Representation and Analysis of Medical Decision Problems with Influence Diagrams

Abstract

Influence diagrams are a powerful graphic representation for decision models, complementary to decision trees. Influence diagrams and decision trees are different graphic representations for the same underlying mathematical model and operations. This article describes the elements of an influence diagram, and shows several familiar decision problems represented as decision trees and as influence diagrams. The authors also contrast the information highlighted in each graphic representation, demonstrate how to calculate the expected utilities of decision alternatives modeled with an influence diagram, provide an overview of the conceptual basis of the solution algorithms that have been developed for influence diagrams, discuss the strengths and limitations of influence diagrams relative to decision trees, and describe the mathematical operations that are used to evaluate both decision trees and influence diagrams. They use clinical examples to illustrate the mathematical operations of the influence-diagram-evaluation algorithm; these operations are arc reversal, chance node removal by averaging, and decision node removal by policy determination. Influence diagrams may be helpful when problems have a high degree of conditional independence, when large models are needed, when communication of the probabilistic relationships is important, or when the analysis requires extensive Bayesian updating. The choice of graphic representation should be governed by convenience, and will depend on the problem being analyzed, on the experience of the analyst, and on the background of the consumers of the analysis. Key words: decision analysis; influence diagrams; cost-effectiveness analysis; Bayesian updating; graphic representation. (Med Decis Making 1997;17:241-262)

Get full access to this article

View all access options for this article.

References

Miller AC , Merkofer MM , Howard RA , Matheson JE , Rice TR. Development of automated aids for decision analysis Menlo Park, CA: Stanford Research Institute, 1976.

Shachter RD , Eddy DM , Hasselblad V. An influence diagram approach to the confidence profile method for health technology assessment Proceedings of the Conference on Influence Diagrams for Decision Analysis, Inference and Prediction. University of California, Berkeley, CA, 1988:299-306.

Eddy DM , Hasselblad V , Shachter R. Meta-Analysis by the Confidence Profile Method The Statistical Synthesis of Evidence. Boston, MA: Academic Press, 1992

Lehmann HP , Shortliffe EH. THOMAS Building Bayesian statistical expert systems to aid in clinical decision making In. Miller RA (ed) Proceedings of the Symposium on Computer Applications in Medical Care Los Alamitos, CA: IEEE Computer Society Press, 1990:58-64.

Lehmann HP Computational formulation of Bayesian statistical models for interpreting clinical research literature [PhD thesis] Section on Medical Informatics, Department of Medicine, Stanford University, Stanford, CA, 1991.

Jimison HB. A representation for gaining insight into clinical decision models [PhD thesis] Section on Medical Informatics, Department of Medicine, Stanford University , Stanford, CA, 1990

Owens DK , Nease RF Development of outcome-based practice guidelines: a method for structuring problems and synthesizing evidence. Joint Commission Journal on Quality Improvement. 1993;19:248-63.

Suermondt HJ. Explanation in Bayesian belief networks [PhD thesis] Section on Medical Informatics, Department of Medicine, Stanford University, Stanford, CA, 1991.

Nease RF Jr , Owens DK. Use of influence diagrams to structure medical decisions. Med Decis Making. 1997,17 263-75

10.

Centers for Disease Control.

1995 revised guidelines for prophylaxis against Pneumocystis carinii pneumonia for children infected with or perinatally exposed to human immunodeficiency virus

MMWR. 1995;44:1-11

11.

Charniak E.

Bayesian networks without tears

AI Magazine. 1991;Winter 50-63.

12.

Shwe MA , Middleton B , Heckerman DE , et al Probabilistic diagnosis using a reformulation of the INTERNIST-1/QMR knowledge base I. The probabilistic model and inference algorithms. Methods Inf Med. 1991;30.241-55.

13.

Middleton B , Shwe MA , Heckerman DE , et al Probabilistic diagnosis using a reformulation of the INTERNIST-1/QMR knowledge base. II. Evaluation of diagnostic performance. Methods Inf Med. 1991,30.256-7.

14.

Owens DK , Holodniy M , McDonald TW , Scott J , Sonnad S.

A meta-analytic evaluation of the polymerase chain reaction for the diagnosis of HIV infection in infants

JAMA. 1996,275. 1342-8.

