MACHINE LEARNING IN PROGNOSIS OF THE FEMORAL-NECK FRACTURE RECOVERY

We compare the performance of several machine learning algorithms in t he problem of prognostics of the femoral neck fracture recovery: the K -nearest neighbours algorithm, the semi-naive Bayesian classifier, bac kpropagation with weight elimination learning of the multilayered neur al networks, the LFC (lookahead feature construction) algorithm, and t he Assistant-I and Assistant-R algorithms for top down induction of de cision trees using information gain and RELIEFF as search heuristics, respectively. We compare the prognostic accuracy and the explanation a bility of different classifiers. Among the different algorithms the se mi-naive Bayesian classifier and Assistant-R seem to be the most appro priate. We analyze the combination of decisions of several classifiers for solving prediction problems and show that the combined classifier improves both performance and the explanation ability.