Hl. Viktor et al., EXTRACTION OF RULES FOR TUBERCULOSIS DIAGNOSIS USING AN ARTIFICIAL NEURAL-NETWORK, Methods of information in medicine, 36(2), 1997, pp. 160-162
Citations number
5
Categorie Soggetti
Computer Science Information Systems","Medical Informatics
The treatment of tuberculosis (TB) is a major challenge throughout the
world. The Western Cape Region of South Africa has the highest occurr
ence of TB in the world. Here, TB is increasing due to improperly mana
ged treatment programmes and inadequate facilities. The development of
rules to aid medical practitioners in the early and accurate diagnosi
s of tuberculosis should prove worthwhile. A method to extract such di
agnostic rules from an artificial neural network is presented. These r
ules accurately represent the knowledge embedded in the ''raw'' TB dat
a.