Comparison of Genetic Algorithms and Other Classification Methods in the Diagnosis of Female Urinary Incontinence

Abstract

Galactica, a newly developed machine-learning system that utilizes a genetic algorithm for learning, was compared with discriminant analysis, logistic regression, k-means cluster analysis, a C4.5 decision-tree generator and a random bit climber hill-climbing algorithm. The methods were evaluated in the diagnosis of female urinary incontinence in terms of prediction accuracy of classifiers, on the basis of patient data. The best methods were discriminant analysis, logistic regression, C4.5 and Galactica. Practically no statistically significant differences existed between the prediction accuracy of these classification methods. We consider that machine-learning systems C4.5 and Galactica are preferable for automatic construction of medical decision aids, because they can cope with missing data values directly and can present a classifier in a comprehensible form. Galactica performed nearly as well as C4.5. The results are in agreement with the results of earlier research, indicating that genetic algorithms are a competitive method for constructing classifiers from medical data.

Pelvic floor pressure distribution profile in urinary incontinence: a classification study with feature selection

“…This result is quite below the 96% accuracy obtained by the discriminant analysis model in the study where two other types of UI were also classified (Laurikkala et al, 1999). In addition to the fact that the data used by Laurikkala et al were categorical, it is not clear if the reported performance was a test or validation accuracy, which, in the latter case, would provide an over-optimistic performance metric.…”

“…In a previous study, the k-means, discriminant analysis, LR, decision tree, and two genetic algorithms were compared when diagnosing three types of incontinence (Laurikkala et al, 1999), including stress UI. The data were categorical and obtained through clinical questionnaires and exams.…”

“…In this context, automatic diagnosis of female urinary incontinence (UI) is an example of a CAD system in the clinical setting that is already approached through ML methods. Categorical clinical variables have been used to evaluate different classifiers (genetic algorithm, k-means, LR, and decision trees) for the task of automatically diagnosing three different types of UI (Laurikkala et al, 1999).…”