Does Bayes have it? Decision Support Systems in diagnostic medicine

• Published in: International journal of industrial ergonomics Vol. 39; no. 3; pp. 524 - 532
• Main Authors: Lindgaard, G., Pyper, C., Frize, M., Walker, R.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.05.2009; Elsevier BV
• Subjects: Algorithms; Artificial intelligence; Base rates; Bayes' Theorem; Decision support systems; Decision Support Systems (DSSs); Diagnostic error; Ergonomics; H1.2; H4.2; I2.1; Individuating information; Medical diagnosis; Psychological aspects; Systems design; Decision Support Systems (DSSs); H4.2; Bayes' Theorem; Individuating information; H1.2; Base rates; I2.1; Diagnostic error
• ISSN: 0169-8141; 1872-8219
• DOI: 10.1016/j.ergon.2008.10.011

This paper aims to show how psychological research can contribute to the design of medical diagnostic Decision Support Systems (DSSs). A brief overview of some popular Artificial Intelligence (AI)-based algorithms typically applied in such DSSs is presented first. The concept of diagnosticity is then introduced, which leads into a brief discussion of DSSs in medicine. A set of biases found in human decision-making is then outlined. This is followed by a summary of five psychological experiments investigating information integration in the presence of nondiagnostic case-specific evidence. The results revealed a robust tendency of medical diagnosticians to pay a disproportionate amount of attention to the first item presented. Finally, the design of a DSS in which the principles uncovered in the five experiments are included is discussed. The design of a Bayesian Decision Support System (DSS) for training medical decision-making under uncertainty is described. Research revealing systematic, robust judgmental biases informed the design. Results showed that diagnosticity is crucial for useful DSSs, and that designers should quantify the variables to be applied in their DSS algorithms. The notion of diagnosticity, the biases uncovered, and the DSS model are applicable to a wide variety of areas of human endeavour characterized by complex decisions and ambiguous information.