Graphic Representation of Sequential Bayesian Analysis

Abstract

Previously undescribed algebraic transforms of Bayes’ theorem define families of operating points in the receiver operating characteristic (ROC) space which, at given pre-test probability, produce constant post-test probabilities. These isopredictive operating points form straight lines in the ROC space. The lines can be used to emulate Bayesian sequential analysis in a strictly graphic procedure, which can be applied in clinical work and medical education.

Keywords

Bayes’ Theorem - Predictive Value of Tests - Diagnosis - Decision Support - ROC Space

• References

• 1 Bayes T. An essay towards solving a problem in the doctrine of chance. Phil Trans Roy Soc 1763; 53: 370-418. (Reproduced in MD Comput 1991; 8: 157-71).
• 2 de Dombal FT, Leaper JD, Staniland JR, McCann AP, Horrocks JC. Computer-aided diagnosis of acute abdominal pain. BMJ 1972; 2: 9-13.
• 3 Heller I, Isakov A, Blinder-Weiner S, Topilsky M. Bayesian classification of vasculitis: a simulation study. Meth Inform Med 1995; 34: 259-65.
• 4 Bernelot Moens HJ, Van der Korst JK. Development and validation of a computer program using Bayes’ theorem to support diagnosis of rheumatic disorders. Ann Rheum Dis 1992; 51: 266-71.
• 5 Metz CE. Basic principles of ROC analysis. Sem Nucl Med 1978; 8: 283-98.
• 6 Pauker SG, Kassirer JP. The threshold approach to clinical decision making. N Engl J Med 1980; 302: 1109-17.
• 7 Bloch DA, Michel BA, Hunder GG. et al. The American College of Rheumatology 1990 criteria for the classification of vasculitis: patients and methods. Arthritis Rheum 1990; 33: 1068-73.
• 8 Lightfoot Jr RW, Michel BA, Bloch DA. et al. The American College of Rheumatology 1990 criteria for the classification of polyarteritis nodosa. Arthritis Rheum 1990; 33: 1088-93.
• 9 Spiegelhalter DJ. Statistical methodology for evaluating gastro-intestinal symptoms. Clinics Gastroenterol 1985; 14: 489-515.