Compiling Causal Knowledge for Diagnostic Reasoning
The use of causality as a pivotal mechanism in diagnostic reasoning was first explored in the CASNET/glaucoma program.4 The causal knowledge in CASNET is represented as a network of pathophysiologic states that correspond to specific physiologic dysfunctions (not complete diseases), a set of tests that provide evidence about the likelihood of existence of those states in a given patient, and causal links between states, with subjective assessments of the transition probabilities from one state to the next. Each disease is described as a possible pattern of causally related states. Diagnosis is carried out by testing for the existence of individual pathophysiologic states, followed by matching the observed pattern of states against the patterns described for various diseases.
KeywordsCausal Relation Causal Link Rheumatic Heart Disease Causal Network Diagnostic Reasoning
Unable to display preview. Download preview PDF.
- 1.Patil RS: Review of causal reasoning in medical diagnosis. p. 11. In: Proceedings of the Tenth Annual Symposium on Computer Applications in Medical Care. IEEE, 1986. Washington, DC.Google Scholar
- 7.Pople HE Jr: Heuristic methods for imposing structure on ill-structured problems: the structuring of medical diagnostics. p. 119. In Szolovits P (ed): Artificial Intelligence in Medicine. Boulder, CO: Westview Press, 1982.Google Scholar
- 8.Patil RS, Szolovits P, Schwartz WB: Causal understanding of patient illness in medical diagnosis. p. 893. In: Proceedings of the Seventh International Joint Conference on Artificial Intelligence, 1981. Vancouver, B.C., Canada, Publ. IJCAI.Google Scholar
- 9.Patil RS: Coordinating clinical and pathophysiological reasoning in medical diagnosis. p. 3. In: Proceedings of AAMSI Congress 1986, American Association for Medical Systems and Informatics, 1986. Anaheim, CA.Google Scholar
- 10.Pople HE Jr: The formation of composite hypotheses in diagnostic problem solving: an exercise in synthetic reasoning. p. 1030. In: Proceedings of the Fifth International Joint Conference on Artificial Intelligence, 1977. MIT, Cambridge, MA Publ. by IJCAI.Google Scholar
- 11.Pople HE, Meyers JD, Miller RA: Dialog: A Model of Diagnostic Logic for Internal Medicine In: Advance Papers of the Fourth International Joint Conference on Artificial Intelligence, 1975. p. 848. Tbilisi, Georgia, USSR; Morgan Kaufmann Publishers, Inc.Google Scholar
- 12.Patil RS: Causal representation of patient illness for electrolyte and acid-base diagnosis. TR 267. Cambridge, MA: Massachusetts Institute of Technology, Laboratory for Computer Science, 1981.Google Scholar
- 13.Long WJ: Causal reasoning in a physiological model as a computational paradigm. In: Proceedings of the IEEE Medcomp Conference, 1983.Google Scholar
- 14.Kuipers B: Qualitative Simulation in Medical Physiology: A Progress Report. TM 280. Cambridge, MA: Massachusetts Institute of Technology, Laboratory for Computer Science, 1985.Google Scholar
- 15.McAllester DA: Reasoning Utility Package User’s Manual. AIM 667. Cambridge, MA: Massachusetts Institute of Technology, Artificial Intelligence Laboratory, 1982.Google Scholar
- 16.Cohen JJ, Kassirer JP: Acid-Base. Boston: Little, Brown, 1982.Google Scholar
- 17.Maxwell MH, Kleeman CR, Narins RG: Clinical Disorders of Fluid and Electrolyte Metabolism. 4th Ed. New York: McGraw-Hill, 1987.Google Scholar