The Relative Accuracy of a Variety of Medical Diagnostic Programs

Abstract

Abstract:Acute abdominal pain is one of the most widely studied applications of computer-aided diagnosis. The usual approach is to apply Bayes’ theorem with the assumption of conditional independence (“independence Bayes”). We compared various approaches to designing diagnostic programs for abdominal pain of suspected gynaecological origin. The methods range from statistical to knowledge-based. All programs were evaluated using a database of 1,270 cases collected retrospectively. Our results suggest that in this application no significant improvement in accuracy can be made by taking interactions into account, either by statistical or by knowledge-based means; independence Bayes is near-optimal. As far as accuracy is concerned, there appears to be little point in pursuing knowledge-based approaches. However, the “nearest neighbours” method using a new metric appears to be at least as accurate as independence Bayes. We argue that the nearest neighbours method is more suitable than independence Bayes for clinical use because of greater accountability.

Idiot's Bayes: Not So Stupid after All?

“…Similarly, in a study comparing classifiers for predicting breast cancer recurrence, Mani, Pazzani & West (1997) found that the independence Bayes model did best. Moreover, in studies of heart disease (Russek, Kronmal & Fisher, 1983), thyroid disease (Nordyke, Kulikowski & Kulikowski, 1971), liver disease (Croft & Machol, 1987), abdominal pain (Gammerman & Thatcher, 1991;Todd & Stamper, 1994;Ohmann et al, 1996), and dyspepsia (Fox, Barber & Bardhan, 1980) the independence model was a good choice. The phenomenon is not limited to medicine.…”

“…In a comparative study of diagnostic programs for abdominal pain, Todd & Stamper (1994) said 'the usual approach is to apply Bayes' theorem with the assumption of conditional independence'.…”

Idiot's Bayes—Not So Stupid After All?

“…Moreover, in studies of heart disease (Russek, Kronmal & Fisher, 1983), thyroid disease (Nordyke, Kulikowslu & Kulikowski, 1971), liver disease (Croft & Macho], 1987). abdominal pain (Gammerman & Thatcher, 1991;Todd & Stamper, 1994;Ohmann et al, 1996), and dyspepsia (Fox, Barber & Bardhan, 1980) the independence model was a good choice. The phenomenon is not limited to medicine.…”

Using quantitative methods to improve the diagnostic workup for abdominal pain in children

“…A group from the United Kingdom studied computer-aided diagnostic programs for abdominal pain of suspected gynecologic etiology. Using a database of 1270 cases collected retrospectively, they determined that the independence BayesT method was near optimal, although they argued that the bnear-neighborsQ method might be more suitable for clinical use [8]. The benefits of having a computerbased Bayesian method of analysis of abdominal pain in a submarine without a physician have also been studied.…”