15.

Owens DK , Nease RF , Harris RA. Cost-effectiveness of HIV screening in acute care settings. Arch Intern Med. 1996;156: 394-404.

16.

Owens DK , Harris RA , Scott PM , Nease RF. Screening surgeons for human immunodeficiency virus (HIV). A cost—effectiveness analysis. Ann Intern Med. 1995,122:641-52.

17.

Raiffa H Decision Analysis Reading, MA: Addison-Wesley , 1968.

18.

Shachter RD.

An ordered examination of influence diagrams

Networks. 1990;20 535-63.

19.

Howard RA , Matheson JE. Influence diagrams In: Howard RA , Matheson JE (eds). The Principles and Applications of Decision Analysis Vol II Menlo Park, CA: Strategic Decisions Group, 1984 720-62

20.

Shachter RD Probabilistic inference and influence diagrams. Oper Res. 1988,36.589-605.

21.

Owens DK , Holodniy M , Garber AM , et al. Polymerase chain reaction for the diagnosis of HIV infection in adults. A meta-analysis with recommendations for clinical practice and study design . Ann Intern Med. 1996,124:803-15.

22.

Shachter RD. Evaluating influence diagrams. Oper Res. 1986; 34:871-882.

23.

Olmsted SM. On representing and solving decision problems [PhD thesis]. Department of Engineering-Economic Systems, Stanford University, Stanford, CA, 1983.

24.

Jensen FV , Olesen KG , Andersen SK. An algebra of Bayesian belief universes for knowledge based systems. Networks. 1990;20.637-59.

25.

Jensen FV , Lauritzen SL , Olesen KG Bayesian updating in causal probabilistic networks by local computations . Comp Stat Q. 1990;4:269-82.

26.

Andersen SK , Olesen KG , Jensen FV , Jensen F. HUGIN: A shell for building belief universes for expert systems. Proceedings of the Eleventh International Joint Conference on Artificial Intelligence. Detroit, MI, 1989:1080-5.

27.

Lauritzen SL , Spiegelhalter DJ. Local computations with probabilities on graphical structures and their application to expert systems. J R Stat Soc. 1988;50:157-224.

28.

Shafer G , Shenoy PP. Probability propagation. Ann Math Artificial Intel. 1990;2:327-52.

29.

Shachter RD , Andersen SK , Poh KL. Directed reduction algorithms and decomposable graphs. In: Bonnisone P , Henrion M , Kanal LN , Lemmer JF (eds). Uncertainty in Artificial Intelligence 6. Amsterdam, The Netherlands: North Holland, 1991:197-208.

30.

30 Ndilikilikesha P. Potential influence diagrams. [Working Paper 235]: School of Business, University of Kansas, Lawrence, KS, 1991.

31.

Shachter RD , Peot MA. Decision making using probabilistic inference methods. In. Uncertainty in Artificial Intelligence: Proceedings of the Eighth Conference San Mateo, CA: Morgan Kaufmann , 1992:276-83.

32.

Shenoy PP. A fusion algorithm for solving Bayesian decision problems. In: D'Ambrosio B , Smets P , Bonissone P (eds) Uncertainty in Artificial Intelligence: Proceedings of the Seventh Conference San Mateo, CA: Morgan Kaufmann, 1991:361-9.

33.

Owens DK , Nease RF. Transmission of human immunodeficiency virus (HIV) infection between physicians and patients : a model-based analysis of risk . In Kaplan E , Brandeau ML (eds). Modeling the AIDS Epidemic: Planning, Policy and Prediction. New York. Raven Press, 1994.153-77.

34.

Heckerman DE Probabilistic similarity networks [PhD thesis]. Section on Medical Informatics, Department of Medicine, Stanford University, Stanford, CA, 1990.

35.

35 Tatman JA. Decision processes in influence diagrams formulation and analysis [PhD thesis]. Department of Engineering-Economic Systems, Stanford University, Stanford, CA, 1985.

36.

Tatman JA , Shachter RD.

Dynamic programming and influence diagrams

IEEE SMC. 1990,20:365-79.

37.

Pauker SG , Kassirer JP.

The threshold approach to clinical decision making

N Engl J Med. 1980;302:1109-17.