Measures of decision sensitivity that have been applied to medical decision problems were examined. Traditional threshold proximity methods have recently been supple mented by probabilistic sensitivity analysis, and by entropy-based measures of sen sitivity. The authors propose a fourth measure based upon the expected value of perfect information (EVPI), which they believe superior both methodologically and prag matically. Both the traditional and the newly suggested sensitivity measures focus en tirely on the likelihood of decision change without attention to corresponding changes in payoff, which are often small. Consequently, these measures can dramatically over state problem sensitivity. EVPI, on the other hand, incorporates both the probability of a decision change and the marginal benefit of such a change into a single measure, and therefore provides a superior picture of problem sensitivity. To lend support to this contention, the authors revisit three problems from the literature and compare the results of sensitivity analyses using probabilistic, entropy-based, and EVPI-based mea sures. Key words: sensitivity analysis; expected value of perfect information. (Med Decis Making 1998;18:95-109)
Sonnenberg FA , Roberts MS, Tsevat J., Wong JB, Barry M., Kent DLToward a peer review process for medical decision analysis modelsMed Care. 1994,32(7) JS52-JS64.
3.
Plante DA, Piccirillo JF, Sofferman RADecision analysis of treatment options in pyriform sinus cancerMed Decis Making1987;774-83
4.
Felli JC, Hazen GB Information value and decision sensitivity. International Engineering Consortium Annual Review of Communications.1996 ;49:243-53.
5.
O'Brien BJ, Drummond MF, Labelle RJ, Willan A.In search of power and significance issues in the design and analysis of stochastic cost—effectiveness studies in health careMed Care1994;32150-63
6.
Buckley JJA mathematical programming approach to sensitivity analysis in single-stage decision makingDecision Sciences1988,19.211-32
7.
Evans JRSensitivity analysis in decision theoryDecision Sciences1984,15239-47
8.
Fishburn PC, Murphy AH, Isaacs HHSensitivity of decisions to probability estimation errors a reexaminationOperations Research1968,16.254-67
9.
Isaacs HHSensitivity of decisions to probability estimation errorsOperations Research. 1963,11536-52
10.
Starr MKA discussion of some normative criteria for decision-making under uncertaintyIndustrial Management Review1966,8.71-8
11.
Rios Insua D., French S.A framework for sensitivity analysis in discrete multi-objective decision-making. European Journal of Operational Research1991;54.176-90
12.
Schneller GO , Sphicas GPOn sensitivity analysis in decision theory . Decision Sciences1985,16399-409
13.
Brown RVAssessment uncertainty technology for making and defending risky decisionsJournal of Behavioral Decision Making1990 ,3.213-28
14.
Brown RV, Ulvila JWDoes a reactor need a safety backfit? Case study on communicating decision and risk analysis information to managers. Risk Analysis1988,8.271-82
15.
Connelly DP , Willard KEMonte Carlo simulation and the clinical laboratory . Arch Pathol Lab Med1989,113750-7
16.
Critchfield GG, Willard KEProbabilistic analysis of decision trees using Monte Carlo simulationMed Decis Making1986 , 6.85-92
17.
Critchfield GG, Willard KE, Connelly DPProbabilistic analysis methods for general decision models. Comput Biomed Res.1986,19254-65
18.
Doubilet P. , Begg CB, Weinstein MC, Braun P., McNeil BJ Probabilistic sensitivity analysis using Monte Carlo simulation. Med Decis Making.1985;5157-77
19.
Dittus RS, Klein RWSimulating medical decision trees with random variable parameters . In Swain JJ, Goldsman D, Crain RC, Wilson JR (eds). Proceedings of the 1992 Winter Simulation Conference1992.1050-6
20.
Dittus RS, Roberts SD, Wilson JRQuantifying uncertainty in medical decisionsJ Am Coll Cardiol . 1989;14(3) 23A-28A.
21.
Shannon CEA mathematical theory of communication Bell SystemTechnical Journal. 1948,27.379-423
22.
Genrich JF, Sommer FSNovel approach to sensitivity analysisJ Petroleum Technology1989930-2, 983-5
23.
Soofi ESCapturing the intangible concept of information. J American Statistical Association1994,89(428) 1243-54
24.
Klein K., Pauker SGRecurrent deep venous thrombosis in pregnancy analysis of the risks and benefits of anticoagulationMed Decis Making1981,1181-202.
25.
Howard RAInformation value theoryIEEE Transactions on Systems Science and Cybernetics1966,SCC-2(1).22-26
26.
Gorry GA, Barnett GOExperience with a model of sequential diagnosisComput Biomed Res1968;1490-507
27.
Gorry GA, Kassirer J., Essig A., Schwartz W.Decision analysis as the basis for computer-aided management of acute renal failureAm J Med1973,55473-84
28.
Heckerman D. , Horvitz E., Middleton B.An approximate non-myopic computation for value of informationProceedings of the Seventh Conference on Uncertainty in Artificial Intelligence1991 135-41
29.
Heckerman D. , Horvitz E., Nathwani B.Toward normative expert systems the Pathfinder project. Technical Report KSL-90-08, Medical Computer Science Group, Section on Medical Informatics, Stanford University, Stanford, CA, 1990
30.
Feinstein ARClinical Epidemiology, The Architecture of Clinical ResearchPhiladelphia, PAW B. Saunders, 1985
31.
Spiegelhalter DJ, Freedman LS, Parmer Mkb.Bayesian approaches to randomized trialsJ Royal Statistical Association1994,( A)157357-416
32.
Spiegelhalter DJ, Freedman LSBayesian approaches to clinical trials In. Bernardo JM, Degroot MH, Lindley DV, Smith AFM (eds) Bayesian Statistics 3. New YorkOxford University Press, 1988453-77
33.
Redelmeier DA , Guyatt GH, Goldstein RSAssessing the minimal important difference in symptoms a comparison of two techniquesJ Clin Epidemiol1996;491215-9
34.
Redelmeier DA, Guyatt GH, Goldstein RS On the debate over methods for estimating the clinically important difference. J Clin Epidemiol1996;49.1223-4
35.
Redelmeier DA, Lorig K.Assessing the clinical importance of symptomatic improvementsArch Intern Med1993;1531337-42
36.
Wright JGThe minimal important difference. who's to say what is important? J Clin Epidemiol1996,491221-2
37.
Wadland WC, Plante DAScreening for asymptomatic bacteriuria in pregnancyJ Fam Pract. 1989,29372-6
38.
Felli JC, Hazen GBDo sensitivity analyses really capture problem sensitivity? An empirical analysis based on information value. Working paper Defense Resources Management Institute, Naval Postgraduate School, Monterey, CA, 1997
39.
Von Winterfeldt D., Edwards W.Decision Analysis and Behavioral Research . Cambridge, U K : Cambridge University Press, 1986
40.
Bernardo JM , Smith AFM Bayesian Theory. West Sussex, U K John Wiley & Sons, Ltd, 1994
