This Article 
 Bibliographic References 
 Add to: 
Dynamic Network Construction and Updating Techniques for the Diagnosis of Acute Abdominal Pain
March 1993 (vol. 15 no. 3)
pp. 299-307

Computing diagnoses in domains with continuously changing data is difficult but essential aspect of solving many problems. To address this task, a dynamic influence diagram (ID) construction and updating system (DYNASTY) and its application to constructing a decision-theoretic model to diagnose acute abdominal pain, which is a domain in which the findings evolve during the diagnostic process, are described. For a system that evolves over time, DYNASTY constructs a parsimonious ID and then dynamically updates the ID, rather than constructing a new network from scratch for every time interval. In addition, DYNASTY contains algorithms that test the sensitivity of the constructed network's system parameters. The main contributions are: (1) presenting an efficient temporal influence diagram technique based on parsimonious model construction; and (2) formalizing the principles underlying a diagnostic tool for acute abdominal pain that explicitly models time-varying findings.

[1] C. Berzuini, R. Bellazi, and S. Quaglini, "Temporal reasoning with probabilities," inProc. Conf. Uncertainty Artificial Intell., 1989, pp. 14-21.
[2] J. Breese, "Construction of belief and decision networks," Tech. Rep. 30, Rockwell Int. Sci. Cen., 1991.
[3] K. Chang and R. Fung, "Refinement and coarsening of Bayesian networks." inProc. Conf. Uncertainty Artificial Intell., 1990, pp. 475-482.
[4] J. R. Clarke, "A concise model for the management of possible appendicitis,"Medical Decision Making, vol. 4, pp. 331-338, 1984.
[5] J. R. Clarke and S. B. Badawy, "Acute pain over the appendix. A model of the surgical decision,"Annales de Chirurgie, vol. 45, pp. 279-283, 1991.
[6] J. R. Clarke and G. M. Provan, "A dynamic decision-theoretic approach to the management of GVHD," inProc. AAAI Spring Symp. AI Med., 1992.
[7] P. Dagum, R. Shachter, and L. Fagan, "Modeling time in belief networks," Tech. Rep. STAN-KSL-91-49, Stanford Univ., Knowledge Syst. Lab., Nov. 1991.
[8] F. T. de Dombal, D. J. Leaper, J. R. Staniland, A. P. McCann, and J. C. Horrocks, "Computer-aided diagnosis of acute abdominal pain,"Brit. Med. J., vol. 2, pp. 9-13, 1972.
[9] T. Dean and K. Kanazawa, "A model for reasoning about persistence and causation,"Comput. Intell., vol. 5, no. 3, pp. 142-150, 1989.
[10] C. Derman,Finite State Markovian Decision Processes. New York: Academic, 1970.
[11] R. Goldman and E. Charniak, "A language for construction of belief networks,"IEEE Trans. Patt. Anal. Machine Intell., this issue, pp. 196- 208.
[12] H. Keshavan (guest editor),PAMI Special Section on Probailistic Reasoning, IEEE Trans. Patt. Anal. Machine Intell., this issue.
[13] D. E. Heckerman and E. J. Horvitz, "Problem formulation as the reduction of a decision model," inProc. Sixth Conf. Uncertainty Artificial Intell.(Boston, MA), July 1990, pp. 82-89; also in P. Bonissone, M. Henrion, L. Kanal, and J. Lemmer, Eds.Uncertainty in Artificial Intelligence 6. New York: North-Holland, 1990, pp. 159-170.
[14] E. Herskovits and G. Cooper, "An entropy-driven system for construction of probabilistic expert systems from databases," inUncertainty in Artificial Intelligence 6(P. P. Bonissone, M. Henrion, L. N. Kanal, and J. F. Lemmer, Eds.). Amsterdam: North Holland, 1991, pp. 117-125.
[15] R. A. Howard and J. E. Matheson, "Influence diagrams," inThe Principles and Applications of Decision Analysis(R. Howard and J. Matheson, Eds.). Strategic Decisions Group, 1981, pp. 720-762.
[16] M. G. Kahn, "Modeling time in medical decision-support systems,"Med. Decision Making, vol. 11, pp. 249-264, 1991.
[17] D. McAllester, "Truth maintenance," inProc. AAAI, 1990, pp. 1109-1115.
[18] M. McLeish and M. Cecile, "Enhancing medical expert systems with knowledge obtained from statistical data,"Ann. Math. Artificial Intell., vol. 2, pp. 261-276, 1990.
[19] R. Neutra, "Indications for the surgical treatment of suspected acute appendicitis: A cost-effectiveness approach," inCosts, Risks, and Benefits of Surgery. New York: Oxford University Press, 1977, pp. 277-307.
[20] H. I. Pass and J. D. Hardy, "The appendix," inHardy's Textbook of Surgery. Philadelphia: J. B. Lippincott, 1988, pp. 574-581, 2nd ed.
[21] J. Pearl,Probabilistic Reasoning in Intelligent Systems. San Mateo, CA: Morgan Kaufmann, 1988.
[22] G. M. Provan, "Dynamic network updating techniques for diagnostic reasoning," inProc. Conf. Uncertainty Artificial Intell., 1991.
[23] G. M. Provan and D. Poole, "The utility of consistency-based diagnostic techniques," inProc. Conf. Principles Knowledge Represent. Reasoning, 1991, pp. 461-472.
[24] G. M. Provan, "Modeling the evolution of acute abdominal pain using temporal influence diagrams," Tech. Rep. MIS-CS-92-69, Univ. of Pennsylvania, Dept. Comput. Inform. Sci., 1992.
[25] G. M. Provan and J. R. Clarke, "Dynamic network construction and updating techniques for the diagnosis of acute abdominal pain," Tech. Rep. MIS-CS-92-68, Univ. of Pennsylvania, Dept. Comput. Inform. Sci., 1992.
[26] S. M. Schwartz, J. Baron, and J. R. Clarke, "A causal Bayesian model for the diagnosis of appendicitis," inUncertainty Artificial Intell.(L. N. Kanal and J. F. Lemmer, Eds.). Amsterdam: Elsevier, North-Holland, 1988, pp. 423-434.
[27] M. Shwe and G. F. Cooper, "An empirical analysis of likelihood-weighting simulation on a large, multiply-connected belief network," inProc. Conf. Uncertainty Artificial Intell., 1990, pp. 498-508.
[28] S. Srinivas and J. Breese, "IDEAL: A software package for analysis of influence diagrams," inProc. Conf. Uncertainty in Artificial Intelligence., 1990, pp. 212-219.
[29] B. L. Webber, R. Rymon, and J. R. Clarke, "Flexible support for trauma management through goal-directed reasoning and planning,"Artificial Intell. Med., vol. 4, no. 2, pp. 145-163, 1992.
[30] M. P. Wellman,Formulation of Tradeoffs in Planning Under Uncertainty. London: Pitman, 1990.
[31] M. Wellman, J. Breese, and R. Goldman, "From knowledge bases to decision models,"Knowledge Eng. Rev., vol. 7, no. 1, 1992.

Index Terms:
acute abdominal pain diagnosis; dynamic influence diagram construction and updating system; medical diagnostic computing; knowledge based systems; diagnostic reasoning; DYNASTY; decision-theoretic model; temporal influence diagram; parsimonious model; knowledge based systems; medical diagnostic computing; patient diagnosis
G.M. Provan, J.R. Clarke, "Dynamic Network Construction and Updating Techniques for the Diagnosis of Acute Abdominal Pain," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 3, pp. 299-307, March 1993, doi:10.1109/34.204913
Usage of this product signifies your acceptance of the Terms of Use.