safran C, Tsichlis P. N, Bluming A. Z, Desforges J. E. Diagnostic planning using computer-assisted decision-making for patients with Hodgkin’s disease. Cancer 1977; 39: 2426-2434.
    CrossrefPubMedGoogle Scholar
  • 18 Spiegelhalter D. J. A statistical view of uncertainty in expert systems. Proc. Workshop on AI and Statistics, Bell Laboratories. London: Addison-Wesley; 1986
    Google Scholar
  • 19 Steve G. Probabilistic inferential engine in expert systems : How should the strength of rules be expressed?. Proc. Internat. Conf. Information Processing and Management of Uncertainty in Knowledge-Based Systems. Paris: 1986. (In press)
    Google Scholar
  • 20 Tverski A, Kahneman D. Judgement under uncertainty, heuristics and biases. Science 1974; 185: 1124-1131.
    CrossrefPubMedGoogle Scholar
  • 21 Van Bemmel J. H. Formalization of medical knowledge, the basis for diagnostic strategies and expert systems. In Van Bemmel J. H., Grémy F., Zvarowa J.. (Eds) Medical Decision Making, Diagnostic Strategies and Expert Systems. North-Holland: Amsterdam; 1985
    Google Scholar
  • 22 White A. P. Inference deficiencies in rule-based expert systems. Proc. IV. Conf. Brit. Computer Soc, Specialist Group on Expert Systems. Cambridge: Cambridge Univ. Press; 1985
    Google Scholar